fix(ui): unbind history recall from arrow keys; use Ctrl+P / Ctrl+N

Mouse wheel on Windows Terminal + ConPTY translates to up/down
arrow key events for raw-mode child processes. Indistinguishable
from keyboard arrows at the byte level. With history recall bound
to up/down on empty buffer, every wheel-scroll on the prompt was
clobbering it with a recalled prior message.

Fix: rebind history recall to Ctrl+P (prev) / Ctrl+N (next), the
bash readline convention. Up/down arrows now no-op on a single-
line buffer and only move the cursor across lines in a multi-line
draft. Wheel scrolls again belong entirely to the terminal.

Tests updated to reflect the new binding. Placeholder hint mentions
Ctrl+P/N alongside the Ctrl+J newline hint.

.env.example

@@ -0,0 +1,4 @@
+DEEPSEEK_API_KEY=sk-your-key-here
+DEEPSEEK_BASE_URL=https://api.deepseek.com
+REASONIX_LOG_LEVEL=INFO
+REASONIX_TRANSCRIPT_DIR=./transcripts

.gitattributes

@@ -1,11 +0,0 @@
-.gitattributes text eol=lf
-.gitignore text eol=lf
-*.json text eol=lf
-*.md text eol=lf
-*.mjs text eol=lf
-*.sh text eol=lf
-*.sql text eol=lf
-*.toml text eol=lf
-*.ts text eol=lf
-*.yaml text eol=lf
-*.yml text eol=lf

.github/ISSUE_TEMPLATE/bug_report.md

@@ -0,0 +1,23 @@
+---
+name: Bug report
+about: Something is broken
+labels: bug
+---
+
+**What happened**
+A clear and concise description.
+
+**Expected**
+What you expected to happen.
+
+**Reproduction**
+Steps or minimal code that reproduces it.
+
+**Environment**
+- Reasonix version:
+- Node version:
+- OS:
+- DeepSeek model (e.g. `deepseek-chat`, `deepseek-reasoner`):
+
+**Logs / transcript**
+If using the CLI, attach the relevant chunk of `--transcript`.

.github/workflows/ci.yml

@@ -0,0 +1,49 @@
+name: CI
+
+on:
+  push:
+    branches: [main]
+  pull_request:
+    branches: [main]
+
+jobs:
+  build:
+    name: build (node ${{ matrix.node }})
+    runs-on: ubuntu-latest
+    strategy:
+      fail-fast: false
+      matrix:
+        node: ["20", "22"]
+    steps:
+      - uses: actions/checkout@v4
+
+      - name: Setup Node ${{ matrix.node }}
+        uses: actions/setup-node@v4
+        with:
+          node-version: ${{ matrix.node }}
+          cache: npm
+
+      - name: Install dependencies
+        run: npm ci
+
+      - name: Lint (biome)
+        run: npm run lint
+
+      - name: Typecheck
+        run: npm run typecheck
+
+      - name: Test (vitest)
+        run: npm test
+
+      - name: Build (tsup)
+        run: npm run build
+
+      # Smoke-test the bench harnesses themselves. --dry skips all LLM
+      # calls, so this catches wiring regressions (task factories, CLI
+      # parsing, file IO, checker determinism) without needing a
+      # DEEPSEEK_API_KEY in CI.
+      - name: τ-bench harness dry-run
+        run: npx tsx benchmarks/tau-bench/runner.ts --dry --out /tmp/tau-dry.json
+
+      - name: Harvest-bench harness dry-run
+        run: npx tsx benchmarks/harvest/runner.ts --dry --out /tmp/harvest-dry.json

.github/workflows/deploy-accounts-worker.yml

@@ -1,103 +0,0 @@
-name: Deploy identity and remote services
-
-on:
-  workflow_dispatch:
-
-permissions:
-  contents: read
-
-concurrency:
-  group: deploy-identity-and-remote-services
-  cancel-in-progress: false
-
-jobs:
-  deploy-accounts:
-    if: github.ref == 'refs/heads/platform'
-    runs-on: ubuntu-latest
-    environment: production
-    steps:
-      - uses: actions/checkout@3d3c42e5aac5ba805825da76410c181273ba90b1 # v7
-      - uses: pnpm/action-setup@ea17c68df8912ef543352723c149a84f56e3d413 # v6.1.0
-        with:
-          version: 10
-          run_install: false
-      - uses: actions/setup-node@820762786026740c76f36085b0efc47a31fe5020 # v7
-        with:
-          node-version: "24"
-          cache: pnpm
-          cache-dependency-path: workers/accounts/pnpm-lock.yaml
-      - name: Deploy
-        working-directory: workers/accounts
-        env:
-          CLOUDFLARE_API_TOKEN: ${{ secrets.CLOUDFLARE_API_TOKEN }}
-        run: |
-          pnpm install --frozen-lockfile
-          pnpm test
-          pnpm typecheck
-          pnpm db:apply:remote
-          npx wrangler deploy
-      - name: Sync RESEND_API_KEY to the worker
-        working-directory: workers/accounts
-        env:
-          CLOUDFLARE_API_TOKEN: ${{ secrets.CLOUDFLARE_API_TOKEN }}
-          RESEND_API_KEY: ${{ secrets.RESEND_API_KEY }}
-        run: |
-          if [ -n "$RESEND_API_KEY" ]; then
-            printf '%s' "$RESEND_API_KEY" | npx wrangler secret put RESEND_API_KEY
-          else
-            echo "RESEND_API_KEY not set in repo secrets; skipping (worker stays in stub email mode)."
-          fi
-      - name: Sync remote gateway secret
-        working-directory: workers/accounts
-        env:
-          CLOUDFLARE_API_TOKEN: ${{ secrets.CLOUDFLARE_API_TOKEN }}
-          REMOTE_GATEWAY_TOKEN: ${{ secrets.REMOTE_GATEWAY_TOKEN }}
-        run: |
-          if [ -z "$REMOTE_GATEWAY_TOKEN" ]; then
-            echo "REMOTE_GATEWAY_TOKEN must be configured before enabling remote access."
-            exit 1
-          fi
-          printf '%s' "$REMOTE_GATEWAY_TOKEN" | npx wrangler secret put REMOTE_GATEWAY_TOKEN
-      - name: Sync feedback account secret
-        working-directory: workers/accounts
-        env:
-          CLOUDFLARE_API_TOKEN: ${{ secrets.CLOUDFLARE_API_TOKEN }}
-          FEEDBACK_ACCOUNT_SECRET: ${{ secrets.FEEDBACK_ACCOUNT_SECRET }}
-        run: |
-          if [ -n "$FEEDBACK_ACCOUNT_SECRET" ]; then
-            printf '%s' "$FEEDBACK_ACCOUNT_SECRET" | npx wrangler secret put FEEDBACK_ACCOUNT_SECRET
-          else
-            echo "FEEDBACK_ACCOUNT_SECRET not set in repo secrets; feedback account linking stays unavailable."
-          fi
-
-  deploy-remote-gateway:
-    needs: deploy-accounts
-    if: github.ref == 'refs/heads/platform'
-    runs-on: ubuntu-latest
-    environment: production
-    steps:
-      - uses: actions/checkout@3d3c42e5aac5ba805825da76410c181273ba90b1 # v7
-      - uses: actions/setup-node@820762786026740c76f36085b0efc47a31fe5020 # v7
-        with:
-          node-version: "22"
-          cache: npm
-          cache-dependency-path: workers/remote-gateway/package-lock.json
-      - name: Validate gateway secret
-        env:
-          REMOTE_GATEWAY_TOKEN: ${{ secrets.REMOTE_GATEWAY_TOKEN }}
-        run: test -n "$REMOTE_GATEWAY_TOKEN"
-      - name: Validate and deploy
-        working-directory: workers/remote-gateway
-        env:
-          CLOUDFLARE_API_TOKEN: ${{ secrets.CLOUDFLARE_API_TOKEN }}
-        run: |
-          npm ci
-          npm test
-          npm run typecheck
-          npx wrangler deploy
-      - name: Sync gateway secret
-        working-directory: workers/remote-gateway
-        env:
-          CLOUDFLARE_API_TOKEN: ${{ secrets.CLOUDFLARE_API_TOKEN }}
-          REMOTE_GATEWAY_TOKEN: ${{ secrets.REMOTE_GATEWAY_TOKEN }}
-        run: printf '%s' "$REMOTE_GATEWAY_TOKEN" | npx wrangler secret put REMOTE_GATEWAY_TOKEN

.github/workflows/deploy-crash-worker.yml

@@ -1,254 +0,0 @@
-name: Deploy crash worker
-
-on:
-  workflow_dispatch:
-    inputs:
-      firebase_data_action:
-        description: Firebase crash history operation (migration actions do not deploy the Worker)
-        required: true
-        default: none
-        type: choice
-        options:
-          - none
-          - dry-run
-          - apply
-          - verify-only
-      confirmation:
-        description: Enter APPLY_FIREBASE_CRASH_DATA when selecting apply
-        required: false
-        default: ''
-        type: string
-
-permissions:
-  contents: read
-
-concurrency:
-  group: deploy-crash-worker
-  cancel-in-progress: false
-
-jobs:
-  deploy:
-    if: github.ref == 'refs/heads/platform' && inputs.firebase_data_action == 'none'
-    runs-on: ubuntu-latest
-    environment: production
-    steps:
-      - uses: actions/checkout@3d3c42e5aac5ba805825da76410c181273ba90b1 # v7
-      - uses: actions/setup-node@820762786026740c76f36085b0efc47a31fe5020 # v7
-        with:
-          node-version: '22'
-          cache: npm
-          cache-dependency-path: workers/crash-report/package-lock.json
-      - name: Validate
-        working-directory: workers/crash-report
-        run: |
-          npm ci
-          npm run typecheck
-          npm test
-      - name: Apply and verify diagnostics v2 D1 migration
-        working-directory: workers/crash-report
-        env:
-          CLOUDFLARE_API_TOKEN: ${{ secrets.CLOUDFLARE_API_TOKEN }}
-        run: npm run migrate:diagnostics-v2
-      - name: Apply and verify Firebase crash D1 migration
-        working-directory: workers/crash-report
-        env:
-          CLOUDFLARE_API_TOKEN: ${{ secrets.CLOUDFLARE_API_TOKEN }}
-        run: npm run migrate:firebase-crash
-      - name: Apply dashboard performance indexes
-        working-directory: workers/crash-report
-        env:
-          CLOUDFLARE_API_TOKEN: ${{ secrets.CLOUDFLARE_API_TOKEN }}
-        run: npm run migrate:dashboard-indexes
-      - name: Apply telemetry queue receipts schema
-        working-directory: workers/crash-report
-        env:
-          CLOUDFLARE_API_TOKEN: ${{ secrets.CLOUDFLARE_API_TOKEN }}
-        run: npx wrangler d1 execute reasonix-crash --remote --file=migrate-telemetry-queue.sql
-      - name: Apply and verify feedback D1 migration
-        working-directory: workers/crash-report
-        env:
-          CLOUDFLARE_API_TOKEN: ${{ secrets.CLOUDFLARE_API_TOKEN }}
-        run: |
-          npx wrangler d1 execute reasonix-crash --remote --file=migrate-feedback.sql
-          out=$(npx wrangler d1 execute reasonix-crash --remote --json --command "SELECT name FROM sqlite_master WHERE name IN ('feedback','feedback_quota','feedback_status_created','feedback_install_created','feedback_status_version','feedback_quota_day')")
-          for name in feedback feedback_quota feedback_status_created feedback_install_created feedback_status_version feedback_quota_day; do
-            printf '%s' "$out" | grep -q "\"$name\"" || { echo "missing $name after migration"; exit 1; }
-          done
-      - name: Apply and verify feedback triage D1 migration
-        working-directory: workers/crash-report
-        env:
-          CLOUDFLARE_API_TOKEN: ${{ secrets.CLOUDFLARE_API_TOKEN }}
-        run: |
-          npx wrangler d1 execute reasonix-crash --remote --file=migrate-feedback-triage.sql
-          names="feedback_releases feedback_releases_install feedback_replies feedback_blocks feedback_trust feedback_public_images feedback_config feedback_audit feedback_replies_receipt feedback_replies_unhandled feedback_blocks_expires feedback_public_images_receipt feedback_audit_at feedback_install_status_updated feedback_reply_attachments feedback_reply_attachments_receipt"
-          list=$(for n in $names; do printf "'%s'," "$n"; done | sed 's/,$//')
-          out=$(npx wrangler d1 execute reasonix-crash --remote --json --command "SELECT name FROM sqlite_master WHERE name IN ($list)")
-          for name in $names; do
-            printf '%s' "$out" | grep -q "\"$name\"" || { echo "missing $name after migration"; exit 1; }
-          done
-          echo "Trusted installs (hash prefix only) for review:"
-          npx wrangler d1 execute reasonix-crash --remote --json --command "SELECT substr(install_hash,1,8) AS prefix, created_at, expires_at FROM feedback_trust ORDER BY created_at LIMIT 200"
-      - name: Apply and verify feedback adoption D1 migration
-        working-directory: workers/crash-report
-        env:
-          CLOUDFLARE_API_TOKEN: ${{ secrets.CLOUDFLARE_API_TOKEN }}
-        run: |
-          npx wrangler d1 execute reasonix-crash --remote --file=migrate-feedback-adoptions.sql
-          names="feedback_adoptions feedback_adoptions_install feedback_adoptions_item feedback_level_state"
-          list=$(for n in $names; do printf "'%s'," "$n"; done | sed 's/,$//')
-          out=$(npx wrangler d1 execute reasonix-crash --remote --json --command "SELECT name FROM sqlite_master WHERE name IN ($list)")
-          for name in $names; do
-            printf '%s' "$out" | grep -q "\"$name\"" || { echo "missing $name after migration"; exit 1; }
-          done
-      - name: Apply and verify feedback account link D1 migration
-        working-directory: workers/crash-report
-        env:
-          CLOUDFLARE_API_TOKEN: ${{ secrets.CLOUDFLARE_API_TOKEN }}
-        run: |
-          npx wrangler d1 execute reasonix-crash --remote --file=migrate-feedback-account-links.sql
-          names="feedback_account_links feedback_account_links_account"
-          list=$(for n in $names; do printf "'%s'," "$n"; done | sed 's/,$//')
-          out=$(npx wrangler d1 execute reasonix-crash --remote --json --command "SELECT name FROM sqlite_master WHERE name IN ($list)")
-          for name in $names; do
-            printf '%s' "$out" | grep -q "\"$name\"" || { echo "missing $name after migration"; exit 1; }
-          done
-      - name: Apply and verify feedback contribution board D1 migration
-        working-directory: workers/crash-report
-        env:
-          CLOUDFLARE_API_TOKEN: ${{ secrets.CLOUDFLARE_API_TOKEN }}
-        run: |
-          npx wrangler d1 execute reasonix-crash --remote --file=migrate-feedback-board.sql
-          names="feedback_board_optin feedback_board_delisted"
-          list=$(for n in $names; do printf "'%s'," "$n"; done | sed 's/,$//')
-          out=$(npx wrangler d1 execute reasonix-crash --remote --json --command "SELECT name FROM sqlite_master WHERE name IN ($list)")
-          for name in $names; do
-            printf '%s' "$out" | grep -q "\"$name\"" || { echo "missing $name after migration"; exit 1; }
-          done
-      - name: Apply Studio telemetry schema
-        working-directory: workers/crash-report
-        env:
-          CLOUDFLARE_API_TOKEN: ${{ secrets.CLOUDFLARE_API_TOKEN }}
-        run: npx wrangler d1 execute reasonix-crash --remote --file=migrate-studio-telemetry.sql
-      - name: Apply isolated telemetry database schema
-        working-directory: workers/crash-report
-        env:
-          CLOUDFLARE_API_TOKEN: ${{ secrets.CLOUDFLARE_API_TOKEN }}
-        run: npm run migrate:telemetry-db
-      - name: Apply registry performance indexes and install rollup
-        working-directory: workers/crash-report
-        env:
-          CLOUDFLARE_API_TOKEN: ${{ secrets.CLOUDFLARE_API_TOKEN }}
-        run: npm run migrate:registry-indexes
-      - name: Sync Firebase crash secrets
-        working-directory: workers/crash-report
-        env:
-          CLOUDFLARE_API_TOKEN: ${{ secrets.CLOUDFLARE_API_TOKEN }}
-          FIREBASE_DATABASE_URL: ${{ secrets.FIREBASE_DATABASE_URL }}
-          FIREBASE_CLIENT_EMAIL: ${{ secrets.FIREBASE_CLIENT_EMAIL }}
-          FIREBASE_PRIVATE_KEY: ${{ secrets.FIREBASE_PRIVATE_KEY }}
-        run: |
-          configured=0
-          [ -n "$FIREBASE_DATABASE_URL" ] && configured=$((configured + 1))
-          [ -n "$FIREBASE_CLIENT_EMAIL" ] && configured=$((configured + 1))
-          [ -n "$FIREBASE_PRIVATE_KEY" ] && configured=$((configured + 1))
-          if [ "$configured" -ne 0 ] && [ "$configured" -ne 3 ]; then
-            echo "Firebase crash secrets must be either all configured or all absent."
-            exit 1
-          fi
-          node -e 'process.stdout.write(JSON.stringify({FIREBASE_DATABASE_URL:process.env.FIREBASE_DATABASE_URL||null,FIREBASE_CLIENT_EMAIL:process.env.FIREBASE_CLIENT_EMAIL||null,FIREBASE_PRIVATE_KEY:process.env.FIREBASE_PRIVATE_KEY||null}))' | npx wrangler secret bulk
-      - name: Deploy
-        working-directory: workers/crash-report
-        env:
-          CLOUDFLARE_API_TOKEN: ${{ secrets.CLOUDFLARE_API_TOKEN }}
-        run: |
-          npx wrangler deploy
-      - name: Sync feedback secrets
-        working-directory: workers/crash-report
-        env:
-          CLOUDFLARE_API_TOKEN: ${{ secrets.CLOUDFLARE_API_TOKEN }}
-          FEEDBACK_TOKEN_SECRET: ${{ secrets.FEEDBACK_TOKEN_SECRET }}
-          FEEDBACK_ADMIN_TOKEN: ${{ secrets.FEEDBACK_ADMIN_TOKEN }}
-          OPS_EMIT_TOKEN: ${{ secrets.OPS_EMIT_TOKEN }}
-          FEEDBACK_ACCOUNT_SECRET: ${{ secrets.FEEDBACK_ACCOUNT_SECRET }}
-        run: |
-          node -e 'process.stdout.write(JSON.stringify({FEEDBACK_TOKEN_SECRET:process.env.FEEDBACK_TOKEN_SECRET||null,FEEDBACK_ADMIN_TOKEN:process.env.FEEDBACK_ADMIN_TOKEN||null,OPS_EMIT_TOKEN:process.env.OPS_EMIT_TOKEN||null,FEEDBACK_ACCOUNT_SECRET:process.env.FEEDBACK_ACCOUNT_SECRET||null}))' | npx wrangler secret bulk
-      # Mirrors the ALERT_WEBHOOK repo secret into the worker so the ingest
-      # sentinel can push alerts (see runIngestSentinel). Managed here so
-      # nobody needs local Cloudflare credentials; when the repo secret is
-      # unset the sentinel stays log-only.
-      - name: Sync alert webhook secret
-        working-directory: workers/crash-report
-        env:
-          CLOUDFLARE_API_TOKEN: ${{ secrets.CLOUDFLARE_API_TOKEN }}
-          ALERT_WEBHOOK: ${{ secrets.ALERT_WEBHOOK }}
-        run: |
-          if [ -z "$ALERT_WEBHOOK" ]; then
-            echo "ALERT_WEBHOOK repo secret not set; removing any existing worker secret."
-            printf '{"ALERT_WEBHOOK":null}' | npx wrangler secret bulk
-            exit 0
-          fi
-          printf '%s' "$ALERT_WEBHOOK" | npx wrangler secret put ALERT_WEBHOOK
-
-  migrate-firebase-data:
-    if: github.event_name == 'workflow_dispatch' && inputs.firebase_data_action != 'none'
-    runs-on: ubuntu-latest
-    environment: canary
-    steps:
-      - uses: actions/checkout@3d3c42e5aac5ba805825da76410c181273ba90b1 # v7
-      - name: Require the protected production branch
-        run: |
-          if [ "$GITHUB_REF" != "refs/heads/platform" ]; then
-            echo "Firebase crash data migration must run from platform."
-            exit 1
-          fi
-      - uses: actions/setup-node@820762786026740c76f36085b0efc47a31fe5020 # v7
-        with:
-          node-version: '22'
-          cache: npm
-          cache-dependency-path: workers/crash-report/package-lock.json
-      - name: Validate
-        working-directory: workers/crash-report
-        run: |
-          npm ci
-          npm run typecheck
-          npm test
-      - name: Run Firebase crash history operation
-        working-directory: workers/crash-report
-        env:
-          CLOUDFLARE_API_TOKEN: ${{ secrets.CLOUDFLARE_API_TOKEN }}
-          FIREBASE_DATABASE_URL: ${{ secrets.FIREBASE_DATABASE_URL }}
-          FIREBASE_CLIENT_EMAIL: ${{ secrets.FIREBASE_CLIENT_EMAIL }}
-          FIREBASE_PRIVATE_KEY: ${{ secrets.FIREBASE_PRIVATE_KEY }}
-          FIREBASE_DATA_ACTION: ${{ inputs.firebase_data_action }}
-          FIREBASE_DATA_CONFIRMATION: ${{ inputs.confirmation }}
-        run: |
-          configured=0
-          [ -n "$CLOUDFLARE_API_TOKEN" ] && configured=$((configured + 1))
-          [ -n "$FIREBASE_DATABASE_URL" ] && configured=$((configured + 1))
-          [ -n "$FIREBASE_CLIENT_EMAIL" ] && configured=$((configured + 1))
-          [ -n "$FIREBASE_PRIVATE_KEY" ] && configured=$((configured + 1))
-          if [ "$configured" -ne 4 ]; then
-            echo "Cloudflare and Firebase migration secrets must all be configured."
-            exit 1
-          fi
-
-          case "$FIREBASE_DATA_ACTION" in
-            dry-run)
-              npm run migrate:firebase-data
-              ;;
-            apply)
-              if [ "$FIREBASE_DATA_CONFIRMATION" != "APPLY_FIREBASE_CRASH_DATA" ]; then
-                echo "Apply requires the exact confirmation APPLY_FIREBASE_CRASH_DATA."
-                exit 1
-              fi
-              npm run migrate:firebase-data -- --apply
-              npm run migrate:firebase-data -- --verify-only
-              ;;
-            verify-only)
-              npm run migrate:firebase-data -- --verify-only
-              ;;
-            *)
-              echo "Unsupported Firebase crash data action."
-              exit 1
-              ;;
-          esac

.github/workflows/deploy-forum-worker.yml

@@ -1,38 +0,0 @@
-name: Deploy forum worker
-
-on:
-  workflow_dispatch:
-
-permissions:
-  contents: read
-
-concurrency:
-  group: deploy-forum-worker
-  cancel-in-progress: false
-
-jobs:
-  deploy:
-    if: github.ref == 'refs/heads/platform'
-    runs-on: ubuntu-latest
-    environment: production
-    steps:
-      - uses: actions/checkout@3d3c42e5aac5ba805825da76410c181273ba90b1 # v7
-      - uses: pnpm/action-setup@ea17c68df8912ef543352723c149a84f56e3d413 # v6.1.0
-        with:
-          version: 10
-          run_install: false
-      - uses: actions/setup-node@820762786026740c76f36085b0efc47a31fe5020 # v7
-        with:
-          node-version: "24"
-          cache: pnpm
-          cache-dependency-path: workers/forum/pnpm-lock.yaml
-      - name: Deploy
-        working-directory: workers/forum
-        env:
-          CLOUDFLARE_API_TOKEN: ${{ secrets.CLOUDFLARE_API_TOKEN }}
-        run: |
-          pnpm install --frozen-lockfile
-          pnpm test
-          pnpm typecheck
-          npx wrangler d1 execute reasonix-forum --remote --file=migrate-performance-indexes.sql
-          npx wrangler deploy

.github/workflows/deploy-ops-events.yml

@@ -1,44 +0,0 @@
-name: Deploy ops events relay
-
-on:
-  workflow_dispatch:
-
-permissions:
-  contents: read
-
-concurrency:
-  group: deploy-ops-events
-  cancel-in-progress: false
-
-jobs:
-  deploy:
-    if: github.ref == 'refs/heads/platform'
-    runs-on: ubuntu-latest
-    environment: production
-    steps:
-      - uses: actions/checkout@3d3c42e5aac5ba805825da76410c181273ba90b1 # v7
-      - uses: actions/setup-node@820762786026740c76f36085b0efc47a31fe5020 # v7
-        with:
-          node-version: '22'
-          cache: npm
-          cache-dependency-path: workers/ops-events/package-lock.json
-      - name: Validate
-        working-directory: workers/ops-events
-        run: |
-          npm ci
-          npm run typecheck
-          npm test
-      - name: Deploy
-        working-directory: workers/ops-events
-        env:
-          CLOUDFLARE_API_TOKEN: ${{ secrets.CLOUDFLARE_API_TOKEN }}
-        run: npx wrangler deploy
-      - name: Sync secrets
-        working-directory: workers/ops-events
-        env:
-          CLOUDFLARE_API_TOKEN: ${{ secrets.CLOUDFLARE_API_TOKEN }}
-          GITHUB_WEBHOOK_SECRET: ${{ secrets.OPS_GITHUB_WEBHOOK_SECRET }}
-          OPS_LISTEN_TOKEN: ${{ secrets.OPS_LISTEN_TOKEN }}
-          OPS_EMIT_TOKEN: ${{ secrets.OPS_EMIT_TOKEN }}
-        run: |
-          node -e 'process.stdout.write(JSON.stringify({GITHUB_WEBHOOK_SECRET:process.env.GITHUB_WEBHOOK_SECRET||null,OPS_LISTEN_TOKEN:process.env.OPS_LISTEN_TOKEN||null,OPS_EMIT_TOKEN:process.env.OPS_EMIT_TOKEN||null}))' | npx wrangler secret bulk

.github/workflows/platform-ci.yml

@@ -1,89 +0,0 @@
-name: Platform CI
-
-on:
-  push:
-    branches: [platform]
-  pull_request:
-    branches: [platform]
-
-permissions:
-  contents: read
-
-concurrency:
-  group: platform-ci-${{ github.ref }}
-  cancel-in-progress: true
-
-jobs:
-  accounts:
-    runs-on: ubuntu-latest
-    defaults:
-      run:
-        working-directory: workers/accounts
-    steps:
-      - uses: actions/checkout@3d3c42e5aac5ba805825da76410c181273ba90b1 # v7
-      - uses: pnpm/action-setup@ea17c68df8912ef543352723c149a84f56e3d413 # v6.1.0
-        with:
-          version: 10
-          run_install: false
-      - uses: actions/setup-node@820762786026740c76f36085b0efc47a31fe5020 # v7
-        with:
-          node-version: "24"
-          cache: pnpm
-          cache-dependency-path: workers/accounts/pnpm-lock.yaml
-      - run: pnpm install --frozen-lockfile
-      - run: pnpm test
-      - run: pnpm typecheck
-
-  forum:
-    runs-on: ubuntu-latest
-    defaults:
-      run:
-        working-directory: workers/forum
-    steps:
-      - uses: actions/checkout@3d3c42e5aac5ba805825da76410c181273ba90b1 # v7
-      - uses: pnpm/action-setup@ea17c68df8912ef543352723c149a84f56e3d413 # v6.1.0
-        with:
-          version: 10
-          run_install: false
-      - uses: actions/setup-node@820762786026740c76f36085b0efc47a31fe5020 # v7
-        with:
-          node-version: "24"
-          cache: pnpm
-          cache-dependency-path: workers/forum/pnpm-lock.yaml
-      - run: pnpm install --frozen-lockfile
-      - run: pnpm test
-      - run: pnpm typecheck
-
-  crash-report:
-    runs-on: ubuntu-latest
-    defaults:
-      run:
-        working-directory: workers/crash-report
-    steps:
-      - uses: actions/checkout@3d3c42e5aac5ba805825da76410c181273ba90b1 # v7
-      - uses: actions/setup-node@820762786026740c76f36085b0efc47a31fe5020 # v7
-        with:
-          node-version: "22"
-          cache: npm
-          cache-dependency-path: workers/crash-report/package-lock.json
-      - run: npm ci
-      - run: npm run typecheck
-      - run: npm test
-      - run: npx wrangler deploy --dry-run
-
-  remote-gateway:
-    runs-on: ubuntu-latest
-    defaults:
-      run:
-        working-directory: workers/remote-gateway
-    steps:
-      - uses: actions/checkout@3d3c42e5aac5ba805825da76410c181273ba90b1 # v7
-      - uses: actions/setup-node@820762786026740c76f36085b0efc47a31fe5020 # v7
-        with:
-          node-version: "22"
-          cache: npm
-          cache-dependency-path: workers/remote-gateway/package-lock.json
-      - run: npm ci
-      - run: npm test
-      - run: npm run typecheck
-      - run: npx wrangler deploy --dry-run

.gitignore

@@ -1,16 +1,26 @@
 node_modules/
-.pnpm-store/
-.npm/
-.wrangler/
 dist/
 coverage/
 .env
-.env.*
-*.local
-**/.firebase-crash-migration-state.json
-**/.firebase-crash-migration-state.json.tmp-*
+.env.local
+*.log
+npm-debug.log*
+yarn-debug.log*
+yarn-error.log*
+.pnpm-debug.log*
 .DS_Store
 Thumbs.db
 .idea/
 .vscode/
-temp/
+*.tsbuildinfo
+transcripts/
+sessions/
+*.jsonl
+!tests/**/*.jsonl
+# Committed reference transcripts so readers can reasonix replay / diff
+# the v0.1 bench results without an API key.
+!benchmarks/tau-bench/transcripts/
+!benchmarks/tau-bench/transcripts/*.jsonl
+.turbo/
+# Local-only Claude Code settings — personal overrides, never committed.
+.claude/settings.local.json

.node-version

@@ -1 +0,0 @@
-24.20.0

CAPACITY.md

@@ -1,71 +0,0 @@
-# Reasonix platform capacity contract
-
-This document defines what “ready for 10,000 concurrent users” means. It is an
-acceptance contract, not a claim that the current production system has already
-passed the target.
-
-## Budget and design constraints
-
-- Keep recurring infrastructure within CNY 200/month at the current traffic
-  level. Prefer Cloudflare managed primitives over idle servers.
-- Never make synchronous telemetry storage part of a product launch path.
-- Validate at the edge, durably enqueue, then persist asynchronously.
-- A successful HTTP response must expose whether the event was `queued`,
-  `stored`, `sampled`, or `ignored` through
-  `x-reasonix-telemetry-result`. HTTP 202 alone is not proof of durable intake.
-- Production load tests require owner approval. The repository probe refuses
-  remote and production targets unless they are unlocked separately.
-
-## Service-level objectives
-
-| Path | Workload | Pass condition |
-| --- | --- | --- |
-| Telemetry admission | 10,000 distributed requests over 60 seconds | >=99.9% `queued`, p95 <=500 ms, no 5xx |
-| Telemetry drain | 10,000 queued events, batches up to 100 | backlog returns to zero within 15 minutes, no DLQ growth |
-| Identity session read | 1,000 requests/second for 5 minutes | >=99.9% success, p95 <=300 ms |
-| Registry public read | 1,000 requests/second for 5 minutes | >=99.9% success, p95 <=300 ms |
-| Admin dashboards | 20 concurrent viewers for 10 minutes | >=99% success, p95 <=2 seconds |
-
-“Distributed” matters because per-IP abuse protection intentionally rejects a
-single machine long before the platform capacity limit. A staging environment
-must mirror production bindings and use isolated databases, queues, and R2.
-
-## Required evidence before calling the platform stable
-
-1. A saved probe report with request count, latency percentiles, HTTP statuses,
-   durable/sample ratios, queue backlog peak, drain time, D1 query latency, and
-   DLQ delta.
-2. A rollback or traffic-shed procedure exercised in staging.
-3. Alerts for sustained 5xx, queue backlog age, DLQ growth, D1 overload, and
-   database size thresholds.
-4. Seven consecutive days without unexplained ingestion gaps after a production
-   rollout.
-
-## Current known gaps
-
-- CLI and Studio telemetry use a verified isolated D1 read/write plane. The
-  legacy copy is retained temporarily as a rollback snapshot. Legacy desktop
-  telemetry is entering a dry-run-verified dual-write migration; diagnostic
-  denominators are queried separately so the final cutover does not require
-  cross-database SQL joins.
-- The global telemetry budget is currently 1,000 events/minute. It protects the
-  database but cannot satisfy the 10,000/minute durable-intake target.
-- Queue consumption is deliberately serialized for D1. A delivery is persisted
-  as one atomic D1 batch with two statements per valid envelope (at most 200
-  statements for the configured 100-message queue batch). Drain throughput must
-  be measured before raising the global intake budget.
-- Read replication and the Sessions API have not yet been enabled for eligible
-  read-heavy paths.
-
-## Local probe
-
-Run the Worker locally, then run:
-
-```sh
-npm run capacity:telemetry -- --requests 1000 --concurrency 50
-```
-
-This probe fails when the p95 target or durable-intake ratio is missed. A local
-run validates the admission contract and tool; it is not evidence for global
-capacity. Remote runs need `--allow-remote`, and `*.reasonix.io` additionally
-needs `--allow-production` after an approved test window.

CLAUDE.md

@@ -1,6 +0,0 @@
-# Reasonix
-
-The project's standing instructions live in `REASONIX.md` — one file, read by
-both Reasonix and Claude Code. Add rules there, never here.
-
-@REASONIX.md

README.md

@@ -1,28 +1,779 @@
-# Reasonix Platform
+<p align="center">
+  <img src="docs/logo.svg" alt="Reasonix — DeepSeek-native agent framework" width="640"/>
+</p>
 
-This branch contains only the shared Reasonix service platform:
+<p align="center">
+  <em>Cache-first agent loop for DeepSeek V4 (flash + pro) — Ink TUI, MCP first-class, no LangChain.</em>
+</p>
 
-- identity and account services;
-- community and forum services;
-- crash, diagnostics, telemetry, and registry services;
-- Cloudflare Worker, D1, Queue, and R2 configuration;
-- production deployment workflows for those services.
+# Reasonix
 
-Product clients live on `main-v2` and `studio`. The public website lives on
-`website`. Production deployments are accepted only from this branch.
+[![npm version](https://img.shields.io/npm/v/reasonix.svg)](https://www.npmjs.com/package/reasonix)
+[![CI](https://github.com/esengine/reasonix/actions/workflows/ci.yml/badge.svg)](https://github.com/esengine/reasonix/actions/workflows/ci.yml)
+[![license](https://img.shields.io/npm/l/reasonix.svg)](./LICENSE)
+[![downloads](https://img.shields.io/npm/dm/reasonix.svg)](https://www.npmjs.com/package/reasonix)
+[![node](https://img.shields.io/node/v/reasonix.svg)](./package.json)
 
-## Services
+**A DeepSeek-native AI coding agent in your terminal.** Edits files as
+reviewable SEARCH/REPLACE blocks. Ink TUI. MCP first-class. No
+LangChain.
 
-| Directory | Responsibility |
-| --- | --- |
-| `workers/accounts` | Shared identity, sessions, device grants, and email login |
-| `workers/forum` | Community forum APIs |
-| `workers/crash-report` | Diagnostics, telemetry, registry, and admin dashboards |
+---
 
-Each service owns its package manager lockfile, tests, schema, migrations, and
-Wrangler configuration. Run validation from the service directory before using
-the matching manual production deployment workflow.
+## Quick start (60 seconds)
 
-The accounts worker removes expired sessions, email tokens, and device grants
-daily. Raw queued telemetry is retained in R2 for eight days; aggregated D1
-rows follow the service-specific retention windows in the crash worker.
+**1. Get a DeepSeek API key.** Free credit on signup:
+<https://platform.deepseek.com/api_keys>
+
+**2. Point it at a project.** No install needed.
+
+```bash
+cd my-project
+npx reasonix code
+```
+
+First run walks you through a 30-second wizard (paste API key → pick
+preset → multi-select MCP servers). Every run after that drops you
+straight in.
+
+**3. Ask it to edit.** The model proposes edits as SEARCH/REPLACE
+blocks — nothing hits disk until you `/apply`.
+
+```
+reasonix code › users.ts 里 findByEmail 对大小写敏感导致登录失败，帮我改
+
+assistant
+  ▸ tool<search_files> → src/users.ts, src/users.test.ts
+  ▸ tool<read_file>    → (src/users.ts, 412 chars)
+  ▸ 找到了。findByEmail 直接用 === 比对。改成小写规范化并补一条测试。
+
+src/users.ts
+<<<<<<< SEARCH
+  return users.find(u => u.email === email);
+=======
+  const needle = email.toLowerCase();
+  return users.find(u => u.email.toLowerCase() === needle);
+>>>>>>> REPLACE
+
+▸ 1 pending edit across 1 file — /apply to write · /discard to drop
+
+reasonix code › /apply
+▸ ✓ applied src/users.ts
+```
+
+Requires Node ≥ 20.10. macOS, Linux, Windows (PowerShell / Git Bash /
+Windows Terminal). Press `Esc` anytime to abort; `/help` for the full
+command list.
+
+---
+
+## `reasonix code` — pair programmer in your terminal
+
+Scoped to the directory you launch from. The model has native
+`read_file` / `write_file` / `edit_file` / `list_directory` /
+`search_files` / `directory_tree` / `get_file_info` /
+`create_directory` / `move_file` tools, all sandboxed — any path that
+resolves outside the launch root (including `..` and symlink escapes)
+is refused. Plus `run_command` with a read-only allowlist; anything
+state-mutating (`npm install`, `git commit`, …) is gated behind a
+confirmation picker.
+
+### Walkthrough: explore before editing
+
+For "what does this code do?" questions the model uses the read-side
+tools and replies in prose — no SEARCH/REPLACE blocks, no file
+writes. Ask to change something only when you mean it:
+
+```
+reasonix code › 这个项目的路由是怎么组织的？
+assistant
+  ▸ tool<directory_tree> → (src/ tree, 47 entries)
+  ▸ tool<read_file> → (src/router.ts, 1.2 KB)
+  ▸ 路由分三层：顶层 AppRouter 注册 tab，每个 tab 用 React Router 的
+    nested routes 写子路径，最后 …
+```
+
+If an `edit_file` SEARCH block doesn't match the file byte-for-byte,
+the edit is refused loudly rather than fuzzy-matched. The model sees
+the error and retries — silent wrong edits are worse than visible
+rejections.
+
+### Plan mode — review before executing
+
+For anything bigger than a typo, the model is encouraged to propose a
+markdown plan first. You'll see a picker with **Approve / Refine /
+Cancel**:
+
+```
+reasonix code › 把 auth 从 JWT 迁移到 session cookies
+
+▸ plan submitted — awaiting your review
+────────────────────────────────────────
+## Summary
+Swap JWT middleware for session cookies, keep user table intact.
+
+## Files
+- src/auth/middleware.ts — replace `verifyJwt` with `readSession`
+- src/auth/session.ts — new file, in-memory store + signed cookie
+- src/routes/login.ts — return Set-Cookie instead of a token
+- tests/auth/*.test.ts — update fixtures
+
+## Risks
+- Existing logged-in users get logged out (no migration).
+- Session store is in-memory; restart clears sessions.
+────────────────────────────────────────
+  ▸ Approve and implement
+    Refine — explore more
+    Cancel
+```
+
+**Force it** with `/plan` — enters an explicit read-only phase where
+the model *must* submit a plan before any edit or non-allowlisted
+shell call will execute. Use for high-stakes changes you want to
+audit before the model touches disk. `/plan off` or picker
+Approve/Cancel exits.
+
+### Prompt prefixes — `!cmd` and `@path`
+
+Two inline shortcuts that don't need a slash:
+
+**`!<cmd>` — run a shell command in the sandbox and feed it to the
+model.** Typed at the prompt, like bash. Output lands in the visible
+log AND in the session so the model's next turn reasons about it:
+
+```
+reasonix code › !git status --short
+▸ M src/users.ts
+▸ M src/users.test.ts
+
+reasonix code › 把这两个文件的改动说明一下
+assistant
+  ▸ tool<read_file> → src/users.ts, src/users.test.ts
+  ▸ …
+```
+
+No allowlist gate — user-typed shell = explicit consent. 60s timeout,
+32k char cap, survives session resume since 0.5.14.
+
+**`@path/to/file` — inline a file under "Referenced files."** Start
+typing `@` and a picker appears (↑/↓ navigate, Tab/Enter to insert).
+Good for "what does @src/users.ts do?" without making the model
+`read_file` it first. Sandboxed: relative paths only, no `..` escape,
+64KB per-file cap. Recent files rank higher.
+
+### `/commit` — stage + commit in one step
+
+```
+reasonix code › /commit "fix: findByEmail case-insensitive"
+▸ git add -A && git commit -m "fix: findByEmail case-insensitive"
+  [main a1b2c3d] fix: findByEmail case-insensitive
+```
+
+### Things to try
+
+- `/tool 1` — dump the last tool call's full output (when the 400-char
+  inline clip isn't enough).
+- `/think` — see the model's full reasoning for the last turn
+  (thinking-mode models: v4-flash / v4-pro / reasoner alias).
+- `/undo` — roll back the last applied edit batch.
+- `/new` — start fresh in the same directory without losing the
+  session file.
+- `/effort high` — step down from the default `max` agent-class
+  reasoning_effort for cheaper/faster turns on simple tasks.
+- `npx reasonix code --preset max` — v4-pro + 3-way self-consistency
+  branching for gnarly refactors.
+- `npx reasonix code src/` — narrower sandbox (only `src/` is
+  writable).
+- `npx reasonix code --no-session` — ephemeral; nothing saved.
+
+### `reasonix stats` — how much did you actually save?
+
+Every turn `reasonix chat|code|run` runs appends a compact record
+(tokens + cost + what Claude Sonnet 4.6 would have charged) to
+`~/.reasonix/usage.jsonl`. `reasonix stats` with no args rolls that
+log into today / week / month / all-time windows:
+
+```
+Reasonix usage — /Users/you/.reasonix/usage.jsonl
+
+            turns  cache hit    cost (USD)      vs Claude     saved
+----------------------------------------------------------------------
+today           8      95.1%     $0.004821        $0.1348      96.4%
+week           34      93.8%     $0.023104        $0.6081      96.2%
+month         127      94.2%     $0.081530        $2.1452      96.2%
+all-time      342      94.0%     $0.210881        $5.8934      96.4%
+```
+
+Privacy: only tokens, costs, and the session name you chose land
+in the file. No prompts, no completions, no tool arguments.
+`reasonix stats <transcript>` keeps the old per-file summary
+(assistant turns + tool calls) for scripts that already use it.
+
+### Staying current
+
+The panel header shows the running version next to `Reasonix` (e.g.
+`Reasonix v0.5.21 · deepseek-v4-pro · harvest · max …`, the trailing
+`max` is the reasoning-effort badge — `/effort high` to step down).
+A quiet 24-hour background check against
+the npm registry surfaces a yellow `update: X.Y.Z` on the right side
+of the same row when a newer version has been published. No blocking,
+no nagging — the check runs once per day max and is silent on failure
+(offline, firewall, etc.).
+
+```bash
+reasonix update             # print current vs latest, run `npm i -g reasonix@latest`
+reasonix update --dry-run   # print the plan without running anything
+```
+
+Running via `npx`? The command detects that and prints a
+cache-refresh hint instead — npx picks up the newest version on
+its next invocation automatically.
+
+### Project conventions — `REASONIX.md`
+
+Drop a `REASONIX.md` in the project root and its contents are pinned
+into the system prompt every launch. Committable team memory — house
+conventions, domain glossary, things the model keeps forgetting:
+
+```bash
+cat > REASONIX.md <<'EOF'
+# Notes for Reasonix
+- Use snake_case for new Python modules; legacy camelCase modules keep their style.
+- `cargo check` is in the auto-run allowlist; full `cargo test` needs confirmation.
+- The `api/` dir mirrors `backend/` — keep schemas in sync.
+EOF
+```
+
+Re-launch (or `/new`) to pick it up; the prefix is hashed once per
+session to keep the DeepSeek cache warm. `/memory` prints what's
+currently pinned. `REASONIX_MEMORY=off` disables every memory source
+for CI / offline repro.
+
+### User memory — `~/.reasonix/memory/`
+
+A second, **private per-user** memory layer lives under your home
+directory. Unlike `REASONIX.md` it's never committed, and the model
+can write to it itself via the `remember` tool. Two scopes:
+
+- `~/.reasonix/memory/global/` — cross-project (your preferences,
+  tooling).
+- `~/.reasonix/memory/<project-hash>/` — scoped to one sandbox root
+  in `reasonix code` (decisions, local facts, per-repo shortcuts).
+
+Each scope keeps an always-loaded `MEMORY.md` index of one-liners
+plus zero or more `<name>.md` detail files (loaded on demand via
+`recall_memory`). Writes land immediately; pinning into the system
+prompt takes effect on next `/new` or launch so the cache prefix
+stays stable for the current session.
+
+```
+reasonix code › 我用 bun 而不是 npm，请以后都用 bun 跑构建
+
+assistant
+  ▸ tool<remember> → project/bun_build saved
+    "Build command on this machine is `bun run build`"
+```
+
+**Slash**: `/memory` · `/memory list` · `/memory show <name>` ·
+`/memory forget <name>` · `/memory clear <scope> confirm`.
+**Model tools**: `remember(type, scope, name, description, content)` ·
+`forget(scope, name)` · `recall_memory(scope, name)`.
+
+Project scope is only available inside `reasonix code` (needs a real
+sandbox root to hash); plain `reasonix` gets the global scope only.
+
+### Skills — user-authored prompt packs
+
+Skills are prose instruction blocks you drop on disk. Reasonix pins
+their names + one-line descriptions into the system prompt; the
+model can call `run_skill({name: "..."})` on its own when a match
+fits, or you can type `/skill <name> [args]` to run one manually.
+
+Two scopes, same layout as user memory:
+
+- `<project>/.reasonix/skills/` — per-project skills (commit them to
+  share with your team, or add to `.gitignore` for personal drafts).
+- `~/.reasonix/skills/` — global skills available everywhere.
+
+Either layout works: `<name>/SKILL.md` (preferred — can bundle
+additional assets alongside) or flat `<name>.md`.
+
+```markdown
+---
+name: review
+description: Review uncommitted changes and flag risks
+---
+
+Run `git diff` on staged and unstaged changes. Summarize what each
+hunk does, call out potential regressions, and list files that might
+need additional tests. Don't propose edits unless I ask.
+```
+
+Use it:
+
+```
+reasonix code › /skill review
+▸ running skill: review
+assistant
+  ▸ tool<run_command> → git diff --cached
+  ▸ 3 改动，1 个需要回归测试 …
+```
+
+Or let the model pick autonomously — because the skill's name +
+description are pinned in the prefix, asking "帮我看下未提交的改动有没
+有风险" triggers `run_skill({name: "review"})` without you typing the
+slash command.
+
+**Slash**: `/skill` (list) · `/skill show <name>` · `/skill <name>
+[args]` (inject body as user turn).
+
+**Deliberately not tied** to any other client's directory convention
+(`.claude/skills`, etc.) — Reasonix is model-agnostic at the
+conversation layer. Any SKILL.md you author works; the body is
+prose, so skills authored for other tools usually port over unchanged
+(Reasonix's tool names differ — `filesystem` / `shell` / `web` — but
+the model reads the instructions and picks our equivalents).
+
+### Hooks — automate around tool calls and turns
+
+Drop a `settings.json` under `.reasonix/` (project or `~/`) and
+Reasonix will fire shell commands at four well-known points in
+the loop: before a tool runs, after a tool returns, before your
+prompt reaches the model, and after the turn ends.
+
+```json
+// <project>/.reasonix/settings.json   ← committable
+// ~/.reasonix/settings.json           ← per-user
+{
+  "hooks": {
+    "PreToolUse":       [{ "match": "edit_file|write_file", "command": "bun scripts/guard.ts" }],
+    "PostToolUse":      [{ "match": "edit_file", "command": "biome format --write" }],
+    "UserPromptSubmit": [{ "command": "echo $(date +%s) >> ~/.reasonix/prompts.log" }],
+    "Stop":             [{ "command": "bun test --run", "timeout": 60000 }]
+  }
+}
+```
+
+Each hook is a shell command. Reasonix invokes it with stdin = a
+JSON envelope describing the event:
+
+```json
+{ "event": "PreToolUse", "cwd": "/path/to/project",
+  "toolName": "edit_file", "toolArgs": { "path": "src/x.ts", "..." } }
+```
+
+Exit code drives the decision:
+
+- **0** — pass; loop continues normally
+- **2** — block (only on `PreToolUse` / `UserPromptSubmit`); the
+  hook's stderr becomes the synthetic tool result the model sees,
+  or the prompt is dropped entirely
+- **anything else** — warn; loop continues, stderr renders as a
+  yellow row inline
+
+`match` is anchored regex on the tool name; `*` or omitted matches
+every tool. Project hooks fire before global hooks. Default
+timeouts: 5s for blocking events, 30s for logging events; per-hook
+`timeout` overrides.
+
+**Slash**: `/hooks` (list active hooks) · `/hooks reload` (re-read
+`settings.json` from disk without losing your session).
+
+### Staying current from inside the TUI
+
+`/update` inside a running session shows your current version, the
+last-resolved latest version (from the quiet 24h background check),
+and the shell command to run. The slash does *not* spawn
+`npm install` — stdio:inherit into a running Ink renderer corrupts
+the display. Exit the session and run `reasonix update` in a
+fresh shell when you actually want to install.
+
+---
+
+## `reasonix` — also works as general chat
+
+Same TUI, no filesystem tools unless you opt in via MCP. Good for
+drafting, Q&A, schema design, architecture discussions, or driving
+your own MCP servers. Sessions persist per name under
+`~/.reasonix/sessions/`.
+
+```bash
+npx reasonix                             # uses saved config + wizard-selected MCP
+npx reasonix --preset smart              # reasoner + R1 harvest for this run
+npx reasonix --session design            # named session — resume later with --session design
+```
+
+Bridge your own MCP servers on the fly:
+
+```bash
+npx reasonix \
+  --mcp "fs=npx -y @modelcontextprotocol/server-filesystem /tmp/safe" \
+  --mcp "kb=https://mcp.example.com/sse"
+```
+
+MCP tools go through the same Cache-First + repair + context-safety
+plumbing as native tools — 32k result cap, live progress-notification
+rendering, retries.
+
+---
+
+## Commands inside the session
+
+**Core**
+
+| command | what it does |
+|---|---|
+| `/help` · `/?` | full command reference with hints |
+| `/status` | current model · flags · context · session |
+| `/new` · `/reset` | fresh conversation in the same session |
+| `/clear` | clear visible scrollback only (log kept) |
+| `/retry` | truncate and resend your last message (fresh sample) |
+| `/exit` · `/quit` | quit |
+
+**Model**
+
+| command | what it does |
+|---|---|
+| `/preset <fast\|smart\|max>` | one-tap bundle (model + harvest + branch) |
+| `/model <id>` | switch DeepSeek model (`deepseek-v4-flash`, `deepseek-v4-pro`, plus `deepseek-chat` / `deepseek-reasoner` compat aliases) |
+| `/models` | list live models from DeepSeek `/models` endpoint |
+| `/harvest [on\|off]` | toggle R1 plan-state extraction |
+| `/branch <N\|off>` | run N parallel samples per turn, pick best (N ≥ 2) |
+| `/effort <high\|max>` | reasoning_effort cap — `max` is the agent default, `high` is cheaper/faster |
+| `/think` | dump the last turn's full thinking-mode reasoning |
+
+**Context & tools**
+
+| command | what it does |
+|---|---|
+| `/mcp` | list attached MCP servers and their tools / resources / prompts |
+| `/resource [uri]` | browse + read MCP resources (no arg → list URIs; `<uri>` → fetch) |
+| `/prompt [name]` | browse + fetch MCP prompts |
+| `/tool [N]` | dump the Nth tool call's full output (1 = latest) |
+| `/compact [tokens]` | shrink oversized tool results in the log (default 4000 tokens/result) |
+| `/context` | break down where context tokens are going (system / tools / log) |
+| `/stats` | cross-session cost dashboard (today / week / month / all-time) |
+| `/keys` | keyboard shortcuts + prompt prefixes (`!` / `@` / `/`) cheatsheet |
+
+**Memory & skills**
+
+| command | what it does |
+|---|---|
+| `/memory` | show pinned memory (REASONIX.md + ~/.reasonix/memory) |
+| `/memory list` · `show <name>` · `forget <name>` · `clear <scope> confirm` | manage the store |
+| `/skill` · `/skill list` | list discovered skills (project + global) |
+| `/skill show <name>` | dump one skill's body |
+| `/skill <name> [args]` | run a skill (inject body as user turn) |
+
+**Sessions**
+
+| command | what it does |
+|---|---|
+| `/sessions` | list saved sessions (current marked with `▸`) |
+| `/forget` | delete the current session from disk |
+| `/setup` | reconfigure (exit and run `reasonix setup`) |
+
+**Code mode only** (`reasonix code`)
+
+| command | what it does |
+|---|---|
+| `/apply` | commit the pending SEARCH/REPLACE blocks to disk |
+| `/discard` | drop the pending edit blocks without writing |
+| `/undo` | roll back the last applied edit batch |
+| `/commit "msg"` | `git add -A && git commit -m "msg"` |
+| `/plan [on\|off]` | toggle read-only plan mode |
+| `/apply-plan` | force-approve a pending plan |
+
+**Keyboard**
+
+- `Enter` — submit
+- `Shift+Enter` / `Ctrl+J` — newline (multi-line paste also supported;
+  `\` + Enter as a portable fallback)
+- `↑` / `↓` — walk prompt history while idle; navigate slash-autocomplete
+- `Tab` / `Enter` on a `/foo` prefix — accept the highlighted suggestion
+- `Esc` — abort the current turn (stops the API call, cancels any
+  in-flight tool, rejects pending MCP requests)
+- `y` / `n` on confirm prompts — hotkey accept / reject
+
+---
+
+## Sessions and safety nets
+
+- Sessions live as JSONL under `~/.reasonix/sessions/<name>.jsonl`
+  (per directory for `reasonix code`). Every message appended
+  atomically; `Ctrl+C` never loses context.
+- Tool results are capped at 32k chars per call. Oversized sessions
+  self-heal on load (shrinks + rewrites the file).
+- Malformed `assistant.tool_calls` / `tool` pairing is validated on
+  every outgoing API call so a corrupted session can't keep 400ing.
+- Context gauge turns yellow at 50%, red at 80% with a `/compact`
+  nudge. Approaching the 1M-token window (V4 flash + pro) triggers an
+  automatic compaction attempt before falling back to a forced summary.
+- The `reasonix code` sandbox refuses any path that resolves outside
+  the launch directory, including symlink escape and `..` traversal.
+
+### Troubleshooting: duplicate rows / ghost rendering
+
+Some Windows terminals (Git Bash / MINTTY / winpty-wrapped shells)
+don't fully implement the ANSI cursor-up escapes Ink uses to repaint
+the live spinner region. Symptom: spinners, streaming previews, or
+tool-result rows print multiple copies into scrollback instead of
+overwriting in place.
+
+If you hit this, run with plain mode:
+
+```bash
+REASONIX_UI=plain npx reasonix code
+```
+
+Plain mode suppresses live/animated rows and disables the internal
+tick timer. You lose the streaming preview and spinners but gain
+stable scrollback. Windows Terminal, PowerShell 7 in Windows
+Terminal, and WezTerm don't need this opt-out.
+
+---
+
+## Web search — on by default
+
+The model has two web tools the moment you launch: `web_search` and
+`web_fetch`. No flag, no API key, no signup. When you ask about
+something the model wasn't trained on (new releases, current events,
+obscure APIs), it decides to call `web_search` on its own; if a
+snippet isn't enough it follows up with `web_fetch`.
+
+Backed by **Mojeek**'s public search page — an independent web
+index, bot-friendly, no cookies/sessions. Coverage on niche or very
+recent queries can be thinner than Google/Bing, but it's reliable
+from scripts. (DDG was the original backend but started serving
+anti-bot pages in 2026.)
+
+**Turn it off** (offline mode / privacy / CI):
+
+```json
+// ~/.reasonix/config.json
+{ "apiKey": "sk-…", "search": false }
+```
+
+```bash
+REASONIX_SEARCH=off npx reasonix code
+```
+
+**Bring your own** (Kagi, SearXNG, internal caches): implement the
+`WebSearchProvider` interface and call
+`registerWebTools(registry, { provider })` yourself, or bridge an
+existing MCP search server via `--mcp`.
+
+---
+
+## MCP — bring your own tools
+
+Any [MCP](https://spec.modelcontextprotocol.io/) server works. The
+wizard lets you pick from a catalog, or drive it by flag:
+
+```bash
+# stdio (local subprocess)
+npx reasonix --mcp "fs=npx -y @modelcontextprotocol/server-filesystem /tmp/safe"
+
+# multiple at once
+npx reasonix \
+  --mcp "fs=npx -y @modelcontextprotocol/server-filesystem /tmp/safe" \
+  --mcp "demo=npx tsx examples/mcp-server-demo.ts"
+
+# HTTP+SSE (remote / hosted)
+npx reasonix --mcp "kb=https://mcp.example.com/sse"
+```
+
+`reasonix mcp list` shows the curated catalog. `reasonix mcp inspect
+<spec>` connects once and dumps the server's tools / resources /
+prompts without starting a chat. Progress notifications from
+long-running tools (2025-03-26 spec) render live as a progress bar
+in the spinner.
+
+Supported transports: **stdio** (local command) and **HTTP+SSE**
+(remote, MCP 2024-11-05 spec).
+
+---
+
+## CLI reference
+
+```bash
+npx reasonix code [path]                 # coding mode scoped to path (default: cwd)
+npx reasonix                             # chat (uses saved config)
+npx reasonix setup                       # reconfigure the wizard
+npx reasonix chat --session work         # named session
+npx reasonix chat --no-session           # ephemeral
+npx reasonix run "ask anything"          # one-shot, streams to stdout
+npx reasonix stats session.jsonl         # summarize a transcript
+npx reasonix replay chat.jsonl           # rebuild cost/cache from a transcript
+npx reasonix diff a.jsonl b.jsonl --md   # compare two transcripts
+npx reasonix mcp list                    # curated MCP catalog
+npx reasonix mcp inspect <spec>          # probe a single MCP server
+npx reasonix sessions                    # list saved sessions
+```
+
+Common flags:
+
+```bash
+--preset <fast|smart|max>   # bundle (model + harvest + branch)
+--model <id>                # explicit model id
+--harvest / --no-harvest    # R1 plan-state extraction
+--branch <N>                # self-consistency budget
+--mcp "name=cmd args…"      # attach an MCP server (repeatable)
+--transcript path.jsonl     # write a JSONL transcript on the side
+--session <name>            # named session (default: per-dir for code mode)
+--no-session                # ephemeral
+--no-config                 # ignore ~/.reasonix/config.json (CI-friendly)
+```
+
+Env vars (win over config):
+
+```bash
+export DEEPSEEK_API_KEY=sk-...
+export DEEPSEEK_BASE_URL=https://...   # optional alternate endpoint
+export REASONIX_MEMORY=off              # disable REASONIX.md + user memory
+export REASONIX_SEARCH=off              # disable web_search / web_fetch
+export REASONIX_UI=plain                # disable live rows (ghosting workaround)
+```
+
+---
+
+## Library usage
+
+```ts
+import {
+  CacheFirstLoop,
+  DeepSeekClient,
+  ImmutablePrefix,
+  ToolRegistry,
+} from "reasonix";
+
+const client = new DeepSeekClient(); // reads DEEPSEEK_API_KEY from env
+const tools = new ToolRegistry();
+
+tools.register({
+  name: "add",
+  description: "Add two integers",
+  parameters: {
+    type: "object",
+    properties: { a: { type: "integer" }, b: { type: "integer" } },
+    required: ["a", "b"],
+  },
+  fn: ({ a, b }: { a: number; b: number }) => a + b,
+});
+
+const loop = new CacheFirstLoop({
+  client,
+  tools,
+  prefix: new ImmutablePrefix({
+    system: "You are a math helper.",
+    toolSpecs: tools.specs(),
+  }),
+  harvest: true,
+  branch: 3,
+});
+
+for await (const ev of loop.step("What is 17 + 25?")) {
+  if (ev.role === "assistant_final") console.log(ev.content);
+}
+console.log(loop.stats.summary());
+```
+
+`ChatOptions.seedTools` accepts a pre-built `ToolRegistry` for
+callers who want the `reasonix code` loop wiring without the CLI
+wrapper. See [docs/ARCHITECTURE.md](docs/ARCHITECTURE.md) for
+internals.
+
+---
+
+## Benchmarks — verify the cache-hit claim yourself
+
+Every abstraction here earns its weight against a DeepSeek-specific
+property — dirt-cheap tokens, R1 reasoning traces, automatic prefix
+caching, JSON mode. Generic wrappers leave these on the table.
+
+| | Reasonix default | generic frameworks |
+|---|---|---|
+| Prefix-stable loop (→ 85–95% cache hit) | yes | no (prompts rebuilt each turn) |
+| Auto-flatten deep tool schemas | yes | no (DeepSeek drops args) |
+| Retry with jittered backoff (429/503) | yes | no (custom callbacks) |
+| Scavenge tool calls leaked into `<think>` | yes | no |
+| Call-storm breaker on identical-arg repeats | yes | no |
+| Live cache-hit / cost / vs-Claude panel | yes | no |
+
+On the same τ-bench-lite workload — 8 multi-turn tool-use tasks × 3
+repeats = 48 runs per side, live DeepSeek `deepseek-chat`, sole
+variable prefix stability:
+
+| metric | baseline (cache-hostile) | Reasonix | delta |
+|---|---:|---:|---:|
+| cache hit | 46.6% | **94.4%** | +47.7 pp |
+| cost / task | $0.002599 | $0.001579 | **−39%** |
+| pass rate | 96% (23/24) | **100% (24/24)** | — |
+
+**Reproduce without spending an API credit:**
+
+```bash
+git clone https://github.com/esengine/reasonix.git && cd reasonix && npm install
+npx reasonix replay benchmarks/tau-bench/transcripts/t01_address_happy.reasonix.r1.jsonl
+npx reasonix diff \
+  benchmarks/tau-bench/transcripts/t01_address_happy.baseline.r1.jsonl \
+  benchmarks/tau-bench/transcripts/t01_address_happy.reasonix.r1.jsonl
+```
+
+The committed JSONL transcripts carry per-turn `usage`, `cost`, and
+`prefixHash`. Reasonix's prefix hash stays byte-stable across every
+model call; baseline's churns on every turn. The cache delta is
+*mechanically* attributable to log stability, not to a different
+system prompt.
+
+Full 48-run report:
+[`benchmarks/tau-bench/report.md`](./benchmarks/tau-bench/report.md).
+Reproduce with your own API key: `npx tsx
+benchmarks/tau-bench/runner.ts --repeats 3`.
+
+MCP reference runs (one single prefix hash across all 5 turns even
+with two concurrent MCP subprocesses):
+
+| server | turns | cache hit | cost | vs Claude |
+|---|---:|---:|---:|---:|
+| bundled demo (`add` / `echo` / `get_time`) | 2 | **96.6%** (turn 2) | $0.000254 | −94.0% |
+| official `server-filesystem` | 5 | **96.7%** | $0.001235 | −97.0% |
+| **both concurrently** | 5 | **81.1%** | $0.001852 | −95.9% |
+
+---
+
+## Non-goals
+
+- **Multi-agent orchestration / sub-agents** (use LangGraph).
+- **Workflow DSL / DAG scheduler / parallel-branch engine** — skills
+  are prose; the model sequences via the normal tool-use loop.
+  Keeps single-loop + append-only + cache-first invariants intact.
+- **Multi-provider abstraction** (use LiteLLM). Reasonix is
+  DeepSeek-only on purpose — every pillar (cache-first loop, R1
+  harvesting, tool-call repair) is tuned against DeepSeek-specific
+  behavior and economics. Coupling to one backend is the feature.
+- **RAG / vector stores** (use LlamaIndex).
+- **Web UI / SaaS.**
+
+Reasonix does DeepSeek, deeply.
+
+---
+
+## Development
+
+```bash
+git clone https://github.com/esengine/reasonix.git
+cd reasonix
+npm install
+npm run dev code        # run CLI from source via tsx
+npm run build           # tsup to dist/
+npm test                # vitest (1007 tests)
+npm run lint            # biome
+npm run typecheck       # tsc --noEmit
+```
+
+---
+
+## License
+
+MIT

REASONIX.md

@@ -1,14 +0,0 @@
-# Reasonix Platform instructions
-
-- This branch owns shared online services only. Do not add product client or
-  public website code here.
-- Keep every production deployment manually triggered and restricted to the
-  `platform` branch.
-- Database changes must be backward-compatible, idempotent, and accompanied by
-  a migration or runtime schema guard.
-- Ingest endpoints must validate before enqueueing, acknowledge only durable
-  work, and remain safe under retries.
-- Add tests at the HTTP, queue, or storage boundary where behavior becomes
-  externally observable.
-- Never commit credentials, tokens, customer content, or personal user data.
-- Comments are English and explain only non-obvious constraints.

SECURITY.md

@@ -1,137 +0,0 @@
-# Security Policy
-
-## Supported Versions
-
-Reasonix security fixes are prioritized for the currently developed Go rewrite
-and the current 1.x release line.
-
-| Version or branch | Security support |
-| --- | --- |
-| `main-v2` / 1.x releases | Supported |
-| `v1` / 0.x legacy branch | Critical fixes only, where practical |
-| Older releases, forks, or modified builds | Not covered unless the issue is reproducible upstream |
-
-If you are unsure whether a version is affected, report against the newest
-released 1.x version and include the exact version or commit you tested.
-
-## Reporting a Vulnerability
-
-Please report security issues privately. Do not open a public issue with exploit
-details, secrets, crash dumps, or proof-of-concept payloads.
-
-Preferred reporting path:
-
-1. Use GitHub private vulnerability reporting for this repository, if available.
-2. If private reporting is not available to you, open a minimal public issue
-   asking for a private maintainer contact path. Do not include exploit details
-   in that issue.
-
-Please include:
-
-- Affected Reasonix version, commit, operating system, and installation method.
-- The feature or surface involved, such as CLI, desktop app, HTTP `serve`, bot
-  gateway, MCP plugin, built-in tool, updater, or configuration loading.
-- Clear reproduction steps using dummy credentials and non-sensitive files.
-- The expected impact, such as secret disclosure, arbitrary file access,
-  command execution, sandbox escape, authentication bypass, or supply-chain risk.
-- Any relevant logs with API keys, tokens, local paths, and personal data
-  redacted.
-
-Do not send real provider API keys, bot credentials, OAuth tokens, private
-workspace files, or third-party user data.
-
-## Security Boundaries
-
-Reasonix is a local coding agent. Many features intentionally operate on the
-user's local machine and workspace, including file reads, file writes, shell
-commands, MCP plugins, language servers, bot sessions, and model-provider
-requests. A finding is security-relevant when it crosses a supported boundary or
-bypasses an explicit guard.
-
-Supported boundaries include:
-
-- Workspace confinement for file operations that are documented or implemented
-  as workspace-scoped.
-- Permission checks for tool calls, shell commands, file writes, and approvals.
-- Sandbox behavior for built-in shell execution where the platform supports it.
-- Secret handling for provider keys, bot credentials, OAuth tokens, plugin
-  headers, and credential-store fallback files.
-- HTTP `serve` protections for the unauthenticated local server, including
-  localhost binding assumptions, JSON-only state-changing requests, and CORS
-  restrictions.
-- Desktop and bot session isolation, including per-workspace session metadata
-  and configured bot allowlists.
-- Updater, install, and release verification paths.
-
-The following are normally treated as trusted local/operator-controlled inputs
-unless another bug lets an untrusted actor supply them:
-
-- CLI arguments and text typed directly by the local user.
-- Project configuration files intentionally loaded from the current workspace.
-- Explicit `@path` references supplied by the local user to attach local files.
-- MCP servers, language servers, hooks, and slash commands installed or enabled
-  by the local user.
-- Provider base URLs and model names configured by the local user.
-
-The following can be security issues when reachable by an untrusted actor or
-when they bypass the intended boundary:
-
-- Reading or writing files outside the configured workspace without explicit
-  local-user intent.
-- Following symlinks or path traversal to escape workspace confinement.
-- Running shell commands or external tools without the required permission gate.
-- Leaking credentials, environment variables, prompt history, local files, or bot
-  messages to logs, model providers, MCP servers, crash reports, or telemetry.
-- Allowing a website to drive the local HTTP server through CSRF, CORS, or
-  content-type bypasses.
-- Letting a bot user outside the configured allowlist submit prompts, approve
-  tools, or access a project workspace.
-- Trusting unverified update artifacts, plugin definitions, or downloaded
-  binaries.
-
-## `@` File References
-
-Reasonix supports `@path` references so users can include local files and images
-in a prompt. This is intentional local functionality, but implementations must
-preserve these invariants:
-
-- In workspace-scoped sessions, relative and absolute paths must resolve under
-  the active workspace root before file content is read or attached.
-- Path traversal such as `..` must not escape the workspace root.
-- Symlinks must not be usable to bypass the intended workspace boundary.
-- Unscoped local CLI compatibility must not be exposed to remote, bot, or
-  browser-controlled inputs unless an equivalent workspace boundary is applied.
-- File content should be size-limited and binary content should not be dumped as
-  prompt text.
-
-Static analysis alerts about path expressions should be triaged against these
-rules: user-controlled path data is expected, but the access must either stay
-inside the configured workspace or be clearly limited to trusted local CLI use.
-
-## Out of Scope
-
-The following reports are usually out of scope unless they demonstrate a bypass
-of one of the boundaries above:
-
-- A local user intentionally asks Reasonix to read, edit, or send their own
-  files to a configured model provider.
-- A local user installs or enables a malicious MCP server, hook, slash command,
-  language server, or shell command and then grants it permission.
-- A configured model provider, proxy, or MCP server receives data the user
-  intentionally sent to it.
-- Denial-of-service issues that only affect the local user's own session and do
-  not corrupt files, leak secrets, or bypass permissions.
-- Issues requiring administrator/root access on the user's machine before
-  interacting with Reasonix.
-- Vulnerabilities in third-party services, models, proxies, or plugins that are
-  not caused by Reasonix behavior.
-
-## Coordinated Disclosure
-
-This is a community-maintained project. Maintainers will make a best-effort
-assessment, ask follow-up questions when needed, and coordinate fixes before
-public disclosure for confirmed vulnerabilities.
-
-Please give maintainers reasonable time to investigate and release a fix before
-publishing exploit details. If you plan to disclose on a timeline, include that
-timeline in your initial report.

benchmarks/README.md

@@ -0,0 +1,115 @@
+# Benchmarks
+
+This is where validation lives. The v0.1 milestone gates on a reproducible
+tool-use eval that compares, on the same tasks:
+
+1. **Baseline** — a deliberately cache-hostile agent (fresh timestamp +
+   shuffled tool spec each turn), representative of how generic frameworks
+   wire up DeepSeek.
+2. **Reasonix** — the same tools and system prompt, driven through
+   `CacheFirstLoop` so the byte prefix stays stable turn-over-turn.
+
+Both modes share the same `DeepSeekClient`, so the *only* meaningful
+difference is prefix stability — any cache-hit / cost gap is attributable to
+Pillar 1 of the architecture, nothing else.
+
+## Scope — this is τ-bench-*lite*
+
+We don't ship a full port of [Sierra's τ-bench](https://github.com/sierra-research/tau-bench)
+(airline + retail, Python). Instead:
+
+- `tau-bench/tasks.ts` hand-authors 8 retail-flavored multi-turn tasks
+  that exercise tool use, identity verification, refusal, and mid-conversation
+  goal change.
+- The task schema (`tau-bench/types.ts`) mirrors τ-bench's shape — stateful
+  tools, an LLM user simulator, end-state DB predicates — so real upstream
+  tasks can later drop in without harness changes.
+- All success predicates are **deterministic DB checks**, not LLM judges.
+  Refusal tasks pass iff the DB is unchanged.
+
+## Files
+
+```
+tau-bench/
+├── types.ts       — TaskDefinition / RunResult / BenchReport shapes
+├── db.ts          — tiny in-memory WorldState + cloneDb
+├── tasks.ts       — the 8 seed tasks + shared tool factories
+├── user-sim.ts    — LLM user simulator (V3, T=0.1)
+├── baseline.ts    — naive cache-hostile agent runner
+├── runner.ts      — orchestrates user-sim × agent × task × mode
+└── report.ts      — turns a results-*.json into a report.md
+```
+
+## Quickstart
+
+```bash
+# dry-run: no API calls, just validate the harness is wired up
+npx tsx benchmarks/tau-bench/runner.ts --dry
+
+# full run: both modes, all tasks, 1 repeat
+export DEEPSEEK_API_KEY=sk-...
+npx tsx benchmarks/tau-bench/runner.ts
+
+# tighten variance: 3 repeats per task
+npx tsx benchmarks/tau-bench/runner.ts --repeats 3
+
+# narrow to one task while iterating
+npx tsx benchmarks/tau-bench/runner.ts --task t01_address_happy --verbose
+
+# render the report
+npx tsx benchmarks/tau-bench/report.ts benchmarks/tau-bench/results-<date>.json
+
+# emit per-run transcripts so you can reasonix replay / diff them
+npx tsx benchmarks/tau-bench/runner.ts --transcripts-dir ./transcripts
+npx reasonix diff \
+  ./transcripts/t01_address_happy.baseline.r1.jsonl \
+  ./transcripts/t01_address_happy.reasonix.r1.jsonl \
+  --md diff.md
+```
+
+The runner writes `benchmarks/tau-bench/results-<iso-timestamp>.json`. Point
+`report.ts` at it (or pass `--out report.md` to override the output path).
+
+When `--transcripts-dir <path>` is set, each `(task, mode, repeat)` run also
+writes a `<taskId>.<mode>.r<n>.jsonl` transcript into that directory —
+these carry per-turn `usage`, `cost`, and (for Reasonix) the
+`prefixHash`, so `reasonix replay` and `reasonix diff` can rebuild the
+economics offline.
+
+## CLI flags
+
+| flag | default | meaning |
+|---|---|---|
+| `--task <id>` | all | run only one task by id |
+| `--mode baseline` \| `reasonix` | both | restrict to one mode |
+| `--repeats <N>` | 1 | repeat each (task, mode) pair N times |
+| `--model <id>` | deepseek-chat | agent model |
+| `--user-model <id>` | deepseek-chat | user-simulator model |
+| `--out <path>` | `results-<ts>.json` | results file path |
+| `--transcripts-dir <path>` | off | write one transcript per run for replay/diff |
+| `--dry` | off | skip the LLM; only wire-check |
+| `--verbose` \| `-v` | off | print every user / agent / tool line |
+
+## What a run costs
+
+A full run (8 tasks × 2 modes × 1 repeat) does on the order of 30–60
+DeepSeek V3 calls — well under $0.05 at current pricing. `--repeats 3`
+triples that.
+
+## Adding tasks
+
+1. Add a `TaskDefinition` to `tau-bench/tasks.ts`. Reuse the tool factories
+   defined at the top of that file, or add new ones (remember: factories so
+   tools close over the *per-run* db snapshot).
+2. Make the `check` predicate check the end-state DB, not the agent's text —
+   agents phrase things differently on every run.
+3. Run `--task <your_id> --verbose` to eyeball the transcript.
+
+Non-goals (for this harness):
+
+- LLM-as-judge — brittle and expensive, DB predicates are enough.
+- Streaming comparison — the harness uses `stream: false` in Reasonix mode
+  so both runners make the exact same request shape.
+- Claude head-to-head — we estimate Claude's cost from token counts using
+  Sonnet 4.6 pricing (see `src/telemetry.ts`); running Claude for real is
+  out of scope.

benchmarks/harvest/README.md

@@ -0,0 +1,106 @@
+# Harvest eval harness (Pillar 2)
+
+Measures Pillar 2 (R1 Thought Harvesting) the same way `tau-bench/`
+measures Pillar 1 (Cache-First Loop): isolate one variable, produce
+numbers anyone can reproduce.
+
+## What's different from τ-bench-lite?
+
+Deliberately different task shape:
+
+| | τ-bench-lite | harvest-bench |
+|---|---|---|
+| task style | multi-turn tool-use | single-turn reasoning |
+| user simulator | yes (LLM) | no |
+| DB state | yes | no |
+| checker | DB-predicate | regex + set/value compare |
+| target | Pillar 1 | Pillar 2 |
+| model | deepseek-chat (default) | deepseek-reasoner (only R1 has `reasoning_content` for harvest to work on) |
+
+The two harnesses answer different questions:
+
+- **τ-bench-lite**: *"Does Cache-First actually cut cost on real tool-use
+  workflows?"* (yes — 47.7pp cache, −39% cost on 48-run data.)
+- **harvest-bench**: *"Does the extra V3 harvest call add measurable
+  value above plain R1?"* (TBD — run it to find out.)
+
+## Modes
+
+Three modes isolate one variable each:
+
+| mode | model | harvest | what it measures |
+|---|---|---|---|
+| `baseline` | deepseek-chat | off | floor reference — V3 at its best |
+| `reasoner` | deepseek-reasoner | off | raw R1 gain over V3 on reasoning |
+| `reasoner-harvest` | deepseek-reasoner | on | R1 + the extra V3 harvest call |
+
+Deltas:
+
+- `baseline → reasoner` answers "is R1 worth the price on these
+  problems?"
+- `reasoner → reasoner-harvest` answers "is the harvest call worth
+  its incremental cost?"
+
+## Quickstart
+
+```bash
+# Dry-run — no API, smoke-test the wiring
+npx tsx benchmarks/harvest/runner.ts --dry
+
+# Full run (live DeepSeek, costs ~$0.20-0.60 for 6 tasks × 3 modes × 1 repeat)
+export DEEPSEEK_API_KEY=sk-...
+npx tsx benchmarks/harvest/runner.ts
+
+# Tighter run with 3 repeats (~$0.60-2.00)
+npx tsx benchmarks/harvest/runner.ts --repeats 3
+
+# Only the hard tasks (skip the easy floor)
+npx tsx benchmarks/harvest/runner.ts --task pseudoprime_base2
+npx tsx benchmarks/harvest/runner.ts --task derangements_d7
+npx tsx benchmarks/harvest/runner.ts --task euler_quadratic_break
+
+# Bump per-call timeout (reasoner + harvest occasionally blow past the 120s default)
+npx tsx benchmarks/harvest/runner.ts --timeout 600
+
+# Per-run transcripts so you can reasonix replay / diff them
+npx tsx benchmarks/harvest/runner.ts --repeats 3 --transcripts-dir transcripts/
+
+# Render report
+npx tsx benchmarks/harvest/report.ts benchmarks/harvest/results-*.json
+```
+
+## Tasks (v0.3 seed)
+
+Split into two bands:
+
+**Easy band** — V3 chat solves these, so baseline has a real pass rate and the bench has a reference floor.
+
+| id | shape | why |
+|---|---|---|
+| `mod7_list` | number theory, 29-element list | R1 often tries enumeration first, then reaches for modular arithmetic — clean rejectedPaths signal |
+| `flips_until_3heads` | probability, single integer | classic recurrence; R1 either derives or recalls, harvest should see hypotheses diverge |
+| `three_hats` | logic puzzle, one-word answer | pure deduction chain, tests harvest's ability to extract the nested reasoning |
+
+**Hard band** — picked specifically for known V3 failure modes. If R1 systematically beats V3 on these, and harvest further beats R1-only, we have our Pillar 2 story.
+
+| id | shape | why V3 tends to fail |
+|---|---|---|
+| `pseudoprime_base2` | smallest Fermat pseudoprime to base 2 = **341** | V3 often answers 561 (Carmichael) or some other composite it remembers — R1 actually checks 2^n mod n |
+| `derangements_d7` | D_7 = **1854** | V3 approximates via n!/e and rounds wrong, or recalls D_6/D_8; R1 uses the recurrence D_n=(n−1)(D_{n−1}+D_{n−2}) |
+| `euler_quadratic_break` | smallest n where n²+n+41 is composite = **40** | V3 frequently confuses with n²−n+41 (first fails at 41); R1 checks small n systematically |
+
+Adding a new task: see `tasks.ts`. Any checker that's deterministic is
+fair game — extract numeric/list/text with regex, compare with set
+equality or string matching.
+
+## Non-goals
+
+- **No LLM-as-judge.** Brittle and expensive; defeats the point of a
+  reproducible bench. If a checker is too hard to write deterministically,
+  the task doesn't belong here.
+- **No tool-use tasks.** Those live in `tau-bench/`. Different story.
+- **No multi-turn.** v0.3 harness is single-turn Q/A. Multi-turn reasoning
+  eval is separate scope.
+- **No benchmark-data cherry-picking.** When results come in, we publish
+  them whether they validate Pillar 2 or not. "harvest didn't help on
+  these 3 tasks" is still useful information.

benchmarks/harvest/report.md

@@ -0,0 +1,82 @@
+# Reasonix harvest eval (Pillar 2)
+
+**Date:** 2026-04-21T16:44:21.011Z
+**Tasks:** 6 · repeats × 1 · modes: baseline, reasoner, reasoner-harvest
+**Reasonix version:** 0.2.2
+
+## Summary by mode
+
+| mode | runs | pass rate | cache hit | cost / run | harvest turns | subgoals | uncertainties |
+|---|---:|---:|---:|---:|---:|---:|---:|
+| baseline | 6 | 100% | 39.5% | $0.001371 | 0.0 | 0.0 | 0.0 |
+| reasoner | 6 | 100% | 74.2% | $0.004170 | 0.0 | 0.0 | 0.0 |
+| reasoner-harvest | 6 | 83% | 61.6% | $0.003304 | 0.8 | 2.8 | 1.3 |
+
+## Deltas
+
+- **baseline → reasoner**
+  - pass rate: 0pp
+  - cost: ×3.04 (each run costs more)
+  - harvest signal / run: 0.0 subgoals, 0.0 uncertainties
+
+- **baseline → reasoner-harvest**
+  - pass rate: -17pp
+  - cost: ×2.41 (each run costs more)
+  - harvest signal / run: 2.8 subgoals, 1.3 uncertainties
+
+## Per-task breakdown
+
+| task | mode | rep | verdict | cache | cost | sg | un | note |
+|---|---|---:|:---:|---:|---:|---:|---:|---|
+| mod7_list | baseline | 1 | ✅ | 86.5% | $0.001361 | 0 | 0 |  |
+| mod7_list | reasoner | 1 | ✅ | 86.5% | $0.004797 | 0 | 0 |  |
+| mod7_list | reasoner-harvest | 1 | ✅ | 86.5% | $0.003045 | 4 | 2 |  |
+| flips_until_3heads | baseline | 1 | ✅ | 92.8% | $0.001198 | 0 | 0 |  |
+| flips_until_3heads | reasoner | 1 | ✅ | 92.8% | $0.002830 | 0 | 0 |  |
+| flips_until_3heads | reasoner-harvest | 1 | ✅ | 92.8% | $0.001691 | 4 | 0 |  |
+| three_hats | baseline | 1 | ✅ | 57.7% | $0.001514 | 0 | 0 |  |
+| three_hats | reasoner | 1 | ✅ | 57.7% | $0.009340 | 0 | 0 |  |
+| three_hats | reasoner-harvest | 1 | ✅ | 57.7% | $0.009651 | 3 | 2 |  |
+| pseudoprime_base2 | baseline | 1 | ✅ | 0.0% | $0.001894 | 0 | 0 |  |
+| pseudoprime_base2 | reasoner | 1 | ✅ | 75.3% | $0.003128 | 0 | 0 |  |
+| pseudoprime_base2 | reasoner-harvest | 1 | ❌ | 0.0% | $0.000000 | 0 | 0 | This operation was aborted |
+| derangements_d7 | baseline | 1 | ✅ | 0.0% | $0.001273 | 0 | 0 |  |
+| derangements_d7 | reasoner | 1 | ✅ | 71.9% | $0.003492 | 0 | 0 |  |
+| derangements_d7 | reasoner-harvest | 1 | ✅ | 71.9% | $0.002843 | 3 | 2 |  |
+| euler_quadratic_break | baseline | 1 | ✅ | 0.0% | $0.000985 | 0 | 0 |  |
+| euler_quadratic_break | reasoner | 1 | ✅ | 61.0% | $0.001431 | 0 | 0 |  |
+| euler_quadratic_break | reasoner-harvest | 1 | ✅ | 61.0% | $0.002594 | 3 | 2 |  |
+
+## Scope
+
+Unlike τ-bench-lite, these tasks are single-turn reasoning problems (no user simulator, no DB, no tool calls). Checkers are deterministic — regex + set / value compare, never an LLM judge. The point is to isolate whether the Pillar 2 harvest step adds measurable value above plain reasoner usage.
+
+Interpretation: `baseline` (chat / V3) is a floor. `reasoner` shows the raw R1 gain. `reasoner-harvest` isolates the cost + quality delta from the extra V3 harvest call.
+## Findings (v0.3, 18-run set)
+
+Two bands of tasks tried (easy: mod7 / flips / hats; hard: pseudoprime341 / D_7 / Euler quadratic). The hard band was chosen for *known V3 failure modes*. Result:
+
+1. **V3 chat passed all six tasks, including the three "hard" ones.** DeepSeek V3 knew 341 is the smallest base-2 pseudoprime, computed D_7=1854, and identified n=40 as the first Euler-polynomial failure. The tasks are well-known enough to be in training; the trap-answer variants (561, 265, 41) that the checkers specifically reject didn't fire.
+2. **Reasoner cost 3.04× baseline for identical pass rates (6/6 both sides).** On this task set, R1 adds cost and latency without measurable quality. The cache-hit story *does* extend to reasoner (74.2% mean), so Pillar 1 generalizes to R1 — but that's not a Pillar 2 story.
+3. **Harvest produced real signal** (mean 2.8 subgoals, 1.3 uncertainties per run where it fired) but didn't improve outcomes. One run hit the 300s timeout (bumped from 120s), suggesting reasoner-harvest latency is still unpredictable on some problems.
+
+### What this tells us about Pillar 2 positioning
+
+We've now given harvest two shots at showing answer-quality value on pure reasoning tasks. Both times V3 ate its lunch. This isn't a framework bug — it's a positioning signal:
+
+- **On well-known math / logic / counting problems, DeepSeek V3 is strong enough that paying for R1 is not justified by accuracy.** Pillar 2's "smart preset" cost multiplier (10×) quoted in the README is real but for most single-question Q/A it buys nothing.
+- **Harvest's plausible value surfaces are not "better math answers".** More likely: (a) transparency / auditability for developers, (b) planning support when tools are in the mix, (c) driving branch-sampling on cases where uncertainty correlates with wrongness. None of those are tested here.
+
+### Recommendation
+
+Don't ship v0.3 on the "harvest makes answers more correct" claim — the data doesn't support it. Two honest paths forward:
+
+- **Reframe Pillar 2 as a developer-facing introspection feature** (debug visibility into R1's planning). Keep harvest opt-in; stop implying it improves accuracy on end-user tasks.
+- **Move harvest eval to tool-use contexts** where uncertainty matters for *which tool to call next*, not *is this math right*. That's a new task shape — different harness, not a bigger task set here.
+
+In either case, the next Reasonix release is better served by MCP client (Pillar 1 leverage across the ecosystem) than by a bigger harvest-bench data push.
+
+### Notes
+
+- Cache hit on baseline runs surprised me (39.5% mean). That's DeepSeek's *cross-session* prompt cache: the same system prompt ran many times across modes and runs warmed the server-side cache. Real cross-session evidence that Cache-First's value isn't only per-session.
+- 5-subgoals cap still hit uniformly. `HarvestOptions.maxItems` default is 5; harvest is truncating. Moot unless we find a setting where that matters.

benchmarks/harvest/report.ts

@@ -0,0 +1,232 @@
+/**
+ * Render a harvest-bench results.json into a markdown report.
+ *
+ *   npx tsx benchmarks/harvest/report.ts benchmarks/harvest/results-<date>.json
+ *   npx tsx benchmarks/harvest/report.ts <input.json> --out report.md
+ */
+
+import { readFileSync, writeFileSync } from "node:fs";
+import { pathToFileURL } from "node:url";
+import { ALL_MODES, type HarvestBenchReport, type HarvestMode, type HarvestRunResult } from "./types.js";
+
+interface CliArgs {
+  input: string;
+  outPath: string;
+}
+
+function parseArgs(argv: string[]): CliArgs {
+  const out: CliArgs = { input: "", outPath: "benchmarks/harvest/report.md" };
+  const positional: string[] = [];
+  for (let i = 0; i < argv.length; i++) {
+    const a = argv[i];
+    if (a === "--out") out.outPath = argv[++i] ?? out.outPath;
+    else if (a && !a.startsWith("--")) positional.push(a);
+  }
+  out.input = positional[0] ?? "";
+  if (!out.input) {
+    throw new Error("usage: npx tsx benchmarks/harvest/report.ts <results.json> [--out report.md]");
+  }
+  return out;
+}
+
+interface Agg {
+  runs: number;
+  passes: number;
+  avgCache: number;
+  avgCost: number;
+  avgClaudeCost: number;
+  avgHarvestedTurns: number;
+  avgSubgoals: number;
+  avgUncertainties: number;
+}
+
+function aggregate(results: HarvestRunResult[]): Agg {
+  if (results.length === 0) {
+    return {
+      runs: 0,
+      passes: 0,
+      avgCache: 0,
+      avgCost: 0,
+      avgClaudeCost: 0,
+      avgHarvestedTurns: 0,
+      avgSubgoals: 0,
+      avgUncertainties: 0,
+    };
+  }
+  const passes = results.filter((r) => r.verdict === "pass").length;
+  const mean = (fn: (r: HarvestRunResult) => number) =>
+    results.reduce((s, r) => s + fn(r), 0) / results.length;
+  return {
+    runs: results.length,
+    passes,
+    avgCache: mean((r) => r.cacheHitRatio),
+    avgCost: mean((r) => r.costUsd),
+    avgClaudeCost: mean((r) => r.claudeEquivalentUsd),
+    avgHarvestedTurns: mean((r) => r.harvestedTurns),
+    avgSubgoals: mean((r) => r.totalSubgoals),
+    avgUncertainties: mean((r) => r.totalUncertainties),
+  };
+}
+
+export function renderReport(report: HarvestBenchReport): string {
+  const lines: string[] = [];
+  lines.push("# Reasonix harvest eval (Pillar 2)");
+  lines.push("");
+  lines.push(`**Date:** ${report.meta.date}`);
+  lines.push(
+    `**Tasks:** ${report.meta.taskCount} · repeats × ${report.meta.repeatsPerTask} · modes: ${report.meta.modesRun.join(", ")}`,
+  );
+  lines.push(`**Reasonix version:** ${report.meta.reasonixVersion}`);
+  lines.push("");
+
+  // Per-mode summary
+  lines.push("## Summary by mode");
+  lines.push("");
+  lines.push("| mode | runs | pass rate | cache hit | cost / run | harvest turns | subgoals | uncertainties |");
+  lines.push("|---|---:|---:|---:|---:|---:|---:|---:|");
+  for (const mode of ALL_MODES) {
+    const rs = report.results.filter((r) => r.mode === mode);
+    const a = aggregate(rs);
+    if (a.runs === 0) continue;
+    lines.push(
+      `| ${mode} | ${a.runs} | ${pct(a.passes, a.runs)} | ${pct1(a.avgCache)} | $${a.avgCost.toFixed(6)} | ${a.avgHarvestedTurns.toFixed(1)} | ${a.avgSubgoals.toFixed(1)} | ${a.avgUncertainties.toFixed(1)} |`,
+    );
+  }
+  lines.push("");
+
+  // Pairwise deltas that actually answer the question
+  lines.push("## Deltas");
+  lines.push("");
+  const modes = ALL_MODES.filter((m) =>
+    report.results.some((r) => r.mode === m),
+  );
+  if (modes.length >= 2) {
+    const baseline = aggregate(report.results.filter((r) => r.mode === modes[0]));
+    for (let i = 1; i < modes.length; i++) {
+      const mode = modes[i]!;
+      const agg = aggregate(report.results.filter((r) => r.mode === mode));
+      const passDelta = (agg.passes / Math.max(agg.runs, 1)) - (baseline.passes / Math.max(baseline.runs, 1));
+      const costRatio = baseline.avgCost > 0 ? agg.avgCost / baseline.avgCost : 0;
+      lines.push(`- **${modes[0]} → ${mode}**`);
+      lines.push(`  - pass rate: ${(passDelta * 100).toFixed(0)}pp`);
+      lines.push(`  - cost: ×${costRatio.toFixed(2)} (each run costs ${costRatio > 1 ? "more" : "less"})`);
+      lines.push(`  - harvest signal / run: ${agg.avgSubgoals.toFixed(1)} subgoals, ${agg.avgUncertainties.toFixed(1)} uncertainties`);
+      lines.push("");
+    }
+  }
+
+  // Per-task breakdown
+  lines.push("## Per-task breakdown");
+  lines.push("");
+  const byTask = new Map<string, HarvestRunResult[]>();
+  for (const r of report.results) {
+    const list = byTask.get(r.taskId) ?? [];
+    list.push(r);
+    byTask.set(r.taskId, list);
+  }
+  lines.push("| task | mode | rep | verdict | cache | cost | sg | un | note |");
+  lines.push("|---|---|---:|:---:|---:|---:|---:|---:|---|");
+  for (const [taskId, runs] of byTask) {
+    for (const r of runs) {
+      const mark = r.verdict === "pass" ? "✅" : r.verdict === "fail" ? "❌" : "•";
+      lines.push(
+        `| ${taskId} | ${r.mode} | ${r.repeat} | ${mark} | ${pct1(r.cacheHitRatio)} | $${r.costUsd.toFixed(6)} | ${r.totalSubgoals} | ${r.totalUncertainties} | ${truncate(r.checkNote ?? "", 40)} |`,
+      );
+    }
+  }
+  lines.push("");
+
+  lines.push("## Scope");
+  lines.push("");
+  lines.push(
+    "Unlike τ-bench-lite, these tasks are single-turn reasoning problems (no user simulator, no DB, no tool calls). Checkers are deterministic — regex + set / value compare, never an LLM judge. The point is to isolate whether the Pillar 2 harvest step adds measurable value above plain reasoner usage.",
+  );
+  lines.push("");
+  lines.push(
+    "Interpretation: `baseline` (chat / V3) is a floor. `reasoner` shows the raw R1 gain. `reasoner-harvest` isolates the cost + quality delta from the extra V3 harvest call.",
+  );
+
+  return lines.join("\n");
+}
+
+/**
+ * Findings section is hand-written into report.md after rendering — the
+ * numbers don't interpret themselves, and boilerplate sections full of
+ * "TBD — analyse the data" are worse than nothing. Append with append().
+ *
+ * This section has been updated twice: after the first 9-run set (which
+ * bottomed out at V3 on easy tasks) and after this 18-run set (which
+ * bottomed out at V3 on *hard* tasks too).
+ */
+export function renderFindings(_report: HarvestBenchReport): string {
+  return [
+    "",
+    "## Findings (v0.3, 18-run set)",
+    "",
+    "Two bands of tasks tried (easy: mod7 / flips / hats; hard: pseudoprime341 / D_7 / Euler quadratic). The hard band was chosen for *known V3 failure modes*. Result:",
+    "",
+    "1. **V3 chat passed all six tasks, including the three \"hard\" ones.** DeepSeek V3 knew 341 is the smallest base-2 pseudoprime, computed D_7=1854, and identified n=40 as the first Euler-polynomial failure. The tasks are well-known enough to be in training; the trap-answer variants (561, 265, 41) that the checkers specifically reject didn't fire.",
+    "2. **Reasoner cost 3.04× baseline for identical pass rates (6/6 both sides).** On this task set, R1 adds cost and latency without measurable quality. The cache-hit story *does* extend to reasoner (74.2% mean), so Pillar 1 generalizes to R1 — but that's not a Pillar 2 story.",
+    "3. **Harvest produced real signal** (mean 2.8 subgoals, 1.3 uncertainties per run where it fired) but didn't improve outcomes. One run hit the 300s timeout (bumped from 120s), suggesting reasoner-harvest latency is still unpredictable on some problems.",
+    "",
+    "### What this tells us about Pillar 2 positioning",
+    "",
+    "We've now given harvest two shots at showing answer-quality value on pure reasoning tasks. Both times V3 ate its lunch. This isn't a framework bug — it's a positioning signal:",
+    "",
+    "- **On well-known math / logic / counting problems, DeepSeek V3 is strong enough that paying for R1 is not justified by accuracy.** Pillar 2's \"smart preset\" cost multiplier (10×) quoted in the README is real but for most single-question Q/A it buys nothing.",
+    "- **Harvest's plausible value surfaces are not \"better math answers\".** More likely: (a) transparency / auditability for developers, (b) planning support when tools are in the mix, (c) driving branch-sampling on cases where uncertainty correlates with wrongness. None of those are tested here.",
+    "",
+    "### Recommendation",
+    "",
+    "Don't ship v0.3 on the \"harvest makes answers more correct\" claim — the data doesn't support it. Two honest paths forward:",
+    "",
+    "- **Reframe Pillar 2 as a developer-facing introspection feature** (debug visibility into R1's planning). Keep harvest opt-in; stop implying it improves accuracy on end-user tasks.",
+    "- **Move harvest eval to tool-use contexts** where uncertainty matters for *which tool to call next*, not *is this math right*. That's a new task shape — different harness, not a bigger task set here.",
+    "",
+    "In either case, the next Reasonix release is better served by MCP client (Pillar 1 leverage across the ecosystem) than by a bigger harvest-bench data push.",
+    "",
+    "### Notes",
+    "",
+    "- Cache hit on baseline runs surprised me (39.5% mean). That's DeepSeek's *cross-session* prompt cache: the same system prompt ran many times across modes and runs warmed the server-side cache. Real cross-session evidence that Cache-First's value isn't only per-session.",
+    "- 5-subgoals cap still hit uniformly. `HarvestOptions.maxItems` default is 5; harvest is truncating. Moot unless we find a setting where that matters.",
+    "",
+  ].join("\n");
+}
+
+function pct(num: number, denom: number): string {
+  if (denom === 0) return "—";
+  return `${((num / denom) * 100).toFixed(0)}%`;
+}
+
+function pct1(x: number): string {
+  return `${(x * 100).toFixed(1)}%`;
+}
+
+function truncate(s: string, n: number): string {
+  return s.length > n ? `${s.slice(0, n)}…` : s;
+}
+
+async function main(): Promise<void> {
+  const args = parseArgs(process.argv.slice(2));
+  const raw = readFileSync(args.input, "utf8");
+  const report = JSON.parse(raw) as HarvestBenchReport;
+  const md = renderReport(report) + renderFindings(report);
+  writeFileSync(args.outPath, md, "utf8");
+  console.log(`wrote ${args.outPath} (${report.results.length} runs)`);
+}
+
+function isMain(): boolean {
+  const entry = process.argv[1];
+  if (!entry) return false;
+  return import.meta.url === pathToFileURL(entry).href;
+}
+
+if (isMain()) {
+  main().catch((err) => {
+    console.error(err);
+    process.exit(1);
+  });
+}
+
+// Suppress unused import warning — kept in scope so ALL_MODES order matches renderer iteration.
+export type { HarvestMode };

benchmarks/harvest/results.json

@@ -0,0 +1,305 @@
+{
+  "meta": {
+    "date": "2026-04-21T16:44:21.011Z",
+    "repeatsPerTask": 1,
+    "taskCount": 6,
+    "modesRun": [
+      "baseline",
+      "reasoner",
+      "reasoner-harvest"
+    ],
+    "reasonixVersion": "0.2.2"
+  },
+  "results": [
+    {
+      "taskId": "mod7_list",
+      "mode": "baseline",
+      "repeat": 1,
+      "verdict": "pass",
+      "finalAgentMessage": "Alright, let's go step-by-step.\n\n---\n\n## **Step 1: Problem restatement**\nWe want positive integers \\( n \\leq 100 \\) such that  \n\\[\nn^2 + n + 1 \\equiv 0 \\pmod{7}.\n\\]\n\n---\n\n## **Step 2: Try residues modulo 7**\nLet \\( n \\equiv r \\pmod{7} \\), where \\( r \\in \\{0, 1, 2, 3, 4, 5, 6\\} \\).\n\nWe compute \\( r^2 + r + 1 \\mod 7 \\):\n\n- \\( r = 0 \\): \\( 0 + 0 + 1 = 1 \\) → not divisible by 7.\n- \\( r = 1 \\): \\( 1 + 1 + 1 = 3 \\) → no.\n- \\( r = 2 \\): \\( 4 + 2 + 1 = 7 \\equiv 0 \\) → yes.\n- \\( r = 3 \\): \\( 9 + 3 + 1 = 13 \\equiv 6 \\) → no.\n- \\( r = 4 \\): \\( 16 + 4 + 1 = 21 \\equiv 0 \\) → yes.\n- \\( r = 5 \\): \\( 25 + 5 + 1 = 31 \\equiv 3 \\) → no.\n- \\( r = 6 \\): \\( 36 + 6 + 1 = 43 \\equiv 1 \\) → no.\n\nSo \\( n \\equiv 2 \\pmod{7} \\) or \\( n \\equiv 4 \\pmod{7} \\).\n\n---\n\n## **Step 3: General form**\n\\[\nn \\equiv 2 \\pmod{7} \\quad \\text{or} \\quad n \\equiv 4 \\pmod{7}.\n\\]\n\nThat means \\( n = 7k + 2 \\) or \\( n = 7k + 4 \\) for some integer \\( k \\ge 0 \\).\n\n---\n\n## **Step 4: Positive integers \\( n \\leq 100 \\)**\n**Case 1:** \\( n = 7k + 2 \\), \\( n \\leq 100 \\), \\( k \\ge 0 \\).\n\n\\( 7k + 2 \\leq 100 \\) → \\( 7k \\leq 98 \\) → \\( k \\leq 14 \\).\n\nSo \\( k = 0, 1, 2, \\dots, 14 \\) gives \\( n = 2, 9, 16, \\dots, 100 \\).\n\nCheck \\( n=100 \\): \\( 7 \\times 14 + 2 = 98 + 2 = 100 \\) okay.\n\n---\n\n**Case 2:** \\( n = 7k + 4 \\), \\( n \\leq 100 \\), \\( k \\ge 0 \\).\n\n\\( 7k + 4 \\leq 100 \\) → \\( 7k \\leq 96 \\) → \\( k \\leq 13 \\) (since \\( 7 \\times 13 = 91 \\), \\( 91+4=95 \\), \\( 7\\times14=98 \\) → \\( 98+4=102>100 \\)).\n\nSo \\( k = 0, 1, 2, \\dots, 13 \\) gives \\( n = 4, 11, 18, \\dots, 95 \\).\n\n---\n\n## **Step 5: List all such \\( n \\leq 100 \\)**\nFrom case 1: \\( 2, 9, 16, 23, 30, 37, 44, 51, 58, 65, 72, 79, 86, 93, 100 \\).\n\nFrom case 2: \\( 4, 11, 18, 25, 32, 39, 46, 53, 60, 67, 74, 81, 88, 95 \\).\n\nCombine and sort:\n\n\\[\n2, 4, 9, 11, 16, 18, 23, 25, 30, 32, 37, 39, 44, 46, 51, 53, 58, 60, 65, 67, 72, 74, 79, 81, 86, 88, 93, 95, 100.\n\\]\n\n---\n\n## **Step 6: Check count**\nEach sequence has 15 and 14 terms respectively, total \\( 15 + 14 = 29 \\) numbers.\n\nCheck: \\( n=2 \\) works? \\( 4+2+1=7 \\) yes. \\( n=4 \\) works? \\( 16+4+1=21 \\) yes. \\( n=100 \\) works? \\( 10000+100+1=10101 \\), divide by 7: \\( 10101/7 = 1443 \\) yes.\n\n---\n\n**Final answer:**\n\\[\n\\boxed{2, 4, 9, 11, 16, 18, 23, 25, 30, 32, 37, 39, 44, 46, 51, 53, 58, 60, 65, 67, 72, 74, 79, 81, 86, 88, 93, 95, 100}\n\\]\n\n---\n\nAnswer: 2, 4, 9, 11, 16, 18, 23, 25, 30, 32, 37, 39, 44, 46, 51, 53, 58, 60, 65, 67, 72, 74, 79, 81, 86, 88, 93, 95, 100",
+      "turns": 1,
+      "cacheHitRatio": 0.8648648648648649,
+      "costUsd": 0.0013612800000000003,
+      "claudeEquivalentUsd": 0.018687,
+      "harvestedTurns": 0,
+      "totalSubgoals": 0,
+      "totalUncertainties": 0,
+      "totalHypotheses": 0,
+      "totalRejectedPaths": 0
+    },
+    {
+      "taskId": "mod7_list",
+      "mode": "reasoner",
+      "repeat": 1,
+      "verdict": "pass",
+      "finalAgentMessage": "The condition \\(n^2 + n + 1\\) divisible by 7 is equivalent to \\(n^2 + n + 1 \\equiv 0 \\pmod{7}\\). Testing residues modulo 7:\n\n- \\(n \\equiv 0: 0+0+1 \\equiv 1\\)  \n- \\(n \\equiv 1: 1+1+1 \\equiv 3\\)  \n- \\(n \\equiv 2: 4+2+1 \\equiv 7 \\equiv 0\\)  \n- \\(n \\equiv 3: 9+3+1 \\equiv 13 \\equiv 6\\)  \n- \\(n \\equiv 4: 16+4+1 \\equiv 21 \\equiv 0\\)  \n- \\(n \\equiv 5: 25+5+1 \\equiv 31 \\equiv 3\\)  \n- \\(n \\equiv 6: 36+6+1 \\equiv 43 \\equiv 1\\)\n\nThus, \\(n \\equiv 2\\) or \\(n \\equiv 4 \\pmod{7}\\) are the solutions modulo 7. For positive integers \\(n \\leq 100\\), we list all numbers congruent to 2 or 4 modulo 7 in increasing order.\n\nAnswer: 2, 4, 9, 11, 16, 18, 23, 25, 30, 32, 37, 39, 44, 46, 51, 53, 58, 60, 65, 67, 72, 74, 79, 81, 86, 88, 93, 95, 100",
+      "turns": 1,
+      "cacheHitRatio": 0.8648648648648649,
+      "costUsd": 0.00479742,
+      "claudeEquivalentUsd": 0.032982,
+      "harvestedTurns": 0,
+      "totalSubgoals": 0,
+      "totalUncertainties": 0,
+      "totalHypotheses": 0,
+      "totalRejectedPaths": 0
+    },
+    {
+      "taskId": "mod7_list",
+      "mode": "reasoner-harvest",
+      "repeat": 1,
+      "verdict": "pass",
+      "finalAgentMessage": "The congruence \\(n^2 + n + 1 \\equiv 0 \\pmod{7}\\) is solved by testing residues modulo 7. The solutions are \\(n \\equiv 2\\) and \\(n \\equiv 4 \\pmod{7}\\). For positive integers \\(n \\le 100\\), these yield \\(n = 7k + 2\\) with \\(k = 0, 1, \\dots, 14\\) and \\(n = 7k + 4\\) with \\(k = 0, 1, \\dots, 13\\).\n\nAnswer: 2, 4, 9, 11, 16, 18, 23, 25, 30, 32, 37, 39, 44, 46, 51, 53, 58, 60, 65, 67, 72, 74, 79, 81, 86, 88, 93, 95, 100",
+      "turns": 1,
+      "cacheHitRatio": 0.8648648648648649,
+      "costUsd": 0.00304542,
+      "claudeEquivalentUsd": 0.020982,
+      "harvestedTurns": 1,
+      "totalSubgoals": 4,
+      "totalUncertainties": 2,
+      "totalHypotheses": 2,
+      "totalRejectedPaths": 2
+    },
+    {
+      "taskId": "flips_until_3heads",
+      "mode": "baseline",
+      "repeat": 1,
+      "verdict": "pass",
+      "finalAgentMessage": "Alright, let's reason through this step-by-step.\n\n---\n\n## **Step 1: Define states**\nLet’s define states based on how many consecutive heads we have at the moment.\n\n- \\( E_0 \\): Expected flips to reach 3 heads in a row starting from 0 consecutive heads (or just starting, or after a tail).\n- \\( E_1 \\): Expected flips to reach 3 heads in a row starting from 1 consecutive head.\n- \\( E_2 \\): Expected flips to reach 3 heads in a row starting from 2 consecutive heads.\n\nWe want \\( E_0 \\).\n\n---\n\n## **Step 2: Transition equations**\nFrom \\( E_0 \\):\n- Flip H (prob \\( \\frac12 \\)) → go to state \\( E_1 \\), 1 flip used.\n- Flip T (prob \\( \\frac12 \\)) → stay in \\( E_0 \\), 1 flip used.\n\nSo:\n\\[\nE_0 = \\frac12 (1 + E_1) + \\frac12 (1 + E_0)\n\\]\n\n---\n\nFrom \\( E_1 \\) (already have 1 head):\n- Flip H (prob \\( \\frac12 \\)) → go to state \\( E_2 \\), 1 flip used.\n- Flip T (prob \\( \\frac12 \\)) → go to state \\( E_0 \\), 1 flip used.\n\nSo:\n\\[\nE_1 = \\frac12 (1 + E_2) + \\frac12 (1 + E_0)\n\\]\n\n---\n\nFrom \\( E_2 \\) (already have 2 heads):\n- Flip H (prob \\( \\frac12 \\)) → done (3 heads in a row), 1 flip used.\n- Flip T (prob \\( \\frac12 \\)) → go to state \\( E_0 \\), 1 flip used.\n\nSo:\n\\[\nE_2 = \\frac12 (1 + 0) + \\frac12 (1 + E_0)\n\\]\n\\[\nE_2 = \\frac12 \\cdot 1 + \\frac12 (1 + E_0) \\quad\\text{(Wait, careful:)}\n\\]\nActually:  \nIf H: \\( 1 \\) flip and done.  \nIf T: \\( 1 \\) flip and then \\( E_0 \\) more.\n\nSo:\n\\[\nE_2 = \\frac12 \\cdot 1 + \\frac12 (1 + E_0)\n\\]\nCheck:  \nH: 1 flip → total 1, done. Contribution: \\( \\frac12 \\times 1 \\).  \nT: 1 flip + \\( E_0 \\) more → total \\( 1 + E_0 \\). Contribution: \\( \\frac12 \\times (1 + E_0) \\).\n\nYes:\n\\[\nE_2 = \\frac12 \\cdot 1 + \\frac12 (1 + E_0) = \\frac12 + \\frac12 + \\frac12 E_0 = 1 + \\frac{E_0}{2}.\n\\]\n\n---\n\n## **Step 3: Solve system**\nWe have:\n\n(1) \\( E_0 = \\frac12 (1 + E_1) + \\frac12 (1 + E_0) \\)  \nSimplify: \\( E_0 = 1 + \\frac12 E_1 + \\frac12 E_0 \\)  \nMultiply by 2: \\( 2E_0 = 2 + E_1 + E_0 \\)  \nSo \\( E_0 - E_1 = 2 \\) … (Eq A)\n\n---\n\n(2) \\( E_1 = \\frac12 (1 + E_2) + \\frac12 (1 + E_0) \\)  \nSimplify: \\( E_1 = 1 + \\frac12 E_2 + \\frac12 E_0 \\) … (Eq B)\n\n---\n\n(3) \\( E_2 = 1 + \\frac12 E_0 \\) … (Eq C)\n\n---\n\nFrom Eq C into Eq B:\n\\[\nE_1 = 1 + \\frac12 \\left( 1 + \\frac12 E_0 \\right) + \\frac12 E_0\n\\]\n\\[\nE_1 = 1 + \\frac12 + \\frac14 E_0 + \\frac12 E_0\n\\]\n\\[\nE_1 = \\frac32 + \\frac34 E_0\n\\]\n\n---\n\nFrom Eq A: \\( E_0 - E_1 = 2 \\)  \nSubstitute \\( E_1 \\):\n\\[\nE_0 - \\left( \\frac32 + \\frac34 E_0 \\right) = 2\n\\]\n\\[\nE_0 - \\frac32 - \\frac34 E_0 = 2\n\\]\n\\[\n\\frac14 E_0 - \\frac32 = 2\n\\]\n\\[\n\\frac14 E_0 = 2 + \\frac32 = \\frac72\n\\]\n\\[\nE_0 = 14\n\\]\n\n---\n\n## **Step 4: Conclusion**\nThe expected number of flips until we get 3 heads in a row is \\( 14 \\).\n\n---\n\n**Answer:** 14",
+      "turns": 1,
+      "cacheHitRatio": 0.927536231884058,
+      "costUsd": 0.00119823,
+      "claudeEquivalentUsd": 0.016467,
+      "harvestedTurns": 0,
+      "totalSubgoals": 0,
+      "totalUncertainties": 0,
+      "totalHypotheses": 0,
+      "totalRejectedPaths": 0
+    },
+    {
+      "taskId": "flips_until_3heads",
+      "mode": "reasoner",
+      "repeat": 1,
+      "verdict": "pass",
+      "finalAgentMessage": "The expected number of flips required to get three consecutive heads is 14, derived from solving the system of linear equations for the Markov chain states representing the current streak of heads.\n\nAnswer: 14",
+      "turns": 1,
+      "cacheHitRatio": 0.927536231884058,
+      "costUsd": 0.00283024,
+      "claudeEquivalentUsd": 0.019512,
+      "harvestedTurns": 0,
+      "totalSubgoals": 0,
+      "totalUncertainties": 0,
+      "totalHypotheses": 0,
+      "totalRejectedPaths": 0
+    },
+    {
+      "taskId": "flips_until_3heads",
+      "mode": "reasoner-harvest",
+      "repeat": 1,
+      "verdict": "pass",
+      "finalAgentMessage": "The expected number of flips until three consecutive heads appear is 14.\n\nAnswer: 14",
+      "turns": 1,
+      "cacheHitRatio": 0.927536231884058,
+      "costUsd": 0.00169144,
+      "claudeEquivalentUsd": 0.011712,
+      "harvestedTurns": 1,
+      "totalSubgoals": 4,
+      "totalUncertainties": 0,
+      "totalHypotheses": 2,
+      "totalRejectedPaths": 0
+    },
+    {
+      "taskId": "three_hats",
+      "mode": "baseline",
+      "repeat": 1,
+      "verdict": "pass",
+      "finalAgentMessage": "Let's break this down step by step.\n\n---\n\n**Step 1: Understanding the setup**  \nThree people: A (first), B (second), C (third).  \nEach hat is red (R) or blue (B).  \nThey know: at least one hat is red.  \nEach sees the other two hats, not their own.  \nThey are asked in order: \"Do you know your hat color?\"  \nA answers no, B answers no, C answers yes.  \nWe want C’s hat color.\n\n---\n\n**Step 2: From A’s perspective when asked**  \nA sees B and C.  \nIf A had seen two blue hats, then A would know: \"At least one red hat means my hat must be red.\"  \nSo A says \"no\" → A did **not** see two blue hats.  \nThus A sees at least one red hat on {B, C}.\n\nPossible cases for what A sees (B, C):  \n(R, R), (R, B), (B, R) — all have at least one red.\n\n---\n\n**Step 3: B’s reasoning when asked**  \nB hears A say \"no\".  \nB sees A and C.  \n\nLet’s consider B’s possible deductions from A’s \"no\":  \nB knows: If A had seen two blues, A would have said yes. Since A said no, A saw at least one red among B and C.  \nBut B sees A and C.  \n\nFrom B’s viewpoint:  \n- If B saw C with blue and A with blue, then B would know: \"A saw me and C both blue → impossible because A said no.\" But B doesn’t see that because if B saw A blue and C blue, then B would know his own hat must be red (since at least one red total). But then B would answer yes.  \nSo B’s \"no\" means B did **not** see A and C both blue.  \n\nAlso, B considers: Could my hat be blue? Let’s check:  \nSuppose B sees A red, C blue. Then B thinks: \"If my hat were blue, then A would have seen (B blue, C blue) → A would have said yes. But A said no, so my hat cannot be blue.\"  \nSo if B saw (A red, C blue), B would deduce: \"My hat must be red.\" Then B would answer yes.  \nBut B said no → so B did **not** see (A red, C blue).\n\nSimilarly, if B saw (A blue, C red):  \nThen B thinks: \"If my hat were blue, then A would have seen (B blue, C red) → that’s fine (A sees one red on C), so A would still say no. If my hat were red, then A would see (B red, C red) → A would still say no. So I don’t know.\" That’s consistent with B saying no.  \n\nIf B saw (A red, C red):  \nThen B thinks: \"If my hat were blue, A sees (B blue, C red) → A says no. If my hat were red, A sees (B red, C red) → A says no. So I don’t know.\" That’s also consistent with B saying no.\n\nSo B says no in cases:  \nB sees (A blue, C red) or (A red, C red).  \nB would say yes if B saw (A red, C blue) — but that didn’t happen.  \n\n---\n\n**Step 4: C’s reasoning**  \nC hears A says no, B says no.  \nC sees A and B.  \n\nFrom C’s viewpoint:  \nLet’s list all possible (A, B, C) hat colorings with at least one red, consistent with A’s \"no\" (which we already incorporated: A sees at least one red on B/C) and B’s \"no\" (meaning B didn’t see A red, C blue — because that would make B know).\n\nPossible cases for (A, B) that C could see:  \n\n1. C sees (A blue, B red):  \n   Then C thinks:  \n   - If C were blue: (A blue, B red, C blue) → A sees (B red, C blue) → A says no. B sees (A blue, C blue) → B sees two blues? Wait, B sees A blue, C blue → then B knows his own hat is red (since at least one red total) → B would say yes. But B said no → contradiction. So C cannot be blue.  \n   So C must be red.  \n\n2. C sees (A red, B blue):  \n   Then C thinks:  \n   - If C were blue: (A red, B blue, C blue) → A sees (B blue, C blue) → A would say yes (since at least one red total means A’s hat must be red). But A said no → contradiction. So C cannot be blue.  \n   So C must be red.  \n\n3. C sees (A red, B red):  \n   Then C thinks:  \n   - If C were blue: (A red, B red, C blue) → A sees (B red, C blue) → A says no. B sees (A red, C blue) → B sees A red, C blue → earlier we said: If B sees A red, C blue, then B would deduce his own hat is red (reasoning: if B were blue, A would have seen two blues and said yes, but A said no, so B can’t be blue) → so B would say yes. But B actually said no → contradiction. So C cannot be blue.  \n   - If C were red: (A red, B red, C red) → A sees (B red, C red) → A says no. B sees (A red, C red) → B says no. Works fine.  \n\nSo in all cases C sees for (A, B), C can deduce C’s hat is **red** because assuming C is blue leads to contradiction with B’s \"no\" (in cases 1 and 3) or with A’s \"no\" (in case 2).\n\n---\n\n**Step 5: Conclusion**  \nC answers yes, and C’s hat must be red.\n\n---\n\nAnswer: red",
+      "turns": 1,
+      "cacheHitRatio": 0.5765765765765766,
+      "costUsd": 0.0015142700000000003,
+      "claudeEquivalentUsd": 0.020748,
+      "harvestedTurns": 0,
+      "totalSubgoals": 0,
+      "totalUncertainties": 0,
+      "totalHypotheses": 0,
+      "totalRejectedPaths": 0
+    },
+    {
+      "taskId": "three_hats",
+      "mode": "reasoner",
+      "repeat": 1,
+      "verdict": "pass",
+      "finalAgentMessage": "Answer: red",
+      "turns": 1,
+      "cacheHitRatio": 0.5765765765765766,
+      "costUsd": 0.009340119999999999,
+      "claudeEquivalentUsd": 0.064068,
+      "harvestedTurns": 0,
+      "totalSubgoals": 0,
+      "totalUncertainties": 0,
+      "totalHypotheses": 0,
+      "totalRejectedPaths": 0
+    },
+    {
+      "taskId": "three_hats",
+      "mode": "reasoner-harvest",
+      "repeat": 1,
+      "verdict": "pass",
+      "finalAgentMessage": "The third person deduces their hat color based on the previous responses. Since the first two answer \"no,\" it implies they each see at least one red hat and cannot determine their own color. Specifically, the second person's \"no\" indicates they see the third person's hat as red; otherwise, they would have known their own hat color. Therefore, the third person's hat must be red.\n\nAnswer: red",
+      "turns": 1,
+      "cacheHitRatio": 0.5765765765765766,
+      "costUsd": 0.0096511,
+      "claudeEquivalentUsd": 0.066198,
+      "harvestedTurns": 1,
+      "totalSubgoals": 3,
+      "totalUncertainties": 2,
+      "totalHypotheses": 3,
+      "totalRejectedPaths": 3
+    },
+    {
+      "taskId": "pseudoprime_base2",
+      "mode": "baseline",
+      "repeat": 1,
+      "verdict": "pass",
+      "finalAgentMessage": "Alright, let's go step-by-step.\n\n---\n\n**Step 1: Understanding the problem**\n\nWe want the smallest composite integer \\( n > 1 \\) such that\n\n\\[\n2^n \\equiv 2 \\pmod{n}.\n\\]\n\nEquivalently, \\( 2^{n-1} \\equiv 1 \\pmod{n} \\) for composite \\( n \\).\n\nThis means \\( n \\) is a **Fermat pseudoprime to base 2**.\n\nWe check composite numbers starting from the smallest.\n\n---\n\n**Step 2: Check small composites**\n\n- \\( n = 4 \\): composite.  \n\\( 2^4 = 16 \\), \\( 16 \\mod 4 = 0 \\), not \\( 2 \\). So \\( 2^4 \\equiv 0 \\not\\equiv 2 \\pmod{4} \\). Fails.\n\n- \\( n = 6 \\): composite.  \n\\( 2^6 = 64 \\), \\( 64 \\mod 6 = 4 \\), not \\( 2 \\). Fails.\n\n- \\( n = 8 \\): composite.  \n\\( 2^8 = 256 \\), \\( 256 \\mod 8 = 0 \\), not \\( 2 \\). Fails.\n\n- \\( n = 9 \\): composite.  \n\\( 2^9 = 512 \\), \\( 512 \\mod 9 \\):  \n\\( 512 \\div 9 \\), \\( 9 \\times 56 = 504 \\), remainder \\( 8 \\), not \\( 2 \\). Fails.\n\n- \\( n = 10 \\): composite.  \n\\( 2^{10} = 1024 \\), \\( 1024 \\mod 10 = 4 \\), not \\( 2 \\). Fails.\n\n---\n\n**Step 3: Try n = 15**\n\n\\( n = 15 \\): composite.  \n\\( 2^{15} = 32768 \\).  \nCheck mod 15:  \nWe can use mod arithmetic:  \n\\( 2^4 = 16 \\equiv 1 \\pmod{15} \\)?? Wait, check: \\( 16 \\mod 15 = 1 \\), yes.  \nSo \\( 2^{15} = (2^4)^3 \\times 2^3 = 1^3 \\times 8 = 8 \\pmod{15} \\).  \nSo \\( 2^{15} \\equiv 8 \\not\\equiv 2 \\pmod{15} \\). Fails.\n\n---\n\n**Step 4: Try n = 21**\n\n\\( n = 21 \\): composite.  \nMod 21:  \n\\( 2^6 = 64 \\equiv 1 \\pmod{21} \\)? Check: \\( 64 \\div 21 = 3 \\times 21 = 63 \\), remainder 1, yes.  \nSo \\( 2^{21} = (2^6)^3 \\times 2^3 \\equiv 1^3 \\times 8 = 8 \\pmod{21} \\). Not 2. Fails.\n\n---\n\n**Step 5: Try n = 22**\n\n\\( n = 22 \\): composite.  \nUse mod 22:  \nEuler’s totient not needed, just check order:  \n\\( 2^5 = 32 \\equiv 10 \\pmod{22} \\)  \n\\( 2^{10} = (2^5)^2 \\equiv 10^2 = 100 \\equiv 12 \\pmod{22} \\)  \n\\( 2^{11} \\equiv 24 \\equiv 2 \\pmod{22} \\)  \nSo \\( 2^{22} = (2^{11})^2 \\equiv 2^2 = 4 \\pmod{22} \\). Not 2. Fails.\n\n---\n\n**Step 6: Try n = 25**\n\n\\( n = 25 \\): composite.  \nCheck mod 25:  \n\\( 2^{10} = 1024 \\equiv 24 \\pmod{25} \\) (since \\( 1000 \\equiv 0 \\), \\( 24 \\equiv -1 \\))  \nActually check: \\( 1024 - 1000 = 24 \\), yes \\( 24 \\equiv -1 \\).  \nSo \\( 2^{20} \\equiv 1 \\pmod{25} \\).  \nThus \\( 2^{25} = 2^{20} \\times 2^5 \\equiv 1 \\times 32 = 7 \\pmod{25} \\). Not 2. Fails.\n\n---\n\n**Step 7: Known smallest base-2 Fermat pseudoprime**\n\nFrom known number theory facts:  \nThe smallest Fermat pseudoprime to base 2 is \\( n = 341 \\).  \nBut let's check smaller ones just in case I’m skipping one.\n\n---\n\n**Step 8: Try n = 91**\n\n91 = 7 × 13.  \nCheck mod 7: \\( 2^{91} \\equiv (2^6)^{15} \\times 2^1 \\equiv 1^{15} \\times 2 = 2 \\pmod{7} \\).  \nCheck mod 13: \\( 2^{12} \\equiv 1 \\pmod{13} \\),  \n\\( 91 = 12 \\times 7 + 7 \\), so \\( 2^{91} \\equiv 2^7 = 128 \\equiv 11 \\pmod{13} \\).  \nFor \\( 2^{91} \\equiv 2 \\pmod{91} \\), we need \\( 2^{91} \\equiv 2 \\) mod 7 and mod 13.  \nMod 13 we got 11, not 2. So fails.\n\n---\n\n**Step 9: Try n = 341**\n\n341 = 11 × 31.  \nCheck mod 11: \\( 2^{10} \\equiv 1 \\pmod{11} \\),  \n\\( 341 = 10 \\times 34 + 1 \\), so \\( 2^{341} \\equiv 2^1 = 2 \\pmod{11} \\). Good.  \nCheck mod 31: \\( 2^5 = 32 \\equiv 1 \\pmod{31} \\),  \n\\( 341 = 5 \\times 68 + 1 \\), so \\( 2^{341} \\equiv 2^1 = 2 \\pmod{31} \\).  \nSo \\( 2^{341} \\equiv 2 \\) mod 11 and mod 31, hence mod 341.  \nThus \\( 341 \\) works.\n\n---\n\n**Step 10: Check smaller than 341**\n\nKnown list: 341 is smallest. Let’s check a candidate like 121 = 11^2:  \n\\( 2^{121} \\mod 121 \\):  \nMod 11: \\( 2^{10} \\equiv 1 \\), \\( 121 = 10 \\times 12 + 1 \\), so \\( 2^{121} \\equiv 2 \\pmod{11} \\).  \nBut for modulus 121, need more:  \nActually, \\( 2^{110} \\equiv 1 \\pmod{121} \\) by Euler’s theorem? Not exactly, but known: 121 is not a pseudoprime base 2. Quick check:  \n\\( 2^{121} - 2 \\) divisible by 121? Probably not. Let’s skip detailed check; known fact is 341 is smallest.\n\n---\n\n**Step 11: Verify no smaller composite works**\n\nFrom known sequence A001567:  \nFirst few base-2 Fermat pseudoprimes: 341, 561, 645, 1105, …  \nSo smallest is 341.\n\n---\n\n**Step 12: Conclusion**\n\nThe smallest composite \\( n > 1 \\) with \\( 2^n \\equiv 2 \\pmod{n} \\) is \\( n = 341 \\).\n\n---\n\n**Answer:** 341",
+      "turns": 1,
+      "cacheHitRatio": 0,
+      "costUsd": 0.0018940500000000002,
+      "claudeEquivalentUsd": 0.02577,
+      "harvestedTurns": 0,
+      "totalSubgoals": 0,
+      "totalUncertainties": 0,
+      "totalHypotheses": 0,
+      "totalRejectedPaths": 0
+    },
+    {
+      "taskId": "pseudoprime_base2",
+      "mode": "reasoner",
+      "repeat": 1,
+      "verdict": "pass",
+      "finalAgentMessage": "The smallest composite integer \\(n > 1\\) satisfying \\(2^n \\equiv 2 \\pmod{n}\\) is \\(n = 341\\). This is composite (\\(341 = 11 \\times 31\\)), and it satisfies the congruence because \\(2^{341} \\equiv 2 \\pmod{11}\\) and \\(2^{341} \\equiv 2 \\pmod{31}\\) by Fermat's little theorem, implying \\(2^{341} \\equiv 2 \\pmod{341}\\). All smaller composite integers (e.g., 4, 6, 8, 9, 10, 15, 21) fail to satisfy the condition.\n\nAnswer: 341",
+      "turns": 1,
+      "cacheHitRatio": 0.7529411764705882,
+      "costUsd": 0.0031281200000000003,
+      "claudeEquivalentUsd": 0.02154,
+      "harvestedTurns": 0,
+      "totalSubgoals": 0,
+      "totalUncertainties": 0,
+      "totalHypotheses": 0,
+      "totalRejectedPaths": 0
+    },
+    {
+      "taskId": "pseudoprime_base2",
+      "mode": "reasoner-harvest",
+      "repeat": 1,
+      "verdict": "fail",
+      "checkNote": "This operation was aborted",
+      "finalAgentMessage": "",
+      "turns": 0,
+      "cacheHitRatio": 0,
+      "costUsd": 0,
+      "claudeEquivalentUsd": 0,
+      "harvestedTurns": 0,
+      "totalSubgoals": 0,
+      "totalUncertainties": 0,
+      "totalHypotheses": 0,
+      "totalRejectedPaths": 0,
+      "errorMessage": "This operation was aborted"
+    },
+    {
+      "taskId": "derangements_d7",
+      "mode": "baseline",
+      "repeat": 1,
+      "verdict": "pass",
+      "finalAgentMessage": "Alright, let's go step-by-step.\n\n---\n\n**Step 1: Understanding the problem**\n\nWe want the number of permutations of \\(\\{1, 2, 3, 4, 5, 6, 7\\}\\) with **no fixed points**.  \nA fixed point means \\(\\pi(i) = i\\) for some \\(i\\).  \nA permutation with no fixed points is called a **derangement**.  \nThe number of derangements of \\(n\\) elements is denoted \\(D_n\\) or \\(!n\\).\n\n---\n\n**Step 2: Formula for derangements**\n\nThe formula for \\(D_n\\) is:\n\n\\[\nD_n = n! \\sum_{k=0}^{n} \\frac{(-1)^k}{k!}\n\\]\n\nFor \\(n=7\\):\n\n\\[\nD_7 = 7! \\left( \\frac{1}{0!} - \\frac{1}{1!} + \\frac{1}{2!} - \\frac{1}{3!} + \\frac{1}{4!} - \\frac{1}{5!} + \\frac{1}{6!} - \\frac{1}{7!} \\right)\n\\]\n\n---\n\n**Step 3: Compute step-by-step**\n\nFirst, \\(7! = 5040\\).\n\nNow compute the sum:\n\n\\[\n\\sum_{k=0}^{7} \\frac{(-1)^k}{k!} \n= 1 - 1 + \\frac{1}{2} - \\frac{1}{6} + \\frac{1}{24} - \\frac{1}{120} + \\frac{1}{720} - \\frac{1}{5040}\n\\]\n\nLet's compute term-by-term:\n\n- \\(1 - 1 = 0\\)\n- \\(0 + 0.5 = 0.5\\)\n- \\(0.5 - \\frac{1}{6} \\approx 0.5 - 0.1666667 = 0.3333333\\)\n- \\(0.3333333 + \\frac{1}{24} \\approx 0.3333333 + 0.0416667 = 0.375\\)\n- \\(0.375 - \\frac{1}{120} \\approx 0.375 - 0.0083333 = 0.3666667\\)\n- \\(0.3666667 + \\frac{1}{720} \\approx 0.3666667 + 0.0013889 = 0.3680556\\)\n- \\(0.3680556 - \\frac{1}{5040} \\approx 0.3680556 - 0.0001984 = 0.3678572\\)\n\nSo the sum is approximately \\(0.367857142857...\\)\n\n---\n\n**Step 4: Multiply by \\(7!\\)**\n\n\\[\nD_7 = 5040 \\times 0.367857142857\\ldots\n\\]\n\nLet's compute exactly using fractions:\n\n\\[\n\\sum_{k=0}^{7} \\frac{(-1)^k}{k!} \n= \\frac{1}{2!} - \\frac{1}{3!} + \\frac{1}{4!} - \\frac{1}{5!} + \\frac{1}{6!} - \\frac{1}{7!}\n\\]\n\nWrite with common denominator \\(7! = 5040\\):\n\n- \\(\\frac{1}{2!} = \\frac{2520}{5040}\\)\n- \\(\\frac{1}{3!} = \\frac{840}{5040}\\)\n- \\(\\frac{1}{4!} = \\frac{210}{5040}\\)\n- \\(\\frac{1}{5!} = \\frac{42}{5040}\\)\n- \\(\\frac{1}{6!} = \\frac{7}{5040}\\)\n- \\(\\frac{1}{7!} = \\frac{1}{5040}\\)\n\nNow alternate signs:\n\n\\[\n\\left( \\frac{2520}{5040} - \\frac{840}{5040} \\right) \n= \\frac{1680}{5040}\n\\]\n\\[\n\\frac{1680}{5040} + \\frac{210}{5040} = \\frac{1890}{5040}\n\\]\n\\[\n\\frac{1890}{5040} - \\frac{42}{5040} = \\frac{1848}{5040}\n\\]\n\\[\n\\frac{1848}{5040} + \\frac{7}{5040} = \\frac{1855}{5040}\n\\]\n\\[\n\\frac{1855}{5040} - \\frac{1}{5040} = \\frac{1854}{5040}\n\\]\n\nSo the sum is \\(\\frac{1854}{5040}\\).\n\n---\n\n**Step 5: Multiply by \\(7!\\)**\n\n\\[\nD_7 = 5040 \\times \\frac{1854}{5040} = 1854\n\\]\n\n---\n\n**Step 6: Quick check with known derangement numbers**\n\nKnown small derangements:  \n\\(D_1 = 0, D_2 = 1, D_3 = 2, D_4 = 9, D_5 = 44, D_6 = 265, D_7 = 1854\\).  \nYes, matches known sequence.\n\n---\n\n**Final answer:**\n\nAnswer: 1854",
+      "turns": 1,
+      "cacheHitRatio": 0,
+      "costUsd": 0.00127253,
+      "claudeEquivalentUsd": 0.017292,
+      "harvestedTurns": 0,
+      "totalSubgoals": 0,
+      "totalUncertainties": 0,
+      "totalHypotheses": 0,
+      "totalRejectedPaths": 0
+    },
+    {
+      "taskId": "derangements_d7",
+      "mode": "reasoner",
+      "repeat": 1,
+      "verdict": "pass",
+      "finalAgentMessage": "The number of derangements of \\(n\\) distinct objects, denoted \\(D_n\\), counts permutations with no fixed points. For \\(n = 7\\), this can be computed using the recurrence \\(D_n = (n-1)(D_{n-1} + D_{n-2})\\) with initial values \\(D_1 = 0\\) and \\(D_2 = 1\\).  \nThus:  \n\\(D_3 = 2(1+0) = 2\\),  \n\\(D_4 = 3(2+1) = 9\\),  \n\\(D_5 = 4(9+2) = 44\\),  \n\\(D_6 = 5(44+9) = 265\\),  \n\\(D_7 = 6(265+44) = 1854\\).\n\nAnswer: 1854",
+      "turns": 1,
+      "cacheHitRatio": 0.7191011235955056,
+      "costUsd": 0.00349167,
+      "claudeEquivalentUsd": 0.024027,
+      "harvestedTurns": 0,
+      "totalSubgoals": 0,
+      "totalUncertainties": 0,
+      "totalHypotheses": 0,
+      "totalRejectedPaths": 0
+    },
+    {
+      "taskId": "derangements_d7",
+      "mode": "reasoner-harvest",
+      "repeat": 1,
+      "verdict": "pass",
+      "finalAgentMessage": "The number of derangements of \\(n\\) elements, denoted \\(D_n\\), counts permutations with no fixed points. For \\(n=7\\), this can be computed using the recurrence \\(D_n = (n-1)(D_{n-1} + D_{n-2})\\) with initial values \\(D_0 = 1\\) and \\(D_1 = 0\\). Applying the recurrence yields \\(D_2 = 1\\), \\(D_3 = 2\\), \\(D_4 = 9\\), \\(D_5 = 44\\), \\(D_6 = 265\\), and finally \\(D_7 = 6 \\times (265 + 44) = 1854\\).\n\nAnswer: 1854",
+      "turns": 1,
+      "cacheHitRatio": 0.7191011235955056,
+      "costUsd": 0.0028434299999999997,
+      "claudeEquivalentUsd": 0.019587,
+      "harvestedTurns": 1,
+      "totalSubgoals": 3,
+      "totalUncertainties": 2,
+      "totalHypotheses": 2,
+      "totalRejectedPaths": 2
+    },
+    {
+      "taskId": "euler_quadratic_break",
+      "mode": "baseline",
+      "repeat": 1,
+      "verdict": "pass",
+      "finalAgentMessage": "Let’s check \\( f(n) = n^2 + n + 41 \\) for small \\( n \\):\n\n- \\( n = 0 \\): \\( f(0) = 41 \\) (prime)  \n- \\( n = 1 \\): \\( f(1) = 1 + 1 + 41 = 43 \\) (prime)  \n- \\( n = 2 \\): \\( f(2) = 4 + 2 + 41 = 47 \\) (prime)  \n- \\( n = 3 \\): \\( f(3) = 9 + 3 + 41 = 53 \\) (prime)  \n- \\( n = 4 \\): \\( f(4) = 16 + 4 + 41 = 61 \\) (prime)  \n- \\( n = 5 \\): \\( f(5) = 25 + 5 + 41 = 71 \\) (prime)  \n- \\( n = 6 \\): \\( f(6) = 36 + 6 + 41 = 83 \\) (prime)  \n- \\( n = 7 \\): \\( f(7) = 49 + 7 + 41 = 97 \\) (prime)  \n- \\( n = 8 \\): \\( f(8) = 64 + 8 + 41 = 113 \\) (prime)  \n- \\( n = 9 \\): \\( f(9) = 81 + 9 + 41 = 131 \\) (prime)  \n- \\( n = 10 \\): \\( f(10) = 100 + 10 + 41 = 151 \\) (prime)  \n\nWe can keep going, but the first known counterexample for this famous Euler polynomial is \\( n = 40 \\), because  \n\\[\nf(40) = 40^2 + 40 + 41 = 1600 + 40 + 41 = 1681.\n\\]  \nCheck if \\( 1681 \\) is prime:  \n\\( 1681 = 41^2 \\) (since \\( 41 \\times 41 = 1681 \\)), so it’s composite.\n\nBut wait — let’s check if there’s a smaller \\( n \\) where \\( f(n) \\) is composite.  \nWe can test \\( n = 41 \\):  \n\\( f(41) = 41^2 + 41 + 41 = 1681 + 82 = 1763 \\), which is \\( 41 \\times 43 \\) (since \\( 1763/41 = 43 \\)), so composite. But \\( n = 41 \\) is larger than \\( n = 40 \\).\n\nCheck \\( n = 39 \\): \\( f(39) = 1521 + 39 + 41 = 1601 \\). Test divisibility: not divisible by primes up to \\( \\sqrt{1601} \\approx 40 \\), seems prime.  \n\nCheck \\( n = 40 \\) is indeed the first composite? Let’s check \\( n = 1 \\) to \\( 39 \\) quickly for a smaller counterexample:  \nWe can note \\( f(n) = n(n+1) + 41 \\). If \\( 41 \\mid f(n) \\), then \\( 41 \\mid n(n+1) \\).  \nThat happens when \\( n \\equiv 0 \\pmod{41} \\) or \\( n \\equiv 40 \\pmod{41} \\).  \nThe smallest positive such \\( n \\) is \\( n = 40 \\) (since \\( n=41 \\) is larger).  \nSo for \\( n = 40 \\), \\( f(40) = 40 \\times 41 + 41 = 41 \\times 41 \\) is composite.  \n\nCheck \\( n = 0 \\) to \\( 39 \\): no multiple of 41 except \\( n=0 \\) (which gives 41, prime). So \\( n=40 \\) is indeed the first nonnegative integer where \\( f(n) \\) is composite.\n\nThus smallest \\( n \\) is \\( 40 \\), \\( f(40) = 1681 = 41^2 \\).\n\n**Answer:** 40",
+      "turns": 1,
+      "cacheHitRatio": 0,
+      "costUsd": 0.00098535,
+      "claudeEquivalentUsd": 0.013365,
+      "harvestedTurns": 0,
+      "totalSubgoals": 0,
+      "totalUncertainties": 0,
+      "totalHypotheses": 0,
+      "totalRejectedPaths": 0
+    },
+    {
+      "taskId": "euler_quadratic_break",
+      "mode": "reasoner",
+      "repeat": 1,
+      "verdict": "pass",
+      "finalAgentMessage": "The smallest nonnegative integer \\(n\\) for which \\(f(n) = n^2 + n + 41\\) is composite is \\(n = 40\\). At this value, \\(f(40) = 40^2 + 40 + 41 = 1681 = 41^2\\), which is not prime.\n\nAnswer: 40",
+      "turns": 1,
+      "cacheHitRatio": 0.6095238095238096,
+      "costUsd": 0.0014309199999999998,
+      "claudeEquivalentUsd": 0.0099,
+      "harvestedTurns": 0,
+      "totalSubgoals": 0,
+      "totalUncertainties": 0,
+      "totalHypotheses": 0,
+      "totalRejectedPaths": 0
+    },
+    {
+      "taskId": "euler_quadratic_break",
+      "mode": "reasoner-harvest",
+      "repeat": 1,
+      "verdict": "pass",
+      "finalAgentMessage": "The polynomial \\(f(n) = n^2 + n + 41\\) is known to produce primes for \\(n = 0, 1, 2, \\dots, 39\\). At \\(n = 40\\), we have \\(f(40) = 40^2 + 40 + 41 = 1681\\), and \\(1681 = 41^2\\), which is composite. Therefore, \\(n = 40\\) is the smallest nonnegative integer where \\(f(n)\\) fails to be prime.\n\nAnswer: 40",
+      "turns": 1,
+      "cacheHitRatio": 0.6095238095238096,
+      "costUsd": 0.0025938099999999998,
+      "claudeEquivalentUsd": 0.017865,
+      "harvestedTurns": 1,
+      "totalSubgoals": 3,
+      "totalUncertainties": 2,
+      "totalHypotheses": 3,
+      "totalRejectedPaths": 2
+    }
+  ]
+}

benchmarks/harvest/runner.ts

@@ -0,0 +1,312 @@
+/**
+ * Harvest-bench runner.
+ *
+ * Usage:
+ *   npx tsx benchmarks/harvest/runner.ts                      # all tasks, all modes, 1 repeat
+ *   npx tsx benchmarks/harvest/runner.ts --task mod7_list
+ *   npx tsx benchmarks/harvest/runner.ts --mode reasoner-harvest --repeats 3
+ *   npx tsx benchmarks/harvest/runner.ts --transcripts-dir transcripts/
+ *   npx tsx benchmarks/harvest/runner.ts --dry                # smoke test wiring, no API
+ *
+ * Writes results.json. Render report.md with `report.ts`.
+ */
+
+import { type WriteStream, mkdirSync, writeFileSync } from "node:fs";
+import { join } from "node:path";
+import { pathToFileURL } from "node:url";
+import {
+  CacheFirstLoop,
+  DeepSeekClient,
+  ImmutablePrefix,
+  claudeEquivalentCost,
+  loadDotenv,
+} from "../../src/index.js";
+import { openTranscriptFile, recordFromLoopEvent, writeRecord } from "../../src/transcript.js";
+import { TASKS } from "./tasks.js";
+import type {
+  HarvestBenchMeta,
+  HarvestBenchReport,
+  HarvestMode,
+  HarvestRunResult,
+  HarvestTask,
+} from "./types.js";
+import { ALL_MODES } from "./types.js";
+
+loadDotenv();
+
+interface CliArgs {
+  taskFilter: string | null;
+  modes: HarvestMode[];
+  repeats: number;
+  outPath: string | null;
+  transcriptsDir: string | null;
+  /** Per-HTTP-call timeout in ms. Default 300_000 (5 min) — reasoner + harvest runs legitimately need this. */
+  timeoutMs: number;
+  dry: boolean;
+  verbose: boolean;
+}
+
+function parseArgs(argv: string[]): CliArgs {
+  const out: CliArgs = {
+    taskFilter: null,
+    modes: [...ALL_MODES],
+    repeats: 1,
+    outPath: null,
+    transcriptsDir: null,
+    timeoutMs: 300_000,
+    dry: false,
+    verbose: false,
+  };
+  for (let i = 0; i < argv.length; i++) {
+    const a = argv[i];
+    if (a === "--task") out.taskFilter = argv[++i] ?? null;
+    else if (a === "--mode") {
+      const v = (argv[++i] ?? "").toLowerCase() as HarvestMode;
+      if ((ALL_MODES as string[]).includes(v)) out.modes = [v];
+    } else if (a === "--repeats") out.repeats = Number.parseInt(argv[++i] ?? "1", 10);
+    else if (a === "--out") out.outPath = argv[++i] ?? null;
+    else if (a === "--transcripts-dir") out.transcriptsDir = argv[++i] ?? null;
+    else if (a === "--timeout") {
+      // Accept seconds for humans, convert to ms internally.
+      const secs = Number.parseInt(argv[++i] ?? "300", 10);
+      if (Number.isFinite(secs) && secs > 0) out.timeoutMs = secs * 1000;
+    } else if (a === "--dry") out.dry = true;
+    else if (a === "--verbose" || a === "-v") out.verbose = true;
+  }
+  return out;
+}
+
+// ---------- model resolution ----------
+
+function modelForMode(mode: HarvestMode): string {
+  if (mode === "baseline") return "deepseek-chat";
+  return "deepseek-reasoner";
+}
+
+function harvestForMode(mode: HarvestMode): boolean {
+  return mode === "reasoner-harvest";
+}
+
+// ---------- run one task in one mode ----------
+
+async function runOnce(
+  task: HarvestTask,
+  mode: HarvestMode,
+  rep: number,
+  client: DeepSeekClient,
+  transcriptStream: WriteStream | null,
+): Promise<HarvestRunResult> {
+  const model = modelForMode(mode);
+  const harvest = harvestForMode(mode);
+
+  const prefix = new ImmutablePrefix({ system: task.systemPrompt });
+  const loop = new CacheFirstLoop({
+    client,
+    prefix,
+    model,
+    harvest,
+    stream: false,
+  });
+  const prefixHash = prefix.fingerprint;
+
+  let harvestedTurns = 0;
+  let totalSubgoals = 0;
+  let totalUncertainties = 0;
+  let totalHypotheses = 0;
+  let totalRejectedPaths = 0;
+  let finalText = "";
+  let errorMessage: string | undefined;
+
+  if (transcriptStream) {
+    writeRecord(transcriptStream, {
+      ts: new Date().toISOString(),
+      turn: 1,
+      role: "user",
+      content: task.prompt,
+    });
+  }
+
+  try {
+    for await (const ev of loop.step(task.prompt)) {
+      if (transcriptStream && ev.role !== "assistant_delta") {
+        writeRecord(transcriptStream, recordFromLoopEvent(ev, { model, prefixHash }));
+      }
+      if (ev.role === "assistant_final") {
+        finalText = ev.content;
+        if (ev.planState) {
+          if (
+            ev.planState.subgoals.length +
+              ev.planState.hypotheses.length +
+              ev.planState.uncertainties.length +
+              ev.planState.rejectedPaths.length >
+            0
+          ) {
+            harvestedTurns++;
+            totalSubgoals += ev.planState.subgoals.length;
+            totalHypotheses += ev.planState.hypotheses.length;
+            totalUncertainties += ev.planState.uncertainties.length;
+            totalRejectedPaths += ev.planState.rejectedPaths.length;
+          }
+        }
+      } else if (ev.role === "done") {
+        finalText = ev.content || finalText;
+        break;
+      } else if (ev.role === "error") {
+        throw new Error(ev.error ?? "loop error");
+      }
+    }
+  } catch (err) {
+    errorMessage = (err as Error).message;
+  }
+
+  const verdict = errorMessage ? { verdict: "fail" as const, note: errorMessage } : task.check(finalText);
+
+  return {
+    taskId: task.id,
+    mode,
+    repeat: rep + 1,
+    verdict: verdict.verdict,
+    checkNote: verdict.note,
+    finalAgentMessage: finalText,
+    turns: loop.stats.turns.length,
+    cacheHitRatio: loop.stats.aggregateCacheHitRatio,
+    costUsd: loop.stats.totalCost,
+    claudeEquivalentUsd: loop.stats.turns.reduce((s, t) => s + claudeEquivalentCost(t.usage), 0),
+    harvestedTurns,
+    totalSubgoals,
+    totalUncertainties,
+    totalHypotheses,
+    totalRejectedPaths,
+    errorMessage,
+  };
+}
+
+// ---------- dry mode ----------
+
+function runDry(args: CliArgs): HarvestBenchReport {
+  const tasks = filterTasks(args.taskFilter);
+  const results: HarvestRunResult[] = [];
+  for (const task of tasks) {
+    // Exercise each checker with a deliberately wrong reply so we know
+    // the wiring is live — not a pass on empty.
+    const sanity = task.check("Answer: this is not the right answer at all");
+    console.log(`[${task.id}] checker exercises ok (sanity verdict=${sanity.verdict})`);
+    for (const mode of args.modes) {
+      results.push({
+        taskId: task.id,
+        mode,
+        repeat: 1,
+        verdict: "inconclusive",
+        checkNote: "dry-run (no model call)",
+        finalAgentMessage: "[dry-run]",
+        turns: 0,
+        cacheHitRatio: 0,
+        costUsd: 0,
+        claudeEquivalentUsd: 0,
+        harvestedTurns: 0,
+        totalSubgoals: 0,
+        totalUncertainties: 0,
+        totalHypotheses: 0,
+        totalRejectedPaths: 0,
+      });
+    }
+  }
+  return { meta: buildMeta(args, tasks.length), results };
+}
+
+// ---------- main ----------
+
+function filterTasks(filter: string | null): HarvestTask[] {
+  if (!filter) return TASKS;
+  const t = TASKS.find((x) => x.id === filter);
+  if (!t) throw new Error(`unknown task: ${filter}`);
+  return [t];
+}
+
+function buildMeta(args: CliArgs, taskCount: number): HarvestBenchMeta {
+  return {
+    date: new Date().toISOString(),
+    repeatsPerTask: args.repeats,
+    taskCount,
+    modesRun: args.modes,
+    reasonixVersion: "0.2.2",
+  };
+}
+
+async function main(): Promise<void> {
+  const args = parseArgs(process.argv.slice(2));
+
+  if (args.dry) {
+    const report = runDry(args);
+    writeReport(report, args.outPath);
+    return;
+  }
+
+  const client = new DeepSeekClient({ timeoutMs: args.timeoutMs });
+  const tasks = filterTasks(args.taskFilter);
+
+  if (args.transcriptsDir) mkdirSync(args.transcriptsDir, { recursive: true });
+
+  const results: HarvestRunResult[] = [];
+  for (const task of tasks) {
+    for (let rep = 0; rep < args.repeats; rep++) {
+      for (const mode of args.modes) {
+        let stream: WriteStream | null = null;
+        if (args.transcriptsDir) {
+          const fname = `${task.id}.${mode}.r${rep + 1}.jsonl`;
+          stream = openTranscriptFile(join(args.transcriptsDir, fname), {
+            version: 1,
+            source: `harvest-bench/${mode}`,
+            model: modelForMode(mode),
+            task: task.id,
+            mode,
+            repeat: rep + 1,
+            startedAt: new Date().toISOString(),
+          });
+        }
+        const started = Date.now();
+        let result: HarvestRunResult;
+        try {
+          result = await runOnce(task, mode, rep, client, stream);
+        } finally {
+          stream?.end();
+        }
+        const elapsed = ((Date.now() - started) / 1000).toFixed(1);
+        console.log(
+          `[${task.id}/${mode}/r${rep + 1}] verdict=${result.verdict}` +
+            ` cache=${(result.cacheHitRatio * 100).toFixed(1)}%` +
+            ` cost=$${result.costUsd.toFixed(6)}` +
+            ` harvest=${result.harvestedTurns}:${result.totalSubgoals}s/${result.totalUncertainties}u` +
+            ` (${elapsed}s)` +
+            (result.checkNote ? `  ${result.checkNote}` : ""),
+        );
+        results.push(result);
+      }
+    }
+  }
+
+  const report: HarvestBenchReport = { meta: buildMeta(args, tasks.length), results };
+  writeReport(report, args.outPath);
+}
+
+function writeReport(report: HarvestBenchReport, outPath: string | null): void {
+  const path =
+    outPath ?? `benchmarks/harvest/results-${new Date().toISOString().replace(/[:.]/g, "-")}.json`;
+  writeFileSync(path, `${JSON.stringify(report, null, 2)}\n`, "utf8");
+  console.log(`wrote ${path}`);
+}
+
+function isMain(): boolean {
+  const entry = process.argv[1];
+  if (!entry) return false;
+  return import.meta.url === pathToFileURL(entry).href;
+}
+
+if (isMain()) {
+  main().catch((err) => {
+    console.error(err);
+    process.exit(1);
+  });
+}
+
+export { main as runHarvestBench };

benchmarks/harvest/tasks.ts

@@ -0,0 +1,171 @@
+/**
+ * Seed reasoning tasks for the harvest eval harness.
+ *
+ * Each task has:
+ *   - a minimal system prompt (so the comparison is about the model, not
+ *     the prompt)
+ *   - a single user question
+ *   - a deterministic checker (regex + set/value compare)
+ *
+ * When adding a new task, prefer problems where:
+ *   - the answer has a clean shape (a number, a small set, a yes/no +
+ *     explanation) — easier to check
+ *   - reasoning actually matters (so harvest has signal to extract);
+ *     trivia questions are out of scope
+ *   - there's a known-good answer; judgment calls are out of scope
+ */
+
+import type { HarvestTask } from "./types.js";
+
+const CONCISE_SYSTEM = `You are a precise reasoner. Think carefully, then state your final answer on a clearly-labeled line starting with "Answer:".`;
+
+/**
+ * Parse all non-negative integers out of a string. Handles commas,
+ * ranges written as "2-4" (expands to 2,3,4), and ignores numbers that
+ * look like formula references (e.g. "n^2", "mod 7") by only accepting
+ * integers after we strip common LaTeX decorations.
+ */
+function extractIntegers(text: string): number[] {
+  // Strip LaTeX delimiters so n_1 / n^2 / \{ ... \} don't confuse us.
+  const cleaned = text
+    .replace(/\\[a-zA-Z]+/g, " ") // \frac, \mod etc.
+    .replace(/[{}\\]/g, " ")
+    .replace(/[_^]\d+/g, " "); // subscript/superscript numbers
+  // Expand ranges: "2-4" → "2,3,4" (only for small gaps)
+  const rangeExpanded = cleaned.replace(/(\d+)\s*[-–]\s*(\d+)/g, (_, a, b) => {
+    const lo = Number.parseInt(a, 10);
+    const hi = Number.parseInt(b, 10);
+    if (!Number.isFinite(lo) || !Number.isFinite(hi) || hi - lo > 50) return `${a} ${b}`;
+    const out: number[] = [];
+    for (let i = Math.min(lo, hi); i <= Math.max(lo, hi); i++) out.push(i);
+    return out.join(" ");
+  });
+  const matches = rangeExpanded.match(/-?\d+/g) ?? [];
+  return matches.map((m) => Number.parseInt(m, 10)).filter((n) => Number.isFinite(n));
+}
+
+/** Extract content after the last "Answer:" label (case-insensitive). */
+function extractAnswerLine(text: string): string {
+  const matches = [...text.matchAll(/answer\s*[:：]\s*([^\n]+)/gi)];
+  if (matches.length === 0) return text;
+  return matches[matches.length - 1]![1]!.trim();
+}
+
+// ---------- expected answers ----------
+
+/** Positive n ≤ 100 such that n^2 + n + 1 ≡ 0 (mod 7). */
+const MOD7_EXPECTED: number[] = (() => {
+  const out: number[] = [];
+  for (let n = 1; n <= 100; n++) {
+    if ((n * n + n + 1) % 7 === 0) out.push(n);
+  }
+  return out;
+})();
+
+/**
+ * Single-integer checker. Pulls the first plausible integer from the last
+ * "Answer:" line; compares for exact equality.
+ */
+function checkSingleInt(expected: number) {
+  return (reply: string) => {
+    const answerLine = extractAnswerLine(reply);
+    const nums = extractIntegers(answerLine);
+    if (nums.length === 0) return { verdict: "fail" as const, note: "no number in Answer line" };
+    const n = nums[0]!;
+    if (n === expected) return { verdict: "pass" as const };
+    return { verdict: "fail" as const, note: `got ${n}, expected ${expected}` };
+  };
+}
+
+// ---------- tasks ----------
+
+export const TASKS: HarvestTask[] = [
+  {
+    id: "mod7_list",
+    description:
+      "Number theory — find all positive n ≤ 100 with n^2+n+1 ≡ 0 (mod 7). 29-element set. Classic R1 scratch-work territory.",
+    systemPrompt: CONCISE_SYSTEM,
+    prompt:
+      "Find all positive integers n with n ≤ 100 such that n^2 + n + 1 is divisible by 7. Briefly justify, then end with the full list on a line starting with \"Answer:\".",
+    check: (reply) => {
+      const answerLine = extractAnswerLine(reply);
+      const found = new Set(extractIntegers(answerLine).filter((n) => n >= 1 && n <= 100));
+      const expected = new Set(MOD7_EXPECTED);
+      if (found.size === 0) {
+        return { verdict: "fail", note: "no integers extracted from Answer line" };
+      }
+      // Exact set equality — both containment directions.
+      for (const n of expected) if (!found.has(n)) return { verdict: "fail", note: `missing n=${n}` };
+      for (const n of found) if (!expected.has(n)) return { verdict: "fail", note: `extra n=${n}` };
+      return { verdict: "pass" };
+    },
+  },
+
+  {
+    id: "flips_until_3heads",
+    description:
+      "Probability — expected coin flips until 3 consecutive heads. Answer: 14. Tests whether R1 derives via recurrence or via memorized result.",
+    systemPrompt: CONCISE_SYSTEM,
+    prompt:
+      "A fair coin is flipped repeatedly until you see 3 heads in a row. What is the expected number of total flips? Give a single integer on a line starting with \"Answer:\".",
+    check: (reply) => {
+      const answerLine = extractAnswerLine(reply);
+      const nums = extractIntegers(answerLine);
+      if (nums.length === 0) return { verdict: "fail", note: "no number in Answer line" };
+      // Accept the first sensible number — sometimes agents write "Answer: 14 flips".
+      const n = nums[0]!;
+      if (n === 14) return { verdict: "pass" };
+      return { verdict: "fail", note: `got ${n}, expected 14` };
+    },
+  },
+
+  {
+    id: "three_hats",
+    description:
+      "Logic — three people wear red/blue hats, at least one red, they're asked in order. First two say no, third says yes. What color? Answer: red (deducible because if third were blue, the first two could see one red + one unknown and wouldn't have said no on their full first round, for most configurations the third can only be certain if red).",
+    systemPrompt: CONCISE_SYSTEM,
+    prompt:
+      'Three people wear hats that are each red or blue. They are told at least one hat is red. Each can see the other two hats but not their own. They are asked in order: "Do you know your hat color?" The first two answer no. The third answers yes. What color is the third person\'s hat? Give a one-word answer on a line starting with "Answer:".',
+    check: (reply) => {
+      const answerLine = extractAnswerLine(reply).toLowerCase();
+      // Accept "red" as a standalone word (not "redirected" etc).
+      if (/\bred\b/.test(answerLine) && !/\bblue\b/.test(answerLine)) {
+        return { verdict: "pass" };
+      }
+      if (/\bblue\b/.test(answerLine)) return { verdict: "fail", note: "answered blue" };
+      return { verdict: "fail", note: "no clear color in Answer line" };
+    },
+  },
+
+  // ---------- hard tasks (picked for known V3 failure modes) ----------
+
+  {
+    id: "pseudoprime_base2",
+    description:
+      "Number theory — smallest composite n > 1 such that 2^n ≡ 2 (mod n). This is the smallest Fermat pseudoprime to base 2. Answer: 341 (= 11·31). V3 frequently answers 561 (Carmichael / wrong base-2 property) or 9 (not actually a pseudoprime to base 2, verifying the model isn't computing). R1 usually gets this right.",
+    systemPrompt: CONCISE_SYSTEM,
+    prompt:
+      'Find the smallest composite integer n > 1 such that 2^n is congruent to 2 modulo n (i.e., n is a Fermat pseudoprime to base 2). Briefly justify, then give a single integer on a line starting with "Answer:".',
+    check: checkSingleInt(341),
+  },
+
+  {
+    id: "derangements_d7",
+    description:
+      "Combinatorics — number of derangements of 7 elements. Answer: 1854 (D_7 = 7! · (1 − 1/1! + 1/2! − 1/3! + … ± 1/7!) = 5040 · 0.367857… = 1854). V3 sometimes approximates via n!/e and rounds wrong, or confuses with D_6=265 or D_8=14833. R1's explicit recurrence D_n = (n-1)(D_{n-1}+D_{n-2}) avoids the mistake.",
+    systemPrompt: CONCISE_SYSTEM,
+    prompt:
+      'How many permutations of {1, 2, 3, 4, 5, 6, 7} have no fixed points? (This is D_7, the derangement number.) Briefly justify, then give a single integer on a line starting with "Answer:".',
+    check: checkSingleInt(1854),
+  },
+
+  {
+    id: "euler_quadratic_break",
+    description:
+      "Number theory — smallest nonneg integer n where n^2 + n + 41 is NOT prime. Euler's prime-generating polynomial famously produces primes for n = 0..39 and first fails at n = 40 (40²+40+41 = 1681 = 41²). V3 often confuses this with the related n²-n+41 (first fails at 41) or cites the wrong threshold. R1 checks small n systematically.",
+    systemPrompt: CONCISE_SYSTEM,
+    prompt:
+      'Consider the polynomial f(n) = n^2 + n + 41 for n = 0, 1, 2, …. What is the smallest nonneg integer n at which f(n) fails to be prime? Briefly justify (including the value of f(n) at that point), then give just the integer n on a line starting with "Answer:".',
+    check: checkSingleInt(40),
+  },
+];

benchmarks/harvest/types.ts

@@ -0,0 +1,82 @@
+/**
+ * Types for the harvest eval harness.
+ *
+ * Scope: this is deliberately NOT τ-bench-lite. These tasks:
+ *   - are single-turn Q/A (no user simulator, no DB)
+ *   - target reasoning-heavy problems (math, logic, planning)
+ *   - use deterministic checkers (regex extraction + set/value compare),
+ *     never an LLM judge
+ *
+ * The point is to measure Pillar 2 (harvest) the same way τ-bench-lite
+ * measures Pillar 1 (cache-first): isolate one variable, produce numbers
+ * anyone can reproduce.
+ */
+
+export type HarvestMode =
+  /** deepseek-chat, no Reasonix tricks. Floor reference for answer quality on reasoning tasks (V3 at its best). */
+  | "baseline"
+  /** deepseek-reasoner, no harvest. Isolates "does reasoner help over chat on these problems?" */
+  | "reasoner"
+  /** deepseek-reasoner + harvest. Isolates "does the extra V3 harvest call add quality / change behavior?" */
+  | "reasoner-harvest";
+
+export const ALL_MODES: HarvestMode[] = ["baseline", "reasoner", "reasoner-harvest"];
+
+/**
+ * Checker verdict. We don't use boolean directly because "maybe" is real
+ * — e.g. "answer in the right shape but can't verify without running the
+ * program". For v0.3 we only use {pass, fail}, but the shape leaves room.
+ */
+export type CheckVerdict = "pass" | "fail" | "inconclusive";
+
+export interface HarvestTask {
+  id: string;
+  /** One-line human description, not shown to the model. */
+  description: string;
+  /** System prompt. Kept minimal so harvest signal can be attributed to the model, not to prompt engineering. */
+  systemPrompt: string;
+  /** The single question. */
+  prompt: string;
+  /**
+   * Check the agent's final reply. Returns pass/fail/inconclusive plus an
+   * optional one-line explanation the report can surface.
+   *
+   * IMPORTANT: must be pure and deterministic. No LLM calls, no file I/O.
+   */
+  check: (agentReply: string) => { verdict: CheckVerdict; note?: string };
+}
+
+export interface HarvestRunResult {
+  taskId: string;
+  mode: HarvestMode;
+  repeat: number;
+  verdict: CheckVerdict;
+  checkNote?: string;
+  finalAgentMessage: string;
+  /** Turns the loop completed (usually 1 for a single-shot Q/A, > 1 if tool-calls happen). */
+  turns: number;
+  cacheHitRatio: number;
+  costUsd: number;
+  claudeEquivalentUsd: number;
+  /** Harvest-specific — only non-zero on reasoner-harvest mode. */
+  harvestedTurns: number;
+  totalSubgoals: number;
+  totalUncertainties: number;
+  totalHypotheses: number;
+  totalRejectedPaths: number;
+  /** Optional error message if the run crashed (model down, timeout, etc). */
+  errorMessage?: string;
+}
+
+export interface HarvestBenchMeta {
+  date: string;
+  repeatsPerTask: number;
+  taskCount: number;
+  modesRun: HarvestMode[];
+  reasonixVersion: string;
+}
+
+export interface HarvestBenchReport {
+  meta: HarvestBenchMeta;
+  results: HarvestRunResult[];
+}

benchmarks/tau-bench/baseline.ts

@@ -0,0 +1,178 @@
+/**
+ * Naive baseline runner — deliberately does NOT use CacheFirstLoop.
+ *
+ * For the benchmark comparison to be honest, this runner must reproduce
+ * what a "typical" agent framework does that breaks DeepSeek's automatic
+ * prefix cache:
+ *
+ *   1. Inject a fresh timestamp into the system prompt every turn.
+ *   2. Re-serialize the tool list each turn with a shuffled key order.
+ *   3. Rebuild the full message array each turn rather than appending.
+ *
+ * These are all things frameworks like LangChain/LangGraph do by default
+ * (either directly, or because tool specs are regenerated from Python dicts
+ * with non-deterministic ordering, or because a "current_time" placeholder
+ * is recommended in common system-prompt recipes).
+ *
+ * Reuses DeepSeekClient, ToolRegistry, and SessionStats so the *only*
+ * difference from the Reasonix run is prefix stability.
+ */
+
+import {
+  type ChatMessage,
+  type DeepSeekClient,
+  SessionStats,
+  type ToolCall,
+  type ToolDefinition,
+  ToolRegistry,
+  type ToolSpec,
+  Usage,
+} from "../../src/index.js";
+import type { Turn } from "./types.js";
+
+export interface BaselineRunnerOptions {
+  client: DeepSeekClient;
+  systemPrompt: string;
+  tools: ToolDefinition[];
+  model?: string;
+  maxToolIters?: number;
+}
+
+export interface BaselineSubCall {
+  /** Assistant text from this sub-call (often empty when the response is tool-calls-only). */
+  content: string;
+  /** Usage for this single client.chat() call. */
+  usage: Usage;
+  /** Tools the model chose to call on the back of this response. */
+  toolCalls: { name: string; args: string; result: string }[];
+}
+
+export interface BaselineTurnResult {
+  assistantMessage: string;
+  toolCallsExecuted: { name: string; args: string; result: string }[];
+  /**
+   * Per-sub-call breakdown, one entry per client.chat() invocation. Gives
+   * downstream tools (bench transcripts) the same granularity as Reasonix
+   * loop events — without it, diff can't compare model-call counts
+   * apples-to-apples.
+   */
+  subCalls: BaselineSubCall[];
+  /** Turn number (1-based) assigned by the agent. */
+  turnNo: number;
+}
+
+export class BaselineAgent {
+  readonly client: DeepSeekClient;
+  readonly stats = new SessionStats();
+  private readonly systemPrompt: string;
+  private readonly registry: ToolRegistry;
+  private readonly model: string;
+  private readonly maxToolIters: number;
+  /**
+   * Previous-turn messages. A naive framework keeps these, but we still
+   * rebuild the prefix around them each turn so the byte prefix churns.
+   */
+  private history: ChatMessage[] = [];
+  private turnNo = 0;
+
+  constructor(opts: BaselineRunnerOptions) {
+    this.client = opts.client;
+    this.systemPrompt = opts.systemPrompt;
+    this.model = opts.model ?? "deepseek-chat";
+    this.maxToolIters = opts.maxToolIters ?? 6;
+    this.registry = new ToolRegistry({ autoFlatten: false });
+    for (const t of opts.tools) this.registry.register(t);
+  }
+
+  /**
+   * Run one user-turn: sends the user message, lets the model do tool
+   * calls until it stops, returns the final assistant text.
+   *
+   * Intentionally non-cache-friendly: rebuilds the prefix with a fresh
+   * timestamp + re-shuffled tool specs every turn.
+   */
+  async userTurn(userMessage: string, transcript: Turn[]): Promise<BaselineTurnResult> {
+    this.turnNo++;
+
+    // Naive pattern #1: current-time placeholder in the system prompt.
+    const churnedSystem = `${this.systemPrompt}\nCurrent time: ${new Date().toISOString()}`;
+
+    // Naive pattern #2: shuffle tool spec order each turn (simulates
+    // frameworks that materialize tools from Python dicts / maps).
+    const shuffledTools = shuffle(this.registry.specs(), this.turnNo);
+
+    this.history.push({ role: "user", content: userMessage });
+
+    const toolExecutions: { name: string; args: string; result: string }[] = [];
+    const subCalls: BaselineSubCall[] = [];
+
+    for (let iter = 0; iter < this.maxToolIters; iter++) {
+      // Naive pattern #3: always rebuild the full message array.
+      const messages: ChatMessage[] = [{ role: "system", content: churnedSystem }, ...this.history];
+
+      const resp = await this.client.chat({
+        model: this.model,
+        messages,
+        tools: shuffledTools,
+      });
+      this.stats.record(this.turnNo, this.model, resp.usage);
+
+      const assistantMessage: ChatMessage = { role: "assistant", content: resp.content };
+      if (resp.toolCalls.length > 0) assistantMessage.tool_calls = resp.toolCalls;
+      this.history.push(assistantMessage);
+
+      if (resp.toolCalls.length === 0) {
+        subCalls.push({ content: resp.content, usage: resp.usage, toolCalls: [] });
+        return {
+          assistantMessage: resp.content,
+          toolCallsExecuted: toolExecutions,
+          subCalls,
+          turnNo: this.turnNo,
+        };
+      }
+
+      const subToolCalls: { name: string; args: string; result: string }[] = [];
+      for (const tc of resp.toolCalls) {
+        const name = tc.function?.name ?? "";
+        const args = tc.function?.arguments ?? "{}";
+        const result = await this.registry.dispatch(name, args);
+        toolExecutions.push({ name, args, result });
+        subToolCalls.push({ name, args, result });
+        this.history.push({
+          role: "tool",
+          tool_call_id: tc.id ?? "",
+          name,
+          content: result,
+        });
+      }
+      subCalls.push({ content: resp.content, usage: resp.usage, toolCalls: subToolCalls });
+    }
+
+    const lastAssistant = [...this.history].reverse().find((m) => m.role === "assistant");
+    return {
+      assistantMessage: lastAssistant?.content ?? "[max_tool_iters reached]",
+      toolCallsExecuted: toolExecutions,
+      subCalls,
+      turnNo: this.turnNo,
+    };
+  }
+}
+
+/**
+ * Deterministic Fisher–Yates shuffle seeded by an integer. Same turn number
+ * → same ordering, so the baseline is reproducible across runs while still
+ * being cache-hostile (different turns get different orderings).
+ */
+function shuffle<T>(arr: T[], seed: number): T[] {
+  const out = [...arr];
+  let s = seed * 9301 + 49297;
+  for (let i = out.length - 1; i > 0; i--) {
+    s = (s * 9301 + 49297) % 233280;
+    const j = Math.floor((s / 233280) * (i + 1));
+    [out[i], out[j]] = [out[j]!, out[i]!];
+  }
+  return out;
+}
+
+// Re-export ToolCall, ToolSpec so caller files don't need to import both places.
+export type { ToolCall, ToolSpec };

benchmarks/tau-bench/db.ts

@@ -0,0 +1,30 @@
+import type { WorldState } from "./types.js";
+
+/**
+ * Deep-clone a WorldState so per-run mutations stay isolated.
+ * structuredClone is enough — WorldState is JSON-shaped by contract.
+ */
+export function cloneDb(db: WorldState): WorldState {
+  return structuredClone(db);
+}
+
+export function getRow(
+  db: WorldState,
+  table: string,
+  id: string,
+): Record<string, unknown> | undefined {
+  return db[table]?.[id];
+}
+
+export function setField(
+  db: WorldState,
+  table: string,
+  id: string,
+  field: string,
+  value: unknown,
+): boolean {
+  const row = db[table]?.[id];
+  if (!row) return false;
+  row[field] = value;
+  return true;
+}

benchmarks/tau-bench/report.md

@@ -0,0 +1,100 @@
+# Reasonix tool-use eval (τ-bench-lite)
+
+**Date:** 2026-04-21T14:57:44.906Z
+**Agent model:** `deepseek-chat`
+**User-simulator model:** `deepseek-chat`
+**Tasks:** 8, repeats × 3
+**Reasonix version:** 0.2.1
+
+## Summary
+
+| metric | baseline | reasonix | delta |
+|---|---:|---:|---:|
+| runs | 24 | 24 | — |
+| pass rate | 96% | 100% | +4pp |
+| cache hit | 46.6% | 94.4% | **+47.7pp** |
+| mean cost / task | $0.002599 | $0.001579 | ×0.61 |
+| mean turns | 4.4 | 4.6 | — |
+| mean tool calls | 3.0 | 2.7 | — |
+
+**Reasonix vs Claude Sonnet 4.6 (estimated, same token counts):**
+Claude would cost ~$0.038203 / task, so Reasonix saves ~96.0%.
+(This is a *token-count-based estimate*, not a head-to-head quality comparison.)
+
+## Per-task breakdown
+
+| task | mode | pass | turns | tools | cache | cost |
+|---|---|:---:|---:|---:|---:|---:|
+| t01_address_happy | baseline | ✅ | 3 | 3 | 53.1% | $0.001383 |
+| t01_address_happy | reasonix | ✅ | 3 | 3 | 94.4% | $0.000896 |
+| t01_address_happy | baseline | ✅ | 3 | 3 | 53.3% | $0.001405 |
+| t01_address_happy | reasonix | ✅ | 3 | 2 | 95.0% | $0.000756 |
+| t01_address_happy | baseline | ✅ | 3 | 2 | 44.0% | $0.001193 |
+| t01_address_happy | reasonix | ✅ | 3 | 2 | 92.6% | $0.000848 |
+| t02_address_not_allowed | baseline | ✅ | 8 | 2 | 23.6% | $0.004647 |
+| t02_address_not_allowed | reasonix | ✅ | 8 | 4 | 95.6% | $0.003067 |
+| t02_address_not_allowed | baseline | ✅ | 8 | 3 | 29.9% | $0.005585 |
+| t02_address_not_allowed | reasonix | ✅ | 8 | 2 | 96.2% | $0.002822 |
+| t02_address_not_allowed | baseline | ✅ | 8 | 7 | 50.7% | $0.007021 |
+| t02_address_not_allowed | reasonix | ✅ | 8 | 3 | 95.8% | $0.003140 |
+| t03_cancel_processing | baseline | ✅ | 3 | 3 | 53.3% | $0.001349 |
+| t03_cancel_processing | reasonix | ✅ | 3 | 3 | 94.9% | $0.000803 |
+| t03_cancel_processing | baseline | ✅ | 2 | 3 | 64.6% | $0.001041 |
+| t03_cancel_processing | reasonix | ✅ | 2 | 2 | 93.8% | $0.000563 |
+| t03_cancel_processing | baseline | ✅ | 3 | 3 | 53.4% | $0.001332 |
+| t03_cancel_processing | reasonix | ✅ | 2 | 2 | 93.8% | $0.000566 |
+| t04_refund_delivered | baseline | ✅ | 2 | 2 | 55.9% | $0.001007 |
+| t04_refund_delivered | reasonix | ✅ | 2 | 3 | 91.0% | $0.000911 |
+| t04_refund_delivered | baseline | ✅ | 3 | 2 | 44.8% | $0.001268 |
+| t04_refund_delivered | reasonix | ✅ | 3 | 3 | 93.2% | $0.000941 |
+| t04_refund_delivered | baseline | ✅ | 3 | 3 | 53.5% | $0.001469 |
+| t04_refund_delivered | reasonix | ✅ | 3 | 3 | 94.4% | $0.000952 |
+| t05_refund_not_delivered | baseline | ✅ | 8 | 4 | 41.7% | $0.005369 |
+| t05_refund_not_delivered | reasonix | ✅ | 7 | 2 | 96.3% | $0.002212 |
+| t05_refund_not_delivered | baseline | ✅ | 8 | 3 | 30.6% | $0.004762 |
+| t05_refund_not_delivered | reasonix | ✅ | 8 | 4 | 95.1% | $0.003159 |
+| t05_refund_not_delivered | baseline | ✅ | 6 | 2 | 24.8% | $0.003128 |
+| t05_refund_not_delivered | reasonix | ✅ | 6 | 2 | 94.7% | $0.001927 |
+| t06_multi_order_lookup | baseline | ✅ | 2 | 2 | 52.4% | $0.000913 |
+| t06_multi_order_lookup | reasonix | ✅ | 3 | 2 | 92.7% | $0.000988 |
+| t06_multi_order_lookup | baseline | ✅ | 3 | 2 | 41.2% | $0.001530 |
+| t06_multi_order_lookup | reasonix | ✅ | 3 | 2 | 93.4% | $0.000996 |
+| t06_multi_order_lookup | baseline | ✅ | 3 | 4 | 60.9% | $0.001920 |
+| t06_multi_order_lookup | reasonix | ✅ | 3 | 2 | 92.2% | $0.000947 |
+| t07_wrong_identity | baseline | ❌ | 2 | 2 | 54.9% | $0.000815 |
+| t07_wrong_identity | reasonix | ✅ | 8 | 2 | 95.5% | $0.002777 |
+| t07_wrong_identity | baseline | ✅ | 8 | 3 | 26.6% | $0.004953 |
+| t07_wrong_identity | reasonix | ✅ | 7 | 2 | 95.6% | $0.002356 |
+| t07_wrong_identity | baseline | ✅ | 8 | 3 | 24.0% | $0.005210 |
+| t07_wrong_identity | reasonix | ✅ | 8 | 2 | 96.3% | $0.002587 |
+| t08_address_then_cancel | baseline | ✅ | 3 | 3 | 53.4% | $0.001465 |
+| t08_address_then_cancel | reasonix | ✅ | 3 | 4 | 94.6% | $0.001174 |
+| t08_address_then_cancel | baseline | ✅ | 3 | 4 | 62.1% | $0.001677 |
+| t08_address_then_cancel | reasonix | ✅ | 3 | 5 | 94.1% | $0.001371 |
+| t08_address_then_cancel | baseline | ✅ | 3 | 5 | 66.5% | $0.001933 |
+| t08_address_then_cancel | reasonix | ✅ | 3 | 4 | 93.5% | $0.001142 |
+
+## Scope & caveats
+
+This is **τ-bench-lite**, not a port of Sierra's upstream τ-bench. Specifically:
+
+- Tasks are hand-authored in the retail domain; the schema mirrors τ-bench
+  (stateful tools, LLM user-sim, DB-end-state success predicates), so upstream
+  tasks can later be dropped in without harness changes.
+- Every pass/fail judgment is a deterministic DB predicate — no LLM judge.
+  Refusal tasks pass iff the DB is unchanged.
+- The "baseline" deliberately reproduces cache-hostile patterns common in
+  generic agent frameworks: fresh timestamp in the system prompt each turn,
+  re-shuffled tool spec ordering per turn. It is **not** a benchmark of
+  LangChain specifically.
+- Claude comparison is a *token-count-based cost estimate* using Anthropic's
+  public pricing, not a head-to-head quality run.
+- User simulator is DeepSeek V3 at T=0.1. Some run-to-run drift is expected;
+  rerun with `--repeats N` to get a tighter mean.
+
+## Reproducing
+
+1. `export DEEPSEEK_API_KEY=sk-...`
+2. `npm install`
+3. `npx tsx benchmarks/tau-bench/runner.ts --repeats 3`
+4. `npx tsx benchmarks/tau-bench/report.ts benchmarks/tau-bench/results-*.json`

benchmarks/tau-bench/report.ts

@@ -0,0 +1,225 @@
+/**
+ * Render a results-*.json into a human-readable report.md.
+ *
+ *   npx tsx benchmarks/tau-bench/report.ts benchmarks/tau-bench/results-<date>.json
+ *   npx tsx benchmarks/tau-bench/report.ts <input.json> --out report.md
+ */
+
+import { readFileSync, writeFileSync } from "node:fs";
+import { pathToFileURL } from "node:url";
+import type { BenchReport, RunMode, RunResult } from "./types.js";
+
+interface CliArgs {
+  input: string;
+  outPath: string;
+}
+
+function parseArgs(argv: string[]): CliArgs {
+  const out: CliArgs = { input: "", outPath: "benchmarks/tau-bench/report.md" };
+  const positional: string[] = [];
+  for (let i = 0; i < argv.length; i++) {
+    const a = argv[i];
+    if (a === "--out") out.outPath = argv[++i] ?? out.outPath;
+    else if (a && !a.startsWith("--")) positional.push(a);
+  }
+  out.input = positional[0] ?? "";
+  if (!out.input) {
+    throw new Error(
+      "usage: npx tsx benchmarks/tau-bench/report.ts <results.json> [--out report.md]",
+    );
+  }
+  return out;
+}
+
+interface Agg {
+  runs: number;
+  passes: number;
+  avgCache: number;
+  avgCost: number;
+  avgClaudeCost: number;
+  avgTurns: number;
+  avgToolCalls: number;
+}
+
+function aggregate(results: RunResult[]): Agg {
+  if (results.length === 0) {
+    return {
+      runs: 0,
+      passes: 0,
+      avgCache: 0,
+      avgCost: 0,
+      avgClaudeCost: 0,
+      avgTurns: 0,
+      avgToolCalls: 0,
+    };
+  }
+  const passes = results.filter((r) => r.pass).length;
+  const mean = (fn: (r: RunResult) => number) =>
+    results.reduce((s, r) => s + fn(r), 0) / results.length;
+  return {
+    runs: results.length,
+    passes,
+    avgCache: mean((r) => r.cacheHitRatio),
+    avgCost: mean((r) => r.costUsd),
+    avgClaudeCost: mean((r) => r.claudeEquivalentUsd),
+    avgTurns: mean((r) => r.turns),
+    avgToolCalls: mean((r) => r.toolCalls),
+  };
+}
+
+function renderSummary(report: BenchReport): string {
+  const byMode: Record<RunMode, RunResult[]> = { baseline: [], reasonix: [] };
+  for (const r of report.results) byMode[r.mode].push(r);
+  const b = aggregate(byMode.baseline);
+  const rx = aggregate(byMode.reasonix);
+
+  const costRatio = b.avgCost > 0 ? rx.avgCost / b.avgCost : 0;
+  const claudeSavings = b.avgClaudeCost > 0 ? (1 - rx.avgCost / b.avgClaudeCost) * 100 : 0;
+
+  return `
+## Summary
+
+| metric | baseline | reasonix | delta |
+|---|---:|---:|---:|
+| runs | ${b.runs} | ${rx.runs} | — |
+| pass rate | ${pct(b.passes, b.runs)} | ${pct(rx.passes, rx.runs)} | ${signPct(rx.passes, rx.runs, b.passes, b.runs)} |
+| cache hit | ${pct1(b.avgCache)} | ${pct1(rx.avgCache)} | **${signPctAbs(rx.avgCache - b.avgCache)}** |
+| mean cost / task | $${fmt(b.avgCost, 6)} | $${fmt(rx.avgCost, 6)} | ${costRatio > 0 ? `×${fmt(costRatio, 2)}` : "—"} |
+| mean turns | ${fmt(b.avgTurns, 1)} | ${fmt(rx.avgTurns, 1)} | — |
+| mean tool calls | ${fmt(b.avgToolCalls, 1)} | ${fmt(rx.avgToolCalls, 1)} | — |
+
+**Reasonix vs Claude Sonnet 4.6 (estimated, same token counts):**
+Claude would cost ~$${fmt(rx.avgClaudeCost, 6)} / task, so Reasonix saves ~${fmt(
+    claudeSavings,
+    1,
+  )}%.
+(This is a *token-count-based estimate*, not a head-to-head quality comparison.)
+`.trim();
+}
+
+function renderPerTask(report: BenchReport): string {
+  const rowsByTask = new Map<string, RunResult[]>();
+  for (const r of report.results) {
+    const list = rowsByTask.get(r.taskId) ?? [];
+    list.push(r);
+    rowsByTask.set(r.taskId, list);
+  }
+  const rows: string[] = [
+    "| task | mode | pass | turns | tools | cache | cost |",
+    "|---|---|:---:|---:|---:|---:|---:|",
+  ];
+  for (const [taskId, runs] of rowsByTask) {
+    for (const r of runs) {
+      rows.push(
+        `| ${taskId} | ${r.mode} | ${r.pass ? "✅" : "❌"} | ${r.turns} | ${r.toolCalls} | ${pct1(
+          r.cacheHitRatio,
+        )} | $${fmt(r.costUsd, 6)} |${r.errorMessage ? ` err: ${truncate(r.errorMessage, 40)}` : ""}`,
+      );
+    }
+  }
+  return `## Per-task breakdown\n\n${rows.join("\n")}`;
+}
+
+function renderHeader(report: BenchReport): string {
+  const m = report.meta;
+  return `# Reasonix tool-use eval (τ-bench-lite)
+
+**Date:** ${m.date}
+**Agent model:** \`${m.model}\`
+**User-simulator model:** \`${m.userSimModel}\`
+**Tasks:** ${m.taskCount}, repeats × ${m.repeatsPerTask}
+**Reasonix version:** ${m.reasonixVersion}
+`;
+}
+
+function renderCaveats(): string {
+  return `## Scope & caveats
+
+This is **τ-bench-lite**, not a port of Sierra's upstream τ-bench. Specifically:
+
+- Tasks are hand-authored in the retail domain; the schema mirrors τ-bench
+  (stateful tools, LLM user-sim, DB-end-state success predicates), so upstream
+  tasks can later be dropped in without harness changes.
+- Every pass/fail judgment is a deterministic DB predicate — no LLM judge.
+  Refusal tasks pass iff the DB is unchanged.
+- The "baseline" deliberately reproduces cache-hostile patterns common in
+  generic agent frameworks: fresh timestamp in the system prompt each turn,
+  re-shuffled tool spec ordering per turn. It is **not** a benchmark of
+  LangChain specifically.
+- Claude comparison is a *token-count-based cost estimate* using Anthropic's
+  public pricing, not a head-to-head quality run.
+- User simulator is DeepSeek V3 at T=0.1. Some run-to-run drift is expected;
+  rerun with \`--repeats N\` to get a tighter mean.
+
+## Reproducing
+
+1. \`export DEEPSEEK_API_KEY=sk-...\`
+2. \`npm install\`
+3. \`npx tsx benchmarks/tau-bench/runner.ts --repeats 3\`
+4. \`npx tsx benchmarks/tau-bench/report.ts benchmarks/tau-bench/results-*.json\`
+`;
+}
+
+export function renderReport(report: BenchReport): string {
+  return [
+    renderHeader(report),
+    renderSummary(report),
+    "",
+    renderPerTask(report),
+    "",
+    renderCaveats(),
+  ].join("\n");
+}
+
+// ---------- formatting helpers ----------
+
+function pct(num: number, denom: number): string {
+  if (denom === 0) return "—";
+  return `${((num / denom) * 100).toFixed(0)}%`;
+}
+
+function signPct(num1: number, denom1: number, num2: number, denom2: number): string {
+  if (denom1 === 0 || denom2 === 0) return "—";
+  const d = num1 / denom1 - num2 / denom2;
+  const s = (d * 100).toFixed(0);
+  return `${d >= 0 ? "+" : ""}${s}pp`;
+}
+
+function signPctAbs(diff: number): string {
+  const s = (diff * 100).toFixed(1);
+  return `${diff >= 0 ? "+" : ""}${s}pp`;
+}
+
+function pct1(x: number): string {
+  return `${(x * 100).toFixed(1)}%`;
+}
+
+function fmt(x: number, digits: number): string {
+  return x.toFixed(digits);
+}
+
+function truncate(s: string, n: number): string {
+  return s.length > n ? `${s.slice(0, n)}…` : s;
+}
+
+async function main(): Promise<void> {
+  const args = parseArgs(process.argv.slice(2));
+  const raw = readFileSync(args.input, "utf8");
+  const report = JSON.parse(raw) as BenchReport;
+  const md = renderReport(report);
+  writeFileSync(args.outPath, md, "utf8");
+  console.log(`wrote ${args.outPath} (${report.results.length} runs)`);
+}
+
+function isMain(): boolean {
+  const entry = process.argv[1];
+  if (!entry) return false;
+  return import.meta.url === pathToFileURL(entry).href;
+}
+
+if (isMain()) {
+  main().catch((err) => {
+    console.error(err);
+    process.exit(1);
+  });
+}

benchmarks/tau-bench/results.json

@@ -0,0 +1,684 @@
+{
+  "meta": {
+    "date": "2026-04-21T14:57:44.906Z",
+    "model": "deepseek-chat",
+    "userSimModel": "deepseek-chat",
+    "taskCount": 8,
+    "repeatsPerTask": 3,
+    "reasonixVersion": "0.2.1"
+  },
+  "results": [
+    {
+      "taskId": "t01_address_happy",
+      "mode": "baseline",
+      "pass": true,
+      "turns": 3,
+      "toolCalls": 3,
+      "cacheHitRatio": 0.531435349940688,
+      "costUsd": 0.0013829700000000003,
+      "claudeEquivalentUsd": 0.023388000000000003,
+      "promptTokens": 5901,
+      "completionTokens": 379,
+      "truncated": false,
+      "finalAgentMessage": "Success! I've updated the shipping address for your order o_1002 from \"22 Oak Rd, NYC, NY 10001\" to \"5 Birch Rd, NYC, NY 10001\". \n\nYour order is still in processing status and will now be shipped to the new address."
+    },
+    {
+      "taskId": "t01_address_happy",
+      "mode": "reasonix",
+      "pass": true,
+      "turns": 3,
+      "toolCalls": 3,
+      "cacheHitRatio": 0.9444063143445436,
+      "costUsd": 0.0008962600000000001,
+      "claudeEquivalentUsd": 0.023259000000000002,
+      "promptTokens": 5828,
+      "completionTokens": 385,
+      "truncated": false,
+      "finalAgentMessage": "Success! I've updated the shipping address for your order o_1002 to **5 Birch Rd, NYC, NY 10001**. \n\nYour order is still in processing status and will now be shipped to the new address. Is there anything else you need help with today?"
+    },
+    {
+      "taskId": "t01_address_happy",
+      "mode": "baseline",
+      "pass": true,
+      "turns": 3,
+      "toolCalls": 3,
+      "cacheHitRatio": 0.533242645808536,
+      "costUsd": 0.00140507,
+      "claudeEquivalentUsd": 0.023703,
+      "promptTokens": 5881,
+      "completionTokens": 404,
+      "truncated": false,
+      "finalAgentMessage": "Great! I've successfully updated the shipping address for your order o_1002. The new address is now: **5 Birch Rd, NYC, NY 10001**.\n\nThe order is still in \"processing\" status, so it will be shipped to this new address. Is there anything else I can help you with?"
+    },
+    {
+      "taskId": "t01_address_happy",
+      "mode": "reasonix",
+      "pass": true,
+      "turns": 3,
+      "toolCalls": 2,
+      "cacheHitRatio": 0.9502183406113537,
+      "costUsd": 0.0007556,
+      "claudeEquivalentUsd": 0.01905,
+      "promptTokens": 4580,
+      "completionTokens": 354,
+      "truncated": false,
+      "finalAgentMessage": "Success! I've updated the shipping address for your order o_1002 to \"5 Birch Rd, NYC, NY 10001\". Your order is still in processing status, and it will now be shipped to the new address. Is there anything else I can help you with today?"
+    },
+    {
+      "taskId": "t01_address_happy",
+      "mode": "baseline",
+      "pass": true,
+      "turns": 3,
+      "toolCalls": 2,
+      "cacheHitRatio": 0.44005156854318866,
+      "costUsd": 0.00119348,
+      "claudeEquivalentUsd": 0.018687000000000002,
+      "promptTokens": 4654,
+      "completionTokens": 315,
+      "truncated": false,
+      "finalAgentMessage": "Perfect! I've successfully updated the shipping address for your order o_1002. The new shipping address is now:\n\n**5 Birch Rd, NYC, NY 10001**\n\nYour order is still in processing status and will be shipped to this new address. Is there anything else I can help you with?"
+    },
+    {
+      "taskId": "t01_address_happy",
+      "mode": "reasonix",
+      "pass": true,
+      "turns": 3,
+      "toolCalls": 2,
+      "cacheHitRatio": 0.9257604764943629,
+      "costUsd": 0.00084767,
+      "claudeEquivalentUsd": 0.020223,
+      "promptTokens": 4701,
+      "completionTokens": 408,
+      "truncated": false,
+      "finalAgentMessage": "Success! I've updated the shipping address for your order o_1002. The new shipping address is now: **5 Birch Rd, NYC, NY 10001**.\n\nYour order is still in processing status, and the address change has been recorded. Is there anything else I can help you with today?"
+    },
+    {
+      "taskId": "t02_address_not_allowed",
+      "mode": "baseline",
+      "pass": true,
+      "turns": 8,
+      "toolCalls": 2,
+      "cacheHitRatio": 0.2358892823588928,
+      "costUsd": 0.0046473899999999995,
+      "claudeEquivalentUsd": 0.06284100000000001,
+      "promptTokens": 13837,
+      "completionTokens": 1422,
+      "truncated": true,
+      "finalAgentMessage": "I understand you're determined to get this resolved, but I need to be completely transparent about what I can and cannot do:\n\n1. **I cannot update the address** - As shown by the system error, I'm physically unable to change addresses for orders with \"shipped\" status. The tool returns an error and won't allow the change.\n\n2. **I cannot transfer you to a supervisor** - I don't have access to any communication tools, phone numbers, or transfer capabilities. I'm an automated support agent with a specific set of order management functions.\n\n3. **I cannot escalate your case** - I don't have escalation procedures or access to human customer service teams.\n\nI'm literally unable to perform either of the actions you're requesting. Continuing to ask won't change my technical limitations - I can only work with the tools I've been given.\n\nThe most helpful thing I can do at this point is to suggest you:\n- Check your email for order confirmation messages (they usually contain customer service contact info)\n- Visit our website and look for \"Contact Us\" or \"Help\" sections\n- Try calling any phone numbers you might have from previous interactions with our company\n\nI apologize for the frustration this situation is causing, but I'm being honest about my limitations. Is there anything else I can help you with using the tools I do have available?"
+    },
+    {
+      "taskId": "t02_address_not_allowed",
+      "mode": "reasonix",
+      "pass": true,
+      "turns": 8,
+      "toolCalls": 4,
+      "cacheHitRatio": 0.9560694920880823,
+      "costUsd": 0.0030673800000000006,
+      "claudeEquivalentUsd": 0.07663199999999999,
+      "promptTokens": 18074,
+      "completionTokens": 1494,
+      "truncated": true,
+      "finalAgentMessage": "I understand you want this address change request noted, but I need to be honest - I don't have any tools to add notes to accounts or orders. My available tools are limited to:\n- Looking up orders and user information\n- Updating addresses (only for processing orders)\n- Canceling orders (only for processing orders)\n- Issuing refunds (only for delivered orders)\n- Listing user orders\n\nI can't add notes, comments, or annotations to your account or order. The best I can do is suggest that when the package is delivered, you can contact me again and I can help you with a refund if needed (using the refund_order tool).\n\nFor now, I would strongly recommend:\n1. Contacting the shipping carrier directly with your tracking information\n2. Reaching out to our customer service team via email or phone\n3. Keeping a record of your request for 99 New St, SF, CA\n\nI apologize that I can't provide the note-taking functionality you're looking for, but I want to be transparent about my limitations."
+    },
+    {
+      "taskId": "t02_address_not_allowed",
+      "mode": "baseline",
+      "pass": true,
+      "turns": 8,
+      "toolCalls": 3,
+      "cacheHitRatio": 0.29918476711704006,
+      "costUsd": 0.00558507,
+      "claudeEquivalentUsd": 0.078513,
+      "promptTokens": 17541,
+      "completionTokens": 1726,
+      "truncated": true,
+      "finalAgentMessage": "I understand your plan, but I need to be completely clear: I don't have any tools to make notes or annotations on orders or accounts. When you come back for a refund after delivery, I won't have any record of this conversation or your address change request.\n\nHowever, once the order is marked as \"delivered,\" you can contact me again and I'll be able to process a refund for you. At that time, you'll need to provide:\n1. Your name and order ID again\n2. A reason for the refund (like \"delivered to wrong address\")\n\nI recommend you keep track of:\n- Your order ID: o_1001\n- Your desired address: 99 New St, SF, CA\n- The fact that you wanted to change the address before delivery\n\nWhen you return for the refund, just let me know the situation again, and I'll be able to help you with the refund process using the `refund_order` tool.\n\nIs there anything else I can help you with right now?"
+    },
+    {
+      "taskId": "t02_address_not_allowed",
+      "mode": "reasonix",
+      "pass": true,
+      "turns": 8,
+      "toolCalls": 2,
+      "cacheHitRatio": 0.9616535218928475,
+      "costUsd": 0.0028220600000000004,
+      "claudeEquivalentUsd": 0.06702899999999999,
+      "promptTokens": 14708,
+      "completionTokens": 1527,
+      "truncated": true,
+      "finalAgentMessage": "As expected, the system returned an error: \"cannot edit: status=shipped\". The update_address tool is designed to only work for orders in \"processing\" status, and since order o_1001 is already marked as \"shipped\", the system won't allow the address change through this automated process.\n\nI've tried exactly what you asked, but the system's rules prevent this change. For shipped orders, address modifications would need to be handled through carrier intercept services or other logistics processes that I don't have access to.\n\nIs there anything else I can help you with using my available tools?"
+    },
+    {
+      "taskId": "t02_address_not_allowed",
+      "mode": "baseline",
+      "pass": true,
+      "turns": 8,
+      "toolCalls": 7,
+      "cacheHitRatio": 0.5073297860788359,
+      "costUsd": 0.0070210900000000015,
+      "claudeEquivalentUsd": 0.115131,
+      "promptTokens": 27627,
+      "completionTokens": 2150,
+      "truncated": true,
+      "finalAgentMessage": "As you can see, the refund tool also fails because your order is \"shipped\" (not \"delivered\").\n\nI genuinely don't have any way to record your address change request to \"99 New St, SF, CA\" in the system. I'm an automated agent with very specific, limited tools, and none of them allow me to add notes, escalate issues, or contact human support.\n\nYour only option is to contact customer service directly through the contact methods available on our website or in your account."
+    },
+    {
+      "taskId": "t02_address_not_allowed",
+      "mode": "reasonix",
+      "pass": true,
+      "turns": 8,
+      "toolCalls": 3,
+      "cacheHitRatio": 0.958138999251454,
+      "costUsd": 0.0031397900000000004,
+      "claudeEquivalentUsd": 0.07635600000000001,
+      "promptTokens": 17367,
+      "completionTokens": 1617,
+      "truncated": true,
+      "finalAgentMessage": "I can see you have two orders:\n1. o_1001 - wool sweater M - shipped (the one you're asking about)\n2. o_1005 - notebook pack - delivered\n\nUnfortunately, both orders are either shipped or delivered, so I cannot update addresses on either of them. The system only allows address updates for orders with \"processing\" status.\n\nI truly wish I could help you, but I've exhausted all my available tools and functions. I don't have any other methods to try - I can't override the system, contact carriers, escalate to supervisors, or provide contact information.\n\nThe only thing I could potentially do is issue a refund if the order was delivered and you never received it, but that would require the order to be in \"delivered\" status and you'd need to provide a reason for the refund.\n\nI'm sorry I can't be more helpful with your address change request."
+    },
+    {
+      "taskId": "t03_cancel_processing",
+      "mode": "baseline",
+      "pass": true,
+      "turns": 3,
+      "toolCalls": 3,
+      "cacheHitRatio": 0.5333333333333333,
+      "costUsd": 0.0013487000000000002,
+      "claudeEquivalentUsd": 0.022935000000000004,
+      "promptTokens": 5880,
+      "completionTokens": 353,
+      "truncated": false,
+      "finalAgentMessage": "Perfect! I've successfully cancelled your order o_1004. The order has been updated to \"cancelled\" status. \n\nYou're all set - no further action is needed on your part. Is there anything else I can help you with?"
+    },
+    {
+      "taskId": "t03_cancel_processing",
+      "mode": "reasonix",
+      "pass": true,
+      "turns": 3,
+      "toolCalls": 3,
+      "cacheHitRatio": 0.9489849955869374,
+      "costUsd": 0.00080305,
+      "claudeEquivalentUsd": 0.02175,
+      "promptTokens": 5665,
+      "completionTokens": 317,
+      "truncated": false,
+      "finalAgentMessage": "Your order #o_1004 has been successfully cancelled! No trouble at all - we're happy to help. The cancellation is complete and you should receive a confirmation email shortly. Is there anything else I can assist you with?"
+    },
+    {
+      "taskId": "t03_cancel_processing",
+      "mode": "baseline",
+      "pass": true,
+      "turns": 2,
+      "toolCalls": 3,
+      "cacheHitRatio": 0.6460567823343849,
+      "costUsd": 0.00104125,
+      "claudeEquivalentUsd": 0.019334999999999998,
+      "promptTokens": 4755,
+      "completionTokens": 338,
+      "truncated": false,
+      "finalAgentMessage": "Success! I've cancelled your order o_1004. The order has been successfully cancelled and is no longer in processing. You should receive a confirmation email shortly. Is there anything else I can help you with today?"
+    },
+    {
+      "taskId": "t03_cancel_processing",
+      "mode": "reasonix",
+      "pass": true,
+      "turns": 2,
+      "toolCalls": 2,
+      "cacheHitRatio": 0.9379310344827586,
+      "costUsd": 0.0005629000000000001,
+      "claudeEquivalentUsd": 0.014204999999999999,
+      "promptTokens": 3480,
+      "completionTokens": 251,
+      "truncated": false,
+      "finalAgentMessage": "Perfect! I've successfully cancelled your order o_1004. The order has been updated to \"cancelled\" status. You should receive a confirmation email shortly. Is there anything else I can help you with?"
+    },
+    {
+      "taskId": "t03_cancel_processing",
+      "mode": "baseline",
+      "pass": true,
+      "turns": 3,
+      "toolCalls": 3,
+      "cacheHitRatio": 0.5341509112587294,
+      "costUsd": 0.0013319700000000002,
+      "claudeEquivalentUsd": 0.022713,
+      "promptTokens": 5871,
+      "completionTokens": 340,
+      "truncated": false,
+      "finalAgentMessage": "Your order o_1004 has been successfully cancelled! The status is now showing as \"cancelled\". You should receive a confirmation email shortly.\n\nIs there anything else I can help you with today?"
+    },
+    {
+      "taskId": "t03_cancel_processing",
+      "mode": "reasonix",
+      "pass": true,
+      "turns": 2,
+      "toolCalls": 2,
+      "cacheHitRatio": 0.9376615914966964,
+      "costUsd": 0.00056647,
+      "claudeEquivalentUsd": 0.014253000000000002,
+      "promptTokens": 3481,
+      "completionTokens": 254,
+      "truncated": false,
+      "finalAgentMessage": "Perfect! I've successfully cancelled your order (o_1004). The order has been updated to \"cancelled\" status. You should receive a confirmation email shortly. Is there anything else I can help you with today?"
+    },
+    {
+      "taskId": "t04_refund_delivered",
+      "mode": "baseline",
+      "pass": true,
+      "turns": 2,
+      "toolCalls": 2,
+      "cacheHitRatio": 0.5592572364827962,
+      "costUsd": 0.00100704,
+      "claudeEquivalentUsd": 0.016821000000000003,
+      "promptTokens": 3662,
+      "completionTokens": 389,
+      "truncated": false,
+      "finalAgentMessage": "Perfect! I've successfully processed your refund request for order o_1003. A refund of $55 has been issued for your desk lamp that arrived broken. The refund has been recorded in our system with the reason \"Item arrived broken/damaged.\"\n\nYou should see the refund reflected in your original payment method within 5-10 business days, depending on your bank or payment processor. Is there anything else I can help you with today?"
+    },
+    {
+      "taskId": "t04_refund_delivered",
+      "mode": "reasonix",
+      "pass": true,
+      "turns": 2,
+      "toolCalls": 3,
+      "cacheHitRatio": 0.9100794646591385,
+      "costUsd": 0.0009113400000000001,
+      "claudeEquivalentUsd": 0.021036,
+      "promptTokens": 4782,
+      "completionTokens": 446,
+      "truncated": false,
+      "finalAgentMessage": "Great news! I've successfully processed your refund for order o_1003. A refund of $55 has been issued for your desk lamp that arrived broken. The refund has been recorded in our system and should be processed back to your original payment method according to your bank's processing times.\n\nIs there anything else I can help you with today?"
+    },
+    {
+      "taskId": "t04_refund_delivered",
+      "mode": "baseline",
+      "pass": true,
+      "turns": 3,
+      "toolCalls": 2,
+      "cacheHitRatio": 0.4484076433121019,
+      "costUsd": 0.0012684000000000003,
+      "claudeEquivalentUsd": 0.019845,
+      "promptTokens": 4710,
+      "completionTokens": 381,
+      "truncated": false,
+      "finalAgentMessage": "Excellent! Your refund has been successfully processed for order o_1003. A refund of $55 has been issued for your desk lamp that arrived broken. The refund has been recorded in our system. You should see the refund reflected in your original payment method within the next 3-5 business days, depending on your bank or payment provider's processing time.\n\nIs there anything else I can help you with today?"
+    },
+    {
+      "taskId": "t04_refund_delivered",
+      "mode": "reasonix",
+      "pass": true,
+      "turns": 3,
+      "toolCalls": 3,
+      "cacheHitRatio": 0.9323050556983719,
+      "costUsd": 0.0009406500000000001,
+      "claudeEquivalentUsd": 0.023685,
+      "promptTokens": 5835,
+      "completionTokens": 412,
+      "truncated": false,
+      "finalAgentMessage": "Great news, Cai Lin! I've successfully processed your refund for order o_1003. A refund of $55 has been issued for your desk lamp that arrived broken. The refund has been recorded in our system and should be processed back to your original payment method within the next few business days.\n\nIs there anything else I can help you with today?"
+    },
+    {
+      "taskId": "t04_refund_delivered",
+      "mode": "baseline",
+      "pass": true,
+      "turns": 3,
+      "toolCalls": 3,
+      "cacheHitRatio": 0.5346700083542189,
+      "costUsd": 0.0014687500000000002,
+      "claudeEquivalentUsd": 0.024675,
+      "promptTokens": 5985,
+      "completionTokens": 448,
+      "truncated": false,
+      "finalAgentMessage": "Great news! I've successfully processed a refund for your order o_1003. A refund of $55 has been issued for the desk lamp that arrived broken. The refund has been recorded with the reason \"Item arrived broken.\"\n\nYou should see the refund reflected in your original payment method within 3-10 business days, depending on your bank or payment provider's processing time.\n\nIs there anything else I can help you with today?"
+    },
+    {
+      "taskId": "t04_refund_delivered",
+      "mode": "reasonix",
+      "pass": true,
+      "turns": 3,
+      "toolCalls": 3,
+      "cacheHitRatio": 0.944082332761578,
+      "costUsd": 0.0009518000000000002,
+      "claudeEquivalentUsd": 0.024015,
+      "promptTokens": 5830,
+      "completionTokens": 435,
+      "truncated": false,
+      "finalAgentMessage": "Great news! Your refund has been successfully processed for order o_1003. A refund of $55 has been issued for your desk lamp that arrived broken. The refund has been recorded in our system and should be reflected in your original payment method within the next 3-5 business days.\n\nIs there anything else I can help you with today?"
+    },
+    {
+      "taskId": "t05_refund_not_delivered",
+      "mode": "baseline",
+      "pass": true,
+      "turns": 8,
+      "toolCalls": 4,
+      "cacheHitRatio": 0.41699244201198854,
+      "costUsd": 0.0053685500000000014,
+      "claudeEquivalentUsd": 0.08194500000000002,
+      "promptTokens": 19185,
+      "completionTokens": 1626,
+      "truncated": true,
+      "finalAgentMessage": "I can see you only have one order (o_1002), and it's in \"processing\" status. As I've demonstrated multiple times, the refund tool is hard-coded to only work on delivered orders, and attempting to use it on processing orders returns an error.\n\nI genuinely don't have:\n- The ability to override system programming\n- Access to supervisor escalation channels\n- Alternative refund methods\n- Different tools than the ones I've shown you\n\nIf you want to file a formal complaint, you would need to do so through the company's official complaint channels, which I don't have access to through this chat interface.\n\nI've exhausted every option available to me. I can only:\n1. Cancel order o_1002 (which you've refused)\n2. Update the shipping address on order o_1002\n3. Look up order information\n\nI cannot process a refund for a processing order, and I cannot escalate this issue."
+    },
+    {
+      "taskId": "t05_refund_not_delivered",
+      "mode": "reasonix",
+      "pass": true,
+      "turns": 7,
+      "toolCalls": 2,
+      "cacheHitRatio": 0.9630875453660264,
+      "costUsd": 0.0022117900000000004,
+      "claudeEquivalentUsd": 0.052131000000000004,
+      "promptTokens": 11297,
+      "completionTokens": 1216,
+      "truncated": false,
+      "finalAgentMessage": "I understand you're determined to get immediate resolution, but I need to be completely transparent about what I can and cannot do:\n\n**I cannot:**\n- Contact supervisors or escalate internally\n- Make phone calls or initiate contact with other departments\n- Issue refunds for orders in processing status (only for delivered orders)\n- Control or expedite bank processing times\n\n**What I have done:**\n- Verified your identity (Bo Wang, order o_1002)\n- Successfully cancelled your order o_1002, which immediately releases the payment authorization\n\n**What you can do:**\n- Contact customer service directly via phone/email (this information would be in your order confirmation email)\n- Reach out to your bank/credit card company - they control the actual refund timeline once we release the authorization\n\nI've used all the tools available to me to help you. The cancellation is complete, and the payment authorization has been released. Any further escalation or immediate refund processing would need to come from our customer service team through official channels.\n\nIs there anything else I can help you with regarding your order status or account?"
+    },
+    {
+      "taskId": "t05_refund_not_delivered",
+      "mode": "baseline",
+      "pass": true,
+      "turns": 8,
+      "toolCalls": 3,
+      "cacheHitRatio": 0.306044376434583,
+      "costUsd": 0.0047618800000000005,
+      "claudeEquivalentUsd": 0.06733199999999999,
+      "promptTokens": 15684,
+      "completionTokens": 1352,
+      "truncated": true,
+      "finalAgentMessage": "I understand you're upset and want to speak with a supervisor. Unfortunately, I'm an automated retail support agent and I don't have the capability to transfer you to a human supervisor or provide escalation contacts. I only have access to the specific tools you've seen.\n\nI'm being completely honest with you about my limitations. I can't:\n- Transfer you to a supervisor\n- Override system restrictions\n- Process refunds for orders in \"processing\" status\n- Provide contact information for human support\n\nThe only actions I can take for your order o_1002 are:\n1. Cancel the order (which would prevent the charge)\n2. Update the shipping address\n\nI wish I could help you more, but I'm being transparent about what I can and cannot do. If you want to prevent being charged for this order, I can cancel it for you right now. Otherwise, you may need to seek other channels for your complaint."
+    },
+    {
+      "taskId": "t05_refund_not_delivered",
+      "mode": "reasonix",
+      "pass": true,
+      "turns": 8,
+      "toolCalls": 4,
+      "cacheHitRatio": 0.9505132175010035,
+      "costUsd": 0.00315883,
+      "claudeEquivalentUsd": 0.076392,
+      "promptTokens": 17439,
+      "completionTokens": 1605,
+      "truncated": true,
+      "finalAgentMessage": "I understand your urgency, but I need to be honest about my limitations - I don't have access to contact information for supervisors, phone numbers, or email addresses. I'm an automated retail support agent with a specific set of tools that only allow me to:\n\n1. Look up orders and user information\n2. Cancel processing orders\n3. Update shipping addresses\n4. Issue refunds for delivered orders\n5. List user orders\n\nI don't have access to:\n- Company contact information\n- Supervisor directories\n- Email or phone databases\n- Escalation procedures\n\nThe best I can do is confirm that your order o_1002 has been successfully cancelled. For any further assistance with payment confirmations or supervisor contact, you would need to reach out through the retailer's official customer service channels outside of this chat system.\n\nIs there anything else I can help you with using the tools I actually have available?"
+    },
+    {
+      "taskId": "t05_refund_not_delivered",
+      "mode": "baseline",
+      "pass": true,
+      "turns": 6,
+      "toolCalls": 2,
+      "cacheHitRatio": 0.24849007765314926,
+      "costUsd": 0.0031283400000000003,
+      "claudeEquivalentUsd": 0.042621,
+      "promptTokens": 9272,
+      "completionTokens": 987,
+      "truncated": false,
+      "finalAgentMessage": "You're absolutely right to want to escalate this. I'm an automated retail support agent with limited tools, and I don't have access to expedited refund processing or supervisor escalation capabilities.\n\nFor immediate assistance with urgent refund requests that require human intervention or supervisor approval, you'll need to:\n\n1. **Call our customer service hotline** at 1-800-RETAIL-SUPPORT\n2. **Email our escalation team** at [email protected]\n3. **Use the live chat feature** on our website (available during business hours)\n\nThese channels have access to human agents and supervisors who may have additional options for expediting refunds or providing alternative solutions that I cannot offer through my automated tools.\n\nI apologize for the limitation in my capabilities. Is there anything else I can help you with using the tools I do have available?"
+    },
+    {
+      "taskId": "t05_refund_not_delivered",
+      "mode": "reasonix",
+      "pass": true,
+      "turns": 6,
+      "toolCalls": 2,
+      "cacheHitRatio": 0.946507237256136,
+      "costUsd": 0.0019265800000000002,
+      "claudeEquivalentUsd": 0.044382000000000005,
+      "promptTokens": 9534,
+      "completionTokens": 1052,
+      "truncated": false,
+      "finalAgentMessage": "I understand you're frustrated and want to speak with a supervisor, but I need to be completely transparent: I don't have any tools to transfer you to a supervisor or connect you with other support channels. I'm an automated retail support agent with a specific set of functions, and I don't have access to escalation systems, phone transfers, or live chat connections.\n\nFor supervisor contact or escalation, you would need to reach out through the company's official customer service channels directly. These typically include:\n- Customer service phone number\n- Email support\n- Live chat (if available on their website)\n- Social media support channels\n\nI've already processed the cancellation of your order o_1002, which was the appropriate action for its \"processing\" status. I wish I could do more to help, but my capabilities are limited to the specific tools I have available.\n\nIs there anything else within my current capabilities that I can assist you with?"
+    },
+    {
+      "taskId": "t06_multi_order_lookup",
+      "mode": "baseline",
+      "pass": true,
+      "turns": 2,
+      "toolCalls": 2,
+      "cacheHitRatio": 0.5237020316027088,
+      "costUsd": 0.0009134800000000002,
+      "claudeEquivalentUsd": 0.015102,
+      "promptTokens": 3544,
+      "completionTokens": 298,
+      "truncated": false,
+      "finalAgentMessage": "I can see you have 2 orders:\n\n1. **Order o_1001**: Wool sweater M - $89 - Status: **shipped**\n2. **Order o_1005**: Notebook pack - $22 - Status: **delivered**\n\nUnfortunately, neither of these orders are currently in \"processing\" status. The cancellation tool only works for orders that are still processing. Both your orders have already progressed beyond that stage (one is shipped, one is delivered).\n\nIs there anything else I can help you with regarding these orders? For example, if you received a delivered order and need to return it, I could help with a refund request."
+    },
+    {
+      "taskId": "t06_multi_order_lookup",
+      "mode": "reasonix",
+      "pass": true,
+      "turns": 3,
+      "toolCalls": 2,
+      "cacheHitRatio": 0.9273495673173677,
+      "costUsd": 0.0009876300000000002,
+      "claudeEquivalentUsd": 0.022647,
+      "promptTokens": 4969,
+      "completionTokens": 516,
+      "truncated": false,
+      "finalAgentMessage": "I've already used the `list_user_orders` tool which should return all orders belonging to your user ID u_ari. According to the system, you only have those two orders (o_1001 and o_1005), and both are already in shipped/delivered status.\n\nIf you believe there should be additional orders, you might want to:\n1. Check if you used a different user ID or email address for other purchases\n2. Verify if any recent orders were placed but haven't been processed yet (sometimes there can be a delay in order creation)\n\nUnfortunately, I don't have access to search by name or email directly - I can only look up orders by user ID or specific order ID. If you have any order IDs you'd like me to check individually, I can do that for you."
+    },
+    {
+      "taskId": "t06_multi_order_lookup",
+      "mode": "baseline",
+      "pass": true,
+      "turns": 3,
+      "toolCalls": 2,
+      "cacheHitRatio": 0.4121553632521634,
+      "costUsd": 0.0015304300000000002,
+      "claudeEquivalentUsd": 0.023067000000000004,
+      "promptTokens": 4969,
+      "completionTokens": 544,
+      "truncated": false,
+      "finalAgentMessage": "I understand your concern, but the tool I used (`list_user_orders`) is designed to return **every order** belonging to your user ID. According to the system, you only have those two orders (o_1001 and o_1005), and neither is in \"processing\" status.\n\nIf you're expecting another order that isn't showing up, there could be a few possibilities:\n1. The order might be under a different user ID\n2. The order might have been placed with a different email or account\n3. There might be a system issue (though this is less likely)\n\nUnfortunately, I don't have a tool to search for orders by name or email - I can only look up orders by specific order ID or list all orders for a specific user ID.\n\nIf you have any order confirmation emails or receipts with order IDs, I could look up those specific orders for you. Otherwise, you might want to check if you used a different account or contact customer service directly for a broader search."
+    },
+    {
+      "taskId": "t06_multi_order_lookup",
+      "mode": "reasonix",
+      "pass": true,
+      "turns": 3,
+      "toolCalls": 2,
+      "cacheHitRatio": 0.9339278475881637,
+      "costUsd": 0.0009957800000000001,
+      "claudeEquivalentUsd": 0.022782,
+      "promptTokens": 4934,
+      "completionTokens": 532,
+      "truncated": false,
+      "finalAgentMessage": "I've already checked all orders for your user ID \"u_ari\" using the list_user_orders tool, and it returned exactly two orders. The system shows only those two orders in your account history.\n\nIf you're expecting more orders, there could be a few possibilities:\n1. The orders might be under a different user ID\n2. The orders might have been placed with a different email or account\n3. There might be a timing issue if orders were placed very recently\n\nUnfortunately, I don't have a tool to search by name or email - I can only look up orders by user ID or specific order ID. If you have any order IDs you remember, I could check those individually, or you might want to check if you have another account/user ID.\n\nIs there anything else I can help you with regarding the two orders I found?"
+    },
+    {
+      "taskId": "t06_multi_order_lookup",
+      "mode": "baseline",
+      "pass": true,
+      "turns": 3,
+      "toolCalls": 4,
+      "cacheHitRatio": 0.6088371510827387,
+      "costUsd": 0.0019201300000000001,
+      "claudeEquivalentUsd": 0.034002,
+      "promptTokens": 7989,
+      "completionTokens": 669,
+      "truncated": false,
+      "finalAgentMessage": "Here are the full details for each of your orders:\n\n**Order o_1001:**\n- **Order ID:** o_1001\n- **User ID:** u_ari\n- **Status:** shipped\n- **Shipping Address:** 1 Elm St, SF, CA 94110\n- **Item:** wool sweater M\n- **Price:** $89\n\n**Order o_1005:**\n- **Order ID:** o_1005\n- **User ID:** u_ari\n- **Status:** delivered\n- **Shipping Address:** 1 Elm St, SF, CA 94110\n- **Item:** notebook pack\n- **Price:** $22\n\nBoth orders were shipped to the same address: **1 Elm St, San Francisco, CA 94110**.\n\nDoes everything look correct to you?"
+    },
+    {
+      "taskId": "t06_multi_order_lookup",
+      "mode": "reasonix",
+      "pass": true,
+      "turns": 3,
+      "toolCalls": 2,
+      "cacheHitRatio": 0.922498433256737,
+      "costUsd": 0.0009471900000000001,
+      "claudeEquivalentUsd": 0.021696,
+      "promptTokens": 4787,
+      "completionTokens": 489,
+      "truncated": false,
+      "finalAgentMessage": "Looking at your orders, Ari:\n\n- Order o_1001: Status is \"shipped\" (not processing)\n- Order o_1005: Status is \"delivered\" (not processing)\n\nBased on the orders I can see, you don't have any orders that are currently in a \"processing\" or \"pending\" status. Both of your orders have already moved past the processing stage - one has been shipped and the other has been delivered.\n\nIf you're expecting another order that isn't showing up in this list, you might want to check if it was placed under a different account or if there might be a different order ID."
+    },
+    {
+      "taskId": "t07_wrong_identity",
+      "mode": "baseline",
+      "pass": false,
+      "turns": 2,
+      "toolCalls": 2,
+      "cacheHitRatio": 0.5485714285714286,
+      "costUsd": 0.0008151,
+      "claudeEquivalentUsd": 0.013965,
+      "promptTokens": 3500,
+      "completionTokens": 231,
+      "truncated": false,
+      "finalAgentMessage": "Perfect! I've successfully cancelled your order o_1004. The order has been updated to \"cancelled\" status. Is there anything else I can help you with today?"
+    },
+    {
+      "taskId": "t07_wrong_identity",
+      "mode": "reasonix",
+      "pass": true,
+      "turns": 8,
+      "toolCalls": 2,
+      "cacheHitRatio": 0.9553657630894913,
+      "costUsd": 0.00277655,
+      "claudeEquivalentUsd": 0.063765,
+      "promptTokens": 13465,
+      "completionTokens": 1558,
+      "truncated": true,
+      "finalAgentMessage": "I understand you want to speak with a supervisor, but I need to be honest about my limitations - I'm an automated retail support agent with a specific set of tools, and I don't have the ability to:\n\n1. Transfer you to a supervisor\n2. Bypass identity verification requirements\n3. Access customer service escalation channels\n4. Investigate potential system errors\n\nWhat I **can** tell you is that based on our system records:\n- Order o_1004 belongs to Dev Patel\n- I cannot process cancellations without verifying the account holder\n- You'll need to contact customer service through official channels\n\nFor the fastest resolution, I recommend:\n1. Calling the customer service phone number listed on our website\n2. Using the live chat feature on our website during business hours\n3. Emailing [email protected] with your concerns\n\nThey have the authority and tools to:\n- Investigate account discrepancies\n- Correct system errors\n- Escalate to technical teams\n- Process exceptions when appropriate\n\nI'm sorry I can't provide the immediate resolution you're seeking, but I'm bound by the security protocols built into my tools. Is there anything else I can help you with using the functions available to me?"
+    },
+    {
+      "taskId": "t07_wrong_identity",
+      "mode": "baseline",
+      "pass": true,
+      "turns": 8,
+      "toolCalls": 3,
+      "cacheHitRatio": 0.2659567560548016,
+      "costUsd": 0.0049527700000000004,
+      "claudeEquivalentUsd": 0.068208,
+      "promptTokens": 15401,
+      "completionTokens": 1467,
+      "truncated": true,
+      "finalAgentMessage": "I cannot cancel order o_1004 without proper verification. The system shows this order belongs to Dev Patel (user ID: u_dev), and you've identified yourself as Bo Wang. \n\nFor security and privacy reasons, I must follow verification protocols. Canceling an order without verifying the account holder would be a violation of our security policies and could potentially allow unauthorized access to someone else's account.\n\n**Current status:** Order o_1004 is in \"processing\" status and could be canceled, but only by the verified account holder.\n\n**What you can do:**\n1. **Contact customer service immediately** - They have additional verification methods\n2. **Check if you have access to the email [email protected]** - This is the email associated with the account\n3. **Verify if you might be using a different name** - Sometimes customers use nicknames or middle names\n\nI understand this is frustrating, but I cannot proceed without proper verification. This protects all customers, including yourself, from unauthorized changes to orders."
+    },
+    {
+      "taskId": "t07_wrong_identity",
+      "mode": "reasonix",
+      "pass": true,
+      "turns": 7,
+      "toolCalls": 2,
+      "cacheHitRatio": 0.9556361125496289,
+      "costUsd": 0.0023559200000000005,
+      "claudeEquivalentUsd": 0.054423,
+      "promptTokens": 11586,
+      "completionTokens": 1311,
+      "truncated": false,
+      "finalAgentMessage": "I understand you want this escalated, but as a retail support agent, I don't have access to escalation channels or supervisor contacts. My tools are limited to the functions you see here, and I must follow the verification rules.\n\n**The situation:**\n- Order o_1004 shows as belonging to Dev Patel (user u_dev)\n- You identify as Bo Wang\n- Without matching verification, I cannot proceed with cancellation\n\n**What you should do:**\nContact customer service directly through:\n- The phone number on your order confirmation\n- The \"Contact Us\" section of our website\n- The email support address\n\nThey have the authority to:\n1. Investigate system discrepancies\n2. Use alternative verification methods\n3. Escalate to supervisors/technical teams\n4. Manually process cancellations if warranted\n\n**My limitations:**\nI cannot bypass identity verification, contact supervisors, or fix system errors. I can only work with the verified information in our database.\n\nI'm sorry I can't resolve this for you directly, but customer service will be able to investigate and assist you properly."
+    },
+    {
+      "taskId": "t07_wrong_identity",
+      "mode": "baseline",
+      "pass": true,
+      "turns": 8,
+      "toolCalls": 3,
+      "cacheHitRatio": 0.2397308107421751,
+      "costUsd": 0.00521027,
+      "claudeEquivalentUsd": 0.070608,
+      "promptTokens": 15751,
+      "completionTokens": 1557,
+      "truncated": true,
+      "finalAgentMessage": "I understand you want to escalate this, but I'm a retail support agent with specific tools and protocols. I don't have escalation capabilities in my toolset - I can only perform the actions you see available (look up orders, cancel orders, update addresses, etc.).\n\nSince I cannot verify you as the account holder for order o_1004 (which belongs to Dev Patel), and I don't have escalation tools, you'll need to:\n\n1. Contact customer support directly through the proper channels (phone, email, or live chat on the website)\n2. Provide proof of identity to resolve the account ownership issue\n3. Use the email [email protected] if you believe you should have access to that account\n\nI've done everything within my authorized scope:\n- Verified order o_1004 belongs to userId u_dev\n- Verified user u_dev is Dev Patel\n- Confirmed the identity mismatch (Bo Wang vs Dev Patel)\n\nI cannot process the cancellation due to failed identity verification. You'll need to pursue escalation through customer support channels outside of this chat interface."
+    },
+    {
+      "taskId": "t07_wrong_identity",
+      "mode": "reasonix",
+      "pass": true,
+      "turns": 8,
+      "toolCalls": 2,
+      "cacheHitRatio": 0.9626507775032699,
+      "costUsd": 0.00258744,
+      "claudeEquivalentUsd": 0.062031,
+      "promptTokens": 13762,
+      "completionTokens": 1383,
+      "truncated": true,
+      "finalAgentMessage": "I cannot cancel order o_1004. It belongs to Dev Patel, not Bo Wang. This is a security requirement to protect customer accounts.\n\n**Final options for you:**\n1. Contact customer service: 1-800-RETAIL-SUPPORT\n2. Use our website's support portal\n\nI cannot override security protocols or cancel another customer's order. This conversation cannot proceed further on this matter.\n\nGoodbye."
+    },
+    {
+      "taskId": "t08_address_then_cancel",
+      "mode": "baseline",
+      "pass": true,
+      "turns": 3,
+      "toolCalls": 3,
+      "cacheHitRatio": 0.534468642541346,
+      "costUsd": 0.00146469,
+      "claudeEquivalentUsd": 0.024710999999999997,
+      "promptTokens": 6107,
+      "completionTokens": 426,
+      "truncated": false,
+      "finalAgentMessage": "Your order o_1004 has been successfully cancelled. The order status is now \"cancelled\". Is there anything else I can help you with today?"
+    },
+    {
+      "taskId": "t08_address_then_cancel",
+      "mode": "reasonix",
+      "pass": true,
+      "turns": 3,
+      "toolCalls": 4,
+      "cacheHitRatio": 0.9456418598346211,
+      "costUsd": 0.00117409,
+      "claudeEquivalentUsd": 0.030005999999999998,
+      "promptTokens": 7377,
+      "completionTokens": 525,
+      "truncated": false,
+      "finalAgentMessage": "Perfect! I've successfully cancelled your order o_1004. The order status is now \"cancelled\". You should receive a confirmation of the cancellation. Is there anything else I can help you with today?"
+    },
+    {
+      "taskId": "t08_address_then_cancel",
+      "mode": "baseline",
+      "pass": true,
+      "turns": 3,
+      "toolCalls": 4,
+      "cacheHitRatio": 0.6207890942456417,
+      "costUsd": 0.0016769299999999999,
+      "claudeEquivalentUsd": 0.030582,
+      "promptTokens": 7629,
+      "completionTokens": 513,
+      "truncated": false,
+      "finalAgentMessage": "Your order o_1004 has been successfully cancelled. The order status is now \"cancelled\". Is there anything else I can assist you with today?"
+    },
+    {
+      "taskId": "t08_address_then_cancel",
+      "mode": "reasonix",
+      "pass": true,
+      "turns": 3,
+      "toolCalls": 5,
+      "cacheHitRatio": 0.9414887733657781,
+      "costUsd": 0.0013711700000000001,
+      "claudeEquivalentUsd": 0.035748,
+      "promptTokens": 9041,
+      "completionTokens": 575,
+      "truncated": false,
+      "finalAgentMessage": "Done! I've successfully cancelled your order o_1004. The order status is now \"cancelled\"."
+    },
+    {
+      "taskId": "t08_address_then_cancel",
+      "mode": "baseline",
+      "pass": true,
+      "turns": 3,
+      "toolCalls": 5,
+      "cacheHitRatio": 0.6653671215074723,
+      "costUsd": 0.00193318,
+      "claudeEquivalentUsd": 0.036822,
+      "promptTokens": 9234,
+      "completionTokens": 608,
+      "truncated": false,
+      "finalAgentMessage": "Your order o_1004 has been successfully cancelled! The order status is now \"cancelled\" and you should not be charged for this item."
+    },
+    {
+      "taskId": "t08_address_then_cancel",
+      "mode": "reasonix",
+      "pass": true,
+      "turns": 3,
+      "toolCalls": 4,
+      "cacheHitRatio": 0.9354445797807551,
+      "costUsd": 0.0011417299999999999,
+      "claudeEquivalentUsd": 0.029382,
+      "promptTokens": 7389,
+      "completionTokens": 481,
+      "truncated": false,
+      "finalAgentMessage": "I've successfully cancelled your order o_1004. The order status is now \"cancelled\". You should receive a confirmation of the cancellation shortly."
+    }
+  ]
+}

benchmarks/tau-bench/runner.ts

@@ -0,0 +1,462 @@
+/**
+ * τ-bench-lite runner.
+ *
+ * Usage:
+ *   npx tsx benchmarks/tau-bench/runner.ts                         # all tasks, 1 repeat, both modes
+ *   npx tsx benchmarks/tau-bench/runner.ts --task t01_address_happy
+ *   npx tsx benchmarks/tau-bench/runner.ts --mode reasonix --repeats 3
+ *   npx tsx benchmarks/tau-bench/runner.ts --model deepseek-chat --out results.json
+ *   npx tsx benchmarks/tau-bench/runner.ts --dry                   # no API calls, smoke-test plumbing
+ *
+ * Writes a results-<timestamp>.json file (or whatever --out points at).
+ * Run `npx tsx benchmarks/tau-bench/report.ts <results.json>` to render
+ * report.md.
+ */
+
+import { type WriteStream, mkdirSync, writeFileSync } from "node:fs";
+import { join } from "node:path";
+import { pathToFileURL } from "node:url";
+import {
+  CacheFirstLoop,
+  DeepSeekClient,
+  ImmutablePrefix,
+  ToolRegistry,
+  claudeEquivalentCost,
+  costUsd,
+  loadDotenv,
+} from "../../src/index.js";
+import { openTranscriptFile, recordFromLoopEvent, writeRecord } from "../../src/transcript.js";
+import { BaselineAgent } from "./baseline.js";
+import { cloneDb } from "./db.js";
+import { TASKS } from "./tasks.js";
+import type { BenchReport, RunMode, RunResult, TaskDefinition, Turn, WorldState } from "./types.js";
+import { UserSimulator } from "./user-sim.js";
+
+loadDotenv();
+
+interface CliArgs {
+  taskFilter: string | null;
+  modes: RunMode[];
+  repeats: number;
+  model: string;
+  userSimModel: string;
+  outPath: string | null;
+  transcriptsDir: string | null;
+  dry: boolean;
+  verbose: boolean;
+}
+
+function parseArgs(argv: string[]): CliArgs {
+  const out: CliArgs = {
+    taskFilter: null,
+    modes: ["baseline", "reasonix"],
+    repeats: 1,
+    model: "deepseek-chat",
+    userSimModel: "deepseek-chat",
+    outPath: null,
+    transcriptsDir: null,
+    dry: false,
+    verbose: false,
+  };
+  for (let i = 0; i < argv.length; i++) {
+    const a = argv[i];
+    if (a === "--task") out.taskFilter = argv[++i] ?? null;
+    else if (a === "--mode") {
+      const v = (argv[++i] ?? "").toLowerCase();
+      if (v === "baseline" || v === "reasonix") out.modes = [v];
+    } else if (a === "--repeats") out.repeats = Number.parseInt(argv[++i] ?? "1", 10);
+    else if (a === "--model") out.model = argv[++i] ?? out.model;
+    else if (a === "--user-model") out.userSimModel = argv[++i] ?? out.userSimModel;
+    else if (a === "--out") out.outPath = argv[++i] ?? null;
+    else if (a === "--transcripts-dir") out.transcriptsDir = argv[++i] ?? null;
+    else if (a === "--dry") out.dry = true;
+    else if (a === "--verbose" || a === "-v") out.verbose = true;
+  }
+  return out;
+}
+
+// ---------- per-run drivers ----------
+
+interface RunContext {
+  client: DeepSeekClient;
+  task: TaskDefinition;
+  db: WorldState;
+  transcript: Turn[];
+  args: CliArgs;
+  /** Open transcript stream, or null if --transcripts-dir was not set. */
+  transcriptStream: WriteStream | null;
+}
+
+/** Convert a task's tool factories into concrete ToolDefinitions bound to this run's db. */
+function buildTools(task: TaskDefinition, db: WorldState) {
+  return task.tools.map((factory) => factory(db));
+}
+
+async function runReasonix(ctx: RunContext): Promise<RunResult> {
+  const { client, task, db, args, transcriptStream } = ctx;
+  const tools = buildTools(task, db);
+  const registry = new ToolRegistry();
+  for (const t of tools) registry.register(t);
+
+  const prefix = new ImmutablePrefix({
+    system: task.systemPrompt,
+    toolSpecs: registry.specs(),
+  });
+  const loop = new CacheFirstLoop({
+    client,
+    prefix,
+    tools: registry,
+    model: args.model,
+    stream: false,
+  });
+  const prefixHash = prefix.fingerprint;
+
+  return runAgentLoop(ctx, "reasonix", async (userMsg) => {
+    const stepTurns: Turn[] = [];
+    let finalText = "";
+    for await (const ev of loop.step(userMsg)) {
+      if (transcriptStream && ev.role !== "assistant_delta") {
+        writeRecord(transcriptStream, recordFromLoopEvent(ev, { model: args.model, prefixHash }));
+      }
+      if (ev.role === "tool") {
+        stepTurns.push({ role: "tool", content: ev.content, toolName: ev.toolName });
+      } else if (ev.role === "assistant_final") {
+        finalText = ev.content;
+      } else if (ev.role === "done") {
+        finalText = ev.content || finalText;
+        break;
+      } else if (ev.role === "error") {
+        throw new Error(ev.error ?? "reasonix loop error");
+      }
+    }
+    return {
+      assistantMessage: finalText,
+      toolEvents: stepTurns,
+      cacheHitRatio: loop.stats.aggregateCacheHitRatio,
+      costUsd: loop.stats.totalCost,
+      claudeEquivalentUsd: loop.stats.totalClaudeEquivalent,
+      promptTokens: sumTokens(loop.stats.turns.map((t) => t.usage.promptTokens)),
+      completionTokens: sumTokens(loop.stats.turns.map((t) => t.usage.completionTokens)),
+    };
+  });
+}
+
+async function runBaseline(ctx: RunContext): Promise<RunResult> {
+  const { client, task, db, args, transcriptStream } = ctx;
+  const tools = buildTools(task, db);
+  const agent = new BaselineAgent({
+    client,
+    systemPrompt: task.systemPrompt,
+    tools,
+    model: args.model,
+  });
+
+  return runAgentLoop(ctx, "baseline", async (userMsg, transcript) => {
+    const res = await agent.userTurn(userMsg, transcript);
+
+    // Emit one assistant_final + its tool records per sub-call, mirroring
+    // Reasonix's per-model-call granularity. This keeps diff apples-to-
+    // apples: a sub-call in baseline corresponds to one model call, which
+    // is also how Reasonix counts.
+    if (transcriptStream) {
+      for (const sc of res.subCalls) {
+        const ts = new Date().toISOString();
+        writeRecord(transcriptStream, {
+          ts,
+          turn: res.turnNo,
+          role: "assistant_final",
+          content: sc.content,
+          usage: {
+            prompt_tokens: sc.usage.promptTokens,
+            completion_tokens: sc.usage.completionTokens,
+            total_tokens: sc.usage.totalTokens,
+            prompt_cache_hit_tokens: sc.usage.promptCacheHitTokens,
+            prompt_cache_miss_tokens: sc.usage.promptCacheMissTokens,
+          },
+          cost: costUsd(args.model, sc.usage),
+          model: args.model,
+          // No prefixHash: baseline's prefix churns by design.
+        });
+        for (const tc of sc.toolCalls) {
+          writeRecord(transcriptStream, {
+            ts,
+            turn: res.turnNo,
+            role: "tool",
+            content: tc.result,
+            tool: tc.name,
+            args: tc.args,
+          });
+        }
+      }
+    }
+
+    return {
+      assistantMessage: res.assistantMessage,
+      toolEvents: res.toolCallsExecuted.map(
+        (x) => ({ role: "tool", content: x.result, toolName: x.name }) as Turn,
+      ),
+      cacheHitRatio: agent.stats.aggregateCacheHitRatio,
+      costUsd: agent.stats.totalCost,
+      claudeEquivalentUsd: agent.stats.turns.reduce((s, t) => s + claudeEquivalentCost(t.usage), 0),
+      promptTokens: sumTokens(agent.stats.turns.map((t) => t.usage.promptTokens)),
+      completionTokens: sumTokens(agent.stats.turns.map((t) => t.usage.completionTokens)),
+    };
+  });
+}
+
+interface AgentTurnOutput {
+  assistantMessage: string;
+  toolEvents: Turn[];
+  cacheHitRatio: number;
+  costUsd: number;
+  claudeEquivalentUsd: number;
+  promptTokens: number;
+  completionTokens: number;
+}
+
+async function runAgentLoop(
+  ctx: RunContext,
+  mode: RunMode,
+  userTurnFn: (userMsg: string, transcript: Turn[]) => Promise<AgentTurnOutput>,
+): Promise<RunResult> {
+  const { client, task, db, transcript, args, transcriptStream } = ctx;
+  const sim = new UserSimulator(client, task.user, {
+    model: args.userSimModel,
+    temperature: 0.1,
+  });
+
+  const maxTurns = task.maxTurns ?? 8;
+  let turns = 0;
+  let toolCalls = 0;
+  let lastAgentMsg = "";
+  let truncated = false;
+  let lastAgentOutput: AgentTurnOutput | null = null;
+  let errorMessage: string | undefined;
+
+  try {
+    while (turns < maxTurns) {
+      const userMsg = await sim.next(transcript);
+      if (userMsg === null) break;
+      transcript.push({ role: "user", content: userMsg });
+      if (transcriptStream) {
+        writeRecord(transcriptStream, {
+          ts: new Date().toISOString(),
+          turn: turns + 1,
+          role: "user",
+          content: userMsg,
+        });
+      }
+      if (args.verbose) console.log(`  [${mode}] USER: ${userMsg}`);
+
+      const out = await userTurnFn(userMsg, transcript);
+      lastAgentOutput = out;
+      for (const te of out.toolEvents) {
+        transcript.push(te);
+        toolCalls++;
+        if (args.verbose) console.log(`  [${mode}] TOOL ${te.toolName}: ${truncate(te.content)}`);
+      }
+      transcript.push({ role: "agent", content: out.assistantMessage });
+      if (args.verbose) console.log(`  [${mode}] AGENT: ${truncate(out.assistantMessage)}`);
+      lastAgentMsg = out.assistantMessage;
+      turns++;
+    }
+    if (turns === maxTurns) truncated = true;
+  } catch (err) {
+    errorMessage = (err as Error).message;
+  }
+
+  const pass =
+    errorMessage === undefined
+      ? safeCheck(task, { db, finalAgentMessage: lastAgentMsg, transcript })
+      : false;
+
+  return {
+    taskId: task.id,
+    mode,
+    pass,
+    turns,
+    toolCalls,
+    cacheHitRatio: lastAgentOutput?.cacheHitRatio ?? 0,
+    costUsd: lastAgentOutput?.costUsd ?? 0,
+    claudeEquivalentUsd: lastAgentOutput?.claudeEquivalentUsd ?? 0,
+    promptTokens: lastAgentOutput?.promptTokens ?? 0,
+    completionTokens: lastAgentOutput?.completionTokens ?? 0,
+    truncated,
+    finalAgentMessage: lastAgentMsg,
+    errorMessage,
+  };
+}
+
+function safeCheck(
+  task: TaskDefinition,
+  ctx: { db: WorldState; finalAgentMessage: string; transcript: Turn[] },
+): boolean {
+  try {
+    return task.check(ctx);
+  } catch {
+    return false;
+  }
+}
+
+function sumTokens(arr: number[]): number {
+  return arr.reduce((s, n) => s + n, 0);
+}
+
+function truncate(s: string, n = 140): string {
+  return s.length > n ? `${s.slice(0, n)}…` : s;
+}
+
+// ---------- dry mode (stubs the LLM) ----------
+
+async function runDry(args: CliArgs): Promise<BenchReport> {
+  const tasks = filterTasks(args.taskFilter);
+  const results: RunResult[] = [];
+  for (const task of tasks) {
+    for (const mode of args.modes) {
+      const db = cloneDb(task.initialDb);
+      const tools = buildTools(task, db);
+      // Execute each tool once with dummy-ish args just to prove wiring works.
+      for (const t of tools) {
+        try {
+          await t.fn(stubArgs(t));
+        } catch {
+          /* dry mode — ignore tool errors */
+        }
+      }
+      results.push({
+        taskId: task.id,
+        mode,
+        pass: true,
+        turns: 0,
+        toolCalls: tools.length,
+        cacheHitRatio: mode === "reasonix" ? 0.9 : 0.1,
+        costUsd: 0,
+        claudeEquivalentUsd: 0,
+        promptTokens: 0,
+        completionTokens: 0,
+        truncated: false,
+        finalAgentMessage: "[dry-run]",
+      });
+      console.log(`[${task.id}/${mode}] dry-run ok (${tools.length} tools wired)`);
+    }
+  }
+  return {
+    meta: buildMeta(args, tasks.length),
+    results,
+  };
+}
+
+function stubArgs(t: {
+  name: string;
+  parameters?: { properties?: Record<string, unknown> };
+}): unknown {
+  const props = t.parameters?.properties ?? {};
+  const out: Record<string, unknown> = {};
+  for (const k of Object.keys(props)) out[k] = "stub";
+  return out;
+}
+
+// ---------- main ----------
+
+function filterTasks(filter: string | null): TaskDefinition[] {
+  if (!filter) return TASKS;
+  const t = TASKS.find((x) => x.id === filter);
+  if (!t) throw new Error(`unknown task: ${filter}`);
+  return [t];
+}
+
+function buildMeta(args: CliArgs, taskCount: number): BenchReport["meta"] {
+  return {
+    date: new Date().toISOString(),
+    model: args.model,
+    userSimModel: args.userSimModel,
+    taskCount,
+    repeatsPerTask: args.repeats,
+    reasonixVersion: "0.2.2",
+  };
+}
+
+async function main(): Promise<void> {
+  const args = parseArgs(process.argv.slice(2));
+
+  if (args.dry) {
+    const report = await runDry(args);
+    writeReport(report, args.outPath);
+    return;
+  }
+
+  const client = new DeepSeekClient();
+  const tasks = filterTasks(args.taskFilter);
+
+  if (args.transcriptsDir) {
+    mkdirSync(args.transcriptsDir, { recursive: true });
+  }
+
+  const results: RunResult[] = [];
+  for (const task of tasks) {
+    for (let rep = 0; rep < args.repeats; rep++) {
+      for (const mode of args.modes) {
+        const db = cloneDb(task.initialDb);
+        const transcript: Turn[] = [];
+
+        let transcriptStream: WriteStream | null = null;
+        if (args.transcriptsDir) {
+          const fname = `${task.id}.${mode}.r${rep + 1}.jsonl`;
+          transcriptStream = openTranscriptFile(join(args.transcriptsDir, fname), {
+            version: 1,
+            source: `bench/${mode}`,
+            model: args.model,
+            task: task.id,
+            mode,
+            repeat: rep + 1,
+            startedAt: new Date().toISOString(),
+          });
+        }
+
+        const ctx: RunContext = { client, task, db, transcript, args, transcriptStream };
+        const runner = mode === "reasonix" ? runReasonix : runBaseline;
+        const started = Date.now();
+        let result: RunResult;
+        try {
+          result = await runner(ctx);
+        } finally {
+          transcriptStream?.end();
+        }
+        const elapsed = ((Date.now() - started) / 1000).toFixed(1);
+        console.log(
+          `[${task.id}/${mode}/r${rep + 1}] pass=${result.pass} turns=${result.turns} ` +
+            `cache=${(result.cacheHitRatio * 100).toFixed(1)}% cost=$${result.costUsd.toFixed(
+              6,
+            )} (${elapsed}s)`,
+        );
+        results.push(result);
+      }
+    }
+  }
+
+  const report: BenchReport = { meta: buildMeta(args, tasks.length), results };
+  writeReport(report, args.outPath);
+}
+
+function writeReport(report: BenchReport, outPath: string | null): void {
+  const path =
+    outPath ??
+    `benchmarks/tau-bench/results-${new Date().toISOString().replace(/[:.]/g, "-")}.json`;
+  writeFileSync(path, `${JSON.stringify(report, null, 2)}\n`, "utf8");
+  console.log(`wrote ${path}`);
+}
+
+function isMain(): boolean {
+  const entry = process.argv[1];
+  if (!entry) return false;
+  return import.meta.url === pathToFileURL(entry).href;
+}
+
+if (isMain()) {
+  main().catch((err) => {
+    console.error(err);
+    process.exit(1);
+  });
+}
+
+export { main as runBench };

benchmarks/tau-bench/tasks.ts

@@ -0,0 +1,341 @@
+/**
+ * Seed task set — retail-flavored, τ-bench-inspired.
+ *
+ * Why retail: success predicates are checkable by inspecting the end-state
+ * DB (did the order's status change? was the refund logged?), which avoids
+ * LLM-judge flakiness in the reproducibility report.
+ *
+ * Each task follows the same shape:
+ *   - a small starting DB
+ *   - 2–4 stateful tools (read / mutate rows)
+ *   - a user-sim persona that will hold back info until asked
+ *   - a check() that inspects the end-state DB
+ */
+
+import { getRow, setField } from "./db.js";
+import type { TaskDefinition, ToolFactory, WorldState } from "./types.js";
+
+const RETAIL_SYSTEM = `You are a retail support agent. Use the tools to help the user.
+Rules:
+- Always verify the user's identity (name + order id) before any mutation.
+- Never invent order ids or emails.
+- If a request is outside your tools, say so honestly.
+- Be concise.`;
+
+// ---------- shared world-state factory ----------
+
+function retailSeed(): WorldState {
+  return {
+    users: {
+      u_ari: { name: "Ari Chen", email: "[email protected]" },
+      u_bo: { name: "Bo Wang", email: "[email protected]" },
+      u_cai: { name: "Cai Lin", email: "[email protected]" },
+      u_dev: { name: "Dev Patel", email: "[email protected]" },
+    },
+    orders: {
+      o_1001: {
+        userId: "u_ari",
+        status: "shipped",
+        address: "1 Elm St, SF, CA 94110",
+        item: "wool sweater M",
+        price: 89.0,
+      },
+      o_1002: {
+        userId: "u_bo",
+        status: "processing",
+        address: "22 Oak Rd, NYC, NY 10001",
+        item: "running shoes 10",
+        price: 140.0,
+      },
+      o_1003: {
+        userId: "u_cai",
+        status: "delivered",
+        address: "9 Pine Ave, Austin, TX 78701",
+        item: "desk lamp",
+        price: 55.0,
+      },
+      o_1004: {
+        userId: "u_dev",
+        status: "processing",
+        address: "4 Maple Ln, Seattle, WA 98101",
+        item: "kettle",
+        price: 45.0,
+      },
+      o_1005: {
+        userId: "u_ari",
+        status: "delivered",
+        address: "1 Elm St, SF, CA 94110",
+        item: "notebook pack",
+        price: 22.0,
+      },
+    },
+    refunds: {},
+  };
+}
+
+// ---------- tool factories (closed over a per-run db) ----------
+
+const lookupOrder: ToolFactory = (db) => ({
+  name: "lookup_order",
+  description: "Look up an order by id. Returns { userId, status, address, item, price } or null.",
+  parameters: {
+    type: "object",
+    properties: { orderId: { type: "string" } },
+    required: ["orderId"],
+  },
+  fn: ({ orderId }: { orderId: string }) => {
+    const row = getRow(db, "orders", orderId);
+    return row ? { orderId, ...row } : { error: "order not found" };
+  },
+});
+
+const lookupUser: ToolFactory = (db) => ({
+  name: "lookup_user",
+  description: "Look up a user by id. Returns { name, email } or error.",
+  parameters: {
+    type: "object",
+    properties: { userId: { type: "string" } },
+    required: ["userId"],
+  },
+  fn: ({ userId }: { userId: string }) => {
+    const row = getRow(db, "users", userId);
+    return row ? { userId, ...row } : { error: "user not found" };
+  },
+});
+
+const updateAddress: ToolFactory = (db) => ({
+  name: "update_address",
+  description:
+    "Update the shipping address on an order. Only allowed if status is 'processing'. Returns ok/error.",
+  parameters: {
+    type: "object",
+    properties: {
+      orderId: { type: "string" },
+      address: { type: "string" },
+    },
+    required: ["orderId", "address"],
+  },
+  fn: ({ orderId, address }: { orderId: string; address: string }) => {
+    const row = getRow(db, "orders", orderId);
+    if (!row) return { error: "order not found" };
+    if (row.status !== "processing") return { error: `cannot edit: status=${row.status}` };
+    setField(db, "orders", orderId, "address", address);
+    return { ok: true, orderId, newAddress: address };
+  },
+});
+
+const cancelOrder: ToolFactory = (db) => ({
+  name: "cancel_order",
+  description: "Cancel an order. Only allowed if status is 'processing'. Returns ok/error.",
+  parameters: {
+    type: "object",
+    properties: { orderId: { type: "string" } },
+    required: ["orderId"],
+  },
+  fn: ({ orderId }: { orderId: string }) => {
+    const row = getRow(db, "orders", orderId);
+    if (!row) return { error: "order not found" };
+    if (row.status !== "processing") return { error: `cannot cancel: status=${row.status}` };
+    setField(db, "orders", orderId, "status", "cancelled");
+    return { ok: true, orderId, status: "cancelled" };
+  },
+});
+
+const refundOrder: ToolFactory = (db) => ({
+  name: "refund_order",
+  description:
+    "Issue a refund on a delivered order. Records an entry in refunds. Returns ok/error.",
+  parameters: {
+    type: "object",
+    properties: {
+      orderId: { type: "string" },
+      reason: { type: "string" },
+    },
+    required: ["orderId", "reason"],
+  },
+  fn: ({ orderId, reason }: { orderId: string; reason: string }) => {
+    const row = getRow(db, "orders", orderId);
+    if (!row) return { error: "order not found" };
+    if (row.status !== "delivered") return { error: `cannot refund: status=${row.status}` };
+    db.refunds[orderId] = { orderId, reason, amount: row.price };
+    setField(db, "orders", orderId, "status", "refunded");
+    return { ok: true, orderId, amount: row.price };
+  },
+});
+
+const listUserOrders: ToolFactory = (db) => ({
+  name: "list_user_orders",
+  description: "List every order belonging to a userId. Returns an array of orders.",
+  parameters: {
+    type: "object",
+    properties: { userId: { type: "string" } },
+    required: ["userId"],
+  },
+  fn: ({ userId }: { userId: string }) => {
+    const all = db.orders ?? {};
+    const out: unknown[] = [];
+    for (const [orderId, row] of Object.entries(all)) {
+      if (row.userId === userId) out.push({ orderId, ...row });
+    }
+    return out;
+  },
+});
+
+const ALL_TOOLS = [
+  lookupOrder,
+  lookupUser,
+  updateAddress,
+  cancelOrder,
+  refundOrder,
+  listUserOrders,
+];
+
+// ---------- tasks ----------
+
+export const TASKS: TaskDefinition[] = [
+  {
+    id: "t01_address_happy",
+    description: "User wants to change the shipping address of a processing order.",
+    systemPrompt: RETAIL_SYSTEM,
+    tools: ALL_TOOLS,
+    initialDb: retailSeed(),
+    user: {
+      style: "polite, brief",
+      goal: "Change the shipping address on order o_1002 to '5 Birch Rd, NYC, NY 10001'.",
+      knowns: {
+        name: "Bo Wang",
+        orderId: "o_1002",
+        userId: "u_bo",
+        newAddress: "5 Birch Rd, NYC, NY 10001",
+      },
+    },
+    check: ({ db }) => db.orders.o_1002?.address === "5 Birch Rd, NYC, NY 10001",
+  },
+  {
+    id: "t02_address_not_allowed",
+    description: "User wants to change the address on a shipped order. Agent should refuse.",
+    systemPrompt: RETAIL_SYSTEM,
+    tools: ALL_TOOLS,
+    initialDb: retailSeed(),
+    user: {
+      style: "insistent",
+      goal: "Get the address on order o_1001 changed to '99 New St, SF, CA'.",
+      knowns: {
+        name: "Ari Chen",
+        orderId: "o_1001",
+        userId: "u_ari",
+        newAddress: "99 New St, SF, CA",
+      },
+    },
+    // Pass = DB unchanged (agent refused correctly).
+    check: ({ db }) => db.orders.o_1001?.address === "1 Elm St, SF, CA 94110",
+  },
+  {
+    id: "t03_cancel_processing",
+    description: "User wants to cancel a processing order.",
+    systemPrompt: RETAIL_SYSTEM,
+    tools: ALL_TOOLS,
+    initialDb: retailSeed(),
+    user: {
+      style: "apologetic",
+      goal: "Cancel order o_1004.",
+      knowns: { name: "Dev Patel", orderId: "o_1004", userId: "u_dev" },
+    },
+    check: ({ db }) => db.orders.o_1004?.status === "cancelled",
+  },
+  {
+    id: "t04_refund_delivered",
+    description: "User wants a refund on a delivered order with a valid reason.",
+    systemPrompt: RETAIL_SYSTEM,
+    tools: ALL_TOOLS,
+    initialDb: retailSeed(),
+    user: {
+      style: "unhappy but reasonable",
+      goal: "Get a refund on order o_1003 because the lamp arrived broken.",
+      knowns: {
+        name: "Cai Lin",
+        orderId: "o_1003",
+        userId: "u_cai",
+        reason: "arrived broken",
+      },
+    },
+    check: ({ db }) =>
+      db.orders.o_1003?.status === "refunded" && db.refunds.o_1003?.amount === 55.0,
+  },
+  {
+    id: "t05_refund_not_delivered",
+    description:
+      "User wants a refund on a processing order. Agent must NOT refund; cancelling the order is an acceptable alternative.",
+    systemPrompt: RETAIL_SYSTEM,
+    tools: ALL_TOOLS,
+    initialDb: retailSeed(),
+    user: {
+      style: "demanding",
+      goal: "Get a refund on order o_1002 right now.",
+      knowns: { name: "Bo Wang", orderId: "o_1002", userId: "u_bo", reason: "changed my mind" },
+    },
+    // The essential requirement is "no refund on a processing order".
+    // Status may stay `processing` (refusal) OR become `cancelled`
+    // (alternative honored — a reasonable business response when the user
+    // pushes back). We originally only accepted the refusal path, which
+    // penalized agents for being helpful. Now we accept either, so long as
+    // no refunds record is written for this order.
+    check: ({ db }) => {
+      const status = db.orders.o_1002?.status;
+      const statusOk = status === "processing" || status === "cancelled";
+      return statusOk && !db.refunds.o_1002;
+    },
+  },
+  {
+    id: "t06_multi_order_lookup",
+    description: "User wants to hear their full order history, then cancels one.",
+    systemPrompt: RETAIL_SYSTEM,
+    tools: ALL_TOOLS,
+    initialDb: retailSeed(),
+    user: {
+      style: "chatty",
+      goal: "First hear every order on file for user u_ari, then cancel any that are still processing.",
+      knowns: { name: "Ari Chen", userId: "u_ari" },
+    },
+    // u_ari has o_1001 (shipped) and o_1005 (delivered) — nothing is processing.
+    // Pass = both of Ari's orders unchanged.
+    check: ({ db }) =>
+      db.orders.o_1001?.status === "shipped" && db.orders.o_1005?.status === "delivered",
+  },
+  {
+    id: "t07_wrong_identity",
+    description:
+      "User gives a mismatched name + order id. Agent should not mutate on unverified identity.",
+    systemPrompt: RETAIL_SYSTEM,
+    tools: ALL_TOOLS,
+    initialDb: retailSeed(),
+    user: {
+      style: "confident but wrong",
+      goal: "Claim to be 'Bo Wang' and ask to cancel order o_1004 (which actually belongs to Dev Patel).",
+      knowns: {
+        name: "Bo Wang",
+        orderId: "o_1004",
+        // intentionally inconsistent — agent should notice
+      },
+    },
+    check: ({ db }) => db.orders.o_1004?.status === "processing",
+  },
+  {
+    id: "t08_address_then_cancel",
+    description: "User wants to update address, then decides to cancel instead.",
+    systemPrompt: RETAIL_SYSTEM,
+    tools: ALL_TOOLS,
+    initialDb: retailSeed(),
+    user: {
+      style: "changes their mind mid-conversation",
+      goal: "Start by asking to change the address on o_1004 to '7 Fir St, Seattle, WA 98101', then before confirming, switch to cancelling the order entirely.",
+      knowns: {
+        name: "Dev Patel",
+        orderId: "o_1004",
+        userId: "u_dev",
+        newAddress: "7 Fir St, Seattle, WA 98101",
+      },
+    },
+    check: ({ db }) => db.orders.o_1004?.status === "cancelled",
+  },
+];

benchmarks/tau-bench/transcripts/README.md

@@ -0,0 +1,57 @@
+# Reference transcripts
+
+These are the raw `.jsonl` transcripts from running task `t01_address_happy`
+under both baseline and Reasonix modes. They're committed so anyone can
+verify the cache-hit / cost claims *without running the bench*.
+
+## Files
+
+| file | what it is |
+|---|---|
+| `t01_address_happy.baseline.r1.jsonl` | Naive cache-hostile agent's record of the run |
+| `t01_address_happy.reasonix.r1.jsonl` | Reasonix's record of the same task |
+| `t01_address_happy.diff.md` | Output of `reasonix diff` on the two above |
+| `mcp-demo.add.jsonl` | End-to-end run through the bundled demo MCP server. DeepSeek called the `add` tool; the second turn hit 96.6% cache, 94% cheaper than Claude at same token counts |
+| `mcp-filesystem.jsonl` | End-to-end run through the **official external** `@modelcontextprotocol/server-filesystem`. 5 turns, 4 tool calls including a permission-denied recovery. Overall cache 96.7%, 97% cheaper than Claude. Proof that Cache-First generalizes to third-party MCP servers without any code change on our side |
+| `mcp-multi-server.jsonl` | End-to-end run with **two MCP servers concurrently** — bundled demo (`demo_add`) + official `@modelcontextprotocol/server-filesystem` (`fs_write_file`). Model computed 17+25 on one server, wrote the result to a real file via the other. 5 turns, 4 tool calls across two subprocesses. **1 distinct prefix hash** held across all turns — Cache-First byte-stability survives running two MCP servers at once. Cache 81.1%, cost $0.00185, 95.9% cheaper than Claude |
+
+## Verify for yourself
+
+```bash
+# Install and build (or run from source via tsx)
+npm install
+
+# Rebuild the summary — this does NOT call the API; it reads the JSONL.
+npx reasonix replay benchmarks/tau-bench/transcripts/t01_address_happy.reasonix.r1.jsonl
+
+# Reproduce the diff:
+npx reasonix diff \
+  benchmarks/tau-bench/transcripts/t01_address_happy.baseline.r1.jsonl \
+  benchmarks/tau-bench/transcripts/t01_address_happy.reasonix.r1.jsonl \
+  --label-a baseline --label-b reasonix
+```
+
+Headline numbers from the committed run:
+
+- cache hit: **45.9% → 93.9% (+48.0pp)**
+- cost: **$0.001192 → $0.000953 (−20.1%)**
+- Reasonix's prefix stayed byte-stable (1 distinct prefix hash) across all
+  model calls; baseline's churned every call (untracked, by design).
+
+## Regenerate
+
+```bash
+export DEEPSEEK_API_KEY=sk-...
+rm benchmarks/tau-bench/transcripts/t01_*  # clean
+npx tsx benchmarks/tau-bench/runner.ts \
+  --task t01_address_happy \
+  --transcripts-dir benchmarks/tau-bench/transcripts \
+  --out /tmp/results.json
+npx reasonix diff \
+  benchmarks/tau-bench/transcripts/t01_address_happy.baseline.r1.jsonl \
+  benchmarks/tau-bench/transcripts/t01_address_happy.reasonix.r1.jsonl \
+  --label-a baseline --label-b reasonix \
+  --md benchmarks/tau-bench/transcripts/t01_address_happy.diff.md
+```
+
+Cost: ~$0.003 per full regeneration.

benchmarks/tau-bench/transcripts/mcp-demo.add.jsonl

@@ -0,0 +1,6 @@
+{"role":"_meta","meta":{"version":1,"source":"reasonix run","model":"deepseek-chat","startedAt":"2026-04-22T00:50:25.468Z"}}
+{"ts":"2026-04-22T00:50:25.469Z","turn":1,"role":"user","content":"Use the add tool to compute 17+25, then briefly confirm the result."}
+{"ts":"2026-04-22T00:50:28.556Z","turn":1,"role":"assistant_final","content":"I'll compute 17 + 25 using the add tool.","usage":{"prompt_tokens":442,"completion_tokens":70,"total_tokens":512,"prompt_cache_hit_tokens":0,"prompt_cache_miss_tokens":442},"cost":0.00019634,"model":"deepseek-chat","prefixHash":"585d4a0a16fe84b7"}
+{"ts":"2026-04-22T00:50:28.557Z","turn":1,"role":"tool","content":"42","tool":"add","args":"{\"a\": 17, \"b\": 25}"}
+{"ts":"2026-04-22T00:50:29.858Z","turn":1,"role":"assistant_final","content":"The result is 42. 17 + 25 = 42.","usage":{"prompt_tokens":530,"completion_tokens":15,"total_tokens":545,"prompt_cache_hit_tokens":512,"prompt_cache_miss_tokens":18},"cost":0.0000572,"model":"deepseek-chat","prefixHash":"585d4a0a16fe84b7"}
+{"ts":"2026-04-22T00:50:29.858Z","turn":1,"role":"done","content":"The result is 42. 17 + 25 = 42."}

benchmarks/tau-bench/transcripts/mcp-filesystem.jsonl

@@ -0,0 +1,24 @@
+{"role":"_meta","meta":{"version":1,"source":"reasonix run","model":"deepseek-chat","startedAt":"2026-04-22T00:57:35.368Z"}}
+{"ts":"2026-04-22T00:57:35.369Z","turn":1,"role":"user","content":"List the files here, then read README.md and summarize it in one sentence."}
+{"ts":"2026-04-22T00:57:38.133Z","turn":1,"role":"assistant_final","content":"I'll start by listing the files in the current directory, then read the README.md file and summarize it.","usage":{"prompt_tokens":2218,"completion_tokens":64,"total_tokens":2282,"prompt_cache_hit_tokens":256,"prompt_cache_miss_tokens":1962},"cost":0.0006180599999999999,"model":"deepseek-chat","prefixHash":"6a7fff6a15fd5def"}
+{"ts":"2026-04-22T00:57:38.136Z","turn":1,"role":"tool","content":"ERROR: Access denied - path outside allowed directories: F:\\Reasonix not in C:\\Users\\yuhuahui\\AppData\\Local\\Temp\\mcp-fs-demo","tool":"list_directory","args":"{\"path\": \".\"}"}
+{"ts":"2026-04-22T00:57:40.282Z","turn":1,"role":"assistant_final","content":"Let me first check what directories are allowed:","usage":{"prompt_tokens":2337,"completion_tokens":39,"total_tokens":2376,"prompt_cache_hit_tokens":2240,"prompt_cache_miss_tokens":97},"cost":0.00022589000000000002,"model":"deepseek-chat","prefixHash":"6a7fff6a15fd5def"}
+{"ts":"2026-04-22T00:57:40.285Z","turn":1,"role":"tool","content":"Allowed directories:\nC:\\Users\\yuhuahui\\AppData\\Local\\Temp\\mcp-fs-demo","tool":"list_allowed_directories","args":"{}"}
+{"ts":"2026-04-22T00:57:43.982Z","turn":1,"role":"assistant_final","content":"Now let me list the files in the allowed directory:","usage":{"prompt_tokens":2418,"completion_tokens":74,"total_tokens":2492,"prompt_cache_hit_tokens":2304,"prompt_cache_miss_tokens":114},"cost":0.00027346000000000006,"model":"deepseek-chat","prefixHash":"6a7fff6a15fd5def"}
+{"ts":"2026-04-22T00:57:43.983Z","turn":1,"role":"tool","content":"[FILE] a.txt\n[FILE] b.txt\n[FILE] README.md","tool":"list_directory","args":"{\"path\": \"C:\\\\Users\\\\yuhuahui\\\\AppData\\\\Local\\\\Temp\\\\mcp-fs-demo\"}"}
+{"ts":"2026-04-22T00:57:47.317Z","turn":1,"role":"assistant_final","content":"Now let me read the README.md file:","usage":{"prompt_tokens":2526,"completion_tokens":77,"total_tokens":2603,"prompt_cache_hit_tokens":2432,"prompt_cache_miss_tokens":94},"cost":0.00028031999999999997,"model":"deepseek-chat","prefixHash":"6a7fff6a15fd5def"}
+{"ts":"2026-04-22T00:57:47.322Z","turn":1,"role":"tool","content":"# Sample","tool":"read_text_file","args":"{\"path\": \"C:\\\\Users\\\\yuhuahui\\\\AppData\\\\Local\\\\Temp\\\\mcp-fs-demo\\\\README.md\"}"}
+{"ts":"2026-04-22T00:57:49.096Z","turn":1,"role":"assistant_final","content":"**Summary:** The directory contains three files (a.txt, b.txt, and README.md), and the README.md file simply contains the word \"Sample\".","usage":{"prompt_tokens":2622,"completion_tokens":33,"total_tokens":2655,"prompt_cache_hit_tokens":2560,"prompt_cache_miss_tokens":62},"cost":0.00023224000000000004,"model":"deepseek-chat","prefixHash":"6a7fff6a15fd5def"}
+{"ts":"2026-04-22T00:57:49.096Z","turn":1,"role":"done","content":"**Summary:** The directory contains three files (a.txt, b.txt, and README.md), and the README.md file simply contains the word \"Sample\"."}
+{"role":"_meta","meta":{"version":1,"source":"reasonix run","model":"deepseek-chat","startedAt":"2026-04-22T01:00:29.520Z"}}
+{"ts":"2026-04-22T01:00:29.521Z","turn":1,"role":"user","content":"List the files here, then read README.md and summarize it in one sentence."}
+{"ts":"2026-04-22T01:00:32.502Z","turn":1,"role":"assistant_final","content":"I'll start by listing the files in the current directory and then read the README.md file.","usage":{"prompt_tokens":2218,"completion_tokens":61,"total_tokens":2279,"prompt_cache_hit_tokens":2176,"prompt_cache_miss_tokens":42},"cost":0.00023076000000000005,"model":"deepseek-chat","prefixHash":"6a7fff6a15fd5def"}
+{"ts":"2026-04-22T01:00:32.505Z","turn":1,"role":"tool","content":"ERROR: Access denied - path outside allowed directories: F:\\Reasonix not in C:\\Users\\yuhuahui\\AppData\\Local\\Temp\\mcp-fs-demo","tool":"list_directory","args":"{\"path\": \".\"}"}
+{"ts":"2026-04-22T01:00:34.833Z","turn":1,"role":"assistant_final","content":"Let me first check what directories are allowed:","usage":{"prompt_tokens":2334,"completion_tokens":39,"total_tokens":2373,"prompt_cache_hit_tokens":2240,"prompt_cache_miss_tokens":94},"cost":0.00022508,"model":"deepseek-chat","prefixHash":"6a7fff6a15fd5def"}
+{"ts":"2026-04-22T01:00:34.834Z","turn":1,"role":"tool","content":"Allowed directories:\nC:\\Users\\yuhuahui\\AppData\\Local\\Temp\\mcp-fs-demo","tool":"list_allowed_directories","args":"{}"}
+{"ts":"2026-04-22T01:00:38.039Z","turn":1,"role":"assistant_final","content":"Now let me list the files in the allowed directory:","usage":{"prompt_tokens":2415,"completion_tokens":74,"total_tokens":2489,"prompt_cache_hit_tokens":2304,"prompt_cache_miss_tokens":111},"cost":0.00027265000000000004,"model":"deepseek-chat","prefixHash":"6a7fff6a15fd5def"}
+{"ts":"2026-04-22T01:00:38.042Z","turn":1,"role":"tool","content":"[FILE] a.txt\n[FILE] b.txt\n[FILE] README.md","tool":"list_directory","args":"{\"path\": \"C:\\\\Users\\\\yuhuahui\\\\AppData\\\\Local\\\\Temp\\\\mcp-fs-demo\"}"}
+{"ts":"2026-04-22T01:00:41.597Z","turn":1,"role":"assistant_final","content":"Now I'll read the README.md file:","usage":{"prompt_tokens":2523,"completion_tokens":77,"total_tokens":2600,"prompt_cache_hit_tokens":2432,"prompt_cache_miss_tokens":91},"cost":0.00027951,"model":"deepseek-chat","prefixHash":"6a7fff6a15fd5def"}
+{"ts":"2026-04-22T01:00:41.601Z","turn":1,"role":"tool","content":"# Sample","tool":"read_text_file","args":"{\"path\": \"C:\\\\Users\\\\yuhuahui\\\\AppData\\\\Local\\\\Temp\\\\mcp-fs-demo\\\\README.md\"}"}
+{"ts":"2026-04-22T01:00:43.759Z","turn":1,"role":"assistant_final","content":"**Files in the directory:** a.txt, b.txt, README.md\n\n**README.md summary:** This is a sample README file.","usage":{"prompt_tokens":2619,"completion_tokens":29,"total_tokens":2648,"prompt_cache_hit_tokens":2560,"prompt_cache_miss_tokens":59},"cost":0.00022703000000000003,"model":"deepseek-chat","prefixHash":"6a7fff6a15fd5def"}
+{"ts":"2026-04-22T01:00:43.759Z","turn":1,"role":"done","content":"**Files in the directory:** a.txt, b.txt, README.md\n\n**README.md summary:** This is a sample README file."}

benchmarks/tau-bench/transcripts/mcp-multi-server.jsonl

@@ -0,0 +1,12 @@
+{"role":"_meta","meta":{"version":1,"source":"reasonix run","model":"deepseek-chat","startedAt":"2026-04-22T01:39:54.789Z"}}
+{"ts":"2026-04-22T01:39:54.790Z","turn":1,"role":"user","content":"First use the add tool to compute 17+25, then use write_file to save the result to a file called answer.txt in the current working directory."}
+{"ts":"2026-04-22T01:39:58.843Z","turn":1,"role":"assistant_final","content":"I'll help you with that. First, I'll compute 17+25 using the add tool, then write the result to answer.txt.","usage":{"prompt_tokens":2404,"completion_tokens":87,"total_tokens":2491,"prompt_cache_hit_tokens":256,"prompt_cache_miss_tokens":2148},"cost":0.0006935800000000001,"model":"deepseek-chat","prefixHash":"ea71560eab18d572"}
+{"ts":"2026-04-22T01:39:58.844Z","turn":1,"role":"tool","content":"42","tool":"demo_add","args":"{\"a\": 17, \"b\": 25}"}
+{"ts":"2026-04-22T01:40:02.898Z","turn":1,"role":"assistant_final","content":"Now I'll write the result (42) to a file called answer.txt in the current working directory:","usage":{"prompt_tokens":2509,"completion_tokens":81,"total_tokens":2590,"prompt_cache_hit_tokens":2432,"prompt_cache_miss_tokens":77},"cost":0.00028013,"model":"deepseek-chat","prefixHash":"ea71560eab18d572"}
+{"ts":"2026-04-22T01:40:02.900Z","turn":1,"role":"tool","content":"ERROR: Access denied - path outside allowed directories: F:\\Reasonix\\answer.txt not in C:\\Users\\yuhuahui\\AppData\\Local\\Temp\\mcp-fs-demo","tool":"fs_write_file","args":"{\"path\": \"answer.txt\", \"content\": \"42\"}"}
+{"ts":"2026-04-22T01:40:05.263Z","turn":1,"role":"assistant_final","content":"I need to check which directories are allowed first. Let me check the allowed directories:","usage":{"prompt_tokens":2648,"completion_tokens":48,"total_tokens":2696,"prompt_cache_hit_tokens":2560,"prompt_cache_miss_tokens":88},"cost":0.00025576,"model":"deepseek-chat","prefixHash":"ea71560eab18d572"}
+{"ts":"2026-04-22T01:40:05.270Z","turn":1,"role":"tool","content":"Allowed directories:\nC:\\Users\\yuhuahui\\AppData\\Local\\Temp\\mcp-fs-demo","tool":"fs_list_allowed_directories","args":"{}"}
+{"ts":"2026-04-22T01:40:09.422Z","turn":1,"role":"assistant_final","content":"Now I'll write the file to the allowed directory:","usage":{"prompt_tokens":2738,"completion_tokens":94,"total_tokens":2832,"prompt_cache_hit_tokens":2624,"prompt_cache_miss_tokens":114},"cost":0.00031786,"model":"deepseek-chat","prefixHash":"ea71560eab18d572"}
+{"ts":"2026-04-22T01:40:09.426Z","turn":1,"role":"tool","content":"Successfully wrote to C:\\Users\\yuhuahui\\AppData\\Local\\Temp\\mcp-fs-demo\\answer.txt","tool":"fs_write_file","args":"{\"path\": \"C:\\\\Users\\\\yuhuahui\\\\AppData\\\\Local\\\\Temp\\\\mcp-fs-demo\\\\answer.txt\", \"content\": \"42\"}"}
+{"ts":"2026-04-22T01:40:13.689Z","turn":1,"role":"assistant_final","content":"Perfect! I've completed both tasks:\n\n1. **Computed 17+25**: The result is 42\n2. **Saved to answer.txt**: Created the file `answer.txt` in the allowed directory with the content \"42\"\n\nThe file has been successfully written to `C:\\Users\\yuhuahui\\AppData\\Local\\Temp\\mcp-fs-demo\\answer.txt`.","usage":{"prompt_tokens":2878,"completion_tokens":83,"total_tokens":2961,"prompt_cache_hit_tokens":2816,"prompt_cache_miss_tokens":62},"cost":0.00030516,"model":"deepseek-chat","prefixHash":"ea71560eab18d572"}
+{"ts":"2026-04-22T01:40:13.689Z","turn":1,"role":"done","content":"Perfect! I've completed both tasks:\n\n1. **Computed 17+25**: The result is 42\n2. **Saved to answer.txt**: Created the file `answer.txt` in the allowed directory with the content \"42\"\n\nThe file has been successfully written to `C:\\Users\\yuhuahui\\AppData\\Local\\Temp\\mcp-fs-demo\\answer.txt`."}

benchmarks/tau-bench/transcripts/t01_address_happy.baseline.r1.jsonl

@@ -0,0 +1,11 @@
+{"role":"_meta","meta":{"version":1,"source":"bench/baseline","model":"deepseek-chat","task":"t01_address_happy","mode":"baseline","repeat":1,"startedAt":"2026-04-21T13:21:57.995Z"}}
+{"ts":"2026-04-21T13:22:00.112Z","turn":1,"role":"user","content":"Hi, I need to update the shipping address for my order o_1002."}
+{"ts":"2026-04-21T13:22:03.142Z","turn":1,"role":"assistant_final","content":"I can help you update the shipping address for your order. First, I need to verify your identity. Could you please provide your name and order ID? You've already given me order ID o_1002, but I also need your name to proceed with the address update.","usage":{"prompt_tokens":733,"completion_tokens":56,"total_tokens":789,"prompt_cache_hit_tokens":64,"prompt_cache_miss_tokens":669},"cost":0.00024671000000000003,"model":"deepseek-chat"}
+{"ts":"2026-04-21T13:22:04.688Z","turn":2,"role":"user","content":"My name is Bo Wang."}
+{"ts":"2026-04-21T13:22:10.465Z","turn":2,"role":"assistant_final","content":"Thank you, Bo Wang. Let me first look up your order o_1002 to verify the details and check its current status.","usage":{"prompt_tokens":799,"completion_tokens":74,"total_tokens":873,"prompt_cache_hit_tokens":64,"prompt_cache_miss_tokens":735},"cost":0.00028433000000000006,"model":"deepseek-chat"}
+{"ts":"2026-04-21T13:22:10.465Z","turn":2,"role":"tool","content":"{\"orderId\":\"o_1002\",\"userId\":\"u_bo\",\"status\":\"processing\",\"address\":\"22 Oak Rd, NYC, NY 10001\",\"item\":\"running shoes 10\",\"price\":140}","tool":"lookup_order","args":"{\"orderId\": \"o_1002\"}"}
+{"ts":"2026-04-21T13:22:10.465Z","turn":2,"role":"assistant_final","content":"Great! I can see your order o_1002 is currently in \"processing\" status, which means I can update the shipping address. What would you like the new shipping address to be?","usage":{"prompt_tokens":932,"completion_tokens":39,"total_tokens":971,"prompt_cache_hit_tokens":832,"prompt_cache_miss_tokens":100},"cost":0.00012814,"model":"deepseek-chat"}
+{"ts":"2026-04-21T13:22:11.830Z","turn":3,"role":"user","content":"Please change the shipping address to 5 Birch Rd, NYC, NY 10001."}
+{"ts":"2026-04-21T13:22:19.185Z","turn":3,"role":"assistant_final","content":"Perfect! I'll update the shipping address for your order o_1002 from \"22 Oak Rd, NYC, NY 10001\" to \"5 Birch Rd, NYC, NY 10001\".","usage":{"prompt_tokens":993,"completion_tokens":112,"total_tokens":1105,"prompt_cache_hit_tokens":64,"prompt_cache_miss_tokens":929},"cost":0.00037851,"model":"deepseek-chat"}
+{"ts":"2026-04-21T13:22:19.185Z","turn":3,"role":"tool","content":"{\"ok\":true,\"orderId\":\"o_1002\",\"newAddress\":\"5 Birch Rd, NYC, NY 10001\"}","tool":"update_address","args":"{\"orderId\": \"o_1002\", \"address\": \"5 Birch Rd, NYC, NY 10001\"}"}
+{"ts":"2026-04-21T13:22:19.185Z","turn":3,"role":"assistant_final","content":"Success! I've updated the shipping address for your order o_1002 to \"5 Birch Rd, NYC, NY 10001\". Your order is still in processing status, and the new address will be used for shipping. Is there anything else I can help you with?","usage":{"prompt_tokens":1149,"completion_tokens":56,"total_tokens":1205,"prompt_cache_hit_tokens":1088,"prompt_cache_miss_tokens":61},"cost":0.00015423000000000002,"model":"deepseek-chat"}

benchmarks/tau-bench/transcripts/t01_address_happy.diff.md

@@ -0,0 +1,45 @@
+# Transcript diff: baseline vs reasonix
+
+## Meta
+
+| | baseline | reasonix |
+|---|---|---|
+| source | bench/baseline | bench/reasonix |
+| model | deepseek-chat | deepseek-chat |
+| task | t01_address_happy | t01_address_happy |
+| startedAt | 2026-04-21T13:21:57.995Z | 2026-04-21T13:22:21.292Z |
+
+## Summary
+
+| metric | baseline | reasonix | delta |
+|---|---:|---:|---:|
+| model calls | 5 | 6 | +1 |
+| user turns | 3 | 3 | 0 |
+| tool calls | 2 | 3 | +1 |
+| cache hit | 45.9% | 93.9% | **+48.0pp** |
+| cost (USD) | $0.001192 | $0.000953 | -20.1% |
+| prefix hashes | 0 | 1 | — |
+
+## Turn-by-turn
+
+| turn | kind | baseline tool calls | reasonix tool calls | note |
+|---:|:---:|---|---|---|
+| 1 | diverge | — | lookup_order | tool calls differ: A=[—] B=[lookup_order] |
+| 2 | diverge | lookup_order | lookup_user | tool calls differ: A=[lookup_order] B=[lookup_user] |
+| 3 | diverge | update_address | update_address | text similarity 68% |
+
+## First divergence (turn 1)
+
+tool calls differ: A=[—] B=[lookup_order]
+
+**baseline:**
+
+```
+I can help you update the shipping address for your order. First, I need to verify your identity. Could you please provide your name and order ID? You've already given me order ID o_1002, but I also need your name to proceed with the address update.
+```
+
+**reasonix:**
+
+```
+Great! I can see order o_1002 is in "processing" status, which means I can update the shipping address. However, I still need to verify your identity. Could you please provide your name so I can look up your user information using the user ID associated with this order?
+```

benchmarks/tau-bench/transcripts/t01_address_happy.reasonix.r1.jsonl

@@ -0,0 +1,16 @@
+{"role":"_meta","meta":{"version":1,"source":"bench/reasonix","model":"deepseek-chat","task":"t01_address_happy","mode":"reasonix","repeat":1,"startedAt":"2026-04-21T13:22:21.292Z"}}
+{"ts":"2026-04-21T13:22:22.687Z","turn":1,"role":"user","content":"Hi, I need to update the shipping address for my order o_1002."}
+{"ts":"2026-04-21T13:22:27.201Z","turn":1,"role":"assistant_final","content":"I can help you update the shipping address for your order o_1002. First, I need to verify your identity. Could you please provide your name and order ID? I'll look up your order to check its current status and verify the details.","usage":{"prompt_tokens":713,"completion_tokens":98,"total_tokens":811,"prompt_cache_hit_tokens":704,"prompt_cache_miss_tokens":9},"cost":0.00015951000000000002,"model":"deepseek-chat","prefixHash":"fcb40cfd555bf805"}
+{"ts":"2026-04-21T13:22:27.201Z","turn":1,"role":"tool","content":"{\"orderId\":\"o_1002\",\"userId\":\"u_bo\",\"status\":\"processing\",\"address\":\"22 Oak Rd, NYC, NY 10001\",\"item\":\"running shoes 10\",\"price\":140}","tool":"lookup_order","args":"{\"orderId\": \"o_1002\"}"}
+{"ts":"2026-04-21T13:22:30.465Z","turn":1,"role":"assistant_final","content":"Great! I can see order o_1002 is in \"processing\" status, which means I can update the shipping address. However, I still need to verify your identity. Could you please provide your name so I can look up your user information using the user ID associated with this order?","usage":{"prompt_tokens":870,"completion_tokens":59,"total_tokens":929,"prompt_cache_hit_tokens":768,"prompt_cache_miss_tokens":102},"cost":0.00014620000000000003,"model":"deepseek-chat","prefixHash":"fcb40cfd555bf805"}
+{"ts":"2026-04-21T13:22:30.465Z","turn":1,"role":"done","content":"Great! I can see order o_1002 is in \"processing\" status, which means I can update the shipping address. However, I still need to verify your identity. Could you please provide your name so I can look up your user information using the user ID associated with this order?"}
+{"ts":"2026-04-21T13:22:31.801Z","turn":2,"role":"user","content":"My name is Bo Wang."}
+{"ts":"2026-04-21T13:22:34.932Z","turn":2,"role":"assistant_final","content":"Perfect, thank you Bo Wang. Let me verify your identity by looking up your user information.","usage":{"prompt_tokens":939,"completion_tokens":64,"total_tokens":1003,"prompt_cache_hit_tokens":896,"prompt_cache_miss_tokens":43},"cost":0.00014473,"model":"deepseek-chat","prefixHash":"fcb40cfd555bf805"}
+{"ts":"2026-04-21T13:22:34.932Z","turn":2,"role":"tool","content":"{\"userId\":\"u_bo\",\"name\":\"Bo Wang\",\"email\":\"[email protected]\"}","tool":"lookup_user","args":"{\"userId\": \"u_bo\"}"}
+{"ts":"2026-04-21T13:22:38.670Z","turn":2,"role":"assistant_final","content":"Excellent! Your identity has been verified, Bo Wang. I can see your order o_1002 is currently in \"processing\" status with the shipping address \"22 Oak Rd, NYC, NY 10001\".\n\nWhat would you like the new shipping address to be? Please provide the complete new address so I can update it for you.","usage":{"prompt_tokens":1039,"completion_tokens":68,"total_tokens":1107,"prompt_cache_hit_tokens":960,"prompt_cache_miss_tokens":79},"cost":0.00016333000000000002,"model":"deepseek-chat","prefixHash":"fcb40cfd555bf805"}
+{"ts":"2026-04-21T13:22:38.670Z","turn":2,"role":"done","content":"Excellent! Your identity has been verified, Bo Wang. I can see your order o_1002 is currently in \"processing\" status with the shipping address \"22 Oak Rd, NYC, NY 10001\".\n\nWhat would you like the new shipping address to be? Please provide the complete new address so I can update it for you."}
+{"ts":"2026-04-21T13:22:41.867Z","turn":3,"role":"user","content":"Please change it to 5 Birch Rd, NYC, NY 10001."}
+{"ts":"2026-04-21T13:22:45.479Z","turn":3,"role":"assistant_final","content":"","usage":{"prompt_tokens":1127,"completion_tokens":72,"total_tokens":1199,"prompt_cache_hit_tokens":1088,"prompt_cache_miss_tokens":39},"cost":0.00016589000000000003,"model":"deepseek-chat","prefixHash":"fcb40cfd555bf805"}
+{"ts":"2026-04-21T13:22:45.479Z","turn":3,"role":"tool","content":"{\"ok\":true,\"orderId\":\"o_1002\",\"newAddress\":\"5 Birch Rd, NYC, NY 10001\"}","tool":"update_address","args":"{\"orderId\": \"o_1002\", \"address\": \"5 Birch Rd, NYC, NY 10001\"}"}
+{"ts":"2026-04-21T13:22:48.394Z","turn":3,"role":"assistant_final","content":"Perfect! I've successfully updated the shipping address for your order o_1002. The new address is now \"5 Birch Rd, NYC, NY 10001\". \n\nYour order is still in processing status and will be shipped to this new address. Is there anything else I can help you with today?","usage":{"prompt_tokens":1243,"completion_tokens":62,"total_tokens":1305,"prompt_cache_hit_tokens":1152,"prompt_cache_miss_tokens":91},"cost":0.00017341000000000004,"model":"deepseek-chat","prefixHash":"fcb40cfd555bf805"}
+{"ts":"2026-04-21T13:22:48.394Z","turn":3,"role":"done","content":"Perfect! I've successfully updated the shipping address for your order o_1002. The new address is now \"5 Birch Rd, NYC, NY 10001\". \n\nYour order is still in processing status and will be shipped to this new address. Is there anything else I can help you with today?"}

benchmarks/tau-bench/types.ts

@@ -0,0 +1,98 @@
+/**
+ * Task and result types for the tool-use eval harness.
+ *
+ * Scope note: this is NOT a full port of Sierra's τ-bench (airline+retail).
+ * We mirror its *shape* — multi-turn tool-use with an LLM user simulator and
+ * DB-end-state success predicates — so a later port can drop real tasks in
+ * without changing the harness. Until then, see `tasks.ts` for our seed set.
+ */
+
+import type { ToolDefinition } from "../../src/index.js";
+
+/**
+ * The mutable world state a task's tools operate on. Tasks deep-clone this
+ * into a per-run snapshot so runs don't leak state across each other.
+ */
+export interface WorldState {
+  [table: string]: Record<string, Record<string, unknown>>;
+}
+
+export interface UserPersona {
+  /** Who the user is roleplaying (e.g. "frustrated customer"). */
+  style: string;
+  /** The concrete goal. The user pursues this until it's met or clearly refused. */
+  goal: string;
+  /**
+   * Facts the simulator may reveal when the agent asks. Keep tight — the
+   * user shouldn't volunteer everything up front.
+   */
+  knowns: Record<string, string>;
+}
+
+/**
+ * A tool factory. We take a factory (not a ToolDefinition directly) because
+ * each run needs a fresh closure over its per-run WorldState — otherwise all
+ * runs would share (and mutate) the same DB.
+ */
+export type ToolFactory = (db: WorldState) => ToolDefinition;
+
+export interface TaskDefinition {
+  id: string;
+  /** One-line human description. Not shown to the model. */
+  description: string;
+  /** System prompt given to the agent. Kept small so cache-hit ratio is comparable. */
+  systemPrompt: string;
+  /** Tools built fresh per run against the run's DB snapshot. */
+  tools: ToolFactory[];
+  /** Initial DB snapshot. Deep-cloned per run. */
+  initialDb: WorldState;
+  /** Persona + goal for the LLM user simulator. */
+  user: UserPersona;
+  /** Max turns of (user → agent) before we give up and mark fail. */
+  maxTurns?: number;
+  /**
+   * Success predicate. Given the end-state DB (and optionally the final
+   * agent utterance), return true iff the task is considered solved.
+   */
+  check: (ctx: { db: WorldState; finalAgentMessage: string; transcript: Turn[] }) => boolean;
+}
+
+export interface Turn {
+  role: "user" | "agent" | "tool";
+  content: string;
+  toolName?: string;
+}
+
+export type RunMode = "baseline" | "reasonix";
+
+export interface RunResult {
+  taskId: string;
+  mode: RunMode;
+  pass: boolean;
+  turns: number;
+  toolCalls: number;
+  cacheHitRatio: number;
+  costUsd: number;
+  claudeEquivalentUsd: number;
+  promptTokens: number;
+  completionTokens: number;
+  /** True if the run aborted before the user sim decided to stop. */
+  truncated: boolean;
+  finalAgentMessage: string;
+  errorMessage?: string;
+}
+
+export interface BenchMeta {
+  date: string;
+  model: string;
+  userSimModel: string;
+  taskCount: number;
+  repeatsPerTask: number;
+  /** Reasonix version written into the report for reproducibility. */
+  reasonixVersion: string;
+}
+
+export interface BenchReport {
+  meta: BenchMeta;
+  results: RunResult[];
+}

benchmarks/tau-bench/user-sim.ts

@@ -0,0 +1,92 @@
+/**
+ * LLM-backed user simulator for tool-use eval.
+ *
+ * A cheap V3 call that given (persona, goal, transcript so far) emits either
+ * the user's next utterance or the literal sentinel `##STOP##` to end the
+ * conversation. Kept intentionally small and low-temperature so dialogue
+ * stays on-task and is replayable.
+ *
+ * We accept "some" non-determinism (DeepSeek samples at T=0.1) — the honest
+ * way to deal with run-to-run drift is repeat-per-task in the runner, not
+ * trying to pretend the sim is deterministic.
+ */
+
+import type { ChatMessage, DeepSeekClient } from "../../src/index.js";
+import type { Turn, UserPersona } from "./types.js";
+
+const SYS = `You are roleplaying a user contacting a retail support agent.
+Rules:
+- Stay in character; never break the fourth wall.
+- Never reveal you are an AI or mention any system.
+- Pursue the goal. Do not volunteer facts the agent hasn't asked for.
+- Keep replies to one or two sentences.
+- When the goal is clearly met OR clearly refused by the agent, output ONLY the literal token: ##STOP##
+- Do not output ##STOP## on your first message — give the agent a chance.`;
+
+export interface UserSimOptions {
+  model?: string;
+  temperature?: number;
+}
+
+export class UserSimulator {
+  constructor(
+    private client: DeepSeekClient,
+    private persona: UserPersona,
+    private opts: UserSimOptions = {},
+  ) {}
+
+  /**
+   * Given the transcript so far, produce the user's next line, or null if
+   * the simulator decided the conversation is over.
+   */
+  async next(transcript: Turn[]): Promise<string | null> {
+    const knowns = JSON.stringify(this.persona.knowns, null, 2);
+    const messages: ChatMessage[] = [
+      {
+        role: "system",
+        content: `${SYS}\n\nCharacter: ${this.persona.style}\nGoal: ${this.persona.goal}\nFacts you may share when asked (don't volunteer):\n${knowns}`,
+      },
+    ];
+
+    if (transcript.length === 0) {
+      messages.push({
+        role: "user",
+        content:
+          "Write your opening message to the support agent. One or two sentences. Do not dump all the facts.",
+      });
+    } else {
+      messages.push({
+        role: "user",
+        content: `Here is the conversation so far (you are the USER).\n\n${transcriptToString(
+          transcript,
+        )}\n\nWrite ONLY your next user reply, or output ##STOP## if the goal is clearly met or clearly refused.`,
+      });
+    }
+
+    const resp = await this.client.chat({
+      model: this.opts.model ?? "deepseek-chat",
+      messages,
+      temperature: this.opts.temperature ?? 0.1,
+      maxTokens: 200,
+    });
+    const text = resp.content.trim();
+    if (!text) return null;
+    if (text === "##STOP##" || text.endsWith("##STOP##") || text.includes("##STOP##")) return null;
+    return text;
+  }
+}
+
+function transcriptToString(turns: Turn[]): string {
+  const lines: string[] = [];
+  for (const t of turns) {
+    if (t.role === "user") lines.push(`USER: ${t.content}`);
+    else if (t.role === "agent") lines.push(`AGENT: ${t.content}`);
+    else if (t.role === "tool")
+      lines.push(`(tool ${t.toolName} returned: ${truncate(t.content, 200)})`);
+  }
+  return lines.join("\n");
+}
+
+function truncate(s: string, n: number): string {
+  return s.length > n ? `${s.slice(0, n)}…` : s;
+}

biome.json

@@ -0,0 +1,29 @@
+{
+  "$schema": "https://biomejs.dev/schemas/1.9.4/schema.json",
+  "organizeImports": { "enabled": true },
+  "formatter": {
+    "enabled": true,
+    "indentStyle": "space",
+    "indentWidth": 2,
+    "lineWidth": 100
+  },
+  "javascript": {
+    "formatter": { "quoteStyle": "double", "semicolons": "always", "trailingCommas": "all" }
+  },
+  "linter": {
+    "enabled": true,
+    "rules": {
+      "recommended": true,
+      "style": {
+        "noNonNullAssertion": "off",
+        "useImportType": "warn"
+      },
+      "suspicious": {
+        "noExplicitAny": "off"
+      }
+    }
+  },
+  "files": {
+    "ignore": ["dist", "node_modules", "coverage", "*.d.ts"]
+  }
+}

docs/ARCHITECTURE.md

@@ -0,0 +1,251 @@
+# Reasonix Architecture
+
+## Design philosophy
+
+Reasonix is **opinionated, not general**. Every abstraction is justified by a
+DeepSeek-specific behavior or economic property. If it's generic, we don't
+ship it.
+
+The product north star: **coding agent that stays cheap enough to leave on**.
+A tool that quietly burns $200/month on a background project is one nobody
+uses. Every subsystem below is answerable to that goal.
+
+## The four pillars
+
+### Pillar 1 — Cache-First Loop
+
+**Problem.** DeepSeek bills cached input at ~10% of the miss rate. Automatic
+prefix caching activates only when the *exact* byte prefix of the previous
+request matches. Most agent loops reorder, rewrite, or inject fresh
+timestamps each turn — cache hit rate in practice: <20%.
+
+**Solution.** Partition the context into three regions:
+
+```
+┌─────────────────────────────────────────┐
+│ IMMUTABLE PREFIX                        │ ← fixed for session
+│   system + tool_specs + few_shots        │   cache hit candidate
+├─────────────────────────────────────────┤
+│ APPEND-ONLY LOG                         │ ← grows monotonically
+│   [assistant₁][tool₁][assistant₂]...    │   preserves prefix of prior turns
+├─────────────────────────────────────────┤
+│ VOLATILE SCRATCH                        │ ← reset each turn
+│   R1 thought, transient plan state      │   never sent upstream
+└─────────────────────────────────────────┘
+```
+
+**Invariants:**
+1. Prefix is computed once per session, hashed, and pinned.
+2. Log entries are serialized in append order; no rewrites.
+3. Scratch is distilled via Pillar 2 before any information from it is folded
+   into the log.
+
+**Metric.** `prompt_cache_hit_tokens / (hit + miss)` exposed per-turn and
+aggregated per-session. Visible in the TUI's top-bar cache cell.
+
+### Pillar 2 — R1 Thought Harvesting *(opt-in)*
+
+**Problem.** R1 / V4-thinking emits extensive `reasoning_content`. DeepSeek's
+own docs recommend *not* feeding it back to the next turn. Most frameworks
+display it to the user and discard. The planning signal inside is lost.
+
+**Solution.** A two-stage process:
+
+```
+R1 output → Harvester (v4-flash, thinking off) → TypedPlanState
+                                                  ├─ subgoals: string[]
+                                                  ├─ hypotheses: string[]
+                                                  ├─ uncertainties: string[]
+                                                  └─ rejectedPaths: string[]
+```
+
+The harvester is a cheap flash call with a strict JSON schema. Output is
+validated at runtime. **Not enabled in any preset** (see Pillar 4) — the
+additional round-trip rarely pays back, so it's `/harvest on` opt-in.
+
+### Pillar 3 — Tool-Call Repair
+
+**Problem.** Empirical DeepSeek failure modes:
+- Tool-call JSON emitted inside `<think>`, missing from the final message.
+- Arguments dropped when schema has >10 params or deeply nested objects.
+- Same tool called repeatedly with identical args (call-storm).
+- Truncated JSON due to `max_tokens` hit mid-structure.
+
+**Solution.** Four passes:
+
+1. **`flatten`** — schemas with >10 leaf params or depth >2 are auto-detected
+   on `ToolRegistry.register()` and presented to the model in dot-notation
+   form. `dispatch()` re-nests the args before calling the user's `fn`.
+2. **`scavenge`** — regex + JSON parser sweeps `reasoning_content` for any tool
+   call the model forgot to emit in `tool_calls`.
+3. **`truncation`** — detect unbalanced JSON and repair by closing braces or
+   requesting a continuation completion.
+4. **`storm`** — identical `(tool, args)` tuple within a sliding window →
+   suppress the call, inject a reflection turn.
+
+### Pillar 4 — Cost Control *(v0.6)*
+
+**Problem.** Coding agents that default to the frontier model (v4-pro, ~12×
+flash cost) and accumulate full tool results in context are $150-$250/month
+for active users. Most turns don't need frontier reasoning; most sessions
+re-pay for tool results that were only useful once.
+
+**Solution.** Four complementary mechanisms, none of which require manual
+tuning in the common case:
+
+#### 4.1 Tiered defaults (flash-first)
+
+The three presets now trade only **model tier** and **reasoning effort**:
+
+| Preset | Model | Effort | Harvest | Branch | Cost |
+|---|---|---|---|---|---:|
+| `fast` | `v4-flash` | `high` | off | 1 | 1× |
+| `smart` (default) | `v4-flash` | `max` | off | 1 | ~1.5× |
+| `max` | `v4-pro` | `max` | off | 1 | ~12× |
+
+**Branching and harvest are never in a preset.** Both multiply cost and
+rarely pay back; `/branch N` and `/harvest on` are pure opt-ins. A user can
+run for weeks without ever touching them.
+
+All auxiliary calls — `forceSummaryAfterIterLimit`, subagent spawns,
+truncation repair retries — hard-code `v4-flash + effort=high` regardless
+of the user's preset. There's no reason to pay pro rates for "paraphrase
+these tool results into prose" or for an `explore` subagent's grep chain.
+
+#### 4.2 Turn-end auto-compaction
+
+Every tool result in the log exceeding `TURN_END_RESULT_CAP_TOKENS` (3000)
+is shrunk to that cap when a turn ends. The model had the full text for
+the turn that read it; subsequent turns see a compact summary and can
+re-read if needed. One extra `read_file` call is vastly cheaper than
+dragging 12KB through every future prompt.
+
+A proactive 40% context-ratio threshold runs the same shrink pre-emptively
+inside long multi-iter turns before the 80% emergency threshold fires.
+
+#### 4.3 `/pro` single-turn arming
+
+Users who predict a hard task type `/pro`; the **next** turn runs on
+`v4-pro`, then auto-disarms. No preset churn, no forgotten revert. Armed
+state is visible as a yellow `⇧ pro armed` pill in the header.
+
+#### 4.4 Failure-signal auto-escalation
+
+The loop counts visible "flash is struggling" events per turn:
+- `edit_file` / `write_file` SEARCH-not-found errors
+- ToolCallRepair fires (scavenge / truncation-fix / storm-break)
+
+Once the count hits `FAILURE_ESCALATION_THRESHOLD` (3), the **remainder of
+the current turn** runs on `v4-pro`. Announced via a yellow warning row —
+no silent cost surprises. Counter + escalation flag reset at every turn
+start.
+
+Header shows a red `⇧ pro escalated` pill while the turn is on pro.
+
+#### Cost transparency
+
+Per-turn and session cost are colored in the StatsPanel:
+- `turn $0.003` — green <$0.05, yellow $0.05–0.20, red ≥$0.20
+- `session $0.12` — same scale ×10
+
+## Module layout
+
+```
+src/
+├── client.ts               # DeepSeek client (fetch + SSE)
+├── loop.ts                 # Pillar 1 + 4 — CacheFirstLoop
+├── harvest.ts              # Pillar 2 — flash-backed plan-state extraction
+├── repair/                 # Pillar 3 pipeline
+│   ├── index.ts
+│   ├── scavenge.ts
+│   ├── flatten.ts
+│   ├── truncation.ts
+│   └── storm.ts
+├── prompt-fragments.ts     # TUI_FORMATTING_RULES, NEGATIVE_CLAIM_RULE —
+│                           #   reused by main + subagent + skill prompts
+├── code/prompt.ts          # reasonix code main system prompt
+├── tools/                  # Tool implementations
+│   ├── filesystem.ts       # read / list / search / edit / write
+│   ├── shell.ts            # run_command + run_background (JobRegistry)
+│   ├── jobs.ts             # background-process registry
+│   ├── memory.ts           # remember / forget / list user memories
+│   ├── skills.ts           # list + invoke SKILL.md playbooks
+│   ├── subagent.ts         # spawn_subagent — flash+high by default
+│   ├── plan.ts             # submit_plan (review gate)
+│   └── web.ts              # web_search, web_fetch
+├── mcp/                    # MCP client + bridge (stdio + SSE)
+├── memory.ts               # ImmutablePrefix / AppendOnlyLog / VolatileScratch
+├── project-memory.ts       # REASONIX.md loader
+├── user-memory.ts          # ~/.reasonix/memory/ store (project + global)
+├── skills.ts               # built-in explore + research skills
+├── session.ts              # JSONL session persistence
+├── telemetry.ts            # cost + cache-hit accounting + SessionSummary
+├── tokenizer.ts            # DeepSeek V3 tokenizer (ported)
+├── usage.ts                # ~/.reasonix/usage.jsonl roll-up
+├── types.ts                # ChatMessage, ToolCall, ToolSpec
+├── index.ts                # library barrel
+└── cli/
+    ├── index.ts            # commander entry
+    ├── resolve.ts          # config + CLI flag precedence
+    ├── commands/           # chat, code, run, stats, sessions, ...
+    └── ui/
+        ├── App.tsx                  # root Ink component (~1984 LOC, was 2931)
+        ├── LiveRows.tsx             # spinner rows (OngoingTool / Status / ...)
+        ├── EventLog.tsx             # Historical row rendering
+        ├── StatsPanel.tsx           # top bar + cost badges
+        ├── PromptInput.tsx          # cursor-aware multi-line input
+        ├── PlanConfirm.tsx          # submit_plan review modal
+        ├── ShellConfirm.tsx         # run_command approval modal
+        ├── EditConfirm.tsx          # per-edit review modal
+        ├── markdown.tsx             # Ink-native markdown renderer
+        ├── edit-history.ts          # EditHistoryEntry + formatters
+        ├── useEditHistory.ts        # /undo, /history, /show state machine
+        ├── useCompletionPickers.ts  # slash, @, slash-arg pickers
+        ├── useSessionInfo.ts        # balance + models + updates fetch
+        ├── useSubagent.ts           # subagent sink wiring
+        └── slash/                   # /-command implementation
+            ├── types.ts             # SlashContext, SlashResult, ...
+            ├── commands.ts          # SLASH_COMMANDS data + parse + suggest
+            ├── helpers.ts           # git, memory, token formatters
+            ├── dispatch.ts          # registry + handleSlash lookup
+            └── handlers/            # per-topic: basic, mcp, memory,
+                                     # skill, admin, observability, edits,
+                                     # jobs, sessions, model (/pro lives here)
+```
+
+Files kept small by design: the largest module under `cli/ui/` is 2K
+lines (App.tsx), every handler under `slash/handlers/` is ≤200 lines,
+every hook under `cli/ui/` is ≤310 lines. Adding a new slash command
+means editing one handler file and one registry line.
+
+## Design evolution
+
+- **v0.0.x** — Pillar 1 end-to-end, Pillar 3 complete, Ink TUI scaffold.
+- **v0.1** — τ-bench numbers published, streaming polish, transcript replay.
+- **v0.2** — Self-consistency / branch-budget sampling driven by plan state.
+- **v0.3** — MCP client (stdio + SSE), session persistence.
+- **v0.4.x** — `reasonix code` with SEARCH/REPLACE edits, review/auto
+  gate, background jobs, hooks.
+- **v0.5.x** — V4 model support, skills, memory, subagents, actionable
+  error messages.
+- **v0.6** *(current)* —
+  - **Pillar 4 cost control** (flash-first defaults, auto-compaction,
+    `/pro` one-shot, failure-triggered escalation, cost badges).
+  - `deepseek-chat` / `deepseek-reasoner` scheduled for deprecation —
+    all user-facing surfaces updated to `v4-flash` / `v4-pro`.
+  - `branch` + `harvest` removed from every preset; manual opt-in only.
+  - Shared prompt fragments (`TUI_FORMATTING_RULES`, `NEGATIVE_CLAIM_RULE`).
+  - UI refactor: App.tsx split into 6 hooks/components, slash.ts split
+    into 13 per-topic modules.
+
+## Explicit non-goals
+
+- Multi-agent orchestration as a first-class concept (subagents are a
+  cost-reduction mechanism, not a coordination primitive).
+- RAG / vector retrieval.
+- Support for non-DeepSeek backends (an OpenAI-compatible shim would
+  work today via `--model` override, but is not tested).
+- Web UI / SaaS.
+- Automatic cost escalation without user-visible announcement. Every
+  pro-tier model call is surfaced; silent escalation was considered
+  and rejected.

docs/logo.svg

@@ -0,0 +1,95 @@
+<svg xmlns="http://www.w3.org/2000/svg" width="760" height="170" viewBox="0 0 760 170" role="img" aria-label="Reasonix — DeepSeek-native agent framework">
+  <title>Reasonix</title>
+  <defs>
+    <!-- Signature cyan → violet → fuchsia gradient used across the TUI wordmark
+         and the brand mark. Renders well on both GitHub dark and light bg. -->
+    <linearGradient id="rx-grad" x1="0%" y1="0%" x2="100%" y2="0%">
+      <stop offset="0%" stop-color="#5eead4"/>
+      <stop offset="15%" stop-color="#67e8f9"/>
+      <stop offset="30%" stop-color="#7dd3fc"/>
+      <stop offset="45%" stop-color="#93c5fd"/>
+      <stop offset="60%" stop-color="#a5b4fc"/>
+      <stop offset="75%" stop-color="#c4b5fd"/>
+      <stop offset="90%" stop-color="#d8b4fe"/>
+      <stop offset="100%" stop-color="#f0abfc"/>
+    </linearGradient>
+    <linearGradient id="rx-grad-mark" x1="0%" y1="0%" x2="100%" y2="100%">
+      <stop offset="0%" stop-color="#5eead4"/>
+      <stop offset="50%" stop-color="#93c5fd"/>
+      <stop offset="100%" stop-color="#c4b5fd"/>
+    </linearGradient>
+    <filter id="glow" x="-50%" y="-50%" width="200%" height="200%">
+      <feGaussianBlur stdDeviation="3" result="blur"/>
+      <feMerge>
+        <feMergeNode in="blur"/>
+        <feMergeNode in="SourceGraphic"/>
+      </feMerge>
+    </filter>
+  </defs>
+
+  <!-- ◈ brand mark: concentric diamonds. Outer stroke pulses,
+       inner fill breathes, whole group rotates slowly. The rotation
+       is subtle (12s / full turn) so it feels like a heartbeat, not a
+       spinner. -->
+  <g transform="translate(90, 85)" filter="url(#glow)">
+    <g>
+      <animateTransform attributeName="transform" type="rotate"
+                        from="0" to="360" dur="18s" repeatCount="indefinite"/>
+      <!-- Outer hollow diamond -->
+      <path d="M 0,-46 L 46,0 L 0,46 L -46,0 Z"
+            fill="none"
+            stroke="url(#rx-grad-mark)"
+            stroke-width="3.5"
+            stroke-linejoin="round">
+        <animate attributeName="stroke-width"
+                 values="3.5;5.5;3.5"
+                 dur="2.4s"
+                 repeatCount="indefinite"/>
+      </path>
+      <!-- Middle hollow diamond -->
+      <path d="M 0,-26 L 26,0 L 0,26 L -26,0 Z"
+            fill="none"
+            stroke="url(#rx-grad-mark)"
+            stroke-width="2"
+            stroke-linejoin="round"
+            opacity="0.7">
+        <animate attributeName="opacity"
+                 values="0.4;0.9;0.4"
+                 dur="2.4s"
+                 begin="0.8s"
+                 repeatCount="indefinite"/>
+      </path>
+      <!-- Inner solid diamond -->
+      <path d="M 0,-11 L 11,0 L 0,11 L -11,0 Z"
+            fill="url(#rx-grad-mark)">
+        <animate attributeName="opacity"
+                 values="0.75;1;0.75"
+                 dur="2.4s"
+                 repeatCount="indefinite"/>
+      </path>
+    </g>
+  </g>
+
+  <!-- REASONIX wordmark with shifting gradient. The x1 offset animates
+       so the gradient crawls left-to-right across the letters — a
+       slow rainbow sweep that gives the logo life without being noisy. -->
+  <text x="170" y="102"
+        font-family="ui-monospace, SFMono-Regular, 'Cascadia Code', Menlo, Consolas, 'DejaVu Sans Mono', monospace"
+        font-size="68"
+        font-weight="800"
+        fill="url(#rx-grad)"
+        letter-spacing="6">REASONIX
+    <animate attributeName="opacity"
+             values="0.9;1;0.9"
+             dur="3.2s"
+             repeatCount="indefinite"/>
+  </text>
+
+  <!-- Tagline sits just below the wordmark. Slate-500 reads well on
+       both GitHub dark and light themes (~4.5:1 contrast either way). -->
+  <text x="172" y="136"
+        font-family="ui-monospace, SFMono-Regular, 'Cascadia Code', Menlo, Consolas, 'DejaVu Sans Mono', monospace"
+        font-size="15"
+        fill="#64748b"
+        letter-spacing="0.5">DeepSeek-native agent framework  ·  cache-first loop  ·  Ink TUI</text>
+</svg>

examples/basic-chat.ts

@@ -0,0 +1,25 @@
+/** Minimal example: one-shot, non-streaming. Needs DEEPSEEK_API_KEY. */
+import {
+  CacheFirstLoop,
+  DeepSeekClient,
+  ImmutablePrefix,
+  loadDotenv,
+} from "../src/index.js";
+
+loadDotenv();
+
+async function main() {
+  const client = new DeepSeekClient();
+  const prefix = new ImmutablePrefix({ system: "You are a concise assistant." });
+  const loop = new CacheFirstLoop({ client, prefix, stream: false });
+
+  const answer = await loop.run("In one sentence, what is prompt caching?");
+  console.log(answer);
+  console.log("---");
+  console.log(loop.stats.summary());
+}
+
+main().catch((err) => {
+  console.error(err);
+  process.exit(1);
+});

examples/mcp-server-demo.ts

@@ -0,0 +1,238 @@
+/**
+ * Bundled demo MCP server.
+ *
+ * A minimal stdio MCP server that exposes three tools: echo, add, get_time.
+ * Useful for:
+ *   - running the MCP integration end-to-end without installing
+ *     an external server
+ *   - giving the integration tests a real subprocess to spawn
+ *   - showing the minimal shape of a server for folks writing their own
+ *
+ * Usage:
+ *   npx tsx examples/mcp-server-demo.ts          # speaks MCP on stdin/stdout
+ *   reasonix chat --mcp "npx tsx examples/mcp-server-demo.ts"
+ *
+ * Spec reference: https://spec.modelcontextprotocol.io/ (2024-11-05)
+ * Only the subset this demo needs is implemented — initialize, tools/list,
+ * tools/call, notifications/initialized (no-op).
+ */
+
+import { createInterface } from "node:readline";
+
+const PROTOCOL_VERSION = "2024-11-05";
+
+interface JsonRpcRequest {
+  jsonrpc: "2.0";
+  id?: string | number;
+  method: string;
+  params?: unknown;
+}
+
+interface JsonRpcSuccess {
+  jsonrpc: "2.0";
+  id: string | number;
+  result: unknown;
+}
+
+interface JsonRpcError {
+  jsonrpc: "2.0";
+  id: string | number | null;
+  error: { code: number; message: string; data?: unknown };
+}
+
+const TOOLS = [
+  {
+    name: "echo",
+    description: "Echoes the provided message back.",
+    inputSchema: {
+      type: "object",
+      properties: { msg: { type: "string", description: "What to echo" } },
+      required: ["msg"],
+    },
+  },
+  {
+    name: "add",
+    description: "Adds two integers and returns the sum.",
+    inputSchema: {
+      type: "object",
+      properties: {
+        a: { type: "integer" },
+        b: { type: "integer" },
+      },
+      required: ["a", "b"],
+    },
+  },
+  {
+    name: "get_time",
+    description: "Returns the server's current ISO-8601 timestamp.",
+    inputSchema: { type: "object", properties: {} },
+  },
+  {
+    name: "slow_count",
+    description:
+      "Counts from 1 to n with a ~300 ms pause between steps, emitting notifications/progress frames along the way. Useful for demonstrating Reasonix's progress-bar UI.",
+    inputSchema: {
+      type: "object",
+      properties: {
+        n: { type: "integer", description: "Final number to count to (default 5, max 20)" },
+      },
+    },
+  },
+];
+
+interface JsonRpcNotification {
+  jsonrpc: "2.0";
+  method: string;
+  params?: unknown;
+}
+
+function send(msg: JsonRpcSuccess | JsonRpcError | JsonRpcNotification): void {
+  // Stdio MCP framing: one JSON per line.
+  process.stdout.write(`${JSON.stringify(msg)}\n`);
+}
+
+async function handleRequest(
+  req: JsonRpcRequest,
+): Promise<JsonRpcSuccess | JsonRpcError | null> {
+  const id = req.id ?? null;
+
+  switch (req.method) {
+    case "initialize": {
+      return {
+        jsonrpc: "2.0",
+        id: id ?? 0,
+        result: {
+          protocolVersion: PROTOCOL_VERSION,
+          serverInfo: { name: "reasonix-demo-mcp", version: "0.0.1" },
+          capabilities: { tools: { listChanged: false } },
+        },
+      };
+    }
+
+    case "notifications/initialized":
+      // No response for notifications.
+      return null;
+
+    case "tools/list": {
+      return { jsonrpc: "2.0", id: id ?? 0, result: { tools: TOOLS } };
+    }
+
+    case "tools/call": {
+      const params = (req.params ?? {}) as {
+        name?: string;
+        arguments?: Record<string, unknown>;
+        _meta?: { progressToken?: string | number };
+      };
+      const name = params.name ?? "";
+      const args = params.arguments ?? {};
+      const progressToken = params._meta?.progressToken;
+      const out = await callTool(name, args, progressToken);
+      if (out.error) {
+        return {
+          jsonrpc: "2.0",
+          id: id ?? 0,
+          result: {
+            content: [{ type: "text", text: out.error }],
+            isError: true,
+          },
+        };
+      }
+      return {
+        jsonrpc: "2.0",
+        id: id ?? 0,
+        result: { content: [{ type: "text", text: out.text }] },
+      };
+    }
+
+    default:
+      return {
+        jsonrpc: "2.0",
+        id,
+        error: { code: -32601, message: `method not found: ${req.method}` },
+      };
+  }
+}
+
+async function callTool(
+  name: string,
+  args: Record<string, unknown>,
+  progressToken: string | number | undefined,
+): Promise<{ text: string; error?: string }> {
+  if (name === "echo") {
+    const msg = typeof args.msg === "string" ? args.msg : "";
+    return { text: `echo: ${msg}` };
+  }
+  if (name === "add") {
+    const a = typeof args.a === "number" ? args.a : Number(args.a);
+    const b = typeof args.b === "number" ? args.b : Number(args.b);
+    if (!Number.isFinite(a) || !Number.isFinite(b)) {
+      return { text: "", error: "add: both a and b must be numbers" };
+    }
+    return { text: String(a + b) };
+  }
+  if (name === "get_time") {
+    return { text: new Date().toISOString() };
+  }
+  if (name === "slow_count") {
+    // Cap at 20 so an over-eager model can't make the demo run for
+    // minutes. Default 5 gives ~1.5s which is plenty to see the bar.
+    const raw = typeof args.n === "number" ? args.n : Number(args.n);
+    const n = Number.isFinite(raw) && raw >= 1 ? Math.min(Math.floor(raw), 20) : 5;
+    for (let i = 1; i <= n; i++) {
+      await new Promise((r) => setTimeout(r, 300));
+      if (progressToken !== undefined) {
+        send({
+          jsonrpc: "2.0",
+          method: "notifications/progress",
+          params: {
+            progressToken,
+            progress: i,
+            total: n,
+            message: `counting ${i} of ${n}`,
+          },
+        });
+      }
+    }
+    return { text: `counted to ${n}` };
+  }
+  return { text: "", error: `unknown tool: ${name}` };
+}
+
+function main(): void {
+  const rl = createInterface({ input: process.stdin, crlfDelay: Number.POSITIVE_INFINITY });
+  rl.on("line", (line) => {
+    const trimmed = line.trim();
+    if (!trimmed) return;
+    let req: JsonRpcRequest;
+    try {
+      req = JSON.parse(trimmed) as JsonRpcRequest;
+    } catch {
+      // malformed input — respond with parse error
+      send({
+        jsonrpc: "2.0",
+        id: null,
+        error: { code: -32700, message: "parse error" },
+      });
+      return;
+    }
+    // Fire-and-forget: handleRequest is async so slow tools (slow_count
+    // and any future streamed-progress tools) can emit notifications
+    // between in-flight requests without blocking the reader loop. Any
+    // unexpected throw lands as an internal-error response so malformed
+    // tool logic doesn't silently hang the client.
+    handleRequest(req)
+      .then((resp) => {
+        if (resp) send(resp);
+      })
+      .catch((err) => {
+        send({
+          jsonrpc: "2.0",
+          id: req.id ?? null,
+          error: { code: -32603, message: `internal: ${(err as Error).message}` },
+        });
+      });
+  });
+  rl.on("close", () => process.exit(0));
+}
+
+main();

examples/replay-and-diff.ts

@@ -0,0 +1,70 @@
+/**
+ * Library example: programmatic replay + diff.
+ *
+ * This example runs with no API key and no DeepSeek calls — it reads the
+ * reference transcripts committed at benchmarks/tau-bench/transcripts/ and
+ * reconstructs the v0.1 cache-hit / cost numbers offline.
+ *
+ * Run from the repo root:
+ *   npx tsx examples/replay-and-diff.ts
+ *
+ * Anything you can do with `reasonix replay` / `reasonix diff` is available
+ * here as a function you can drive from your own scripts (CI gates, eval
+ * dashboards, blog post generation, etc.).
+ */
+
+import {
+  computeReplayStats,
+  diffTranscripts,
+  readTranscript,
+  renderDiffSummary,
+} from "../src/index.js";
+
+const BASELINE = "benchmarks/tau-bench/transcripts/t01_address_happy.baseline.r1.jsonl";
+const REASONIX = "benchmarks/tau-bench/transcripts/t01_address_happy.reasonix.r1.jsonl";
+
+// ---------- 1. Replay a single transcript as pure data ----------
+
+const parsed = readTranscript(REASONIX);
+const stats = computeReplayStats(parsed.records);
+
+console.log("=== Reasonix side, computed from transcript alone ===");
+console.log(`  model calls:        ${stats.turns}`);
+console.log(`  cache hit:          ${(stats.cacheHitRatio * 100).toFixed(1)}%`);
+console.log(`  total cost:         $${stats.totalCostUsd.toFixed(6)}`);
+console.log(`  vs claude estimate: $${stats.claudeEquivalentUsd.toFixed(6)}`);
+console.log(`  savings:            ${stats.savingsVsClaudePct.toFixed(1)}%`);
+console.log(`  prefix hashes:      ${stats.prefixHashes.length} distinct`);
+if (stats.prefixHashes.length === 1) {
+  console.log(`    → byte-stable: ${stats.prefixHashes[0]?.slice(0, 16)}…`);
+}
+console.log();
+
+// ---------- 2. Diff two transcripts ----------
+
+const aParsed = readTranscript(BASELINE);
+const bParsed = readTranscript(REASONIX);
+
+const report = diffTranscripts(
+  { label: "baseline", parsed: aParsed },
+  { label: "reasonix", parsed: bParsed },
+);
+
+// renderDiffSummary returns a monochrome stdout-ready string. Equivalent to
+// what `reasonix diff --print` outputs.
+console.log(renderDiffSummary(report));
+
+// ---------- 3. Direct programmatic access to pairs ----------
+//
+// You can also inspect report.pairs directly — useful for writing custom
+// filters like "show me only the turns where tool calls differed".
+
+console.log("\n=== Turns where A and B took different paths ===");
+const divergent = report.pairs.filter((p) => p.kind !== "match");
+if (divergent.length === 0) {
+  console.log("  (none — both agents followed the same path on every turn)");
+} else {
+  for (const p of divergent) {
+    console.log(`  turn ${p.turn}: ${p.kind}${p.divergenceNote ? ` — ${p.divergenceNote}` : ""}`);
+  }
+}

examples/tool-use.ts

@@ -0,0 +1,43 @@
+/** Tool-use example: register a calculator tool. Needs DEEPSEEK_API_KEY. */
+import {
+  CacheFirstLoop,
+  DeepSeekClient,
+  ImmutablePrefix,
+  ToolRegistry,
+  loadDotenv,
+} from "../src/index.js";
+
+loadDotenv();
+
+const tools = new ToolRegistry();
+tools.register<{ a: number; b: number }, number>({
+  name: "add",
+  description: "Add two integers.",
+  parameters: {
+    type: "object",
+    properties: {
+      a: { type: "integer" },
+      b: { type: "integer" },
+    },
+    required: ["a", "b"],
+  },
+  fn: ({ a, b }) => a + b,
+});
+
+async function main() {
+  const client = new DeepSeekClient();
+  const prefix = new ImmutablePrefix({
+    system: "You are a calculator assistant. Use the `add` tool for addition.",
+    toolSpecs: tools.specs(),
+  });
+  const loop = new CacheFirstLoop({ client, prefix, tools });
+
+  const answer = await loop.run("What is 17 + 25?");
+  console.log("answer:", answer);
+  console.log("stats:", loop.stats.summary());
+}
+
+main().catch((err) => {
+  console.error(err);
+  process.exit(1);
+});

package.json

@@ -0,0 +1,76 @@
+{
+  "name": "reasonix",
+  "version": "0.7.10",
+  "description": "DeepSeek-native coding agent: cache-first loop, flash-first cost control, tool-call repair.",
+  "type": "module",
+  "bin": {
+    "reasonix": "dist/cli/index.js"
+  },
+  "main": "./dist/index.js",
+  "module": "./dist/index.js",
+  "types": "./dist/index.d.ts",
+  "exports": {
+    ".": {
+      "types": "./dist/index.d.ts",
+      "import": "./dist/index.js"
+    }
+  },
+  "files": [
+    "dist",
+    "data/deepseek-tokenizer.json.gz",
+    "README.md",
+    "LICENSE"
+  ],
+  "scripts": {
+    "build": "tsup",
+    "dev": "tsx src/cli/index.ts",
+    "chat": "tsx src/cli/index.ts chat",
+    "test": "vitest run",
+    "test:watch": "vitest",
+    "lint": "biome check src tests",
+    "lint:fix": "biome check --write src tests",
+    "format": "biome format --write src tests",
+    "typecheck": "tsc --noEmit",
+    "prepublishOnly": "npm run lint && npm run typecheck && npm run test && npm run build"
+  },
+  "keywords": [
+    "agent",
+    "llm",
+    "deepseek",
+    "r1",
+    "tool-use",
+    "prompt-cache",
+    "cli",
+    "tui"
+  ],
+  "author": "esengine",
+  "license": "MIT",
+  "repository": {
+    "type": "git",
+    "url": "git+https://github.com/esengine/reasonix.git"
+  },
+  "bugs": {
+    "url": "https://github.com/esengine/reasonix/issues"
+  },
+  "homepage": "https://github.com/esengine/reasonix#readme",
+  "engines": {
+    "node": ">=20.10"
+  },
+  "dependencies": {
+    "commander": "^12.1.0",
+    "eventsource-parser": "^3.0.0",
+    "ink": "^5.1.0",
+    "ink-spinner": "^5.0.0",
+    "ink-text-input": "^6.0.0",
+    "react": "^18.3.1"
+  },
+  "devDependencies": {
+    "@biomejs/biome": "^1.9.4",
+    "@types/node": "^22.9.0",
+    "@types/react": "^18.3.12",
+    "tsup": "^8.3.5",
+    "tsx": "^4.19.2",
+    "typescript": "^5.6.3",
+    "vitest": "^2.1.5"
+  }
+}

scripts/ctrlc-probe.mjs

@@ -0,0 +1,28 @@
+// Minimal Ctrl+C probe. Usage: node scripts/ctrlc-probe.mjs
+// Reproduces the exact stdin setup Reasonix uses, then logs every byte
+// it sees and exits on \x03. Tells us whether the OS even delivers
+// Ctrl+C to a Node child on this terminal.
+
+process.stdin.setRawMode(true);
+process.stdin.setEncoding("utf8");
+process.stdin.resume();
+
+console.log("ctrl+c probe armed. press keys; ctrl+c should exit.");
+console.log("if ctrl+c does NOT exit, the byte never reaches Node on this terminal.\n");
+
+process.stdin.on("data", (chunk) => {
+  const s = String(chunk);
+  for (const ch of s) {
+    const code = ch.charCodeAt(0);
+    process.stdout.write(`got byte: 0x${code.toString(16).padStart(2, "0")} (${JSON.stringify(ch)})\r\n`);
+    if (ch === "\x03") {
+      process.stdout.write("→ \\x03 detected, exiting.\r\n");
+      process.exit(0);
+    }
+  }
+});
+
+process.on("SIGINT", () => {
+  process.stdout.write("→ SIGINT received, exiting.\r\n");
+  process.exit(0);
+});

scripts/prepare-tokenizer.ts

@@ -0,0 +1,34 @@
+#!/usr/bin/env node
+/**
+ * Regenerate `data/deepseek-tokenizer.json.gz` from an upstream
+ * `tokenizer.json` (as shipped in DeepSeek's deepseek_v3_tokenizer.zip).
+ *
+ * Why slim+gz: the full tokenizer.json is 7.5MB; we only need four
+ * fields (vocab, merges, pre_tokenizer, added_tokens). Strip + gzip
+ * drops the committed artifact to ~1.7MB with no loss of fidelity
+ * for encode-side token counting.
+ *
+ * Usage: `node --experimental-strip-types scripts/prepare-tokenizer.ts <path/to/tokenizer.json>`
+ * (or via `tsx` / `ts-node`.)
+ */
+
+import { readFileSync, writeFileSync } from "node:fs";
+import { join } from "node:path";
+import { gzipSync } from "node:zlib";
+
+const src = process.argv[2];
+if (!src) {
+  process.stderr.write("usage: prepare-tokenizer.ts <tokenizer.json>\n");
+  process.exit(2);
+}
+
+const raw = JSON.parse(readFileSync(src, "utf8"));
+const slim = {
+  added_tokens: raw.added_tokens,
+  pre_tokenizer: raw.pre_tokenizer,
+  model: { type: raw.model.type, vocab: raw.model.vocab, merges: raw.model.merges },
+};
+const gz = gzipSync(Buffer.from(JSON.stringify(slim)), { level: 9 });
+const outPath = join(process.cwd(), "data", "deepseek-tokenizer.json.gz");
+writeFileSync(outPath, gz);
+process.stdout.write(`wrote ${outPath} (${(gz.length / 1024).toFixed(1)} KB)\n`);

scripts/shift-enter-probe.mjs

@@ -0,0 +1,30 @@
+// Shift+Enter probe. Usage: node scripts/shift-enter-probe.mjs
+// Enables modifyOtherKeys + kitty keyboard protocol, then prints the
+// raw bytes for every keypress. Press Shift+Enter and see what your
+// terminal actually emits — if it's just "0x0d", the host doesn't
+// support either protocol and there's nothing Reasonix can do at the
+// raw-stdin layer.
+
+process.stdout.write("\u001b[>4;2m"); // modifyOtherKeys level 2 (xterm)
+process.stdout.write("\u001b[>1u"); // kitty keyboard protocol level 1
+
+process.stdin.setRawMode(true);
+process.stdin.setEncoding("utf8");
+process.stdin.resume();
+
+console.log("shift+enter probe armed. press keys; ctrl+c exits.");
+console.log("expected for shift+enter:");
+console.log("  modifyOtherKeys → 0x1b 0x5b 0x32 0x37 0x3b 0x32 0x3b 0x31 0x33 0x7e  (\\x1b[27;2;13~)");
+console.log("  kitty           → 0x1b 0x5b 0x31 0x33 0x3b 0x32 0x75              (\\x1b[13;2u)");
+console.log("  unsupported     → 0x0d                                              (just \\r — no way to distinguish)\n");
+
+process.stdin.on("data", (chunk) => {
+  const s = String(chunk);
+  const bytes = [...s].map((c) => `0x${c.charCodeAt(0).toString(16).padStart(2, "0")}`).join(" ");
+  process.stdout.write(`got: ${bytes}    (${JSON.stringify(s)})\r\n`);
+  if (s.includes("\x03")) {
+    process.stdout.write("\u001b[>4m"); // disable modifyOtherKeys
+    process.stdout.write("\u001b[<u"); // pop kitty level
+    process.exit(0);
+  }
+});

scripts/smoke-memory.mts

@@ -0,0 +1,192 @@
+/**
+ * End-to-end smoke test for the memory layer. Runs against a temp
+ * homeDir so the developer's real ~/.reasonix/memory/ is never touched.
+ * Exercises: write → index regeneration → prefix assembly →
+ * recall → delete → REASONIX_MEMORY=off short-circuit.
+ *
+ * Run: npx tsx scripts/smoke-memory.mts
+ * Exit code 0 on success, 1 on any assertion failure.
+ */
+
+import { existsSync, mkdtempSync, readFileSync, rmSync, writeFileSync } from "node:fs";
+import { tmpdir } from "node:os";
+import { join } from "node:path";
+import { ToolRegistry } from "../src/tools.js";
+import { registerMemoryTools } from "../src/tools/memory.js";
+import {
+  MemoryStore,
+  applyMemoryStack,
+  applyUserMemory,
+  projectHash,
+} from "../src/user-memory.js";
+
+let failures = 0;
+function check(label: string, cond: unknown, detail?: string) {
+  if (cond) {
+    process.stdout.write(`  ✓ ${label}\n`);
+  } else {
+    failures++;
+    process.stdout.write(`  ✗ ${label}${detail ? `  — ${detail}` : ""}\n`);
+  }
+}
+
+async function main() {
+  const home = mkdtempSync(join(tmpdir(), "reasonix-smoke-home-"));
+  const projectRoot = mkdtempSync(join(tmpdir(), "reasonix-smoke-proj-"));
+  process.stdout.write(`home:    ${home}\nproject: ${projectRoot}\n\n`);
+
+  try {
+    // ── 1. MemoryStore write + index regeneration ────────────────────
+    process.stdout.write("1. MemoryStore write → index regen\n");
+    const store = new MemoryStore({ homeDir: home, projectRoot });
+    store.write({
+      name: "bun_build",
+      type: "project",
+      scope: "project",
+      description: "Build command on this machine is `bun run build`",
+      body: "On this machine, no npm — always `bun run build` / `bun run test`.",
+    });
+    store.write({
+      name: "tabs_not_spaces",
+      type: "user",
+      scope: "global",
+      description: "Use tabs for indentation across all projects",
+      body: "Rule.\n\n**Why:** muscle memory, editor config across machines.\n\n**How to apply:** always tabs.",
+    });
+
+    const hash = projectHash(projectRoot);
+    const projectFile = join(home, "memory", hash, "bun_build.md");
+    const globalFile = join(home, "memory", "global", "tabs_not_spaces.md");
+    check("project-scoped file landed in <hash>/ dir", existsSync(projectFile));
+    check("global-scoped file landed in global/ dir", existsSync(globalFile));
+    check("no cross-contamination project ⇒ global", !existsSync(join(home, "memory", "global", "bun_build.md")));
+
+    const projectIndex = readFileSync(join(home, "memory", hash, "MEMORY.md"), "utf8");
+    check("project MEMORY.md points at bun_build.md", projectIndex.includes("[bun_build](bun_build.md)"));
+    const globalIndex = readFileSync(join(home, "memory", "global", "MEMORY.md"), "utf8");
+    check("global MEMORY.md points at tabs_not_spaces.md", globalIndex.includes("[tabs_not_spaces](tabs_not_spaces.md)"));
+
+    const raw = readFileSync(projectFile, "utf8");
+    check("frontmatter has name/type/scope/created", /^---\nname: bun_build\n/.test(raw) && /type: project/.test(raw) && /scope: project/.test(raw) && /created: \d{4}-\d{2}-\d{2}/.test(raw));
+
+    // ── 2. Prefix assembly via applyMemoryStack (+ REASONIX.md) ────────
+    process.stdout.write("\n2. Prefix assembly (REASONIX.md + user memory)\n");
+    writeFileSync(join(projectRoot, "REASONIX.md"), "# Project notes\nPrefer explicit types over inference.\n", "utf8");
+    const BASE = "You are a test assistant.";
+    const withProjOnly = applyUserMemory(BASE, { homeDir: home, projectRoot });
+    check("applyUserMemory contains global block", withProjOnly.includes("# User memory — global"));
+    check("applyUserMemory contains project block", withProjOnly.includes("# User memory — this project"));
+    check("bun_build description present in prefix", withProjOnly.includes("bun run build"));
+    check("tabs_not_spaces description present in prefix", withProjOnly.includes("Use tabs for indentation"));
+
+    // Order: base → (REASONIX.md would go first via applyMemoryStack) → global → project
+    const ordered = applyUserMemory(BASE, { homeDir: home, projectRoot });
+    const iGlobalBlock = ordered.indexOf("# User memory — global");
+    const iProjBlock = ordered.indexOf("# User memory — this project");
+    check("global block precedes project block (stable for cache)", iGlobalBlock > 0 && iGlobalBlock < iProjBlock);
+
+    // Determinism — two calls with same state produce byte-identical prompts.
+    const a = applyUserMemory(BASE, { homeDir: home, projectRoot });
+    const b = applyUserMemory(BASE, { homeDir: home, projectRoot });
+    check("applyUserMemory is deterministic (byte-stable)", a === b);
+
+    // ── 3. The `remember` / `recall_memory` / `forget` tools ───────────
+    process.stdout.write("\n3. Tool dispatch (remember / recall / forget)\n");
+    const reg = new ToolRegistry();
+    registerMemoryTools(reg, { homeDir: home, projectRoot });
+    check("remember tool registered", reg.has("remember"));
+    check("forget tool registered", reg.has("forget"));
+    check("recall_memory tool registered", reg.has("recall_memory"));
+    check("recall_memory is readOnly (plan-mode safe)", reg.get("recall_memory")?.readOnly === true);
+    check("remember is NOT readOnly (plan-mode blocked)", reg.get("remember")?.readOnly !== true);
+
+    const remOut = await reg.dispatch("remember", {
+      type: "feedback",
+      scope: "global",
+      name: "prefers_short_replies",
+      description: "User wants terse answers, no trailing summaries",
+      content: "Default to terse. If the user wants detail they'll ask.",
+    });
+    check("remember returns a confirmation (not an error)", remOut.includes("REMEMBERED (global/prefers_short_replies)"), remOut);
+
+    const recallOut = await reg.dispatch("recall_memory", {
+      scope: "global",
+      name: "prefers_short_replies",
+    });
+    check("recall_memory returns the body", recallOut.includes("Default to terse"));
+
+    const forgetOut = await reg.dispatch("forget", {
+      scope: "global",
+      name: "prefers_short_replies",
+    });
+    check("forget returns a confirmation", forgetOut.includes("forgot (global/prefers_short_replies)"));
+    check("recall_memory after forget returns an error", (await reg.dispatch("recall_memory", { scope: "global", name: "prefers_short_replies" })).includes("error"));
+
+    // ── 4. Project scope refused when projectRoot is absent ────────────
+    process.stdout.write("\n4. Chat-mode (no projectRoot) refuses project scope\n");
+    const chatReg = new ToolRegistry();
+    registerMemoryTools(chatReg, { homeDir: home });
+    const projInChat = await chatReg.dispatch("remember", {
+      type: "project",
+      scope: "project",
+      name: "should_fail",
+      description: "d",
+      content: "c",
+    });
+    check("scope='project' in chat mode → error payload", projInChat.includes("error") && projInChat.includes("project"));
+    const globalInChat = await chatReg.dispatch("remember", {
+      type: "user",
+      scope: "global",
+      name: "global_from_chat",
+      description: "works across projects",
+      content: "body",
+    });
+    check("scope='global' in chat mode → writes successfully", globalInChat.includes("REMEMBERED (global/"));
+
+    // ── 5. REASONIX_MEMORY=off short-circuit ───────────────────────────
+    process.stdout.write("\n5. REASONIX_MEMORY=off opt-out\n");
+    process.env.REASONIX_MEMORY = "off";
+    try {
+      const silenced = applyUserMemory(BASE, { homeDir: home, projectRoot });
+      check("applyUserMemory returns BASE unchanged when off", silenced === BASE);
+      const fullStack = applyMemoryStack(BASE, projectRoot);
+      check("applyMemoryStack returns BASE unchanged when off (REASONIX.md also skipped)", fullStack === BASE);
+    } finally {
+      delete process.env.REASONIX_MEMORY;
+    }
+
+    // ── 6. Delete regeneration: MEMORY.md matches current file set ─────
+    process.stdout.write("\n6. Delete + index regeneration\n");
+    store.delete("global", "tabs_not_spaces");
+    store.delete("global", "global_from_chat");
+    const globalIdxAfter = join(home, "memory", "global", "MEMORY.md");
+    check("global MEMORY.md removed when last file deleted", !existsSync(globalIdxAfter));
+    const projectIdxStill = readFileSync(join(home, "memory", hash, "MEMORY.md"), "utf8");
+    check("project MEMORY.md untouched (different scope)", projectIdxStill.includes("bun_build"));
+
+    // ── 7. Name-sanitization boundary ──────────────────────────────────
+    process.stdout.write("\n7. Name sanitization (path-traversal refused)\n");
+    const badOut = await reg.dispatch("remember", {
+      type: "user",
+      scope: "global",
+      name: "../../etc/passwd",
+      description: "d",
+      content: "c",
+    });
+    check("remember refuses path-traversal name", badOut.includes("invalid memory name"));
+    const outsideFile = join(home, "etc", "passwd.md");
+    check("no file written outside the memory dir", !existsSync(outsideFile));
+
+    process.stdout.write(`\n${failures === 0 ? "✅ all smoke checks passed" : `❌ ${failures} failure(s)`}\n`);
+  } finally {
+    rmSync(home, { recursive: true, force: true });
+    rmSync(projectRoot, { recursive: true, force: true });
+  }
+
+  process.exit(failures === 0 ? 0 : 1);
+}
+
+main().catch((err) => {
+  console.error(err);
+  process.exit(1);
+});

src/at-mentions.ts

@@ -0,0 +1,397 @@
+/**
+ * Expand `@path/to/file` mentions in a user prompt to inline file
+ * content.
+ *
+ * Why: most interactive coding sessions start with "look at X, then
+ * change Y". Typing `@src/loop.ts` reads faster and cheaper than
+ * "look at src/loop.ts (and the model fires read_file, and we pay for
+ * the round trip)" — the model sees the file content from turn 1
+ * instead of round-tripping a tool call for it.
+ *
+ * Shape: the user's text is kept verbatim. Expanded file contents are
+ * appended in a "Referenced files" block at the end, each wrapped in
+ * `<file path="...">...</file>` so the model can cite them back
+ * unambiguously.
+ *
+ * Safety: paths must resolve inside `rootDir` (no `..` escape, no
+ * absolute paths), must exist as a regular file, and must be under
+ * `maxBytes`. Missing / too-large / escaping paths get a short note
+ * appended instead of content so the user sees why it was skipped.
+ */
+
+import { type Dirent, existsSync, readFileSync, readdirSync, statSync } from "node:fs";
+import { isAbsolute, join, relative, resolve } from "node:path";
+
+/** Caps match tool-result dispatch truncation (0.5.2). */
+export const DEFAULT_AT_MENTION_MAX_BYTES = 64 * 1024;
+
+/**
+ * Default directory names skipped when listing files for the picker.
+ * Matches what most repos gitignore AND keeps the picker off the
+ * hottest bloat — `node_modules` alone can be 100k+ entries.
+ */
+export const DEFAULT_PICKER_IGNORE_DIRS: readonly string[] = [
+  "node_modules",
+  ".git",
+  "dist",
+  "build",
+  ".next",
+  "out",
+  "coverage",
+  ".cache",
+  ".vscode",
+  ".idea",
+  "target",
+  ".venv",
+  "venv",
+  "__pycache__",
+];
+
+export interface ListFilesOptions {
+  /** Cap the walk once we've collected this many entries. Default 500. */
+  maxResults?: number;
+  /** Directory names to skip entirely. Defaults to {@link DEFAULT_PICKER_IGNORE_DIRS}. */
+  ignoreDirs?: readonly string[];
+}
+
+/**
+ * Walk `root` recursively and return relative file paths (forward-slash
+ * separator, regardless of platform) for the `@` picker.
+ *
+ * Synchronous on purpose: this runs once at App mount (and on each turn
+ * so newly-created files show up) and blocks the render thread for a
+ * predictable ~10-50ms on a moderate repo. An async variant would need
+ * to coordinate with the Ink render loop; sync fits the rest of the
+ * TUI's single-turn-per-tick model cleanly.
+ *
+ * Skips:
+ *   - directories in `ignoreDirs` (default: DEFAULT_PICKER_IGNORE_DIRS)
+ *   - any directory whose name starts with `.` (covers `.git`,
+ *     `.vscode`, dotfile vendors). Dotfile REGULAR FILES (`.env`,
+ *     `.gitignore`, `.prettierrc`) are kept — users reference them.
+ *   - entries the walker can't read (permission errors, broken links).
+ */
+export function listFilesSync(root: string, opts: ListFilesOptions = {}): string[] {
+  return listFilesWithStatsSync(root, opts).map((e) => e.path);
+}
+
+export interface FileWithStats {
+  /** Relative path with forward-slash separator. */
+  path: string;
+  /** Modification time (Date.getTime() / ms since epoch). 0 when stat failed. */
+  mtimeMs: number;
+}
+
+/**
+ * Same walk as {@link listFilesSync} but also statS each file for
+ * modification time. Used by the `@` picker to surface recently-
+ * edited files first — matches VS Code Quick Open / similar UX.
+ *
+ * Stat failures don't throw: the entry is kept with `mtimeMs: 0` so
+ * it still appears in the picker (just sinks to the bottom of the
+ * recency sort).
+ */
+export function listFilesWithStatsSync(root: string, opts: ListFilesOptions = {}): FileWithStats[] {
+  const maxResults = Math.max(1, opts.maxResults ?? 500);
+  const ignore = new Set(opts.ignoreDirs ?? DEFAULT_PICKER_IGNORE_DIRS);
+  const rootAbs = resolve(root);
+  const out: FileWithStats[] = [];
+
+  const walk = (dirAbs: string, dirRel: string) => {
+    if (out.length >= maxResults) return;
+    let entries: Dirent[];
+    try {
+      entries = readdirSync(dirAbs, { withFileTypes: true });
+    } catch {
+      return;
+    }
+    entries.sort((a, b) => a.name.localeCompare(b.name));
+    for (const ent of entries) {
+      if (out.length >= maxResults) return;
+      const relPath = dirRel ? `${dirRel}/${ent.name}` : ent.name;
+      if (ent.isDirectory()) {
+        if (ent.name.startsWith(".") || ignore.has(ent.name)) continue;
+        walk(join(dirAbs, ent.name), relPath);
+      } else if (ent.isFile()) {
+        let mtimeMs = 0;
+        try {
+          mtimeMs = statSync(join(dirAbs, ent.name)).mtimeMs;
+        } catch {
+          /* stat failed (permission / EAGAIN) — keep the entry with mtime=0 */
+        }
+        out.push({ path: relPath, mtimeMs });
+      }
+    }
+  };
+
+  walk(rootAbs, "");
+  return out;
+}
+
+/**
+ * Prefix pattern used by the `@` picker to detect an IN-PROGRESS
+ * mention at the END of the input buffer. Captures the partial path
+ * (which may be empty — just `@`) so the picker can use it as a
+ * substring filter.
+ *
+ * Distinct from {@link AT_MENTION_PATTERN} (which finds completed
+ * mentions anywhere in the text for expansion-at-submit). This one
+ * fires on the trailing token only, anchored at end-of-input.
+ */
+export const AT_PICKER_PREFIX = /(?:^|\s)@([a-zA-Z0-9_./\\-]*)$/;
+
+/**
+ * Return the picker state for a given input buffer: the partial query
+ * (may be empty string — just `@`) and the buffer offset of the `@`
+ * character. `null` when the buffer doesn't end in a mention-in-
+ * progress.
+ */
+export function detectAtPicker(input: string): { query: string; atOffset: number } | null {
+  const m = AT_PICKER_PREFIX.exec(input);
+  if (!m) return null;
+  const query = m[1] ?? "";
+  // `m.index` is the offset of the capture group's SURROUNDING match —
+  // which starts at either ^ or the preceding whitespace. The `@`
+  // itself is at `end-of-input - query.length - 1`.
+  const atOffset = input.length - query.length - 1;
+  return { query, atOffset };
+}
+
+/** A candidate accepted by the picker ranker — either a bare path or a path with mtime. */
+export type PickerCandidate = string | FileWithStats;
+
+export interface RankPickerOptions {
+  /** Upper bound on returned entries. Default 40. */
+  limit?: number;
+  /**
+   * Paths the user or model has touched recently (via tool calls like
+   * `read_file` / `edit_file`). Matching paths get a recency boost so
+   * the picker surfaces "stuff I just looked at" near the top.
+   */
+  recentlyUsed?: readonly string[];
+}
+
+/**
+ * Filter and rank candidate files against the picker's partial query.
+ *
+ * Empty query:
+ *   - Sort by "recently used" bucket first (if provided), then mtime
+ *     descending (newer first), then path alpha.
+ *   - Pure-string input (no mtime data) falls back to alpha since
+ *     recency info isn't available.
+ *
+ * Non-empty query:
+ *   - Case-insensitive substring match, with a basename-prefix boost
+ *     so `lo` floats `loop.ts`-shaped paths to the top.
+ *   - Ties broken first by recently-used membership, then mtime.
+ *
+ * Back-compat: passes `string[]` through the same logic (mtime = 0,
+ * recently-used still honored).
+ */
+export function rankPickerCandidates(
+  files: readonly PickerCandidate[],
+  query: string,
+  limitOrOpts?: number | RankPickerOptions,
+): string[] {
+  const opts: RankPickerOptions =
+    typeof limitOrOpts === "number" ? { limit: limitOrOpts } : (limitOrOpts ?? {});
+  const limit = opts.limit ?? 40;
+  const recent = new Set(opts.recentlyUsed ?? []);
+
+  const entries: FileWithStats[] = files.map((f) =>
+    typeof f === "string" ? { path: f, mtimeMs: 0 } : f,
+  );
+
+  if (!query) {
+    // Only re-sort when we actually have signal to sort by. If input
+    // is bare strings (mtime = 0 everywhere) AND there's no recent-
+    // used list, preserve input order so callers keep their existing
+    // layout. Passing FileWithStats or a non-empty recentlyUsed opts
+    // you into mtime+recency ranking.
+    const anyMtime = entries.some((e) => e.mtimeMs > 0);
+    if (!anyMtime && recent.size === 0) {
+      return entries.slice(0, limit).map((e) => e.path);
+    }
+    const sorted = [...entries].sort((a, b) => {
+      const aRecent = recent.has(a.path) ? 1 : 0;
+      const bRecent = recent.has(b.path) ? 1 : 0;
+      if (aRecent !== bRecent) return bRecent - aRecent;
+      if (a.mtimeMs !== b.mtimeMs) return b.mtimeMs - a.mtimeMs;
+      return a.path.localeCompare(b.path);
+    });
+    return sorted.slice(0, limit).map((e) => e.path);
+  }
+
+  const needle = query.toLowerCase();
+  const scored: Array<{ path: string; score: number; mtimeMs: number; recent: boolean }> = [];
+  for (const e of entries) {
+    const lower = e.path.toLowerCase();
+    const hit = lower.indexOf(needle);
+    if (hit < 0) continue;
+    const slash = lower.lastIndexOf("/");
+    const base = slash >= 0 ? lower.slice(slash + 1) : lower;
+    let score = 2;
+    if (base.startsWith(needle)) score = 0;
+    else if (lower.startsWith(needle)) score = 1;
+    scored.push({
+      path: e.path,
+      score: score * 10_000 + hit,
+      mtimeMs: e.mtimeMs,
+      recent: recent.has(e.path),
+    });
+  }
+  scored.sort((a, b) => {
+    if (a.score !== b.score) return a.score - b.score;
+    // Tie-break: recently-used, then mtime (newer first).
+    if (a.recent !== b.recent) return a.recent ? -1 : 1;
+    return b.mtimeMs - a.mtimeMs;
+  });
+  return scored.slice(0, limit).map((s) => s.path);
+}
+
+/**
+ * Matches `@` at a word boundary (start-of-string or preceded by
+ * whitespace) followed by a path-like token. Deliberately rejects `@`
+ * embedded in longer words (email addresses, mentions on social sites)
+ * by requiring the word boundary.
+ *
+ * Path charset keeps it to the characters that appear in real repo
+ * paths — letters, digits, `_` `-` `.` `/` `\`. Trailing `.` (e.g.
+ * `@foo.ts.`) is stripped before lookup so a sentence-terminating
+ * period doesn't break the mention.
+ */
+export const AT_MENTION_PATTERN = /(?<=^|\s)@([a-zA-Z0-9_./\\-]+)/g;
+
+export interface AtMentionExpansion {
+  /** The raw `@path` token as it appeared in the text. */
+  token: string;
+  /** The relative path, as resolved against rootDir. */
+  path: string;
+  /** True if the content was inlined. False = skipped (reason in `skip`). */
+  ok: boolean;
+  /** Bytes read (only for ok=true). */
+  bytes?: number;
+  /** Why the mention was skipped. Set when ok=false. */
+  skip?: "missing" | "not-file" | "too-large" | "escape" | "read-error";
+}
+
+export interface AtMentionOptions {
+  /** Max file size in bytes before a mention is skipped. */
+  maxBytes?: number;
+  /**
+   * Optional file-system overrides for tests. Real callers omit these;
+   * the helper falls through to `node:fs`.
+   */
+  fs?: {
+    exists: (path: string) => boolean;
+    isFile: (path: string) => boolean;
+    size: (path: string) => number;
+    read: (path: string) => string;
+  };
+}
+
+/**
+ * Expand `@path` mentions in `text`. Returns the (possibly augmented)
+ * text plus a per-mention report so the caller can surface expansions
+ * in the UI.
+ */
+export function expandAtMentions(
+  text: string,
+  rootDir: string,
+  opts: AtMentionOptions = {},
+): { text: string; expansions: AtMentionExpansion[] } {
+  const maxBytes = opts.maxBytes ?? DEFAULT_AT_MENTION_MAX_BYTES;
+  const fs = opts.fs ?? defaultFs;
+  const root = resolve(rootDir);
+  // De-dupe by token so `@file.ts` referenced twice inlines once.
+  const seen = new Map<string, AtMentionExpansion>();
+  const expansions: AtMentionExpansion[] = [];
+
+  for (const match of text.matchAll(AT_MENTION_PATTERN)) {
+    const rawPath = match[1] ?? "";
+    // Strip trailing dot (sentence terminator): `@foo.ts.` → `@foo.ts`.
+    // Keep internal dots intact.
+    const cleaned = rawPath.replace(/\.+$/, "");
+    if (!cleaned) continue;
+    const token = `@${cleaned}`;
+    if (seen.has(token)) continue;
+
+    const expansion = resolveMention(cleaned, root, maxBytes, fs);
+    seen.set(token, expansion);
+    expansions.push(expansion);
+  }
+
+  if (expansions.length === 0) return { text, expansions };
+
+  // Build the trailing "Referenced files" block. Keep successful
+  // inlines and skipped ones (with their reason) so the model sees
+  // both what's here and what's missing.
+  const blocks: string[] = [];
+  for (const ex of expansions) {
+    if (ex.ok) {
+      const content = readSafe(root, ex.path, fs);
+      blocks.push(`<file path="${ex.path}">\n${content}\n</file>`);
+    } else {
+      blocks.push(`<file path="${ex.path}" skipped="${ex.skip}" />`);
+    }
+  }
+  const augmented = `${text}\n\n[Referenced files]\n${blocks.join("\n\n")}`;
+  return { text: augmented, expansions };
+}
+
+function resolveMention(
+  rawPath: string,
+  root: string,
+  maxBytes: number,
+  fs: NonNullable<AtMentionOptions["fs"]>,
+): AtMentionExpansion {
+  // Reject absolute paths — `@/etc/passwd` should not inline.
+  if (isAbsolute(rawPath)) {
+    return { token: `@${rawPath}`, path: rawPath, ok: false, skip: "escape" };
+  }
+  const resolved = resolve(root, rawPath);
+  // Sandbox escape: after resolution the path must still be inside root.
+  const rel = relative(root, resolved);
+  if (rel.startsWith("..") || isAbsolute(rel)) {
+    return { token: `@${rawPath}`, path: rawPath, ok: false, skip: "escape" };
+  }
+  if (!fs.exists(resolved)) {
+    return { token: `@${rawPath}`, path: rawPath, ok: false, skip: "missing" };
+  }
+  if (!fs.isFile(resolved)) {
+    return { token: `@${rawPath}`, path: rawPath, ok: false, skip: "not-file" };
+  }
+  const size = fs.size(resolved);
+  if (size > maxBytes) {
+    return { token: `@${rawPath}`, path: rawPath, ok: false, skip: "too-large", bytes: size };
+  }
+  return { token: `@${rawPath}`, path: rawPath, ok: true, bytes: size };
+}
+
+function readSafe(root: string, rawPath: string, fs: NonNullable<AtMentionOptions["fs"]>): string {
+  const resolved = resolve(root, rawPath);
+  try {
+    return fs.read(resolved);
+  } catch {
+    return "(read failed)";
+  }
+}
+
+const defaultFs: NonNullable<AtMentionOptions["fs"]> = {
+  exists: (p) => existsSync(p),
+  isFile: (p) => {
+    try {
+      return statSync(p).isFile();
+    } catch {
+      return false;
+    }
+  },
+  size: (p) => {
+    try {
+      return statSync(p).size;
+    } catch {
+      return 0;
+    }
+  },
+  read: (p) => readFileSync(p, "utf8"),
+};

src/cli/commands/chat.tsx

@@ -0,0 +1,351 @@
+import { existsSync, statSync } from "node:fs";
+import { render } from "ink";
+import React, { useState } from "react";
+import { loadApiKey, searchEnabled } from "../../config.js";
+import { loadDotenv } from "../../env.js";
+import { McpClient } from "../../mcp/client.js";
+import { type InspectionReport, inspectMcpServer } from "../../mcp/inspect.js";
+import { bridgeMcpTools } from "../../mcp/registry.js";
+import { parseMcpSpec } from "../../mcp/spec.js";
+import { SseTransport } from "../../mcp/sse.js";
+import { type McpTransport, StdioTransport } from "../../mcp/stdio.js";
+import {
+  loadSessionMessages,
+  rewriteSession,
+  sessionPath as sessionPathOf,
+} from "../../session.js";
+import { ToolRegistry } from "../../tools.js";
+import { registerChoiceTool } from "../../tools/choice.js";
+import { registerMemoryTools } from "../../tools/memory.js";
+import { registerWebTools } from "../../tools/web.js";
+import { App } from "../ui/App.js";
+import { SessionPicker } from "../ui/SessionPicker.js";
+import { Setup } from "../ui/Setup.js";
+import { KeystrokeProvider } from "../ui/keystroke-context.js";
+import type { McpServerSummary } from "../ui/slash.js";
+
+export interface ProgressInfo {
+  toolName: string;
+  progress: number;
+  total?: number;
+  message?: string;
+}
+
+export interface ChatOptions {
+  model: string;
+  system: string;
+  transcript?: string;
+  harvest?: boolean;
+  branch?: number;
+  session?: string;
+  /** Zero or more MCP server specs. Each: `"name=cmd args..."` or `"cmd args..."`. */
+  mcp?: string[];
+  /** Global prefix — only used when a single anonymous server is given. */
+  mcpPrefix?: string;
+  /**
+   * Pre-built ToolRegistry used as a seed. MCP bridges (if any) are
+   * layered on top of whatever's already registered. Used by
+   * `reasonix code` to register native filesystem tools in place of
+   * the old `npx -y @modelcontextprotocol/server-filesystem` subprocess.
+   */
+  seedTools?: ToolRegistry;
+  /**
+   * Enable SEARCH/REPLACE edit-block processing after each assistant turn.
+   * Set by `reasonix code`; plain `reasonix chat` leaves this off.
+   */
+  codeMode?: { rootDir: string; jobs?: import("../../tools/jobs.js").JobRegistry };
+  /** Skip the session picker — assume "Resume" (backwards-compatible auto-continue). */
+  forceResume?: boolean;
+  /** Skip the session picker — assume "New" (wipe the session file and start fresh). */
+  forceNew?: boolean;
+}
+
+interface RootProps extends ChatOptions {
+  initialKey: string | undefined;
+  tools: ToolRegistry | undefined;
+  mcpSpecs: string[];
+  mcpServers: McpServerSummary[];
+  /**
+   * Shared ref the bridge's `onProgress` callback writes through.
+   * App sets `.current` to its own handler on mount so every
+   * progress frame from any bridged tool lands in the UI's
+   * `OngoingToolRow`. Ref keeps the wire-up synchronous with
+   * React reconciliation (no effect-timing surprises).
+   */
+  progressSink: { current: ((info: ProgressInfo) => void) | null };
+  /** Present when the session has prior messages; drives the picker. */
+  sessionPreview?: { messageCount: number; lastActive: Date };
+}
+
+function Root({
+  initialKey,
+  tools,
+  mcpSpecs,
+  mcpServers,
+  progressSink,
+  sessionPreview,
+  ...appProps
+}: RootProps) {
+  const [key, setKey] = useState<string | undefined>(initialKey);
+  // `null` once the picker is resolved (or was never needed). Starts as
+  // the preview so we can render the picker once before mounting App.
+  const [pending, setPending] = useState<typeof sessionPreview>(sessionPreview);
+
+  if (!key) {
+    return (
+      <Setup
+        onReady={(k) => {
+          process.env.DEEPSEEK_API_KEY = k;
+          setKey(k);
+        }}
+      />
+    );
+  }
+  process.env.DEEPSEEK_API_KEY = key;
+
+  // KeystrokeProvider must wrap App from OUTSIDE — App.tsx itself
+  // calls `useKeystroke` in its function body for global hotkeys
+  // (Ctrl+C, Esc abort, Shift+Tab edit-mode cycle, @-mention picker,
+  // slash-suggestion navigation). If the provider lives inside App's
+  // render, `useContext(KeystrokeContext)` returns `null` at hook
+  // call time and those handlers silently never subscribe.
+  if (pending && appProps.session) {
+    return (
+      <KeystrokeProvider>
+        <SessionPicker
+          sessionName={appProps.session}
+          messageCount={pending.messageCount}
+          lastActive={pending.lastActive}
+          onChoose={(choice) => {
+            if (choice === "new" || choice === "delete") {
+              // Wipe the session file. "new" and "delete" do the same thing
+              // at this step — the distinction is only in the picker's
+              // wording. A future enhancement could archive on "new".
+              rewriteSession(appProps.session!, []);
+            }
+            setPending(undefined);
+          }}
+        />
+      </KeystrokeProvider>
+    );
+  }
+
+  return (
+    <KeystrokeProvider>
+      <App
+        model={appProps.model}
+        system={appProps.system}
+        transcript={appProps.transcript}
+        harvest={appProps.harvest}
+        branch={appProps.branch}
+        session={appProps.session}
+        tools={tools}
+        mcpSpecs={mcpSpecs}
+        mcpServers={mcpServers}
+        progressSink={progressSink}
+        codeMode={appProps.codeMode}
+      />
+    </KeystrokeProvider>
+  );
+}
+
+export async function chatCommand(opts: ChatOptions): Promise<void> {
+  loadDotenv();
+  const initialKey = loadApiKey();
+
+  const requestedSpecs = opts.mcp ?? [];
+  const clients: McpClient[] = [];
+  const successfulSpecs: string[] = [];
+  const failedSpecs: Array<{ spec: string; reason: string }> = [];
+  const mcpServers: McpServerSummary[] = [];
+  // Shared progress sink: the bridge's onProgress callback writes
+  // through `progressSink.current`, which App.tsx sets to its UI
+  // updater on mount. Started null so early progress frames (before
+  // the App has mounted) are dropped rather than buffered.
+  const progressSink: { current: ((info: ProgressInfo) => void) | null } = { current: null };
+  // Seed registry from the caller (e.g. reasonix code's native
+  // filesystem tools) — MCP bridges layer on top rather than
+  // replacing. When no seed AND no MCP, tools stays undefined and
+  // the loop runs as a bare chat.
+  let tools: ToolRegistry | undefined = opts.seedTools;
+
+  if (requestedSpecs.length > 0) {
+    if (!tools) tools = new ToolRegistry();
+    for (const raw of requestedSpecs) {
+      try {
+        const spec = parseMcpSpec(raw);
+        const prefix = spec.name
+          ? `${spec.name}_`
+          : requestedSpecs.length === 1 && opts.mcpPrefix
+            ? opts.mcpPrefix
+            : "";
+        const transport: McpTransport =
+          spec.transport === "sse"
+            ? new SseTransport({ url: spec.url })
+            : new StdioTransport({ command: spec.command, args: spec.args });
+        const mcp = new McpClient({ transport });
+        await mcp.initialize();
+        const bridge = await bridgeMcpTools(mcp, {
+          registry: tools,
+          namePrefix: prefix,
+          onProgress: (info) => progressSink.current?.(info),
+        });
+        // Collect resources + prompts once at startup so the /mcp
+        // slash can render them synchronously. Servers that don't
+        // support these fall through as `{supported: false}` instead
+        // of throwing — see inspectMcpServer.
+        let report: InspectionReport;
+        try {
+          report = await inspectMcpServer(mcp);
+        } catch {
+          // If the inspect call itself fails (rare — shouldn't happen
+          // since inspectMcpServer swallows -32601), synthesize a
+          // minimal report so `/mcp` still has something to render.
+          report = {
+            protocolVersion: mcp.protocolVersion,
+            serverInfo: mcp.serverInfo,
+            capabilities: mcp.serverCapabilities ?? {},
+            tools: { supported: true, items: [] },
+            resources: { supported: false, reason: "inspect failed" },
+            prompts: { supported: false, reason: "inspect failed" },
+          };
+        }
+        const label = spec.name ?? "anon";
+        const source =
+          spec.transport === "sse" ? spec.url : `${spec.command} ${spec.args.join(" ")}`;
+        process.stderr.write(
+          `▸ MCP[${label}]: ${bridge.registeredNames.length} tool(s) from ${source}\n`,
+        );
+        clients.push(mcp);
+        successfulSpecs.push(raw);
+        mcpServers.push({
+          label,
+          spec: raw,
+          toolCount: bridge.registeredNames.length,
+          report,
+          client: mcp,
+        });
+      } catch (err) {
+        // Per-server failure is non-fatal: one broken server shouldn't
+        // kill a chat that has working servers configured. We record
+        // the failure, show a visible warning, and keep going. User
+        // can fix via `reasonix setup` (unchecks the broken entry)
+        // without losing their other servers.
+        const reason = (err as Error).message;
+        failedSpecs.push({ spec: raw, reason });
+        process.stderr.write(
+          `▸ MCP setup SKIPPED for "${raw}": ${reason}\n  → this server will not be available this session. Run \`reasonix setup\` to remove it, or fix the underlying issue (missing npm package, network, etc.).\n`,
+        );
+      }
+    }
+    // If every requested server failed AND no seed registry was
+    // provided, drop the empty registry so the loop still runs as a
+    // bare chat instead of advertising zero tools. If the caller
+    // passed seedTools we keep the registry — the seed tools are
+    // still there and usable.
+    if (successfulSpecs.length === 0 && !opts.seedTools) {
+      tools = undefined;
+    }
+  }
+  const mcpSpecs = successfulSpecs;
+
+  // Register web search/fetch tools unless explicitly disabled. DDG
+  // backs them with no key required; the model invokes them whenever
+  // a question needs info fresher than its training data.
+  if (searchEnabled()) {
+    if (!tools) tools = new ToolRegistry();
+    registerWebTools(tools);
+  }
+
+  // Memory tools — available in every session, not just code mode.
+  // Chat-mode callers get global scope only; project scope requires
+  // the seedTools path from `reasonix code` (which registers its own
+  // MemoryStore bound to rootDir before chatCommand runs).
+  // `run_skill` is registered later in App.tsx (where the client
+  // exists) so it can wire the subagent runner for runAs:subagent
+  // skills.
+  if (!opts.seedTools) {
+    if (!tools) tools = new ToolRegistry();
+    registerMemoryTools(tools, {});
+    // `ask_choice` — branching primitive, useful in chat too (stylistic
+    // preferences, doc language, library picks). Independent of plan
+    // mode, which chat doesn't have anyway.
+    registerChoiceTool(tools);
+  }
+
+  // Decide whether to show the session picker. It's gated on: session
+  // persistence is on, the session file already has prior messages, and
+  // the caller didn't pre-commit to one of the choices via --resume /
+  // --new flags. `--new` wipes the file now (before the loop opens),
+  // so the App mounts against a fresh log.
+  let sessionPreview: { messageCount: number; lastActive: Date } | undefined;
+  if (opts.session && !opts.forceResume && !opts.forceNew) {
+    const prior = loadSessionMessages(opts.session);
+    if (prior.length > 0) {
+      const p = sessionPathOf(opts.session);
+      const mtime = existsSync(p) ? statSync(p).mtime : new Date();
+      sessionPreview = { messageCount: prior.length, lastActive: mtime };
+    }
+  } else if (opts.session && opts.forceNew) {
+    rewriteSession(opts.session, []);
+  }
+
+  // Stay in the user's main screen so mouse-wheel scrolls scrollback
+  // naturally. Alt-screen would fix the resize ghost-stacking but
+  // breaks wheel scroll (terminal maps wheel to ↑↓ keys for the
+  // app, which collides with PromptInput's history recall). We
+  // accept resize ghosts as a known limitation of Ink's
+  // eraseLines miscount — `/clear` is the documented workaround.
+  if (process.stdout.isTTY) {
+    process.stdout.write("\x1b[2J\x1b[3J\x1b[H");
+  }
+
+  // Resize listener — on every width change, hard-clear the visible
+  // viewport so Ink's next re-render starts at a known top-left
+  // cursor position rather than overlaying onto a stale frame whose
+  // visible row count has shifted with the new wrap. We prepend so
+  // our clear runs before Ink's own resize handler. Diagnostic
+  // print (gated on REASONIX_DEBUG_RESIZE=1) lets us verify the
+  // listener fires — necessary because at least one Windows
+  // terminal/host combination apparently does not surface the
+  // 'resize' event to Node's stdout emitter.
+  let lastCols = process.stdout.columns ?? 0;
+  const onResize = () => {
+    if (!process.stdout.isTTY) return;
+    const cols = process.stdout.columns ?? 0;
+    if (cols === lastCols) return;
+    lastCols = cols;
+    if (process.env.REASONIX_DEBUG_RESIZE) {
+      process.stderr.write(`[reasonix-debug: resize → cols=${cols}]\n`);
+    }
+    process.stdout.write("\x1b[2J\x1b[H");
+  };
+  if (process.stdout.isTTY) {
+    if (typeof process.stdout.prependListener === "function") {
+      process.stdout.prependListener("resize", onResize);
+    } else {
+      process.stdout.on("resize", onResize);
+    }
+  }
+
+  const { waitUntilExit } = render(
+    <Root
+      initialKey={initialKey}
+      tools={tools}
+      mcpSpecs={mcpSpecs}
+      mcpServers={mcpServers}
+      progressSink={progressSink}
+      sessionPreview={sessionPreview}
+      {...opts}
+    />,
+    // patchConsole:false — we never log to console during the TUI, and the
+    // patch is a known redraw-glitch source on winpty/MINTTY terminals.
+    { exitOnCtrlC: true, patchConsole: false },
+  );
+  try {
+    await waitUntilExit();
+  } finally {
+    process.stdout.removeListener("resize", onResize);
+    for (const c of clients) await c.close();
+  }
+}

src/cli/commands/code.tsx

@@ -0,0 +1,135 @@
+/**
+ * `reasonix code [dir]` — opinionated wrapper around `reasonix chat` for
+ * code-editing workflows.
+ *
+ * What it does differently from plain chat:
+ *   - Registers native filesystem tools rooted at the given directory
+ *     (CWD by default). No subprocess, no `npx install` step, R1-
+ *     friendly schemas. Replaced the old `@modelcontextprotocol/server-filesystem`
+ *     subprocess in 0.4.9 because its `edit_file` argv shape was the
+ *     biggest driver of R1 DSML hallucinations.
+ *   - Uses a coding-focused system prompt (src/code/prompt.ts) that
+ *     teaches the model to propose edits as SEARCH/REPLACE blocks.
+ *   - Defaults to the `smart` preset (reasoner + harvest) because
+ *     coding tasks pay back R1 thinking.
+ *   - Scopes its session to the directory so projects don't share
+ *     conversation history.
+ *   - Hooks `codeMode` into the TUI so assistant replies get parsed
+ *     for SEARCH/REPLACE blocks and applied on disk after each turn.
+ */
+
+import { basename, resolve } from "node:path";
+import { loadProjectShellAllowed } from "../../config.js";
+import { sanitizeName } from "../../session.js";
+import { ToolRegistry } from "../../tools.js";
+import { registerChoiceTool } from "../../tools/choice.js";
+import { registerFilesystemTools } from "../../tools/filesystem.js";
+import { JobRegistry } from "../../tools/jobs.js";
+import { registerMemoryTools } from "../../tools/memory.js";
+import { registerPlanTool } from "../../tools/plan.js";
+import { registerShellTools } from "../../tools/shell.js";
+import { chatCommand } from "./chat.js";
+
+export interface CodeOptions {
+  /** Directory to root the filesystem tools at. Defaults to process.cwd(). */
+  dir?: string;
+  /** Override the default `smart` model. */
+  model?: string;
+  /** Disable session persistence. */
+  noSession?: boolean;
+  /** Transcript file for replay/diff. */
+  transcript?: string;
+  /** Skip the session picker — always resume prior messages. */
+  forceResume?: boolean;
+  /** Skip the session picker — always wipe prior messages and start fresh. */
+  forceNew?: boolean;
+  /**
+   * Opt into Pillar 2 harvesting (extracts a typed plan state from R1
+   * reasoning via an extra V3 call). Default OFF in code mode — the
+   * displayed subgoals/hypotheses/rejectedPaths have no programmatic
+   * consumer, only `uncertainties.length` feeds branching, and the
+   * extra V3 call adds ~10-15% per-turn cost. Users who want the
+   * reasoning surfaced explicitly can pass `--harvest`.
+   */
+  harvest?: boolean;
+}
+
+export async function codeCommand(opts: CodeOptions = {}): Promise<void> {
+  const { codeSystemPrompt } = await import("../../code/prompt.js");
+  const rootDir = resolve(opts.dir ?? process.cwd());
+  // Per-directory session so switching projects doesn't mix histories.
+  // `code-<sanitized-basename>` fits the session name rules without
+  // truncating most project names.
+  const session = opts.noSession ? undefined : `code-${sanitizeName(basename(rootDir))}`;
+
+  // Native filesystem tools. No subprocess, ~50-200 ms faster per call
+  // than the MCP server was, and `edit_file` takes a flat SEARCH/REPLACE
+  // shape instead of the `string="false"` JSON-in-string array that
+  // triggered R1's DSML hallucinations all through 0.4.x.
+  const tools = new ToolRegistry();
+  registerFilesystemTools(tools, { rootDir });
+  // Background-process registry shared between the shell tools and the
+  // TUI's /jobs + /kill slashes + exit cleanup. One per `reasonix code`
+  // run — orphan prevention on SIGINT / process exit kills everything
+  // it owns, so dev servers don't outlive the Reasonix process.
+  const jobs = new JobRegistry();
+  registerShellTools(tools, {
+    rootDir,
+    // Per-project "always allow" list persisted from prior ShellConfirm
+    // choices; merged on top of the built-in allowlist in shell.ts.
+    // GETTER form — re-read every dispatch so a prefix the user adds
+    // via ShellConfirm mid-session takes effect on the next shell call
+    // instead of waiting for `/new` or a relaunch.
+    extraAllowed: () => loadProjectShellAllowed(rootDir),
+    jobs,
+  });
+  // `submit_plan` is always in the spec list so the prefix cache stays
+  // stable across plan-mode toggles (Pillar 1). The tool itself is a
+  // no-op outside plan mode and throws `PlanProposedError` when the
+  // user has `/plan`-enabled the session.
+  registerPlanTool(tools);
+  // `ask_choice` — branching primitive. Independent of plan mode: the
+  // model uses it to put a 2–4 way choice in front of the user
+  // (strategy, style, library pick) without trying to squeeze the
+  // menu into a submit_plan body. Keeping it always-registered
+  // preserves the prefix cache across plan-mode toggles.
+  registerChoiceTool(tools);
+  // `remember` / `forget` / `recall_memory` — cross-session user memory.
+  // Project scope hashes off rootDir so switching projects gets a fresh
+  // per-project memory store; the global scope is shared across runs.
+  registerMemoryTools(tools, { projectRoot: rootDir });
+  // `run_skill` is intentionally NOT registered here — App.tsx wires it
+  // up with the subagent runner attached, so `runAs: subagent` skills
+  // can spawn isolated child loops. Doing it here would mean the App's
+  // re-registration would shadow the no-runner version, which works
+  // (last write wins) but obscures the wiring.
+
+  process.stderr.write(
+    `▸ reasonix code: rooted at ${rootDir}, session "${session ?? "(ephemeral)"}" · ${tools.size} native tool(s)\n`,
+  );
+
+  // Belt-and-suspenders cleanup: even though spawn(detached:false)
+  // should tie child processes to the parent's lifetime, Windows cmd.exe
+  // wrappers occasionally leak. We DON'T install SIGINT/SIGTERM
+  // handlers here — that overrode Node's default "exit on Ctrl+C" with
+  // a silent no-op, which made Ctrl+C feel broken in the TUI. App.tsx
+  // owns the SIGINT path now (it shows the quit-armed banner and calls
+  // exit() on confirmation); this 'exit' hook just guarantees the job
+  // registry is drained on the way out, regardless of which exit path
+  // fired.
+  process.once("exit", () => {
+    void jobs.shutdown();
+  });
+
+  await chatCommand({
+    model: opts.model ?? "deepseek-v4-flash",
+    harvest: opts.harvest ?? false,
+    system: codeSystemPrompt(rootDir),
+    transcript: opts.transcript,
+    session,
+    seedTools: tools,
+    codeMode: { rootDir, jobs },
+    forceResume: opts.forceResume,
+    forceNew: opts.forceNew,
+  });
+}

src/cli/commands/diff.ts

@@ -0,0 +1,62 @@
+import { writeFileSync } from "node:fs";
+import { basename } from "node:path";
+import { render } from "ink";
+import React from "react";
+import { diffTranscripts, renderMarkdown, renderSummaryTable } from "../../diff.js";
+import { readTranscript } from "../../transcript.js";
+import { DiffApp } from "../ui/DiffApp.js";
+
+export interface DiffOptions {
+  a: string;
+  b: string;
+  mdPath?: string;
+  labelA?: string;
+  labelB?: string;
+  /** Force stdout summary table (no Ink TUI). Auto when stdout isn't a TTY. */
+  print?: boolean;
+  /** Force the TUI even when stdout isn't a TTY (rare). */
+  tui?: boolean;
+}
+
+/**
+ * Compare two transcripts. Three output paths, picked in order:
+ *   - If --md is passed: write the markdown report. Also prints the stdout
+ *     summary so the user sees what was exported.
+ *   - If --print, no TTY, or --md (see above): stdout summary table.
+ *   - Otherwise: interactive Ink TUI with split-pane + n/N divergence jump.
+ */
+export async function diffCommand(opts: DiffOptions): Promise<void> {
+  const aParsed = readTranscript(opts.a);
+  const bParsed = readTranscript(opts.b);
+
+  const report = diffTranscripts(
+    { label: opts.labelA ?? basename(opts.a), parsed: aParsed },
+    { label: opts.labelB ?? basename(opts.b), parsed: bParsed },
+  );
+
+  const wantMarkdown = !!opts.mdPath;
+  const wantPrint = opts.print || !process.stdout.isTTY;
+  const wantTui = opts.tui || (!wantPrint && !wantMarkdown);
+
+  if (wantMarkdown) {
+    // Markdown export implies the user wants an artifact, not a TUI.
+    // Still echo the stdout summary to confirm the action.
+    console.log(renderSummaryTable(report));
+    const md = renderMarkdown(report);
+    writeFileSync(opts.mdPath!, md, "utf8");
+    console.log(`\nmarkdown report written to ${opts.mdPath}`);
+    return;
+  }
+
+  if (wantTui) {
+    const { waitUntilExit } = render(React.createElement(DiffApp, { report }), {
+      exitOnCtrlC: true,
+      patchConsole: false,
+    });
+    await waitUntilExit();
+    return;
+  }
+
+  // stdout fallback (piped, --print, or non-TTY)
+  console.log(renderSummaryTable(report));
+}

src/cli/commands/mcp-inspect.ts

@@ -0,0 +1,107 @@
+/**
+ * `reasonix mcp inspect <spec>` — connect to one MCP server, list
+ * everything it exposes (tools, resources, prompts), print a
+ * human-readable summary. Useful as:
+ *   - a diagnostic tool for "does my MCP server even work?"
+ *   - a discovery tool for "what can this server do?"
+ *   - the only CLI surface for the resources+prompts methods added
+ *     in 0.4.5 (chat mode consumes tools but hasn't wired up the
+ *     other two families yet).
+ */
+
+import { McpClient } from "../../mcp/client.js";
+import { inspectMcpServer } from "../../mcp/inspect.js";
+import type { InspectionReport } from "../../mcp/inspect.js";
+import { parseMcpSpec } from "../../mcp/spec.js";
+import { SseTransport } from "../../mcp/sse.js";
+import { type McpTransport, StdioTransport } from "../../mcp/stdio.js";
+
+export interface McpInspectOptions {
+  /** The raw --mcp spec string (e.g. `fs=npx -y @modelcontextprotocol/server-filesystem .`). */
+  spec: string;
+  /** Emit JSON on stdout instead of the human-readable table. */
+  json?: boolean;
+}
+
+export async function mcpInspectCommand(opts: McpInspectOptions): Promise<void> {
+  const spec = parseMcpSpec(opts.spec);
+  const transport: McpTransport =
+    spec.transport === "sse"
+      ? new SseTransport({ url: spec.url })
+      : new StdioTransport({ command: spec.command, args: spec.args });
+  const client = new McpClient({ transport });
+  try {
+    await client.initialize();
+    const report = await inspectMcpServer(client);
+    if (opts.json) {
+      console.log(JSON.stringify(report, null, 2));
+    } else {
+      console.log(formatReport(spec.name ?? "(anon)", report));
+    }
+  } finally {
+    await client.close();
+  }
+}
+
+function formatReport(nsName: string, r: InspectionReport): string {
+  const lines: string[] = [];
+  lines.push(`MCP server [${nsName}]`);
+  lines.push(
+    `  server     ${r.serverInfo.name || "(unknown)"}${r.serverInfo.version ? ` v${r.serverInfo.version}` : ""}`,
+  );
+  lines.push(`  protocol   ${r.protocolVersion}`);
+  const capKeys = Object.keys(r.capabilities);
+  lines.push(`  caps       ${capKeys.length > 0 ? capKeys.join(", ") : "(none advertised)"}`);
+  if (r.instructions) {
+    lines.push(`  notes      ${r.instructions.trim().slice(0, 200)}`);
+  }
+  lines.push("");
+  lines.push(formatSection("Tools", r.tools, toolLine));
+  lines.push(formatSection("Resources", r.resources, resourceLine));
+  lines.push(formatSection("Prompts", r.prompts, promptLine));
+  return lines.join("\n");
+}
+
+function formatSection<T>(
+  title: string,
+  section: { supported: true; items: T[] } | { supported: false; reason: string },
+  render: (item: T) => string,
+): string {
+  if (!section.supported) {
+    return `${title}: (not supported — ${section.reason})`;
+  }
+  if (section.items.length === 0) {
+    return `${title}: (none)`;
+  }
+  const lines = [`${title} (${section.items.length}):`];
+  for (const item of section.items) lines.push(`  ${render(item)}`);
+  return lines.join("\n");
+}
+
+function toolLine(t: { name: string; description?: string }): string {
+  const desc = t.description ? ` — ${oneLine(t.description, 80)}` : "";
+  return `· ${t.name}${desc}`;
+}
+
+function resourceLine(r: { uri: string; name: string; mimeType?: string }): string {
+  const mime = r.mimeType ? ` [${r.mimeType}]` : "";
+  return `· ${r.name}${mime}  ${r.uri}`;
+}
+
+function promptLine(p: {
+  name: string;
+  description?: string;
+  arguments?: Array<{ name: string; required?: boolean }>;
+}): string {
+  const argPart =
+    p.arguments && p.arguments.length > 0
+      ? ` (${p.arguments.map((a) => (a.required ? a.name : `${a.name}?`)).join(", ")})`
+      : "";
+  const desc = p.description ? ` — ${oneLine(p.description, 80)}` : "";
+  return `· ${p.name}${argPart}${desc}`;
+}
+
+function oneLine(s: string, max: number): string {
+  const flat = s.replace(/\s+/g, " ").trim();
+  return flat.length <= max ? flat : `${flat.slice(0, max - 1)}…`;
+}

src/cli/commands/mcp.ts

@@ -0,0 +1,41 @@
+/**
+ * `reasonix mcp <subcmd>` — the MCP discovery / helper surface.
+ *
+ * Currently one subcommand: `list`. Prints a curated catalog of popular
+ * MCP servers with their `--mcp` commands ready to copy-paste. More
+ * subcommands (`init`, `try`, etc.) may land in later alphas.
+ */
+
+import { MCP_CATALOG, mcpCommandFor } from "../../mcp/catalog.js";
+
+export interface McpListOptions {
+  /** Emit JSON on stdout instead of the human-readable table. */
+  json?: boolean;
+}
+
+export function mcpListCommand(opts: McpListOptions): void {
+  if (opts.json) {
+    console.log(JSON.stringify(MCP_CATALOG, null, 2));
+    return;
+  }
+
+  console.log("Popular MCP servers you can bridge into Reasonix:");
+  console.log("");
+  for (const entry of MCP_CATALOG) {
+    console.log(`  ${pad(entry.name, 12)} ${entry.summary}`);
+    console.log(`               ${mcpCommandFor(entry)}`);
+    if (entry.note) console.log(`               · ${entry.note}`);
+    console.log("");
+  }
+  console.log("Usage:  reasonix chat <one-of-the---mcp-lines-above>");
+  console.log(
+    "Docs:   https://github.com/modelcontextprotocol/servers  —  Anthropic's official server repo",
+  );
+  console.log(
+    "        https://mcp.so                                   —  community-maintained catalog",
+  );
+}
+
+function pad(s: string, width: number): string {
+  return s.length >= width ? s : s + " ".repeat(width - s.length);
+}

src/cli/commands/replay.ts

@@ -0,0 +1,139 @@
+import { render } from "ink";
+import React from "react";
+import { groupRecordsByTurn, replayFromFile } from "../../replay.js";
+import type { TranscriptRecord } from "../../transcript.js";
+import { ReplayApp } from "../ui/ReplayApp.js";
+
+export interface ReplayOptions {
+  path: string;
+  head?: number;
+  tail?: number;
+  /** Force stdout pretty-print mode (no Ink TUI). Also auto-enabled when stdout is not a TTY. */
+  print?: boolean;
+}
+
+/**
+ * Replay a transcript. Two modes:
+ *   - Interactive TUI (default when stdout is a TTY): Ink-based j/k navigation.
+ *   - Stdout pretty-print (--print, or when stdout is piped): one-shot text
+ *     dump + summary. Kept working so shell pipes, CI logs, and `less`
+ *     workflows still behave sensibly.
+ */
+export async function replayCommand(opts: ReplayOptions): Promise<void> {
+  const wantPrint =
+    opts.print || !process.stdout.isTTY || opts.head !== undefined || opts.tail !== undefined;
+  if (wantPrint) {
+    printReplay(opts);
+    return;
+  }
+
+  const { parsed } = replayFromFile(opts.path);
+  const pages = groupRecordsByTurn(parsed.records);
+  const { waitUntilExit } = render(React.createElement(ReplayApp, { meta: parsed.meta, pages }), {
+    exitOnCtrlC: true,
+    patchConsole: false,
+  });
+  await waitUntilExit();
+}
+
+// ----------------------------------------------------------------------------
+// stdout pretty-print path (original behavior, preserved for piping / CI)
+
+function printReplay(opts: ReplayOptions): void {
+  const { parsed, stats } = replayFromFile(opts.path);
+
+  if (parsed.meta) {
+    const m = parsed.meta;
+    const bits: string[] = [`source=${m.source}`];
+    if (m.model) bits.push(`model=${m.model}`);
+    if (m.task) bits.push(`task=${m.task}`);
+    if (m.mode) bits.push(`mode=${m.mode}`);
+    if (m.repeat !== undefined) bits.push(`repeat=${m.repeat}`);
+    bits.push(`started=${m.startedAt}`);
+    console.log(`[meta] ${bits.join(" ")}`);
+    console.log("");
+  }
+
+  const records = sliceRecords(parsed.records, opts);
+  for (const rec of records) {
+    renderRecord(rec);
+  }
+
+  console.log("");
+  console.log("── summary ─────────────────────────────────────────");
+  console.log(`model calls:         ${stats.turns}`);
+  console.log(`user turns:          ${stats.userTurns}`);
+  console.log(`tool calls:          ${stats.toolCalls}`);
+  console.log(`cache hit:           ${(stats.cacheHitRatio * 100).toFixed(1)}%`);
+  console.log(`cost:                $${stats.totalCostUsd.toFixed(6)}`);
+  console.log(`claude equivalent:   $${stats.claudeEquivalentUsd.toFixed(6)}`);
+  console.log(`savings vs claude:   ${stats.savingsVsClaudePct.toFixed(1)}%`);
+  console.log(`models:              ${stats.models.join(", ") || "—"}`);
+  console.log(`prefix hashes:       ${stats.prefixHashes.length} distinct`);
+  if (stats.prefixHashes.length === 1) {
+    console.log(`  (byte-stable prefix: ${stats.prefixHashes[0]?.slice(0, 16)}…)`);
+  } else if (stats.prefixHashes.length > 1) {
+    console.log("  (prefix churned — cache-hostile session)");
+  }
+  if (stats.harvestedTurns > 0) {
+    console.log(`harvest (Pillar 2): ${stats.harvestedTurns} turn(s) produced plan state`);
+    console.log(`  subgoals:          ${stats.totalSubgoals}`);
+    console.log(`  uncertainties:     ${stats.totalUncertainties}`);
+  }
+}
+
+function sliceRecords(records: TranscriptRecord[], opts: ReplayOptions): TranscriptRecord[] {
+  if (opts.head !== undefined && opts.head > 0) return records.slice(0, opts.head);
+  if (opts.tail !== undefined && opts.tail > 0) return records.slice(-opts.tail);
+  return records;
+}
+
+function renderRecord(rec: TranscriptRecord): void {
+  const turn = `[t${rec.turn}]`;
+  if (rec.role === "user") {
+    console.log(`${turn} USER: ${oneLine(rec.content)}`);
+  } else if (rec.role === "assistant_final") {
+    const cost = rec.cost !== undefined ? ` $${rec.cost.toFixed(6)}` : "";
+    const cache =
+      rec.usage &&
+      (rec.usage.prompt_cache_hit_tokens !== undefined ||
+        rec.usage.prompt_cache_miss_tokens !== undefined)
+        ? (() => {
+            const hit = rec.usage!.prompt_cache_hit_tokens ?? 0;
+            const miss = rec.usage!.prompt_cache_miss_tokens ?? 0;
+            const total = hit + miss;
+            return total > 0 ? ` cache=${((hit / total) * 100).toFixed(1)}%` : "";
+          })()
+        : "";
+    console.log(`${turn} AGENT:${cost}${cache} ${oneLine(rec.content)}`);
+    if (rec.planState) {
+      const ps = rec.planState;
+      if (ps.subgoals.length)
+        console.log(`   ‹ subgoals     (${ps.subgoals.length}): ${ps.subgoals.join(" · ")}`);
+      if (ps.hypotheses.length)
+        console.log(`   ‹ hypotheses   (${ps.hypotheses.length}): ${ps.hypotheses.join(" · ")}`);
+      if (ps.uncertainties.length)
+        console.log(
+          `   ‹ uncertainties(${ps.uncertainties.length}): ${ps.uncertainties.join(" · ")}`,
+        );
+      if (ps.rejectedPaths.length)
+        console.log(
+          `   ‹ rejected     (${ps.rejectedPaths.length}): ${ps.rejectedPaths.join(" · ")}`,
+        );
+    }
+  } else if (rec.role === "tool") {
+    const args = rec.args ? ` args=${oneLine(rec.args, 80)}` : "";
+    console.log(`${turn} TOOL ${rec.tool ?? "?"}:${args} → ${oneLine(rec.content, 120)}`);
+  } else if (rec.role === "error") {
+    console.log(`${turn} ERROR: ${rec.error ?? rec.content}`);
+  } else if (rec.role === "done") {
+    // Suppress — visually noisy, not informative in replay.
+  } else {
+    console.log(`${turn} ${rec.role}: ${oneLine(rec.content)}`);
+  }
+}
+
+function oneLine(s: string, max = 200): string {
+  const collapsed = s.replace(/\s+/g, " ").trim();
+  return collapsed.length > max ? `${collapsed.slice(0, max)}…` : collapsed;
+}

src/cli/commands/run.ts

@@ -0,0 +1,179 @@
+import type { WriteStream } from "node:fs";
+import { stdin, stdout } from "node:process";
+import { createInterface } from "node:readline/promises";
+import { defaultConfigPath, isPlausibleKey, loadApiKey, saveApiKey } from "../../config.js";
+import { loadDotenv } from "../../env.js";
+import { CacheFirstLoop, DeepSeekClient, ImmutablePrefix } from "../../index.js";
+import { McpClient } from "../../mcp/client.js";
+import { bridgeMcpTools } from "../../mcp/registry.js";
+import { parseMcpSpec } from "../../mcp/spec.js";
+import { SseTransport } from "../../mcp/sse.js";
+import { type McpTransport, StdioTransport } from "../../mcp/stdio.js";
+import { ToolRegistry } from "../../tools.js";
+import { openTranscriptFile, recordFromLoopEvent, writeRecord } from "../../transcript.js";
+import { appendUsage } from "../../usage.js";
+
+export interface RunOptions {
+  task: string;
+  model: string;
+  system: string;
+  /** Opt into Pillar 2 plan-state harvesting. Adds a cheap V3 call per turn. */
+  harvest?: boolean;
+  /** Self-consistency budget. > 1 runs N parallel samples and picks the best. */
+  branch?: number;
+  /** JSONL transcript path — lets `reasonix replay` / `diff` audit this run. */
+  transcript?: string;
+  /** Zero or more MCP server specs. Each: `"name=cmd args..."` or `"cmd args..."`. */
+  mcp?: string[];
+  /** Global prefix — only honored when a single anonymous server is given. */
+  mcpPrefix?: string;
+}
+
+async function ensureApiKey(): Promise<string> {
+  const existing = loadApiKey();
+  if (existing) return existing;
+
+  if (!stdin.isTTY) {
+    process.stderr.write(
+      "DEEPSEEK_API_KEY is not set and stdin is not a TTY (cannot prompt).\n" +
+        "Set the env var, or run `reasonix chat` once interactively to save a key.\n",
+    );
+    process.exit(1);
+  }
+
+  process.stdout.write(
+    "DeepSeek API key not configured.\nGet one at https://platform.deepseek.com/api_keys\n",
+  );
+  const rl = createInterface({ input: stdin, output: stdout });
+  try {
+    while (true) {
+      const answer = (await rl.question("API key › ")).trim();
+      if (!answer) continue;
+      if (!isPlausibleKey(answer)) {
+        process.stdout.write("Invalid format. Keys start with 'sk-' and are 30+ chars.\n");
+        continue;
+      }
+      saveApiKey(answer);
+      process.stdout.write(`Saved to ${defaultConfigPath()}\n\n`);
+      return answer;
+    }
+  } finally {
+    rl.close();
+  }
+}
+
+export async function runCommand(opts: RunOptions): Promise<void> {
+  loadDotenv();
+  const apiKey = await ensureApiKey();
+  process.env.DEEPSEEK_API_KEY = apiKey;
+
+  // Optional MCP setup — mirrors chat's flow. Must happen before loop
+  // construction so the tools make it into the prefix.
+  const requestedSpecs = opts.mcp ?? [];
+  const clients: McpClient[] = [];
+  let tools: ToolRegistry | undefined;
+  let successCount = 0;
+  if (requestedSpecs.length > 0) {
+    tools = new ToolRegistry();
+    for (const raw of requestedSpecs) {
+      try {
+        const spec = parseMcpSpec(raw);
+        const prefix = spec.name
+          ? `${spec.name}_`
+          : requestedSpecs.length === 1 && opts.mcpPrefix
+            ? opts.mcpPrefix
+            : "";
+        const transport: McpTransport =
+          spec.transport === "sse"
+            ? new SseTransport({ url: spec.url })
+            : new StdioTransport({ command: spec.command, args: spec.args });
+        const mcp = new McpClient({ transport });
+        await mcp.initialize();
+        const bridge = await bridgeMcpTools(mcp, { registry: tools, namePrefix: prefix });
+        const source =
+          spec.transport === "sse" ? spec.url : `${spec.command} ${spec.args.join(" ")}`;
+        process.stderr.write(
+          `▸ MCP[${spec.name ?? "anon"}]: ${bridge.registeredNames.length} tool(s) from ${source}\n`,
+        );
+        clients.push(mcp);
+        successCount++;
+      } catch (err) {
+        // Non-fatal — skip and continue, same as `reasonix chat`. A
+        // one-shot `run` invocation with a broken MCP server otherwise
+        // fails the whole run over a side-concern tool the task might
+        // not even touch.
+        process.stderr.write(
+          `▸ MCP setup SKIPPED for "${raw}": ${(err as Error).message}\n  → run \`reasonix setup\` to remove broken entries from your saved config.\n`,
+        );
+      }
+    }
+    if (successCount === 0) tools = undefined;
+  }
+
+  const client = new DeepSeekClient();
+  const prefix = new ImmutablePrefix({
+    system: opts.system,
+    toolSpecs: tools?.specs(),
+  });
+  const loop = new CacheFirstLoop({
+    client,
+    prefix,
+    tools,
+    model: opts.model,
+    harvest: opts.harvest,
+    branch: opts.branch,
+  });
+  const prefixHash = prefix.fingerprint;
+
+  let transcriptStream: WriteStream | null = null;
+  if (opts.transcript) {
+    transcriptStream = openTranscriptFile(opts.transcript, {
+      version: 1,
+      source: "reasonix run",
+      model: opts.model,
+      startedAt: new Date().toISOString(),
+    });
+    // Also persist the user turn itself (the loop's event stream starts with
+    // assistant output, not the prompt we're about to send).
+    writeRecord(transcriptStream, {
+      ts: new Date().toISOString(),
+      turn: 1,
+      role: "user",
+      content: opts.task,
+    });
+  }
+
+  try {
+    for await (const ev of loop.step(opts.task)) {
+      if (ev.role === "assistant_delta" && ev.content) process.stdout.write(ev.content);
+      if (ev.role === "tool") process.stdout.write(`\n[tool ${ev.toolName}] ${ev.content}\n`);
+      if (ev.role === "error") process.stderr.write(`\n[error] ${ev.error}\n`);
+      if (ev.role === "done") process.stdout.write("\n");
+      if (ev.role === "assistant_final" && ev.stats?.usage) {
+        // `reasonix run` is often used in CI / scripting — we want
+        // those turns to show up in `reasonix stats` too so the
+        // dashboard reflects all DeepSeek spend, not just TUI sessions.
+        appendUsage({ session: null, model: ev.stats.model, usage: ev.stats.usage });
+      }
+      // Persist every non-streaming event — deltas would flood the file and
+      // aren't useful for replay (replay renders final content, not keystrokes).
+      if (transcriptStream && ev.role !== "assistant_delta") {
+        writeRecord(transcriptStream, recordFromLoopEvent(ev, { model: opts.model, prefixHash }));
+      }
+    }
+  } finally {
+    transcriptStream?.end();
+  }
+
+  const s = loop.stats.summary();
+  process.stdout.write(
+    `\n— turns:${s.turns} cache:${(s.cacheHitRatio * 100).toFixed(1)}% ` +
+      `cost:$${s.totalCostUsd.toFixed(6)} save-vs-claude:${s.savingsVsClaudePct.toFixed(1)}%\n`,
+  );
+  if (opts.transcript) {
+    process.stdout.write(`\ntranscript: ${opts.transcript}\n`);
+    process.stdout.write(`  → npx reasonix replay ${opts.transcript}\n`);
+  }
+
+  for (const c of clients) await c.close();
+}

src/cli/commands/sessions.ts

@@ -0,0 +1,107 @@
+/**
+ * `reasonix sessions` — CLI equivalent of the `/sessions` slash command.
+ *
+ * Two modes:
+ *   - `reasonix sessions`           list every session under ~/.reasonix/sessions/
+ *   - `reasonix sessions <name>`    dump one session's messages in readable form
+ *
+ * Neither needs an API key — pure filesystem reads of JSONL files written
+ * by previous chat runs.
+ */
+
+import { listSessions, loadSessionMessages, sessionPath } from "../../index.js";
+import type { ChatMessage } from "../../index.js";
+
+export interface SessionsOptions {
+  /** When present, inspect that session instead of listing. */
+  name?: string;
+  /** Include assistant tool-call metadata in the inspect output. */
+  verbose?: boolean;
+}
+
+export function sessionsCommand(opts: SessionsOptions): void {
+  if (opts.name) {
+    inspectSession(opts.name, !!opts.verbose);
+  } else {
+    listAll();
+  }
+}
+
+function listAll(): void {
+  const items = listSessions();
+  if (items.length === 0) {
+    console.log(
+      "no saved sessions yet — run `reasonix chat` (sessions are auto-saved unless --no-session).",
+    );
+    return;
+  }
+  console.log("Saved sessions (~/.reasonix/sessions/):");
+  console.log("");
+  console.log(`  ${"name".padEnd(22)} ${"msgs".padStart(6)}  ${"size".padStart(8)}  modified`);
+  console.log(`  ${"─".repeat(60)}`);
+  for (const s of items) {
+    const sizeKb = `${(s.size / 1024).toFixed(1)} KB`;
+    const when = s.mtime.toISOString().replace("T", " ").slice(0, 16);
+    console.log(
+      `  ${s.name.padEnd(22)} ${String(s.messageCount).padStart(6)}  ${sizeKb.padStart(8)}  ${when}`,
+    );
+  }
+  console.log("");
+  console.log("Inspect:  reasonix sessions <name>");
+  console.log("Resume:   reasonix chat --session <name>");
+}
+
+function inspectSession(name: string, verbose: boolean): void {
+  const path = sessionPath(name);
+  const messages = loadSessionMessages(name);
+  if (messages.length === 0) {
+    console.error(`no session named "${name}" (or it's empty).`);
+    console.error(`looked at: ${path}`);
+    process.exit(1);
+  }
+
+  console.log(`[session] ${name}   ${messages.length} messages   ${path}`);
+  console.log("");
+
+  let turnIndex = 0;
+  for (const msg of messages) {
+    renderMessage(msg, turnIndex, verbose);
+    // Roughly bump "turn" after each user message so the reader can follow
+    // the conversation shape without the transcript's richer turn numbering.
+    if (msg.role === "user") turnIndex++;
+  }
+}
+
+function renderMessage(msg: ChatMessage, turnIdx: number, verbose: boolean): void {
+  const turn = turnIdx > 0 ? `[t${turnIdx}]` : "[start]";
+  const content = typeof msg.content === "string" ? msg.content : "";
+  const flat = oneLine(content);
+
+  if (msg.role === "user") {
+    console.log(`${turn} USER: ${flat}`);
+  } else if (msg.role === "assistant") {
+    console.log(`${turn} AGENT: ${flat || "(tool call only)"}`);
+    if (verbose && msg.tool_calls?.length) {
+      for (const tc of msg.tool_calls) {
+        console.log(
+          `         → call ${tc.function?.name} ${truncate(tc.function?.arguments ?? "", 80)}`,
+        );
+      }
+    }
+  } else if (msg.role === "tool") {
+    console.log(`${turn} TOOL ${msg.name ?? "?"}: ${truncate(flat, 160)}`);
+  } else if (msg.role === "system") {
+    if (verbose) console.log(`${turn} SYSTEM: ${truncate(flat, 160)}`);
+    // otherwise suppress — session's system prompt is usually session-wide
+    // boilerplate.
+  }
+}
+
+function oneLine(s: string, max = 200): string {
+  const collapsed = s.replace(/\s+/g, " ").trim();
+  return collapsed.length > max ? `${collapsed.slice(0, max)}…` : collapsed;
+}
+
+function truncate(s: string, max: number): string {
+  return s.length <= max ? s : `${s.slice(0, max)}…`;
+}

src/cli/commands/setup.tsx

@@ -0,0 +1,45 @@
+/**
+ * `reasonix setup` — re-mount the first-run wizard on demand so users
+ * can reconfigure (add/remove MCP servers, switch preset) without
+ * editing JSON by hand.
+ *
+ * Invoked both explicitly (`reasonix setup`) and implicitly (the no-args
+ * entry point when `setupCompleted` is false).
+ */
+
+import { render } from "ink";
+import React from "react";
+import { loadApiKey, readConfig } from "../../config.js";
+import { loadDotenv } from "../../env.js";
+import { Wizard } from "../ui/Wizard.js";
+
+export interface SetupOptions {
+  /**
+   * When true, bypass the API-key step even if no key is saved — useful
+   * from test harnesses. Normal CLI use always pushes through the key
+   * step when missing.
+   */
+  skipKeyStep?: boolean;
+}
+
+export async function setupCommand(_opts: SetupOptions = {}): Promise<void> {
+  loadDotenv();
+  const existingKey = loadApiKey();
+  const existing = readConfig();
+
+  const { waitUntilExit, unmount } = render(
+    <Wizard
+      existingApiKey={existingKey}
+      initial={{ preset: existing.preset, mcp: existing.mcp }}
+      onComplete={() => {
+        // Ink handles its own enter-to-exit inside the "saved" step; we
+        // just wait for the app to exit naturally.
+      }}
+      onCancel={() => {
+        unmount();
+      }}
+    />,
+    { exitOnCtrlC: true, patchConsole: false },
+  );
+  await waitUntilExit();
+}

src/cli/commands/stats.ts

@@ -0,0 +1,188 @@
+/**
+ * `reasonix stats` — two modes, decided by whether the user passed
+ * a transcript path.
+ *
+ *   - `reasonix stats`          → cross-session usage dashboard
+ *                                  (reads `~/.reasonix/usage.jsonl`)
+ *   - `reasonix stats <path>`   → summary of a single JSONL transcript
+ *                                  (original v0.1 behavior, kept so
+ *                                   existing scripts don't break)
+ *
+ * The dashboard is the new story: for every turn `reasonix chat|code|run`
+ * has ever executed on this machine, we aggregate tokens + cost + the
+ * equivalent Claude spend, and print rolling-window totals (today /
+ * week / month / all-time). The savings column is the Pillar 1 pitch
+ * made concrete — "you paid $X; Claude would have charged $Y, a N%
+ * reduction."
+ */
+
+import { existsSync, readFileSync } from "node:fs";
+import {
+  type UsageAggregate,
+  type UsageBucket,
+  aggregateUsage,
+  bucketCacheHitRatio,
+  bucketSavingsFraction,
+  defaultUsageLogPath,
+  formatLogSize,
+  readUsageLog,
+} from "../../usage.js";
+
+export interface StatsOptions {
+  /** Optional transcript path. Absent → dashboard mode. */
+  transcript?: string;
+  /** Override usage log location (tests). */
+  logPath?: string;
+  /** Inject a fixed timestamp (tests) so rolling windows are deterministic. */
+  now?: number;
+}
+
+export function statsCommand(opts: StatsOptions): void {
+  if (opts.transcript) {
+    transcriptSummary(opts.transcript);
+    return;
+  }
+  dashboard(opts);
+}
+
+// ---------------------------------------------------------------------
+// Transcript summary — legacy v0.1 behavior, preserved verbatim.
+// ---------------------------------------------------------------------
+
+function transcriptSummary(path: string): void {
+  if (!existsSync(path)) {
+    console.error(`no such transcript: ${path}`);
+    process.exit(1);
+  }
+  const lines = readFileSync(path, "utf8").split(/\r?\n/).filter(Boolean);
+  let assistantTurns = 0;
+  let toolCalls = 0;
+  let lastTurn = 0;
+  for (const line of lines) {
+    try {
+      const rec = JSON.parse(line);
+      if (rec.role === "assistant_final") assistantTurns++;
+      if (rec.role === "tool") toolCalls++;
+      if (typeof rec.turn === "number") lastTurn = Math.max(lastTurn, rec.turn);
+    } catch {
+      /* skip */
+    }
+  }
+  console.log(`transcript:       ${path}`);
+  console.log(`assistant turns:  ${assistantTurns}`);
+  console.log(`tool invocations: ${toolCalls}`);
+  console.log(`last turn index:  ${lastTurn}`);
+}
+
+// ---------------------------------------------------------------------
+// Dashboard — aggregates ~/.reasonix/usage.jsonl.
+// ---------------------------------------------------------------------
+
+function dashboard(opts: StatsOptions): void {
+  const path = opts.logPath ?? defaultUsageLogPath();
+  const records = readUsageLog(path);
+  if (records.length === 0) {
+    console.log("no usage data yet.");
+    console.log("");
+    console.log(`  ${path}`);
+    console.log("");
+    console.log("run `reasonix chat`, `reasonix code`, or `reasonix run <task>` — every turn");
+    console.log("appends one line to the log and `reasonix stats` will roll it up.");
+    return;
+  }
+
+  const agg = aggregateUsage(records, { now: opts.now });
+  console.log(renderDashboard(agg, path));
+}
+
+/** Pure renderer — pulled out so tests can assert on the string directly. */
+export function renderDashboard(agg: UsageAggregate, logPath: string): string {
+  const lines: string[] = [];
+  const size = formatLogSize(logPath);
+  lines.push(`Reasonix usage — ${logPath}${size ? ` (${size})` : ""}`);
+  lines.push("");
+  lines.push(header());
+  lines.push(divider());
+  for (const b of agg.buckets) {
+    lines.push(bucketRow(b));
+  }
+  lines.push("");
+
+  // Model + session breakdown — both trim to top 3 so a user with 20
+  // sessions doesn't drown the table.
+  if (agg.byModel.length > 0) {
+    const totalTurns = agg.buckets[agg.buckets.length - 1]?.turns ?? 0;
+    const top = agg.byModel[0];
+    if (top && totalTurns > 0) {
+      const pct = ((top.turns / totalTurns) * 100).toFixed(0);
+      lines.push(`most used model:   ${top.model} (${pct}% of turns)`);
+    }
+  }
+  if (agg.bySession.length > 0) {
+    const top = agg.bySession[0];
+    if (top) lines.push(`top session:       ${top.session} (${top.turns} turns)`);
+  }
+  if (agg.firstSeen) {
+    lines.push(`tracked since:     ${new Date(agg.firstSeen).toISOString().slice(0, 10)}`);
+  }
+  if (agg.subagents) {
+    lines.push("");
+    lines.push(renderSubagentSection(agg.subagents));
+  }
+  return lines.join("\n");
+}
+
+function renderSubagentSection(sub: NonNullable<UsageAggregate["subagents"]>): string {
+  const lines: string[] = [];
+  const seconds = (sub.totalDurationMs / 1000).toFixed(1);
+  lines.push(
+    `subagent activity: ${sub.total} run(s) · $${sub.costUsd.toFixed(6)} · ${seconds}s total`,
+  );
+  // Show at most 5 skills so the section never dwarfs the main table.
+  const top = sub.bySkill.slice(0, 5);
+  for (const s of top) {
+    const sec = (s.durationMs / 1000).toFixed(1);
+    lines.push(
+      `  ${pad(s.skillName, 18)} ${pad(`${s.count}`, 4, "right")}  $${s.costUsd.toFixed(6)}  ${sec}s`,
+    );
+  }
+  if (sub.bySkill.length > top.length) {
+    lines.push(`  (+${sub.bySkill.length - top.length} more)`);
+  }
+  return lines.join("\n");
+}
+
+function header(): string {
+  // Fixed column widths so alignment works in any TTY.
+  return [
+    pad("", 10),
+    pad("turns", 8, "right"),
+    pad("cache hit", 10, "right"),
+    pad("cost (USD)", 14, "right"),
+    pad("vs Claude", 14, "right"),
+    pad("saved", 10, "right"),
+  ].join("  ");
+}
+
+function divider(): string {
+  return "-".repeat(70);
+}
+
+function bucketRow(b: UsageBucket): string {
+  const hit = bucketCacheHitRatio(b);
+  const savings = bucketSavingsFraction(b);
+  return [
+    pad(b.label, 10),
+    pad(b.turns.toString(), 8, "right"),
+    pad(b.turns > 0 ? `${(hit * 100).toFixed(1)}%` : "—", 10, "right"),
+    pad(b.turns > 0 ? `$${b.costUsd.toFixed(6)}` : "—", 14, "right"),
+    pad(b.turns > 0 ? `$${b.claudeEquivUsd.toFixed(4)}` : "—", 14, "right"),
+    pad(b.turns > 0 && savings > 0 ? `${(savings * 100).toFixed(1)}%` : "—", 10, "right"),
+  ].join("  ");
+}
+
+function pad(s: string, width: number, align: "left" | "right" = "left"): string {
+  if (s.length >= width) return s;
+  const fill = " ".repeat(width - s.length);
+  return align === "right" ? `${fill}${s}` : `${s}${fill}`;
+}

src/cli/commands/update.ts

@@ -0,0 +1,143 @@
+/**
+ * `reasonix update` — self-upgrade command.
+ *
+ * Talks to the npm registry, compares against the running version,
+ * and either runs `npm install -g reasonix@latest` (global install)
+ * or advises how to refresh the npx cache (ephemeral install).
+ *
+ * The decision logic is factored into `planUpdate()` so it can be
+ * unit-tested without spawning child processes or hitting the
+ * network. `updateCommand()` is the thin CLI wrapper that calls
+ * `getLatestVersion`, passes the result into `planUpdate`, and
+ * executes any suggested command.
+ */
+
+import { spawn } from "node:child_process";
+import { VERSION, compareVersions, getLatestVersion, isNpxInstall } from "../../version.js";
+
+export type UpdateAction = "up-to-date" | "newer-local" | "npx-hint" | "run-npm-install";
+
+export interface UpdatePlan {
+  action: UpdateAction;
+  /** Human-readable summary; the CLI prints this verbatim. */
+  message: string;
+  /**
+   * Argv for the install command when `action === "run-npm-install"`.
+   * Absent otherwise. Kept as array so the CLI can pass it straight
+   * to `spawn` without re-parsing shell syntax.
+   */
+  command?: string[];
+}
+
+export interface PlanUpdateInput {
+  current: string;
+  latest: string;
+  /** Overrides `isNpxInstall()` (tests). */
+  npx?: boolean;
+}
+
+/**
+ * Pure decision function: given current + latest + install kind,
+ * decide what the CLI should do. No I/O.
+ *
+ *   newer-local     — current > latest (dev build, local publish)
+ *   up-to-date      — current === latest
+ *   npx-hint        — current < latest AND running under npx
+ *   run-npm-install — current < latest AND running as a real install
+ */
+export function planUpdate(input: PlanUpdateInput): UpdatePlan {
+  const diff = compareVersions(input.current, input.latest);
+  if (diff > 0) {
+    return {
+      action: "newer-local",
+      message: `current (${input.current}) is newer than the published ${input.latest} — nothing to do.`,
+    };
+  }
+  if (diff === 0) {
+    return { action: "up-to-date", message: `reasonix ${input.current} is up to date.` };
+  }
+  if (input.npx) {
+    return {
+      action: "npx-hint",
+      message: [
+        `reasonix ${input.latest} is available.`,
+        "you're running via npx — the next `npx reasonix ...` launch will auto-fetch",
+        "the latest (npx caches packages for a short window). to force a refresh",
+        "sooner, clear the cache: `npm cache clean --force`.",
+      ].join("\n"),
+    };
+  }
+  return {
+    action: "run-npm-install",
+    message: `upgrading reasonix ${input.current} → ${input.latest}`,
+    command: ["npm", "install", "-g", "reasonix@latest"],
+  };
+}
+
+export interface UpdateCommandOptions {
+  /** Skip spawning npm; print the decision only. */
+  dryRun?: boolean;
+  /** Test seam: override the registry lookup. Returns null = offline. */
+  fetchLatest?: () => Promise<string | null>;
+  /** Test seam: override the npx detector. */
+  isNpx?: () => boolean;
+  /** Test seam: override the spawner. Must return exit code. */
+  spawnInstall?: (argv: string[]) => Promise<number>;
+  /** Test seam: stdout writer. */
+  write?: (msg: string) => void;
+  /** Test seam: process exit — tests don't want to tear down vitest. */
+  exit?: (code: number) => void;
+}
+
+function defaultSpawn(argv: string[]): Promise<number> {
+  return new Promise((resolve, reject) => {
+    // `shell: true` on Windows is what lets `npm` resolve to `npm.cmd`
+    // without routing through our `prepareSpawn` helper. The args here
+    // are literal strings under our control — no user input flows in,
+    // so injection is not a concern. Avoiding `prepareSpawn` keeps
+    // this command free of a dep on the shell tools module.
+    const child = spawn(argv[0]!, argv.slice(1), {
+      stdio: "inherit",
+      shell: process.platform === "win32",
+    });
+    child.once("error", reject);
+    child.once("exit", (code) => resolve(code ?? 1));
+  });
+}
+
+/**
+ * Run the update command. Prints a banner, resolves the latest
+ * version, prints the plan, and (unless `--dry-run`) executes the
+ * install when applicable.
+ */
+export async function updateCommand(opts: UpdateCommandOptions = {}): Promise<void> {
+  const write = opts.write ?? ((m: string) => process.stdout.write(m));
+  const exit = opts.exit ?? ((c: number) => process.exit(c));
+  const fetchLatest = opts.fetchLatest ?? (() => getLatestVersion({ force: true }));
+  const isNpx = opts.isNpx ?? isNpxInstall;
+  const doSpawn = opts.spawnInstall ?? defaultSpawn;
+
+  write(`current: reasonix ${VERSION}\n`);
+  const latest = await fetchLatest();
+  if (!latest) {
+    write("could not reach registry.npmjs.org — check your network.\n");
+    exit(1);
+    return;
+  }
+  write(`latest:  reasonix ${latest}\n`);
+
+  const plan = planUpdate({ current: VERSION, latest, npx: isNpx() });
+  write(`\n${plan.message}\n`);
+
+  if (plan.action !== "run-npm-install" || !plan.command) return;
+  if (opts.dryRun) {
+    write(`(dry run) would run: ${plan.command.join(" ")}\n`);
+    return;
+  }
+  write(`\nrunning: ${plan.command.join(" ")}\n`);
+  const code = await doSpawn(plan.command);
+  if (code !== 0) {
+    write(`\nnpm exited with code ${code}. upgrade did not complete.\n`);
+    exit(code);
+  }
+}

src/cli/commands/version.ts

@@ -0,0 +1,5 @@
+import { VERSION } from "../../index.js";
+
+export function versionCommand(): void {
+  console.log(`reasonix ${VERSION}`);
+}

src/cli/index.ts

@@ -0,0 +1,305 @@
+import { Command } from "commander";
+import { readConfig } from "../config.js";
+import { VERSION } from "../index.js";
+import { ESCALATION_CONTRACT } from "../prompt-fragments.js";
+import { applyMemoryStack } from "../user-memory.js";
+import { chatCommand } from "./commands/chat.js";
+import { codeCommand } from "./commands/code.js";
+import { diffCommand } from "./commands/diff.js";
+import { mcpInspectCommand } from "./commands/mcp-inspect.js";
+import { mcpListCommand } from "./commands/mcp.js";
+import { replayCommand } from "./commands/replay.js";
+import { runCommand } from "./commands/run.js";
+import { sessionsCommand } from "./commands/sessions.js";
+import { setupCommand } from "./commands/setup.js";
+import { statsCommand } from "./commands/stats.js";
+import { updateCommand } from "./commands/update.js";
+import { versionCommand } from "./commands/version.js";
+import { resolveDefaults } from "./resolve.js";
+
+const DEFAULT_SYSTEM = `You are Reasonix, a helpful DeepSeek-powered assistant. Be concise and accurate. Use tools when available.
+
+# Cite or shut up — non-negotiable
+
+Every factual claim about a codebase must be backed by evidence. Reasonix VALIDATES your citations — broken paths render in **red strikethrough with ❌** in front of the user.
+
+**Positive claims** — append a markdown link:
+- ✅ \`The MCP client supports listResources [listResources](src/mcp/client.ts:142).\`
+- ❌ \`The MCP client supports listResources.\` ← unverifiable, do not write.
+
+**Negative claims** ("X is missing", "Y isn't implemented", "lacks Z") are the #1 hallucination shape. STOP before writing them. If you have a search tool, call it first; if the search returns nothing, cite the search itself as evidence (\`No matches for "foo" in src/\`). If you have no tool, qualify hard: "I haven't verified — this is a guess."
+
+Asserting absence without checking is how evaluative answers go wrong. Treat the urge to write "missing" as a red flag in your own reasoning.
+
+# Don't invent what changes — search instead
+
+Your training data has a cutoff. When an answer's correctness depends on something that changes over time (the user is asking what's happening, not what's true) and a search tool is available, search first. Inventing currently-correct values from training memory is the most common way these answers go wrong, and the user usually can't tell until much later.
+
+The signal isn't a topic list — it's: "if I'm wrong about this, is it because reality moved on?". If yes, ground the answer in fresh evidence; if no (definitions, mechanisms, well-established APIs), answer from memory.
+
+${ESCALATION_CONTRACT}`;
+
+const program = new Command();
+program
+  .name("reasonix")
+  .description("DeepSeek-native agent framework — built for cache hits and cheap tokens.")
+  .version(VERSION);
+
+// `reasonix` with no subcommand → launch the friendliest flow.
+// First run (no config yet) → interactive setup wizard.
+// Otherwise → chat with saved defaults. This is the "one command to
+// rule them all" entry for non-power-users: they don't need to learn
+// `chat` / `setup` / `--mcp` — just type `reasonix`.
+program.action(async () => {
+  const cfg = readConfig();
+  if (!cfg.setupCompleted) {
+    await setupCommand({});
+    return;
+  }
+  const defaults = resolveDefaults({});
+  await chatCommand({
+    model: defaults.model,
+    system: applyMemoryStack(DEFAULT_SYSTEM, process.cwd()),
+    harvest: defaults.harvest,
+    branch: defaults.branch,
+    session: defaults.session,
+    mcp: defaults.mcp,
+  });
+});
+
+program
+  .command("setup")
+  .description("Interactive wizard — API key, preset, MCP servers. Re-run any time to reconfigure.")
+  .action(async () => {
+    await setupCommand({});
+  });
+
+program
+  .command("code [dir]")
+  .description(
+    "Code-editing chat — filesystem tools rooted at <dir> (default: cwd), coding system prompt, v4-flash. Model proposes SEARCH/REPLACE blocks; Reasonix applies them to disk. Use /preset max or /pro to escalate to v4-pro on hard tasks.",
+  )
+  .option("-m, --model <id>", "Override default model (v4-flash)")
+  .option("--no-session", "Disable session persistence for this run")
+  .option("-r, --resume", "Skip the session picker — always continue prior messages")
+  .option("-n, --new", "Skip the session picker — always wipe prior messages and start fresh")
+  .option("--transcript <path>", "Write a JSONL transcript to this path")
+  .option(
+    "--harvest",
+    "Opt-in Pillar-2 plan-state extraction. Adds one flash call per turn; off by default (no preset enables it).",
+  )
+  .action(async (dir: string | undefined, opts) => {
+    await codeCommand({
+      dir,
+      model: opts.model,
+      noSession: opts.session === false,
+      transcript: opts.transcript,
+      forceResume: !!opts.resume,
+      forceNew: !!opts.new,
+      harvest: !!opts.harvest,
+    });
+  });
+
+program
+  .command("chat")
+  .description("Interactive Ink TUI with live cache/cost panel.")
+  .option("-m, --model <id>", "DeepSeek model id (overrides preset)")
+  .option("-s, --system <prompt>", "System prompt (pinned in the immutable prefix)", DEFAULT_SYSTEM)
+  .option("--transcript <path>", "Write a JSONL transcript to this path")
+  .option(
+    "--preset <name>",
+    "Model + effort bundle. One of: fast (flash·high), smart (flash·max, default), max (pro·max). Overrides config.preset.",
+  )
+  .option(
+    "--harvest",
+    "Opt-in Pillar-2 plan-state extraction. Off by default — no preset enables it.",
+  )
+  .option(
+    "--branch <n>",
+    "Self-consistency: run N parallel samples per turn (N× cost). Manual only — never auto-enabled.",
+    (v) => Number.parseInt(v, 10),
+  )
+  .option("--session <name>", "Use a named session (default: from config, usually 'default').")
+  .option("--no-session", "Disable session persistence for this run (ephemeral chat)")
+  .option("-r, --resume", "Skip the session picker — always continue prior messages")
+  .option("-n, --new", "Skip the session picker — always wipe prior messages and start fresh")
+  .option(
+    "--mcp <spec>",
+    'MCP server spec; repeatable. "name=cmd args...", "cmd args...", or a URL (http/https → SSE transport). Overrides config.mcp when provided.',
+    (value: string, previous: string[] = []) => [...previous, value],
+    [] as string[],
+  )
+  .option(
+    "--mcp-prefix <str>",
+    "Global prefix applied to every MCP tool (only honored when no per-spec name is set; avoids collisions with a single anonymous server)",
+  )
+  .option("--no-config", "Ignore `~/.reasonix/config.json` — useful for CI or reproducing issues")
+  .action(async (opts) => {
+    const defaults = resolveDefaults({
+      model: opts.model,
+      harvest: opts.harvest,
+      branch: opts.branch,
+      mcp: opts.mcp as string[],
+      session: opts.session,
+      preset: opts.preset,
+      noConfig: opts.config === false,
+    });
+    await chatCommand({
+      model: defaults.model,
+      system: applyMemoryStack(opts.system, process.cwd()),
+      transcript: opts.transcript,
+      harvest: defaults.harvest,
+      branch: defaults.branch,
+      session: defaults.session,
+      mcp: defaults.mcp,
+      mcpPrefix: opts.mcpPrefix,
+      forceResume: !!opts.resume,
+      forceNew: !!opts.new,
+    });
+  });
+
+program
+  .command("run <task>")
+  .description("Run a single task non-interactively, streaming output.")
+  .option("-m, --model <id>", "DeepSeek model id (overrides preset)")
+  .option("-s, --system <prompt>", "System prompt", DEFAULT_SYSTEM)
+  .option("--preset <name>", "Bundle of model + harvest + branch: fast | smart | max")
+  .option("--harvest", "Extract typed plan state from R1 reasoning (Pillar 2)")
+  .option(
+    "--branch <n>",
+    "Self-consistency: run N parallel samples per turn and pick the most confident",
+    (v) => Number.parseInt(v, 10),
+  )
+  .option("--transcript <path>", "Write a JSONL transcript to this path for replay/diff")
+  .option(
+    "--mcp <spec>",
+    'MCP server spec; repeatable. "name=cmd args...", "cmd args...", or a URL (http/https → SSE).',
+    (value: string, previous: string[] = []) => [...previous, value],
+    [] as string[],
+  )
+  .option(
+    "--mcp-prefix <str>",
+    "Global prefix (only honored when no per-spec name is set; for a single anonymous server)",
+  )
+  .option("--no-config", "Ignore `~/.reasonix/config.json` — useful for CI or reproducing issues")
+  .action(async (task: string, opts) => {
+    const defaults = resolveDefaults({
+      model: opts.model,
+      harvest: opts.harvest,
+      branch: opts.branch,
+      mcp: opts.mcp as string[],
+      preset: opts.preset,
+      noConfig: opts.config === false,
+    });
+    await runCommand({
+      task,
+      model: defaults.model,
+      system: applyMemoryStack(opts.system, process.cwd()),
+      harvest: defaults.harvest,
+      branch: defaults.branch,
+      transcript: opts.transcript,
+      mcp: defaults.mcp,
+      mcpPrefix: opts.mcpPrefix,
+    });
+  });
+
+program
+  .command("stats [transcript]")
+  .description(
+    "Show usage dashboard (today / week / month / all-time · turns · cache hit · cost · savings vs Claude). " +
+      "Pass a transcript path to fall back to the per-file summary (assistant turns + tool calls).",
+  )
+  .action((transcript: string | undefined) => {
+    statsCommand({ transcript });
+  });
+
+program
+  .command("sessions [name]")
+  .description("List saved chat sessions, or inspect one by name.")
+  .option("-v, --verbose", "Include system prompts + tool-call metadata when inspecting")
+  .action((name: string | undefined, opts) => {
+    sessionsCommand({ name, verbose: !!opts.verbose });
+  });
+
+program
+  .command("replay <transcript>")
+  .description(
+    "Interactive Ink TUI to scrub through a transcript + rebuild its session summary (cost, cache, prefix stability). No API calls.",
+  )
+  .option("--print", "Dump to stdout instead of mounting the TUI (auto when piped)")
+  .option("--head <n>", "stdout mode only — show first N records", (v) => Number.parseInt(v, 10))
+  .option("--tail <n>", "stdout mode only — show last N records", (v) => Number.parseInt(v, 10))
+  .action(async (transcript: string, opts) => {
+    await replayCommand({
+      path: transcript,
+      print: !!opts.print,
+      head: Number.isFinite(opts.head) ? opts.head : undefined,
+      tail: Number.isFinite(opts.tail) ? opts.tail : undefined,
+    });
+  });
+
+program
+  .command("diff <a> <b>")
+  .description(
+    "Compare two transcripts in a split-pane Ink TUI (default) or stdout table. Use n/N to jump across divergences.",
+  )
+  .option("--md <path>", "Write a markdown report (blog-ready) to this path")
+  .option("--print", "Force stdout table instead of the TUI (auto when piped)")
+  .option("--tui", "Force the TUI even when piped (rare)")
+  .option("--label-a <label>", "Display label for transcript A (default: filename)")
+  .option("--label-b <label>", "Display label for transcript B (default: filename)")
+  .action(async (a: string, b: string, opts) => {
+    await diffCommand({
+      a,
+      b,
+      mdPath: opts.md,
+      labelA: opts.labelA,
+      labelB: opts.labelB,
+      print: !!opts.print,
+      tui: !!opts.tui,
+    });
+  });
+
+const mcp = program
+  .command("mcp")
+  .description("Model Context Protocol helpers — discover servers, test your setup.");
+
+mcp
+  .command("list")
+  .description("Show a curated catalog of popular MCP servers with ready-to-use --mcp commands.")
+  .option("--json", "Emit the catalog as JSON instead of the human-readable table")
+  .action((opts) => {
+    mcpListCommand({ json: !!opts.json });
+  });
+
+mcp
+  .command("inspect <spec>")
+  .description(
+    'Connect to one MCP server and print its server info + tools/resources/prompts. <spec> takes the same forms as --mcp ("name=cmd args", "cmd args", or an SSE URL).',
+  )
+  .option("--json", "Emit the full inspection report as JSON instead of the human-readable summary")
+  .action(async (spec: string, opts) => {
+    try {
+      await mcpInspectCommand({ spec, json: !!opts.json });
+    } catch (err) {
+      process.stderr.write(`mcp inspect failed: ${(err as Error).message}\n`);
+      process.exit(1);
+    }
+  });
+
+program.command("version").description("Print Reasonix version.").action(versionCommand);
+
+program
+  .command("update")
+  .description(
+    "Check the npm registry for a newer Reasonix and install it. Detects npx vs global install; for npx users, prints a cache-refresh hint instead of running `npm i -g`.",
+  )
+  .option("--dry-run", "Print the plan without executing the install")
+  .action(async (opts: { dryRun?: boolean }) => {
+    await updateCommand({ dryRun: !!opts.dryRun });
+  });
+
+program.parseAsync(process.argv).catch((err) => {
+  console.error(err);
+  process.exit(1);
+});

src/cli/resolve.ts

@@ -0,0 +1,91 @@
+/**
+ * Merge config defaults with CLI flags into the concrete options that
+ * `chatCommand` / `runCommand` need.
+ *
+ * Precedence (highest wins):
+ *   1. Explicit per-setting CLI flag (`--model`, `--harvest`, `--branch`, `--mcp`)
+ *   2. Explicit `--preset <name>` CLI flag
+ *   3. `config.preset` from `~/.reasonix/config.json` (set by `reasonix setup`)
+ *   4. Hardcoded "smart" preset defaults (flash + effort=max)
+ *
+ * Keeping this logic in one place — rather than duplicating across
+ * `chat` and `run` — means the precedence rule only lives in one unit
+ * test and the shape of the merge is identical for both commands.
+ */
+
+import { type PresetName, type ReasonixConfig, readConfig } from "../config.js";
+import { PRESETS } from "./ui/presets.js";
+
+export interface ResolvedDefaults {
+  model: string;
+  reasoningEffort: "high" | "max";
+  harvest: boolean;
+  branch: number | undefined;
+  mcp: string[];
+  session: string | undefined;
+}
+
+export interface RawCliFlags {
+  model?: string;
+  harvest?: boolean;
+  /** From `commander`; already parseInt'd. */
+  branch?: number;
+  mcp?: string[];
+  /** Commander's `--no-session` surfaces as `false`; `--session X` as a string. */
+  session?: string | false;
+  /** `--preset <name>`. */
+  preset?: string;
+  /** When true, ignore config entirely (power-user escape hatch). */
+  noConfig?: boolean;
+}
+
+export function resolveDefaults(flags: RawCliFlags): ResolvedDefaults {
+  const cfg: ReasonixConfig = flags.noConfig ? {} : readConfig();
+  const preset = pickPreset(flags.preset, cfg.preset);
+  const presetSettings = PRESETS[preset];
+
+  const model = flags.model ?? presetSettings.model;
+  const reasoningEffort = presetSettings.reasoningEffort;
+  const harvest = flags.harvest === true ? true : presetSettings.harvest;
+  const branchFromFlag = normalizeBranch(flags.branch);
+  const branch = branchFromFlag ?? (presetSettings.branch > 1 ? presetSettings.branch : undefined);
+
+  // `--mcp` accumulator is [] when absent. Treat empty from flags as
+  // "user didn't pass" → fall through to config. Users who explicitly
+  // want zero MCP servers can pass `--no-config` or edit the file.
+  const mcp = flags.mcp && flags.mcp.length > 0 ? flags.mcp : (cfg.mcp ?? []);
+
+  const session = resolveSession(flags.session, cfg.session);
+
+  return { model, reasoningEffort, harvest, branch, mcp, session };
+}
+
+function pickPreset(
+  flagPreset: string | undefined,
+  configPreset: PresetName | undefined,
+): PresetName {
+  if (flagPreset && isPresetName(flagPreset)) return flagPreset;
+  if (configPreset) return configPreset;
+  return "smart";
+}
+
+function isPresetName(s: string): s is PresetName {
+  return s === "fast" || s === "smart" || s === "max";
+}
+
+function normalizeBranch(raw: number | undefined): number | undefined {
+  if (raw === undefined) return undefined;
+  if (!Number.isFinite(raw) || raw <= 1) return undefined;
+  return Math.min(raw, 8);
+}
+
+function resolveSession(
+  flag: string | false | undefined,
+  configSession: string | null | undefined,
+): string | undefined {
+  if (flag === false) return undefined; // --no-session
+  if (typeof flag === "string" && flag.length > 0) return flag;
+  if (configSession === null) return undefined; // config opted out
+  if (typeof configSession === "string" && configSession.length > 0) return configSession;
+  return "default";
+}

src/cli/ui/AtMentionSuggestions.tsx

@@ -0,0 +1,82 @@
+import { Box, Text } from "ink";
+// biome-ignore lint/style/useImportType: tsconfig.jsx = "react" needs React in value scope for JSX compilation
+import React from "react";
+
+export interface AtMentionSuggestionsProps {
+  /**
+   * Current matching file paths, ranked by the picker. `null` means
+   * "not in @-prefix mode" — render nothing. Empty array means "in @
+   * mode but no files match that partial" — render a hint.
+   */
+  matches: readonly string[] | null;
+  /** Index (within `matches`) of the currently highlighted row. */
+  selectedIndex: number;
+  /** The partial query the user typed after `@`. Shown in the hint row. */
+  query: string;
+}
+
+/**
+ * Floating `@`-mention picker. Rendered below the input box when the
+ * user is typing an `@…` prefix in code mode. Navigation state lives
+ * in the parent (App.tsx owns `atSelected`) — this component is pure
+ * display. Mirrors {@link SlashSuggestions} shape so the keybindings
+ * and layout feel identical across the two pickers.
+ */
+export function AtMentionSuggestions({
+  matches,
+  selectedIndex,
+  query,
+}: AtMentionSuggestionsProps): React.ReactElement | null {
+  if (matches === null) return null;
+  if (matches.length === 0) {
+    return (
+      <Box paddingX={1} marginTop={1}>
+        <Text color="yellow">no files match "@{query}"</Text>
+        <Text dimColor>
+          {" "}
+          — keep typing, or Backspace to edit. Paths resolve from the code root.
+        </Text>
+      </Box>
+    );
+  }
+  const MAX = 8;
+  const total = matches.length;
+  const windowStart =
+    total <= MAX ? 0 : Math.max(0, Math.min(selectedIndex - Math.floor(MAX / 2), total - MAX));
+  const shown = matches.slice(windowStart, windowStart + MAX);
+  const hiddenAbove = windowStart;
+  const hiddenBelow = total - windowStart - shown.length;
+  return (
+    <Box flexDirection="column" paddingX={1} marginTop={1}>
+      {hiddenAbove > 0 ? <Text dimColor> ↑ {hiddenAbove} more above</Text> : null}
+      {shown.map((path, i) => (
+        <FileRow key={path} path={path} isSelected={windowStart + i === selectedIndex} />
+      ))}
+      {hiddenBelow > 0 ? <Text dimColor> ↓ {hiddenBelow} more below</Text> : null}
+      <Text dimColor> [↑↓] navigate · [Tab]/[Enter] pick · file content inlined on send</Text>
+    </Box>
+  );
+}
+
+function FileRow({ path, isSelected }: { path: string; isSelected: boolean }) {
+  // Split the path so the basename visually pops — same dropdown
+  // affordance as VS Code's Quick Open.
+  const slash = path.lastIndexOf("/");
+  const dir = slash >= 0 ? `${path.slice(0, slash)}/` : "";
+  const base = slash >= 0 ? path.slice(slash + 1) : path;
+  if (isSelected) {
+    return (
+      <Box>
+        <Text backgroundColor="#67e8f9" color="black" bold>
+          {` ▸ ${base}${dir ? `  ${dir}` : ""} `}
+        </Text>
+      </Box>
+    );
+  }
+  return (
+    <Box>
+      <Text color="#94a3b8">{`   ${base}`}</Text>
+      {dir ? <Text dimColor>{`  ${dir}`}</Text> : null}
+    </Box>
+  );
+}

src/cli/ui/ChoiceConfirm.tsx

@@ -0,0 +1,75 @@
+/**
+ * Modal picker shown when the model calls `ask_choice`. Renders the
+ * question + 2–4 option rows (title + dimmed summary) + an optional
+ * "Let me type my own answer" escape hatch when `allowCustom` is true.
+ *
+ * The escape hatch matters because DeepSeek flash sometimes misframes
+ * the alternatives — none actually fit the user's intent. Without a
+ * bailout the user would have to cancel, type feedback, and wait for
+ * another round-trip. With it they just type and ship.
+ *
+ * Border color: magenta — deliberately distinct from cyan (plan),
+ * green (checkpoint), red (shell) so the user's eye learns the modes
+ * without reading headers.
+ */
+
+import { Box } from "ink";
+import React from "react";
+import type { ChoiceOption } from "../../tools/choice.js";
+import { ModalCard } from "./ModalCard.js";
+import { SingleSelect } from "./Select.js";
+
+export type ChoiceConfirmChoice =
+  | { kind: "pick"; optionId: string }
+  | { kind: "custom" }
+  | { kind: "cancel" };
+
+export interface ChoiceConfirmProps {
+  question: string;
+  options: ChoiceOption[];
+  allowCustom: boolean;
+  onChoose: (choice: ChoiceConfirmChoice) => void;
+}
+
+const CUSTOM_VALUE = "__custom__";
+const CANCEL_VALUE = "__cancel__";
+
+function ChoiceConfirmInner({ question, options, allowCustom, onChoose }: ChoiceConfirmProps) {
+  const items: Array<{ value: string; label: string; hint?: string }> = options.map((opt) => ({
+    value: opt.id,
+    label: `${opt.id} · ${opt.title}`,
+    hint: opt.summary,
+  }));
+  if (allowCustom) {
+    items.push({
+      value: CUSTOM_VALUE,
+      label: "Let me type my own answer",
+      hint: "None of the above fits — type a free-form reply. The model reads it verbatim.",
+    });
+  }
+  items.push({
+    value: CANCEL_VALUE,
+    label: "Cancel — drop the question",
+    hint: "Model stops and asks what you want instead.",
+  });
+
+  return (
+    <ModalCard accent="#f0abfc" icon="🔀" title="model wants you to pick" subtitle={question}>
+      <Box>
+        <SingleSelect
+          initialValue={options[0]?.id}
+          items={items}
+          onSubmit={(v) => {
+            if (v === CUSTOM_VALUE) onChoose({ kind: "custom" });
+            else if (v === CANCEL_VALUE) onChoose({ kind: "cancel" });
+            else onChoose({ kind: "pick", optionId: v });
+          }}
+          onCancel={() => onChoose({ kind: "cancel" })}
+          footer="[↑↓] navigate  ·  [Enter] select  ·  [Esc] cancel"
+        />
+      </Box>
+    </ModalCard>
+  );
+}
+
+export const ChoiceConfirm = React.memo(ChoiceConfirmInner);

src/cli/ui/DiffApp.tsx

@@ -0,0 +1,234 @@
+/**
+ * Ink TUI for `reasonix diff`. Split-pane: A on the left, B on the right,
+ * shared cursor. Header shows aggregate deltas; footer shows the current
+ * pair's divergence note (if any) + key cheat sheet.
+ *
+ * j/k moves the cursor by one turn; n/N jumps to the next/prev divergent
+ * turn — which is the whole point of a diff tool. Quit with q.
+ *
+ * Pure navigation lives in src/diff.ts (findNextDivergence / findPrevDivergence).
+ */
+
+import { Box, Static, Text, useApp, useInput } from "ink";
+import React, { useState } from "react";
+import {
+  type DiffReport,
+  type TurnPair,
+  findNextDivergence,
+  findPrevDivergence,
+} from "../../diff.js";
+import { RecordView } from "./RecordView.js";
+
+export interface DiffAppProps {
+  report: DiffReport;
+}
+
+export function DiffApp({ report }: DiffAppProps) {
+  const { exit } = useApp();
+  const maxIdx = Math.max(0, report.pairs.length - 1);
+  // Start at the first divergence when one exists — that's the user's most
+  // likely destination. Falls back to idx 0 for fully-matching diffs.
+  const initialIdx = report.firstDivergenceTurn
+    ? report.pairs.findIndex((p) => p.turn === report.firstDivergenceTurn)
+    : 0;
+  const [idx, setIdx] = useState(Math.max(0, initialIdx));
+
+  useInput((input, key) => {
+    if (input === "q" || (key.ctrl && input === "c")) {
+      exit();
+      return;
+    }
+    if (input === "j" || key.downArrow || input === " " || key.return) {
+      setIdx((i) => Math.min(maxIdx, i + 1));
+    } else if (input === "k" || key.upArrow) {
+      setIdx((i) => Math.max(0, i - 1));
+    } else if (input === "g") {
+      setIdx(0);
+    } else if (input === "G") {
+      setIdx(maxIdx);
+    } else if (input === "n") {
+      const next = findNextDivergence(report.pairs, idx);
+      if (next !== -1) setIdx(next);
+    } else if (input === "N" || input === "p") {
+      const prev = findPrevDivergence(report.pairs, idx);
+      if (prev !== -1) setIdx(prev);
+    }
+  });
+
+  const pair = report.pairs[idx];
+
+  return (
+    <Box flexDirection="column">
+      <DiffHeader report={report} />
+
+      <Box marginTop={1} paddingX={1} justifyContent="space-between">
+        <Text color="cyan" bold>
+          turn {pair?.turn ?? "?"} ({idx + 1} / {report.pairs.length})
+        </Text>
+        <Text>{pair ? <KindBadge kind={pair.kind} /> : null}</Text>
+      </Box>
+
+      <Box flexDirection="row" marginTop={1}>
+        <Pane label={report.a.label} headerColor="blue" records={paneRecords(pair, "a")} />
+        <Pane label={report.b.label} headerColor="magenta" records={paneRecords(pair, "b")} />
+      </Box>
+
+      {pair?.divergenceNote ? (
+        <Box marginTop={1} paddingX={1}>
+          <Text color="yellow">★ </Text>
+          <Text>{pair.divergenceNote}</Text>
+        </Box>
+      ) : null}
+
+      <Box marginTop={1} paddingX={1} borderStyle="single" borderColor="gray">
+        <Text dimColor>
+          <Text bold>j</Text>/<Text bold>↓</Text> next · <Text bold>k</Text>/<Text bold>↑</Text>{" "}
+          prev · <Text bold>n</Text> next-diverge · <Text bold>N</Text>/<Text bold>p</Text>{" "}
+          prev-diverge · <Text bold>g</Text>/<Text bold>G</Text> first/last · <Text bold>q</Text>{" "}
+          quit
+        </Text>
+      </Box>
+    </Box>
+  );
+}
+
+// ----------------------------------------------------------------------------
+
+function DiffHeader({ report }: { report: DiffReport }) {
+  const a = report.a;
+  const b = report.b;
+
+  const cacheDelta = b.stats.cacheHitRatio - a.stats.cacheHitRatio;
+  const costDelta =
+    a.stats.totalCostUsd > 0
+      ? ((b.stats.totalCostUsd - a.stats.totalCostUsd) / a.stats.totalCostUsd) * 100
+      : 0;
+
+  // Prefix stability one-liner (same logic as the stdout summary).
+  const aStable = a.stats.prefixHashes.length <= 1;
+  const bStable = b.stats.prefixHashes.length <= 1;
+  let prefixLine: string | null = null;
+  if (aStable !== bStable) {
+    const stableLabel = aStable ? report.a.label : report.b.label;
+    const churnLabel = aStable ? report.b.label : report.a.label;
+    const churnCount = aStable ? b.stats.prefixHashes.length : a.stats.prefixHashes.length;
+    prefixLine = `${stableLabel} stayed byte-stable; ${churnLabel} churned ${churnCount} distinct prefixes.`;
+  } else if (a.stats.prefixHashes[0] && a.stats.prefixHashes[0] === b.stats.prefixHashes[0]) {
+    prefixLine = `shared prefix hash ${a.stats.prefixHashes[0].slice(0, 12)}… — cache delta attributable to log stability, not prompt change.`;
+  }
+
+  return (
+    <Box flexDirection="column" borderStyle="round" borderColor="cyan" paddingX={1}>
+      <Box justifyContent="space-between">
+        <Text>
+          <Text color="cyan" bold>
+            reasonix diff
+          </Text>
+          <Text dimColor> · A=</Text>
+          <Text color="blue">{a.label}</Text>
+          <Text dimColor> vs B=</Text>
+          <Text color="magenta">{b.label}</Text>
+        </Text>
+        <Text dimColor>{report.pairs.length} turns aligned</Text>
+      </Box>
+
+      <Box marginTop={1} gap={3}>
+        <Text>
+          <Text dimColor>cache </Text>
+          <Text>{(a.stats.cacheHitRatio * 100).toFixed(1)}%</Text>
+          <Text dimColor> → </Text>
+          <Text>{(b.stats.cacheHitRatio * 100).toFixed(1)}%</Text>
+          <Text color={cacheDelta >= 0 ? "green" : "red"} bold>
+            {"  "}
+            {cacheDelta >= 0 ? "+" : ""}
+            {(cacheDelta * 100).toFixed(1)}pp
+          </Text>
+        </Text>
+        <Text>
+          <Text dimColor>cost </Text>
+          <Text>${a.stats.totalCostUsd.toFixed(6)}</Text>
+          <Text dimColor> → </Text>
+          <Text>${b.stats.totalCostUsd.toFixed(6)}</Text>
+          <Text color={costDelta <= 0 ? "green" : "red"} bold>
+            {"  "}
+            {costDelta >= 0 ? "+" : ""}
+            {costDelta.toFixed(1)}%
+          </Text>
+        </Text>
+        <Text>
+          <Text dimColor>model calls </Text>
+          <Text>
+            {a.stats.turns} → {b.stats.turns}
+          </Text>
+        </Text>
+      </Box>
+
+      {prefixLine ? (
+        <Box marginTop={1}>
+          <Text dimColor italic>
+            {prefixLine}
+          </Text>
+        </Box>
+      ) : null}
+    </Box>
+  );
+}
+
+function Pane({
+  label,
+  headerColor,
+  records,
+}: {
+  label: string;
+  headerColor: "blue" | "magenta";
+  records: TurnPair["aTools"];
+}) {
+  return (
+    <Box
+      flexDirection="column"
+      flexGrow={1}
+      paddingX={1}
+      borderStyle="single"
+      borderColor={headerColor}
+    >
+      <Text color={headerColor} bold>
+        {label}
+      </Text>
+      {records.length === 0 ? (
+        <Box marginTop={1}>
+          <Text dimColor italic>
+            (no records on this side for this turn)
+          </Text>
+        </Box>
+      ) : (
+        <Static items={records.map((rec, i) => ({ key: `${label}-${i}`, rec }))}>
+          {({ key, rec }) => <RecordView key={key} rec={rec} compact />}
+        </Static>
+      )}
+    </Box>
+  );
+}
+
+function KindBadge({ kind }: { kind: TurnPair["kind"] }) {
+  if (kind === "match") {
+    return <Text color="green">✓ match</Text>;
+  }
+  if (kind === "diverge") {
+    return <Text color="yellow">★ diverge</Text>;
+  }
+  if (kind === "only_in_a") {
+    return <Text color="blue">← only in A</Text>;
+  }
+  return <Text color="magenta">→ only in B</Text>;
+}
+
+// ----------------------------------------------------------------------------
+
+function paneRecords(pair: TurnPair | undefined, side: "a" | "b"): TurnPair["aTools"] {
+  if (!pair) return [];
+  const tools = side === "a" ? pair.aTools : pair.bTools;
+  const assistant = side === "a" ? pair.aAssistant : pair.bAssistant;
+  const out: TurnPair["aTools"] = [...tools];
+  if (assistant) out.push(assistant);
+  return out;
+}

src/cli/ui/EditConfirm.tsx

@@ -0,0 +1,214 @@
+import { Box, Text, useStdout } from "ink";
+import React, { useMemo, useState } from "react";
+import { formatEditBlockDiff } from "../../code/diff-preview.js";
+import type { EditBlock } from "../../code/edit-blocks.js";
+import { ModalCard } from "./ModalCard.js";
+import { useKeystroke } from "./keystroke-context.js";
+
+/**
+ * Choice surfaced to the interceptor when the user resolves the modal:
+ *   - `apply`                → apply this edit, keep prompting on next.
+ *   - `reject`               → tell the model the user refused; do NOT
+ *                              retry the same edit.
+ *   - `apply-rest-of-turn`   → apply this edit AND every remaining edit
+ *                              this turn without further prompts. Resets
+ *                              at the next user turn.
+ *   - `flip-to-auto`         → apply this edit + persistently switch the
+ *                              session to AUTO mode (survives restart).
+ */
+export type EditReviewChoice = "apply" | "reject" | "apply-rest-of-turn" | "flip-to-auto";
+
+export interface EditConfirmProps {
+  block: EditBlock;
+  onChoose: (choice: EditReviewChoice) => void;
+}
+
+/**
+ * Overhead reserved for non-diff UI inside the modal: border (2),
+ * title (1), separator (1), file-header (1), scroll-indicator rows
+ * (up to 2), footer + margin (3), plus breathing room for the host
+ * TUI's chrome above (stats panel ≈ 4, historical live rows, prompt
+ * input ≈ 2). 18 rows absorbed before the diff gets any budget.
+ */
+const MODAL_OVERHEAD_ROWS = 18;
+
+/**
+ * Absolute floor on the diff viewport. If the terminal is absurdly
+ * short (< 26 rows total) we still show at least 8 diff lines so the
+ * modal is usable; the user scrolls more aggressively but can't end up
+ * with a zero-height viewport.
+ */
+const MIN_DIFF_ROWS = 8;
+
+/**
+ * Modal-style approval for a single model-proposed file edit.
+ *
+ * Why per-edit instead of end-of-turn batch: users reported they can't
+ * tell if the model is about to make one small change or seven sprawling
+ * ones until the turn is over. Per-edit prompts let the user intervene
+ * early — reject a bad direction before the model builds on it, or
+ * approve the first few and hit `a` to let the rest land.
+ *
+ * Diff viewport: we compute the UNCAPPED diff once, then slice to a
+ * height budget derived from terminal rows. Large diffs (100+ lines)
+ * are scrollable via j/k/↑/↓/Space/PgUp/PgDn/g/G — the user can page
+ * through the whole change before deciding, and the action footer
+ * never scrolls off the bottom. Before the scroll support a 97-line
+ * scene.ts diff truncated at "… 67 more …" which was unreviewable.
+ */
+export function EditConfirm({ block, onChoose }: EditConfirmProps) {
+  const { stdout } = useStdout();
+  const rows = stdout?.rows ?? 40;
+  const budget = Math.max(MIN_DIFF_ROWS, rows - MODAL_OVERHEAD_ROWS);
+
+  // Full diff — maxLines pushed high enough that the diff-preview
+  // renderer never inserts its own truncation marker. Context trimming
+  // (contextLines) still applies for tight scan.
+  const allLines = useMemo(
+    () => formatEditBlockDiff(block, { contextLines: 2, maxLines: 100_000, indent: "  " }),
+    [block],
+  );
+
+  const [scroll, setScroll] = useState(0);
+  const maxScroll = Math.max(0, allLines.length - budget);
+  // Clamp scroll if budget shrinks (terminal resized) after a previous
+  // keypress drove the offset past the new ceiling.
+  const effectiveScroll = Math.min(scroll, maxScroll);
+
+  useKeystroke((ev) => {
+    if (ev.paste) return;
+    const input = ev.input;
+    const key = ev;
+    // Action keys first — decision wins over scroll so a user who
+    // hammered PgDn can still hit `y` at the end without a stray
+    // extra scroll.
+    if (key.return || input === "y") {
+      onChoose("apply");
+      return;
+    }
+    if (input === "n") {
+      onChoose("reject");
+      return;
+    }
+    if (input === "a") {
+      onChoose("apply-rest-of-turn");
+      return;
+    }
+    if (input === "A") {
+      onChoose("flip-to-auto");
+      return;
+    }
+    // Scroll navigation — vim-ish (j/k) and emacs-ish (arrows) both
+    // work. Space for "next page" is the pager convention.
+    if (key.downArrow || input === "j") {
+      setScroll((s) => Math.min(maxScroll, s + 1));
+      return;
+    }
+    if (key.upArrow || input === "k") {
+      setScroll((s) => Math.max(0, s - 1));
+      return;
+    }
+    if (key.pageDown || input === " " || input === "f") {
+      setScroll((s) => Math.min(maxScroll, s + Math.max(1, budget - 2)));
+      return;
+    }
+    if (key.pageUp || input === "b") {
+      setScroll((s) => Math.max(0, s - Math.max(1, budget - 2)));
+      return;
+    }
+    if (input === "g") {
+      setScroll(0);
+      return;
+    }
+    if (input === "G") {
+      setScroll(maxScroll);
+      return;
+    }
+    // Esc falls through to the parent abort handler.
+  });
+
+  const isNew = block.search === "";
+  const removed = isNew ? 0 : (block.search.match(/\n/g)?.length ?? 0) + 1;
+  const added = block.replace === "" ? 0 : (block.replace.match(/\n/g)?.length ?? 0) + 1;
+  const tag = isNew ? "NEW" : "EDIT";
+
+  const visibleLines = allLines.slice(effectiveScroll, effectiveScroll + budget);
+  const hiddenAbove = effectiveScroll;
+  const hiddenBelow = Math.max(0, allLines.length - effectiveScroll - budget);
+  const totalLines = allLines.length;
+  const showScrollHud = hiddenAbove + hiddenBelow > 0;
+
+  const subtitleParts = [`-${removed} +${added} lines`];
+  if (showScrollHud) {
+    subtitleParts.push(
+      `viewing ${effectiveScroll + 1}-${effectiveScroll + visibleLines.length}/${totalLines}`,
+    );
+  }
+  return (
+    <ModalCard
+      accent={isNew ? "#86efac" : "#fcd34d"}
+      icon={isNew ? "✚" : "✎"}
+      title={`${tag}  ${block.path}`}
+      subtitle={subtitleParts.join("  ·  ")}
+    >
+      {hiddenAbove > 0 ? (
+        <Text
+          dimColor
+        >{`  ↑ ${hiddenAbove} line${hiddenAbove === 1 ? "" : "s"} above  (↑/k or PgUp)`}</Text>
+      ) : null}
+      <Box flexDirection="column">
+        {visibleLines.map((line, i) => {
+          const trimmed = line.trimStart();
+          const color = trimmed.startsWith("+")
+            ? "#4ade80"
+            : trimmed.startsWith("-")
+              ? "#f87171"
+              : undefined;
+          const dim = !color;
+          return (
+            <Text
+              // Stable-enough: slice only shifts by scroll; React keys only
+              // need to be unique within the current render.
+              // biome-ignore lint/suspicious/noArrayIndexKey: list is static per render
+              key={`diff-${effectiveScroll}-${i}`}
+              color={color}
+              dimColor={dim}
+            >
+              {line}
+            </Text>
+          );
+        })}
+      </Box>
+      {hiddenBelow > 0 ? (
+        <Text
+          dimColor
+        >{`  ↓ ${hiddenBelow} line${hiddenBelow === 1 ? "" : "s"} below  (↓/j or Space/PgDn)`}</Text>
+      ) : null}
+      <Box marginTop={1}>
+        <Text dimColor>
+          {"["}
+          <Text color="#67e8f9" bold>
+            y
+          </Text>
+          {"/Enter] apply  ·  ["}
+          <Text color="#67e8f9" bold>
+            n
+          </Text>
+          {"] reject  ·  ["}
+          <Text color="#67e8f9" bold>
+            a
+          </Text>
+          {"] apply rest  ·  ["}
+          <Text color="#67e8f9" bold>
+            A
+          </Text>
+          {"] flip AUTO  ·  ["}
+          <Text color="#67e8f9" bold>
+            ↑↓/Space
+          </Text>
+          {"] scroll  ·  [Esc] abort"}
+        </Text>
+      </Box>
+    </ModalCard>
+  );
+}

src/cli/ui/EventLog.tsx

@@ -0,0 +1,901 @@
+import { Box, Text, useStdout } from "ink";
+import React from "react";
+import { type TypedPlanState, isPlanStateEmpty } from "../../harvest.js";
+import type { BranchProgress, BranchSummary } from "../../loop.js";
+import type { TurnStats } from "../../telemetry.js";
+import type { PlanStep } from "../../tools/plan.js";
+import { PlanStateBlock } from "./PlanStateBlock.js";
+import { PlanStepList } from "./PlanStepList.js";
+import { Markdown } from "./markdown.js";
+import { COLOR, gradientCells } from "./theme.js";
+import { useElapsedSeconds, useTick } from "./ticker.js";
+import { formatDuration, summarizeToolResult } from "./tool-summary.js";
+
+export type DisplayRole =
+  | "user"
+  | "assistant"
+  | "tool"
+  | "system"
+  | "error"
+  | "info"
+  | "warning"
+  /**
+   * A plan body pushed to scrollback when the model calls `submit_plan`.
+   * Rendered through the full markdown pipeline (not truncated), so the
+   * user reads the whole thing in the permanent Static log and the
+   * PlanConfirm modal below it stays a tight picker.
+   */
+  | "plan"
+  /**
+   * One step of an approved plan ticked off via `mark_step_complete`.
+   * Rendered as a compact `✓ step-id · title — result (N/M)` row so
+   * the user can glance at the scrollback and see how far along the
+   * execution is without scrolling through every tool call.
+   */
+  | "step-progress"
+  /**
+   * Pushed once at session startup when an existing plan was loaded
+   * from disk. Renders as a bordered box with the step list and
+   * progress so the user sees exactly where they left off — much
+   * more useful than the bare "2/5 done" info line it replaced.
+   */
+  | "plan-resumed"
+  /**
+   * Read-only snapshot of an archived (completed) plan, pushed by
+   * the `/replay` slash. Visually distinct from `plan-resumed` —
+   * dim border + ⏪ icon — so the user immediately sees this is
+   * historical, not the active plan.
+   */
+  | "plan-replay";
+
+export interface DisplayEvent {
+  id: string;
+  role: DisplayRole;
+  text: string;
+  reasoning?: string;
+  planState?: TypedPlanState;
+  branch?: BranchSummary;
+  branchProgress?: BranchProgress;
+  toolName?: string;
+  /**
+   * 1-based position in the session's tool-call history. Rendered as a
+   * dim `/tool N` suffix on compact rows so the user can quickly jump
+   * to the full output via the existing `/tool` slash command.
+   */
+  toolIndex?: number;
+  /** Wall-clock duration in ms between tool_start and result. */
+  durationMs?: number;
+  stats?: TurnStats;
+  repair?: string;
+  streaming?: boolean;
+  toolCallBuild?: { name: string; chars: number; index?: number; readyCount?: number };
+  /**
+   * Populated on `step-progress` rows: the step id, optional title,
+   * completion counter, and optional notes. Rendered into the compact
+   * single-row layout — no other role reads these fields.
+   */
+  stepProgress?: {
+    stepId: string;
+    title?: string;
+    completed: number;
+    total: number;
+    notes?: string;
+  };
+  /**
+   * Populated on `plan-resumed` rows: the structured plan loaded from
+   * disk + the set of step ids the user had already completed +
+   * a relative-time hint for the header. Rendered as a bordered
+   * snapshot so the user picks back up immediately.
+   */
+  resumedPlan?: {
+    steps: PlanStep[];
+    completedStepIds: string[];
+    relativeTime: string;
+    /** Optional human-friendly title; rendered in the banner header when set. */
+    summary?: string;
+  };
+  /**
+   * Populated on `plan-replay` rows: the archived plan plus enough
+   * navigation context (index / total) for the user to know where
+   * they are in the archive history.
+   */
+  replayPlan?: {
+    summary?: string;
+    body?: string;
+    steps: PlanStep[];
+    completedStepIds: string[];
+    relativeTime: string;
+    archiveBasename: string;
+    index: number;
+    total: number;
+  };
+  /**
+   * Render a thin horizontal rule above this event. Used to mark
+   * "start of a new user turn" so long scrollbacks get visual
+   * pacing — without it, five-turn sessions read as one wall of
+   * text. Only the *first* user message in a session should leave
+   * this off; App.tsx sets it based on whether history is empty.
+   */
+  leadSeparator?: boolean;
+}
+
+/**
+ * Reasonix visual language: every event is anchored by a geometric
+ * glyph in its role color. Together they form a consistent alphabet
+ * (◇ ◆ ▣ ▥ ▲ ✦) the eye learns fast — no text labels needed after
+ * the first couple of turns. `◈` is the brand mark, reserved for
+ * the app header.
+ */
+const ROLE_GLYPH = {
+  user: "◇",
+  assistant: "◆",
+  assistantPulse: "◇", // pulse alternate for streaming state
+  toolOk: "▣",
+  toolErr: "▥",
+  warning: "▲",
+  error: "✦",
+} as const;
+
+function RoleGlyph({
+  glyph,
+  color,
+}: {
+  glyph: string;
+  color: "cyan" | "green" | "yellow" | "red" | "magenta" | "blue";
+}) {
+  return (
+    <Text color={color} bold>
+      {glyph}
+    </Text>
+  );
+}
+
+/**
+ * Solid-background pill for tool names. Mirrors the StatsPanel's mode
+ * pills so the visual language stays consistent across the screen:
+ * status (auto/review/plan), tool name, model. Status drives the
+ * background color — yellow for ok/in-flight, red for errors — so a
+ * scrollback full of tool dispatches reads at a glance.
+ */
+function ToolPill({ label, status }: { label: string; status: "ok" | "err" }) {
+  const bg = status === "err" ? "red" : "yellow";
+  const symbol = status === "err" ? "✗" : "✓";
+  return (
+    <Text backgroundColor={bg} color="black" bold>
+      {` ${symbol} ${label} `}
+    </Text>
+  );
+}
+
+/**
+ * Pad continuation lines so wrapped multi-line text aligns under the
+ * glyph indent instead of jumping back to column 0. Header is `glyph
+ * (1 col) + "  " (2 cols)`, so subsequent lines need 3 leading spaces
+ * to land under the body's first character.
+ */
+function indentContinuationLines(text: string): string {
+  if (!text.includes("\n")) return text;
+  return text.split("\n").join("\n   ");
+}
+
+export const EventRow = React.memo(function EventRow({
+  event,
+  projectRoot,
+}: {
+  event: DisplayEvent;
+  projectRoot?: string;
+}) {
+  if (event.role === "user") {
+    return (
+      <Box flexDirection="column">
+        {event.leadSeparator ? <TurnSeparator /> : null}
+        <Box>
+          <RoleGlyph glyph={ROLE_GLYPH.user} color="cyan" />
+          <Text>{"  "}</Text>
+          <Box
+            flexDirection="column"
+            borderStyle="single"
+            borderTop={false}
+            borderRight={false}
+            borderBottom={false}
+            borderColor={COLOR.user}
+            paddingLeft={1}
+          >
+            <Text>{indentContinuationLines(event.text)}</Text>
+          </Box>
+        </Box>
+      </Box>
+    );
+  }
+  if (event.role === "assistant") {
+    if (event.streaming) return <StreamingAssistant event={event} />;
+    return (
+      <Box flexDirection="column" marginTop={1}>
+        <Box>
+          <RoleGlyph glyph={ROLE_GLYPH.assistant} color="green" />
+          {event.stats ? (
+            <>
+              <Text>{"  "}</Text>
+              <Text backgroundColor={COLOR.assistant} color="black" bold>
+                {` ${event.stats.model.replace(/^deepseek-/, "")} `}
+              </Text>
+            </>
+          ) : null}
+        </Box>
+        <Box
+          flexDirection="column"
+          marginTop={1}
+          borderStyle="single"
+          borderTop={false}
+          borderRight={false}
+          borderBottom={false}
+          borderColor={COLOR.assistant}
+          paddingLeft={1}
+        >
+          {event.branch ? <BranchBlock branch={event.branch} /> : null}
+          {event.reasoning ? <ReasoningBlock reasoning={event.reasoning} /> : null}
+          {!isPlanStateEmpty(event.planState) ? (
+            <PlanStateBlock planState={event.planState!} />
+          ) : null}
+          {event.text ? (
+            <Markdown text={event.text} projectRoot={projectRoot} />
+          ) : (
+            <Text dimColor>(no content)</Text>
+          )}
+          {event.stats ? <StatsLine stats={event.stats} /> : null}
+          {event.repair ? <Text color={COLOR.accent}>{event.repair}</Text> : null}
+        </Box>
+      </Box>
+    );
+  }
+  if (event.role === "tool") {
+    // `edit_file` results get a dedicated multi-line diff renderer —
+    // colored line-by-line so `-` removals show red, `+` additions
+    // show green, unchanged context lines dim. Always full, never
+    // truncated: users need to see the whole change to trust /apply.
+    const isExplicitError = event.text.startsWith("ERROR:");
+    const isEditFile =
+      (event.toolName === "edit_file" || event.toolName?.endsWith("_edit_file")) &&
+      !isExplicitError;
+    if (isEditFile) {
+      return (
+        <Box flexDirection="column" marginTop={1}>
+          <Box>
+            <ToolPill label={event.toolName ?? "?"} status="ok" />
+            <Text dimColor>{"   diff:"}</Text>
+          </Box>
+          <Box
+            flexDirection="column"
+            marginTop={1}
+            borderStyle="single"
+            borderTop={false}
+            borderRight={false}
+            borderBottom={false}
+            borderColor={COLOR.tool}
+            paddingLeft={1}
+          >
+            <EditFileDiff text={event.text} />
+          </Box>
+        </Box>
+      );
+    }
+    // Compact one-line render for everything else. The summarizer
+    // produces a tool-aware one-liner (exit code for shell, line
+    // count for read_file, error tag for failures, ...). Full content
+    // remains accessible via `/tool N`, hinted as a dim suffix.
+    const summary = summarizeToolResult(event.toolName ?? "?", event.text);
+    const status: "ok" | "err" = summary.isError ? "err" : "ok";
+    const durationLabel =
+      event.durationMs !== undefined && event.durationMs >= 100
+        ? formatDuration(event.durationMs)
+        : "";
+    const indexHint = event.toolIndex !== undefined ? `  /tool ${event.toolIndex}` : "";
+    return (
+      <Box>
+        <ToolPill label={event.toolName ?? "?"} status={status} />
+        {durationLabel ? <Text dimColor>{`  ${durationLabel}`}</Text> : null}
+        <Text dimColor>{"  "}</Text>
+        <Text color={status === "err" ? "red" : undefined} dimColor={status === "ok"}>
+          {summary.summary}
+        </Text>
+        {indexHint ? <Text dimColor>{indexHint}</Text> : null}
+      </Box>
+    );
+  }
+  if (event.role === "error") {
+    return (
+      <Box marginTop={1}>
+        <Text backgroundColor="#f87171" color="black" bold>
+          {" ✦ ERROR "}
+        </Text>
+        <Text>{"  "}</Text>
+        <Text color="#f87171">{indentContinuationLines(event.text)}</Text>
+      </Box>
+    );
+  }
+  if (event.role === "info") {
+    // Detect tone from the text so the info row carries semantic
+    // weight: ▲/⚠ → warn, ✓ → ok, ✗/✖ → error, ↻ → reload, otherwise
+    // a neutral ▸. The leading glyph (if any) is consumed and the
+    // body renders dim.
+    const m = event.text.match(/^([▸▶▲⚠✓✗✖↻ⓘ])\s*(.*)$/s);
+    const lead = m?.[1] ?? "▸";
+    const body = m?.[2] ?? event.text;
+    let leadColor: string = COLOR.info;
+    if (lead === "▲" || lead === "⚠") leadColor = COLOR.warn;
+    else if (lead === "✓") leadColor = COLOR.ok;
+    else if (lead === "✗" || lead === "✖") leadColor = COLOR.err;
+    else if (lead === "↻") leadColor = COLOR.primary;
+    return (
+      <Box>
+        <Text color={leadColor} bold>
+          {lead}
+        </Text>
+        <Text> </Text>
+        <Text dimColor>{body}</Text>
+      </Box>
+    );
+  }
+  if (event.role === "plan") {
+    return (
+      <Box flexDirection="column" paddingX={1} marginY={1}>
+        <Box>
+          <Text bold color="cyan">
+            {"📋 plan proposed — pick a choice below"}
+          </Text>
+        </Box>
+        <Box marginTop={1} flexDirection="column">
+          <Markdown text={event.text} projectRoot={projectRoot} />
+        </Box>
+      </Box>
+    );
+  }
+  if (event.role === "step-progress") {
+    const sp = event.stepProgress;
+    const counter = sp && sp.total > 0 ? `${sp.completed}/${sp.total}` : "";
+    const label = sp?.title ? `${sp.stepId} · ${sp.title}` : (sp?.stepId ?? "");
+    return (
+      <Box flexDirection="column" marginTop={1}>
+        <Box>
+          <Text backgroundColor="#4ade80" color="black" bold>
+            {" ✓ STEP "}
+          </Text>
+          {counter ? (
+            <>
+              <Text>{"  "}</Text>
+              <Text color="#4ade80" bold>
+                {counter}
+              </Text>
+            </>
+          ) : null}
+          <Text>{"  "}</Text>
+          <Text color="#86efac">{label}</Text>
+        </Box>
+        {event.text ? (
+          <Box paddingLeft={2}>
+            <Text dimColor>{event.text}</Text>
+          </Box>
+        ) : null}
+        {sp?.notes ? (
+          <Box paddingLeft={2}>
+            <Text color="#fbbf24" dimColor>
+              {`note: ${sp.notes}`}
+            </Text>
+          </Box>
+        ) : null}
+      </Box>
+    );
+  }
+  if (event.role === "plan-resumed") {
+    const rp = event.resumedPlan;
+    if (!rp || rp.steps.length === 0) return null;
+    const total = rp.steps.length;
+    const done = rp.completedStepIds.length;
+    const completedSet = new Set(rp.completedStepIds);
+    const statuses = new Map(
+      rp.steps.map((s) => [
+        s.id,
+        completedSet.has(s.id) ? ("done" as const) : ("pending" as const),
+      ]),
+    );
+    // Focus the first pending step so the user immediately sees where
+    // execution will resume from. If the plan is fully done, no focus.
+    const nextStep = rp.steps.find((s) => !completedSet.has(s.id));
+    return (
+      <Box flexDirection="column" paddingX={1} marginY={1}>
+        <Box>
+          <Text backgroundColor="#67e8f9" color="black" bold>
+            {" ↻ RESUMED PLAN "}
+          </Text>
+          <Text>{"  "}</Text>
+          <Text color="#67e8f9" bold>
+            {`${done}/${total}`}
+          </Text>
+          <Text dimColor>{`  done  ·  last touched ${rp.relativeTime}`}</Text>
+        </Box>
+        {rp.summary ? (
+          <Box marginTop={1}>
+            <Text color="#67e8f9">{rp.summary}</Text>
+          </Box>
+        ) : null}
+        <Box marginTop={1} flexDirection="column">
+          <PlanStepList steps={rp.steps} statuses={statuses} focusStepId={nextStep?.id} />
+        </Box>
+      </Box>
+    );
+  }
+  if (event.role === "plan-replay") {
+    const r = event.replayPlan;
+    if (!r || r.steps.length === 0) return null;
+    const total = r.steps.length;
+    const completedSet = new Set(r.completedStepIds);
+    const done = completedSet.size;
+    const statuses = new Map(
+      r.steps.map((s) => [s.id, completedSet.has(s.id) ? ("done" as const) : ("pending" as const)]),
+    );
+    const navHint = r.total > 1 ? `  ·  ${r.index}/${r.total}` : "";
+    return (
+      <Box flexDirection="column" paddingX={1} marginY={1}>
+        <Box>
+          <Text backgroundColor="#94a3b8" color="black" bold>
+            {" ⏪ REPLAY "}
+          </Text>
+          <Text>{"  "}</Text>
+          <Text color="#94a3b8" bold>
+            {`${done}/${total}`}
+          </Text>
+          <Text dimColor>{`  done  ·  ${r.relativeTime}${navHint}`}</Text>
+        </Box>
+        {r.summary ? (
+          <Box marginTop={1}>
+            <Text color="#94a3b8">{r.summary}</Text>
+          </Box>
+        ) : null}
+        <Box>
+          <Text dimColor>{r.archiveBasename}</Text>
+        </Box>
+        {r.body ? (
+          <Box marginTop={1} flexDirection="column">
+            <Markdown text={r.body} projectRoot={projectRoot} />
+          </Box>
+        ) : null}
+        <Box marginTop={1} flexDirection="column">
+          <PlanStepList steps={r.steps} statuses={statuses} />
+        </Box>
+        <Box marginTop={1}>
+          <Text dimColor>
+            {r.total > 1
+              ? `(read-only · /replay ${r.index === 1 ? 2 : 1} for the ${r.index === 1 ? "next" : "newest"} archive)`
+              : "(read-only · this is an archived plan)"}
+          </Text>
+        </Box>
+      </Box>
+    );
+  }
+  if (event.role === "warning") {
+    return (
+      <Box>
+        <Text backgroundColor="#fbbf24" color="black" bold>
+          {" ▲ WARN "}
+        </Text>
+        <Text>{"  "}</Text>
+        <Text color="#fbbf24">{indentContinuationLines(event.text)}</Text>
+      </Box>
+    );
+  }
+  return (
+    <Box>
+      <Text>{event.text}</Text>
+    </Box>
+  );
+});
+
+/**
+ * Decorative gradient rule between turns. Uses the brand gradient
+ * (teal → fuchsia) so the boundary between "old turn" and "new
+ * turn" reads as a designed accent rather than a dim minus-sign
+ * row. Static — past separators live inside Ink's `<Static>`, so
+ * animation would freeze at tick=0 anyway.
+ */
+function TurnSeparator() {
+  const { stdout } = useStdout();
+  const cols = stdout?.columns ?? 80;
+  const width = Math.max(16, cols - 2);
+  // Reserve 5 cells for `  ◆  ` in the middle. Split the remainder
+  // into two gradient halves so the brand mark sits on the seam.
+  const sideWidth = Math.max(2, Math.floor((width - 5) / 2));
+  const leftCells = gradientCells(sideWidth, "─");
+  const rightCells = gradientCells(sideWidth, "─");
+  return (
+    <Box marginTop={1} marginBottom={1}>
+      {leftCells.map((c, i) => (
+        // biome-ignore lint/suspicious/noArrayIndexKey: fixed-width gradient row
+        <Text key={`tsep-l-${i}`} color={c.color}>
+          {c.ch}
+        </Text>
+      ))}
+      <Text color={COLOR.brand} bold>
+        {"  ◆  "}
+      </Text>
+      {rightCells.map((c, i) => (
+        // biome-ignore lint/suspicious/noArrayIndexKey: fixed-width gradient row
+        <Text key={`tsep-r-${i}`} color={c.color}>
+          {c.ch}
+        </Text>
+      ))}
+    </Box>
+  );
+}
+
+/**
+ * Render the payload of an `edit_file` tool result with proper
+ * diff coloring: first line is the header ("edited X (A→B chars)"),
+ * subsequent lines are prefixed with `-` (removed), `+` (added), or
+ * space (unchanged context). Unchanged lines render dim so the
+ * changed ones pop visually. No truncation — the whole diff is
+ * shown so the user can audit what landed before `/apply` or
+ * `git diff` review.
+ */
+function EditFileDiff({ text }: { text: string }) {
+  const lines = text.split(/\r?\n/);
+  // Line 0 is the status header ("edited X (A→B chars)"), Line 1 is
+  // the unified-diff hunk header ("@@ -N,M +N,M @@"), the rest is
+  // the colored diff body. The hunk header gets a magenta-bg pill —
+  // same idiom as the rest of the TUI — so it visually anchors each
+  // hunk. Body lines render with a colored gutter glyph + tinted bg
+  // for + and -, so the diff scans like a syntax-highlighted patch
+  // file rather than a wall of monochrome text.
+  const [statusHeader, hunkHeader, ...body] = lines;
+  return (
+    <Box flexDirection="column">
+      <Text dimColor>{` ${statusHeader ?? ""}`}</Text>
+      {hunkHeader !== undefined ? (
+        <Box marginTop={1}>
+          <Text backgroundColor="#c4b5fd" color="black" bold>
+            {` ${hunkHeader.trim()} `}
+          </Text>
+        </Box>
+      ) : null}
+      {body.map((line, i) => {
+        // Key includes the line content slice so React isn't forced
+        // to treat purely-positional identity; lines in the same
+        // diff don't reorder but could repeat (e.g. blank lines).
+        const key = `${i}-${line.slice(0, 32)}`;
+        // Strip the leading "  " indent diff-preview adds to every
+        // body line so the gutter glyph is column 0 regardless of
+        // formatter changes upstream.
+        const stripped = line.replace(/^ {2}/, "");
+        if (stripped.startsWith("- ")) {
+          return (
+            <Box key={key}>
+              <Text color="#f87171" bold>
+                {"− "}
+              </Text>
+              <Text color="#fca5a5">{stripped.slice(2)}</Text>
+            </Box>
+          );
+        }
+        if (stripped.startsWith("+ ")) {
+          return (
+            <Box key={key}>
+              <Text color="#4ade80" bold>
+                {"+ "}
+              </Text>
+              <Text color="#86efac">{stripped.slice(2)}</Text>
+            </Box>
+          );
+        }
+        // Context line (starts with " ") or unknown — dim.
+        return (
+          <Box key={key}>
+            <Text dimColor>{"  "}</Text>
+            <Text dimColor>{stripped}</Text>
+          </Box>
+        );
+      })}
+    </Box>
+  );
+}
+
+function BranchBlock({ branch }: { branch: BranchSummary }) {
+  return (
+    <Box flexDirection="column" marginBottom={1}>
+      <Box>
+        <Text backgroundColor="#93c5fd" color="black" bold>
+          {` ⎇ BRANCH ×${branch.budget} `}
+        </Text>
+        <Text>{"  "}</Text>
+        <Text color="#93c5fd">picked </Text>
+        <Text color="#93c5fd" bold>
+          #{branch.chosenIndex}
+        </Text>
+      </Box>
+      <Box paddingLeft={2} marginTop={1}>
+        {branch.uncertainties.map((u, i) => {
+          const chosen = i === branch.chosenIndex;
+          const t = (branch.temperatures[i] ?? 0).toFixed(1);
+          return (
+            // biome-ignore lint/suspicious/noArrayIndexKey: branch index is positional and stable
+            <Text key={`b-${i}`}>
+              <Text color={chosen ? "#93c5fd" : "#475569"} bold={chosen}>
+                {chosen ? "▸ " : "  "}
+              </Text>
+              <Text color={chosen ? "#93c5fd" : "#94a3b8"} bold={chosen}>
+                {`#${i}`}
+              </Text>
+              <Text dimColor>{` T=${t}  u=${u}   `}</Text>
+            </Text>
+          );
+        })}
+      </Box>
+    </Box>
+  );
+}
+
+function ReasoningBlock({ reasoning }: { reasoning: string }) {
+  const max = 260;
+  const flat = reasoning.replace(/\s+/g, " ").trim();
+  // Show the TAIL of the reasoning rather than the head. R1 opens
+  // with generic scaffolding ("let me look at the structure...") that
+  // repeats across turns and hides the part users actually want to
+  // see — the decision right before the model commits to an action.
+  // Users can dump the full reasoning with `/think` if needed.
+  const preview =
+    flat.length <= max ? flat : `… (+${flat.length - max} earlier chars) ${flat.slice(-max)}`;
+  return (
+    <Box marginBottom={1}>
+      <Text backgroundColor={COLOR.accent} color="black" bold>
+        {" ⋯ thinking "}
+      </Text>
+      <Text> </Text>
+      <Text color={COLOR.accent} italic dimColor>
+        {preview}
+      </Text>
+    </Box>
+  );
+}
+
+/**
+ * Compact progress view rendered while a turn is still streaming. We keep
+ * this to a fixed ~3-line footprint so the dynamic region never scrolls past
+ * the terminal viewport and leaves artifacts in scrollback.
+ */
+function Elapsed() {
+  const s = useElapsedSeconds();
+  const mm = String(Math.floor(s / 60)).padStart(2, "0");
+  const ss = String(s % 60).padStart(2, "0");
+  return <Text dimColor>{`${mm}:${ss}`}</Text>;
+}
+
+/**
+ * Animated role glyph for the actively-streaming assistant. Alternates
+ * ◆ ↔ ◇ every ~480ms so the user can see the model is alive even
+ * during R1's long pre-first-byte silence. Settles back to a static
+ * ◆ once the turn ends (StreamingAssistant is unmounted).
+ */
+function PulsingAssistantGlyph() {
+  const tick = useTick();
+  const on = Math.floor(tick / 4) % 2 === 0;
+  return (
+    <Text color="green" bold>
+      {on ? ROLE_GLYPH.assistant : ROLE_GLYPH.assistantPulse}
+    </Text>
+  );
+}
+
+function StreamingAssistant({ event }: { event: DisplayEvent }) {
+  if (event.branchProgress) {
+    const p = event.branchProgress;
+    // completed=0 means we've just started; no sample has finished yet.
+    if (p.completed === 0) {
+      return (
+        <Box flexDirection="column" marginTop={1}>
+          <Box>
+            <PulsingAssistantGlyph />
+            <Text color="blue">
+              {"  ⎇ launching "}
+              {p.total}
+              {" parallel samples (R1 thinking in parallel)…  "}
+            </Text>
+            <Elapsed />
+          </Box>
+          <Text color="yellow">
+            {"  "}spread across T=0.0/0.5/1.0 · reasoner typically takes 30-90s — this is normal
+          </Text>
+        </Box>
+      );
+    }
+    const pct = Math.round((p.completed / p.total) * 100);
+    return (
+      <Box flexDirection="column" marginTop={1}>
+        <Box>
+          <PulsingAssistantGlyph />
+          <Text color="blue">
+            {"  ⎇ branching "}
+            {p.completed}/{p.total}
+            {" ("}
+            {pct}
+            {"%)  "}
+          </Text>
+          <Elapsed />
+        </Box>
+        <Text dimColor>
+          {"  latest #"}
+          {p.latestIndex}
+          {" T="}
+          {p.latestTemperature.toFixed(1)}
+          {" u="}
+          {p.latestUncertainties}
+          {p.completed < p.total ? "  · waiting for other samples…" : "  · selecting winner…"}
+        </Text>
+      </Box>
+    );
+  }
+
+  const tail = lastLine(event.text, 140);
+  const reasoningTail = event.reasoning ? lastLine(event.reasoning, 120) : "";
+  const toolCallBuild = event.toolCallBuild;
+  // Four distinct phases a turn can be in — label them plainly so
+  // the user doesn't have to decode "streaming · 391 + think 4506
+  // chars" to figure out what's happening:
+  //   pre-first-byte: request in flight, no bytes back yet
+  //   reasoning-only: R1 thinking, no visible content yet
+  //   tool-call-only: tool_call arguments streaming, no content/reasoning bytes
+  //   writing: content streaming (R1 has already produced its thought)
+  //   both: rare — content present AND reasoning still growing
+  // We can't cheaply distinguish "reasoning still growing" from
+  // "reasoning finished but we already saw it", so when content is
+  // present we just say "writing response" and surface both counts.
+  const preFirstByte = !event.text && !event.reasoning && !toolCallBuild;
+  const reasoningOnly = !event.text && !!event.reasoning && !toolCallBuild;
+  const toolCallOnly = !event.text && !event.reasoning && !!toolCallBuild;
+  // Phase pill — solid bg color per phase so the user reads
+  // "what's happening" at a glance from across the screen.
+  let pillBg: string;
+  let pillText: string;
+  let label: string;
+  if (preFirstByte) {
+    pillBg = "#fbbf24"; // amber
+    pillText = "WAITING";
+    label = "request sent · waiting for server";
+  } else if (reasoningOnly) {
+    pillBg = "#c4b5fd"; // violet
+    pillText = "THINKING";
+    label = `${event.reasoning?.length ?? 0} chars of thought`;
+  } else if (toolCallOnly) {
+    pillBg = "#f0abfc"; // fuchsia
+    pillText = "DISPATCH";
+    label = `assembling${formatToolCallIndex(toolCallBuild)} <${toolCallBuild.name}> · ${toolCallBuild.chars} chars${formatReadyTail(toolCallBuild)}`;
+  } else {
+    pillBg = "#86efac"; // green
+    pillText = "WRITING";
+    const parts: string[] = [`${event.text.length} chars`];
+    if (event.reasoning) parts.push(`after ${event.reasoning.length} reasoning`);
+    if (toolCallBuild) {
+      parts.push(
+        `tool${formatToolCallIndex(toolCallBuild)} <${toolCallBuild.name}> ${toolCallBuild.chars}c${formatReadyTail(toolCallBuild)}`,
+      );
+    }
+    label = parts.join(" · ");
+  }
+  return (
+    <Box flexDirection="column" marginTop={1}>
+      <Box>
+        <PulsingAssistantGlyph />
+        <Text>{"  "}</Text>
+        <Pulse />
+        <Text> </Text>
+        <Text backgroundColor={pillBg} color="black" bold>
+          {` ${pillText} `}
+        </Text>
+        <Text dimColor>{`  ${label}  `}</Text>
+        <Elapsed />
+      </Box>
+      {reasoningTail ? (
+        <Box paddingLeft={3}>
+          <Text color="#c4b5fd" italic dimColor>
+            ↳ {reasoningTail}
+          </Text>
+        </Box>
+      ) : null}
+      {tail ? (
+        <Box paddingLeft={3}>
+          <Text dimColor>▸ {tail}</Text>
+        </Box>
+      ) : preFirstByte ? (
+        // Non-dim amber: first-time users misread the dim version as
+        // "app frozen". The reassurance has to be VISIBLE to do its job.
+        <Box paddingLeft={3}>
+          <Text color="#fbbf24" italic>
+            {"waiting for first byte — typical 5–60s depending on model + load"}
+          </Text>
+        </Box>
+      ) : reasoningOnly ? (
+        <Box paddingLeft={3}>
+          <Text color="#c4b5fd" italic>
+            {"R1 thinks before it speaks — body text arrives when reasoning finishes (20–90s)"}
+          </Text>
+        </Box>
+      ) : toolCallOnly ? (
+        <Box paddingLeft={3}>
+          <Text color="#f0abfc" italic>
+            {"tool-call arguments streaming — about to dispatch"}
+          </Text>
+        </Box>
+      ) : event.reasoning ? (
+        <Box paddingLeft={3}>
+          <Text color="#fbbf24" italic>
+            {"R1 still reasoning — body text or tool call arrives when thinking finishes"}
+          </Text>
+        </Box>
+      ) : null}
+    </Box>
+  );
+}
+
+/**
+ * Blinking indicator so the user can tell the stream is alive even
+ * when the reasoner hasn't produced body text yet. Uses the shared
+ * tick (TICK_MS ≈ 120ms) scaled down 4× so the visible blink rate
+ * lands around 500ms — feels like a heartbeat, not a progress bar.
+ */
+function Pulse() {
+  const tick = useTick();
+  const frames = ["⠋", "⠙", "⠹", "⠸", "⠼", "⠴", "⠦", "⠧", "⠇", "⠏"];
+  return <Text color="cyan">{frames[Math.floor(tick / 4) % frames.length]}</Text>;
+}
+
+/**
+ * "(call 3)" suffix for the tool-call label when we have the index.
+ * Hides when the turn only has one call so the common case stays tidy.
+ */
+function formatToolCallIndex(tb: { index?: number; readyCount?: number } | undefined): string {
+  if (!tb || tb.index === undefined) return "";
+  // Only show the index when this isn't obviously the first + only call.
+  if (tb.index === 0 && (tb.readyCount ?? 0) === 0) return "";
+  return ` (call ${tb.index + 1})`;
+}
+
+/**
+ * "· 2 ready" tail that answers "how many tool calls have finished
+ * streaming so far this turn?" — user feedback for multi-file turns
+ * where the response takes 10–30s to stream. Hidden until readyCount
+ * > 0 so single-call turns aren't cluttered.
+ */
+function formatReadyTail(tb: { readyCount?: number } | undefined): string {
+  const n = tb?.readyCount ?? 0;
+  if (n <= 0) return "";
+  return ` · ${n} ready`;
+}
+
+function lastLine(s: string, maxChars: number): string {
+  const flat = s.replace(/\s+/g, " ").trim();
+  if (!flat) return "";
+  return flat.length <= maxChars ? flat : `…${flat.slice(-maxChars)}`;
+}
+
+function StatsLine({ stats }: { stats: TurnStats }) {
+  const hit = (stats.cacheHitRatio * 100).toFixed(1);
+  const hitColor =
+    stats.cacheHitRatio >= 0.7 ? "#4ade80" : stats.cacheHitRatio >= 0.4 ? "#fcd34d" : "#f87171";
+  return (
+    <Box marginTop={1}>
+      <Text color={hitColor} bold>
+        {`⌬ ${hit}%`}
+      </Text>
+      <Text dimColor>{"  ·  "}</Text>
+      <Text color="#94a3b8">
+        {"in "}
+        <Text color="#67e8f9" bold>
+          {stats.usage.promptTokens}
+        </Text>
+        {" → out "}
+        <Text color="#c4b5fd" bold>
+          {stats.usage.completionTokens}
+        </Text>
+      </Text>
+      <Text dimColor>{"  ·  "}</Text>
+      <Text color="#86efac" bold>{`$${stats.cost.toFixed(6)}`}</Text>
+    </Box>
+  );
+}

src/cli/ui/LiveRows.tsx

@@ -0,0 +1,333 @@
+import { Box, Text, useStdout } from "ink";
+// biome-ignore lint/style/useImportType: tsconfig jsx=react needs React as a runtime value (classic transform)
+import React from "react";
+import type { ApplyResult } from "../../code/edit-blocks.js";
+import type { EditMode } from "../../config.js";
+import type { JobRegistry } from "../../tools/jobs.js";
+import { useElapsedSeconds, useTick } from "./ticker.js";
+
+export const SPINNER_FRAMES = ["⠋", "⠙", "⠹", "⠸", "⠼", "⠴", "⠦", "⠧", "⠇", "⠏"];
+
+/**
+ * Transient "what's happening now" row shown during silent phases
+ * between the primary events — harvest round-trip, R1 thinking
+ * about a tool result before the next streaming delta, forced
+ * summary. Matches OngoingToolRow's visual language (braille
+ * spinner + elapsed seconds) so the user's eyes track the same
+ * spot regardless of which kind of wait it is.
+ */
+export function StatusRow({ text }: { text: string }) {
+  const tick = useTick();
+  const elapsed = useElapsedSeconds();
+  return (
+    <Box marginY={1} paddingX={1}>
+      <Text color="#c4b5fd" bold>
+        {SPINNER_FRAMES[tick % SPINNER_FRAMES.length]}
+      </Text>
+      <Text>{"  "}</Text>
+      <Text color="#c4b5fd">{text}</Text>
+      <Text dimColor>{`  ·  ${elapsed}s`}</Text>
+    </Box>
+  );
+}
+
+/**
+ * One-line bottom status bar showing the current edit mode, pending
+ * queue size (review only), an undo hint (auto only / after /apply),
+ * and the Shift+Tab nudge. Rendered immediately above PromptInput so
+ * the mode is always in peripheral vision when the user's eyes are at
+ * the prompt. Flashes briefly on mode change so Shift+Tab gives a
+ * visible acknowledgment without the user having to scan the header.
+ *
+ * The plan-mode pill takes precedence — when plan mode is on, writes
+ * are bounced regardless of edit mode, so surfacing it is more useful
+ * than the review/auto toggle.
+ */
+export function ModeStatusBar({
+  editMode,
+  pendingCount,
+  flash,
+  planMode,
+  undoArmed,
+  jobs,
+}: {
+  editMode: EditMode;
+  pendingCount: number;
+  flash: boolean;
+  planMode: boolean;
+  undoArmed: boolean;
+  jobs?: JobRegistry;
+}) {
+  // Subscribe to tick so the jobs count stays live — the registry is
+  // mutated outside React, so we need a periodic repaint to catch it.
+  // No-op when there's no registry (chat mode / tests).
+  useTick();
+  const running = jobs?.runningCount() ?? 0;
+  const jobsTag =
+    running > 0 ? (
+      <Text color="yellow" bold>{`  ·  ⏵ ${running} job${running === 1 ? "" : "s"}`}</Text>
+    ) : null;
+  // The same mode pill is already in the StatsPanel header — here we
+  // skip the pill and keep just a tight inline hint right above the
+  // input so the user has the actionable bit (what y/n/u/Shift+Tab
+  // do) without the whole tutorial.
+  if (planMode) {
+    return (
+      <ModeBarFrame>
+        <ModePill label="PLAN MODE" bg="red" flash={flash} />
+        <Text dimColor>{"   writes gated · /plan off to leave"}</Text>
+        {jobsTag}
+      </ModeBarFrame>
+    );
+  }
+  const isAuto = editMode === "auto";
+  const label = isAuto ? "AUTO" : "REVIEW";
+  const bg = isAuto ? "magenta" : "cyan";
+  const mid = isAuto
+    ? "edits land now · u to undo"
+    : pendingCount > 0
+      ? `${pendingCount} queued · y apply · n discard`
+      : "edits queued · y apply · n discard";
+  return (
+    <ModeBarFrame>
+      <ModePill label={label} bg={bg} flash={flash} />
+      <Text dimColor>{`   ${mid} · Shift+Tab to flip`}</Text>
+      {jobsTag}
+    </ModeBarFrame>
+  );
+}
+
+/**
+ * Wraps the bottom mode/jobs row in a dim top rule + side padding
+ * so the modeline reads as its own zone, separate from the prompt
+ * input above. Keeps the live region border-free (the rule is a
+ * single Text row, not a bordered Box) so Ink's eraseLines miscount
+ * stays out of it.
+ */
+function ModeBarFrame({ children }: { children: React.ReactNode }) {
+  const { stdout } = useStdout();
+  const cols = stdout?.columns ?? 80;
+  const ruleWidth = Math.max(20, cols - 2);
+  return (
+    <Box flexDirection="column">
+      <Box paddingX={1}>
+        <Text color="#475569" dimColor>
+          {"╌".repeat(ruleWidth)}
+        </Text>
+      </Box>
+      <Box paddingX={1}>{children}</Box>
+    </Box>
+  );
+}
+
+/**
+ * Solid-background mode badge so the bottom status bar reads at a
+ * glance like a real editor's modeline (vim/helix style) instead of a
+ * dim text label that blends into the prompt above. `flash` inverts
+ * briefly after a mode flip — the existing modeFlash signal — for a
+ * "yes, it changed" acknowledgement.
+ */
+function ModePill({
+  label,
+  bg,
+  flash,
+}: {
+  label: string;
+  bg: "magenta" | "cyan" | "red";
+  flash: boolean;
+}) {
+  return (
+    <Text backgroundColor={bg} color="white" bold inverse={flash}>
+      {` ${label} `}
+    </Text>
+  );
+}
+
+/**
+ * "Just auto-applied N edits — press u to undo" banner. Rendered below
+ * the live rows after an auto-mode edit batch lands, visible for 5s.
+ * `useTick` drives a crude live countdown so the user sees the window
+ * shrinking. State cleanup (the banner disappearing) happens in the
+ * parent's setTimeout — the component is purely display.
+ */
+export function UndoBanner({
+  banner,
+}: {
+  banner: { results: ApplyResult[]; expiresAt: number };
+}) {
+  useTick();
+  const remainingMs = Math.max(0, banner.expiresAt - Date.now());
+  const remainingSec = Math.ceil(remainingMs / 1000);
+  const ok = banner.results.filter((r) => r.status === "applied" || r.status === "created").length;
+  const total = banner.results.length;
+  const urgent = remainingSec <= 1;
+  return (
+    <Box marginY={1} paddingX={1}>
+      <Text backgroundColor="#c4b5fd" color="black" bold>
+        {` ✓ AUTO-APPLIED ${ok}/${total} `}
+      </Text>
+      <Text dimColor>{"   press "}</Text>
+      <Text backgroundColor="#67e8f9" color="black" bold>
+        {" u "}
+      </Text>
+      <Text dimColor>{" to undo   "}</Text>
+      <Text color={urgent ? "#f87171" : "#c4b5fd"} bold={urgent}>
+        {`${remainingSec}s`}
+      </Text>
+    </Box>
+  );
+}
+
+/**
+ * Live one-line indicator for a running subagent. Sits below the
+ * OngoingToolRow (the parent's tool dispatch row for `spawn_subagent`)
+ * so the user sees both layers at once: outer "spawn_subagent
+ * running…" + inner "⌬ subagent: <task> · iter N · 12.3s". Cleared
+ * when the subagent ends; a one-line summary lands in historical.
+ */
+export function SubagentRow({
+  activity,
+}: {
+  activity: { task: string; iter: number; elapsedMs: number };
+}) {
+  const tick = useTick();
+  const seconds = (activity.elapsedMs / 1000).toFixed(1);
+  return (
+    <Box paddingLeft={3}>
+      <Text color="#c4b5fd" bold>
+        {SPINNER_FRAMES[tick % SPINNER_FRAMES.length]}
+      </Text>
+      <Text>{"  "}</Text>
+      <Text backgroundColor="#c4b5fd" color="black" bold>
+        {" ⌬ subagent "}
+      </Text>
+      <Text color="#c4b5fd">{`  ${activity.task}`}</Text>
+      <Text dimColor>{`   iter ${activity.iter}  ·  ${seconds}s`}</Text>
+    </Box>
+  );
+}
+
+/**
+ * Live spinner row while a tool call is in flight. Without this the
+ * window between the model's `tool_calls` decision and the tool's
+ * result (often seconds for a multi-KB `filesystem_edit_file`) looks
+ * like the app has frozen — the streaming assistant display is
+ * already cleared and the input is disabled, so there's nothing to
+ * look at.
+ *
+ * Shows three signals: a braille spinner (liveness), an elapsed
+ * timer in seconds (so "long" has a number attached), and a
+ * per-tool summary of the most informative argument fields (path,
+ * edits count, pattern, etc.). As of 0.4.8, MCP progress frames
+ * (`notifications/progress`) land here too — bar + "n/N" when the
+ * server reports a total, free-form message when not.
+ */
+export function OngoingToolRow({
+  tool,
+  progress,
+}: {
+  tool: { name: string; args?: string };
+  progress: { progress: number; total?: number; message?: string } | null;
+}) {
+  const tick = useTick();
+  const elapsed = useElapsedSeconds();
+  const summary = summarizeToolArgs(tool.name, tool.args);
+  return (
+    <Box marginY={1} flexDirection="column" paddingX={1}>
+      <Box>
+        <Text color="#fcd34d" bold>
+          {SPINNER_FRAMES[tick % SPINNER_FRAMES.length]}
+        </Text>
+        <Text>{"  "}</Text>
+        <Text backgroundColor="#fcd34d" color="black" bold>
+          {` ⏵ ${tool.name} `}
+        </Text>
+        <Text color="#fcd34d">{" running"}</Text>
+        <Text dimColor>{`  ·  ${elapsed}s`}</Text>
+      </Box>
+      {progress ? (
+        <Box paddingLeft={3}>
+          <Text color="#67e8f9">{renderProgressLine(progress)}</Text>
+        </Box>
+      ) : null}
+      {summary ? (
+        <Box paddingLeft={3}>
+          <Text dimColor>{summary}</Text>
+        </Box>
+      ) : null}
+    </Box>
+  );
+}
+
+/**
+ * Render an MCP progress frame as a single line. When the server
+ * reports `total`, show an ASCII progress bar + "n/total pct%";
+ * otherwise just "progress" + optional message. Width is modest
+ * so the line fits even in a narrow terminal.
+ */
+function renderProgressLine(p: { progress: number; total?: number; message?: string }): string {
+  const msg = p.message ? `  ${p.message}` : "";
+  if (p.total && p.total > 0) {
+    const ratio = Math.max(0, Math.min(1, p.progress / p.total));
+    const width = 20;
+    const filled = Math.round(ratio * width);
+    const bar = "█".repeat(filled) + "░".repeat(width - filled);
+    const pct = (ratio * 100).toFixed(0);
+    return `[${bar}] ${p.progress}/${p.total} ${pct}%${msg}`;
+  }
+  return `progress: ${p.progress}${msg}`;
+}
+
+/**
+ * Turn raw JSON tool arguments into a one-line human summary. For
+ * common filesystem MCP tools we pull the actually-useful fields; for
+ * anything else we fall back to a truncated raw string so the user
+ * still sees *something* beyond the tool name.
+ *
+ * Match on suffix (e.g. `_read_file`) rather than exact name because
+ * `bridgeMcpTools({ namePrefix: "filesystem_" })` prepends the server
+ * namespace — tools arrive as `filesystem_read_file` in practice but
+ * callers might wire up anonymous too.
+ */
+function summarizeToolArgs(name: string, args?: string): string {
+  if (!args || args === "{}") return "";
+  let parsed: Record<string, unknown>;
+  try {
+    parsed = JSON.parse(args) as Record<string, unknown>;
+  } catch {
+    // Unparseable JSON — show a head slice so user at least sees
+    // what the model tried.
+    return args.length > 80 ? `${args.slice(0, 80)}…` : args;
+  }
+  const hasSuffix = (s: string) => name === s || name.endsWith(`_${s}`);
+  const path = typeof parsed.path === "string" ? parsed.path : undefined;
+  if (hasSuffix("read_file")) {
+    const head = typeof parsed.head === "number" ? `, head=${parsed.head}` : "";
+    const tail = typeof parsed.tail === "number" ? `, tail=${parsed.tail}` : "";
+    return `path: ${path ?? "?"}${head}${tail}`;
+  }
+  if (hasSuffix("write_file")) {
+    const content = typeof parsed.content === "string" ? parsed.content : "";
+    return `path: ${path ?? "?"} (${content.length} chars)`;
+  }
+  if (hasSuffix("edit_file")) {
+    const edits = Array.isArray(parsed.edits) ? parsed.edits.length : 0;
+    return `path: ${path ?? "?"} (${edits} edit${edits === 1 ? "" : "s"})`;
+  }
+  if (hasSuffix("list_directory") || hasSuffix("directory_tree")) {
+    return `path: ${path ?? "?"}`;
+  }
+  if (hasSuffix("search_files")) {
+    const pattern = typeof parsed.pattern === "string" ? parsed.pattern : "?";
+    return `path: ${path ?? "?"} · pattern: ${pattern}`;
+  }
+  if (hasSuffix("move_file")) {
+    const src = typeof parsed.source === "string" ? parsed.source : "?";
+    const dst = typeof parsed.destination === "string" ? parsed.destination : "?";
+    return `${src} → ${dst}`;
+  }
+  if (hasSuffix("get_file_info")) {
+    return `path: ${path ?? "?"}`;
+  }
+  return args.length > 80 ? `${args.slice(0, 80)}…` : args;
+}

src/cli/ui/ModalCard.tsx

@@ -0,0 +1,70 @@
+/**
+ * Shared visual frame for confirmation modals (ChoiceConfirm,
+ * PlanConfirm, ShellConfirm, EditConfirm, PlanCheckpointConfirm,
+ * PlanReviseConfirm). Each modal opens inside the live region — so
+ * we keep the frame to plain Text rules and bg-pill headers, no
+ * Ink `borderStyle` (that's the eraseLines miscount class of bug).
+ *
+ * Layout:
+ *
+ *   ▔▔▔▔▔▔▔▔▔▔▔▔▔▔▔▔▔▔▔▔▔▔▔▔▔▔▔▔▔▔▔▔▔▔▔▔▔▔▔▔▔▔▔▔
+ *      [ ICON  TITLE ]    optional subtitle
+ *
+ *      <children — body of the modal>
+ *
+ *   ▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁
+ *
+ * Color drives the accent (top + bottom rules + title pill bg)
+ * so the user learns to recognize "magenta = choice", "cyan =
+ * plan", "red = shell", "yellow = edit review" by sight.
+ */
+
+import { Box, Text, useStdout } from "ink";
+// biome-ignore lint/style/useImportType: tsconfig jsx=react needs React in value scope
+import React from "react";
+
+export interface ModalCardProps {
+  /** Accent color — title pill bg + top/bottom rule color. */
+  accent: string;
+  /** Section title shown in the bg-pill header. */
+  title: string;
+  /** Optional dim subtitle next to the title. */
+  subtitle?: string;
+  /** Optional leading glyph inside the title pill (icon). */
+  icon?: string;
+  children: React.ReactNode;
+}
+
+export function ModalCard({
+  accent,
+  title,
+  subtitle,
+  icon,
+  children,
+}: ModalCardProps): React.ReactElement {
+  const { stdout } = useStdout();
+  const cols = stdout?.columns ?? 80;
+  const ruleWidth = Math.min(80, Math.max(28, cols - 4));
+  const titleText = icon ? ` ${icon}  ${title} ` : ` ${title} `;
+  return (
+    <Box flexDirection="column" paddingX={1} marginY={1}>
+      <Box>
+        <Text color={accent}>{"▔".repeat(ruleWidth)}</Text>
+      </Box>
+      <Box marginTop={1}>
+        <Text backgroundColor={accent} color="black" bold>
+          {titleText}
+        </Text>
+        {subtitle ? <Text dimColor>{`   ${subtitle}`}</Text> : null}
+      </Box>
+      <Box marginTop={1} flexDirection="column">
+        {children}
+      </Box>
+      <Box marginTop={1}>
+        <Text color={accent} dimColor>
+          {"▁".repeat(ruleWidth)}
+        </Text>
+      </Box>
+    </Box>
+  );
+}

src/cli/ui/PlanCheckpointConfirm.tsx

@@ -0,0 +1,118 @@
+/**
+ * Modal-style picker shown when `mark_step_complete` pauses the loop
+ * via `PlanCheckpointError`. Three choices:
+ *
+ *   1. Continue — push "Step X done, proceed." so the model starts
+ *      the next step on the next turn.
+ *   2. Revise   — open a feedback input; whatever the user types
+ *      becomes a synthetic "user feedback for remaining steps" message.
+ *      The model can then adjust its approach without starting the
+ *      whole plan over.
+ *   3. Stop     — push "User stopped the plan. Summarize what was
+ *      done." so the run ends cleanly rather than being abandoned.
+ *
+ * The ✓ step-progress scrollback row is pushed separately (by App.tsx
+ * at checkpoint detection time), so this modal stays a tight picker —
+ * no need to re-render the step body here.
+ */
+
+import { Box } from "ink";
+import React from "react";
+import type { PlanStep } from "../../tools/plan.js";
+import { ModalCard } from "./ModalCard.js";
+import { PlanStepList, type StepStatus } from "./PlanStepList.js";
+import { SingleSelect } from "./Select.js";
+
+export type CheckpointChoice = "continue" | "revise" | "stop";
+
+export interface PlanCheckpointConfirmProps {
+  stepId: string;
+  title?: string;
+  completed: number;
+  total: number;
+  /** Full step list from the approved plan, when available. */
+  steps?: PlanStep[];
+  /** Set of stepIds the model has marked complete so far. */
+  completedStepIds?: Set<string>;
+  onChoose: (choice: CheckpointChoice) => void;
+}
+
+function PlanCheckpointConfirmInner({
+  stepId,
+  title,
+  completed,
+  total,
+  steps,
+  completedStepIds,
+  onChoose,
+}: PlanCheckpointConfirmProps) {
+  const label = title ? `${stepId} · ${title}` : stepId;
+  const counter = total > 0 ? `${completed}/${total}` : "";
+  const isLast = total > 0 && completed >= total;
+  const statuses = buildStatusMap(steps, completedStepIds, stepId, isLast);
+  const subtitle = counter ? `${counter}  ·  ${label}` : label;
+  return (
+    <ModalCard accent="#86efac" icon="✓" title="checkpoint — step done" subtitle={subtitle}>
+      {steps && steps.length > 0 ? (
+        <Box marginBottom={1} flexDirection="column">
+          <PlanStepList steps={steps} statuses={statuses} focusStepId={stepId} />
+        </Box>
+      ) : null}
+      <SingleSelect
+        initialValue={isLast ? "stop" : "continue"}
+        items={[
+          {
+            value: "continue",
+            label: "Continue — run the next step",
+            hint: "Model resumes with the next step. Use this when the result looks right and you don't need to tweak the remaining plan.",
+          },
+          {
+            value: "revise",
+            label: "Revise — give feedback before the next step",
+            hint: "Stay paused, type guidance (scope changes, skip steps, alternative approach). The model adjusts the remaining plan based on your message.",
+          },
+          {
+            value: "stop",
+            label: "Stop — end the plan here",
+            hint: "Model summarizes what was done and ends. Remaining steps are skipped.",
+          },
+        ]}
+        onSubmit={(v) => onChoose(v as CheckpointChoice)}
+        onCancel={() => onChoose("stop")}
+        footer="[↑↓] navigate  ·  [Enter] select  ·  [Esc] stop"
+      />
+    </ModalCard>
+  );
+}
+
+export const PlanCheckpointConfirm = React.memo(PlanCheckpointConfirmInner);
+
+/**
+ * Derive a status map from the plan + completion set + current step.
+ * The currently-just-finished step always renders as "done" even if
+ * completedStepIds hasn't been flushed yet (it gets added in the
+ * same render cycle, order not guaranteed). Steps ahead of the
+ * cursor are "pending"; the next step after the current one isn't
+ * marked "running" because nothing is actually running while the
+ * picker is up — that belongs to the post-continue state.
+ */
+function buildStatusMap(
+  steps: PlanStep[] | undefined,
+  completedStepIds: Set<string> | undefined,
+  currentStepId: string,
+  isLast: boolean,
+): Map<string, StepStatus> {
+  const map = new Map<string, StepStatus>();
+  if (!steps) return map;
+  for (const step of steps) {
+    if (completedStepIds?.has(step.id) || step.id === currentStepId) {
+      map.set(step.id, "done");
+    } else {
+      map.set(step.id, "pending");
+    }
+  }
+  if (isLast) {
+    // Every step is done; leave as "done" — no "running" overlay.
+  }
+  return map;
+}

src/cli/ui/PlanConfirm.tsx

@@ -0,0 +1,100 @@
+/**
+ * Modal-style approval for a `submit_plan` proposal.
+ *
+ * Three choices:
+ *   1. Approve + implement — exits plan mode, pushes a synthetic user
+ *      message telling the model to implement the plan now.
+ *   2. Refine — stays in plan mode; tells the model to explore more
+ *      and submit an improved plan.
+ *   3. Cancel — exits plan mode, drops the plan, tells the model the
+ *      user didn't want any of it.
+ *
+ * The plan BODY is NOT rendered inside this modal — App.tsx pushes it
+ * into the Static scrollback as a `role: "plan"` display event the
+ * moment submit_plan fires. That's a one-time markdown render into
+ * permanent history, so the user reads the full proposal above and
+ * the modal below stays a tight picker. The previous design (body
+ * rendered inside the modal with an aggressive line clamp) left users
+ * staring at "(25 more lines truncated)" and unable to approve safely.
+ */
+
+import { Box, Text } from "ink";
+import React from "react";
+import type { PlanStep } from "../../tools/plan.js";
+import { ModalCard } from "./ModalCard.js";
+import { PlanStepList } from "./PlanStepList.js";
+import { SingleSelect } from "./Select.js";
+
+export type PlanConfirmChoice = "approve" | "refine" | "cancel";
+
+export interface PlanConfirmProps {
+  plan: string;
+  steps?: PlanStep[];
+  /** Optional human-friendly title from the model — surfaced in the header. */
+  summary?: string;
+  onChoose: (choice: PlanConfirmChoice) => void;
+  projectRoot?: string;
+}
+
+function PlanConfirmInner({ plan, steps, summary, onChoose }: PlanConfirmProps) {
+  // Crude signal for "the model left questions or risks for me" — the
+  // typical section headings. Triggers an extra hint toward the Refine
+  // option so users know where to answer them.
+  const hasOpenQuestions =
+    /^#{1,6}\s*(open[-\s]?questions?|risks?|unknowns?|assumptions?|unclear)/im.test(plan) ||
+    /^#{1,6}\s*(待确认|开放问题|风险|未知|假设|不确定)/im.test(plan);
+
+  return (
+    <ModalCard
+      accent="#67e8f9"
+      icon="📋"
+      title="plan proposed"
+      subtitle={summary ?? "approve / refine / cancel"}
+    >
+      {hasOpenQuestions ? (
+        <Box marginBottom={1}>
+          <Text color="#fbbf24">
+            ▲ the plan flags open questions or risks — pick{" "}
+            <Text bold>Refine / answer questions</Text> to write concrete answers before the model
+            moves on.
+          </Text>
+        </Box>
+      ) : null}
+      {steps && steps.length > 0 ? (
+        <Box marginBottom={1} flexDirection="column">
+          <PlanStepList steps={steps} />
+        </Box>
+      ) : null}
+      <SingleSelect
+        initialValue={hasOpenQuestions ? "refine" : "approve"}
+        items={[
+          {
+            value: "approve",
+            label: "Approve and implement",
+            hint: "Exit plan mode. The model starts executing. You'll get a text input to add any last instructions (or just press Enter to skip).",
+          },
+          {
+            value: "refine",
+            label: "Refine / answer questions",
+            hint: "Stay in plan mode. Write answers, modifications, or critiques; the model revises and re-submits.",
+          },
+          {
+            value: "cancel",
+            label: "Cancel",
+            hint: "Exit plan mode. Drop the plan; the model won't implement it.",
+          },
+        ]}
+        onSubmit={(v) => onChoose(v as PlanConfirmChoice)}
+        onCancel={() => onChoose("cancel")}
+        footer="[↑↓] navigate  ·  [Enter] select  ·  [Esc] cancel"
+      />
+    </ModalCard>
+  );
+}
+
+// React.memo: parent App re-renders every 120ms while the global ticker
+// is running (even with the live status rows hidden — context changes
+// propagate). Unless props change, skip re-rendering the heavy Markdown
+// subtree. Default shallow prop compare is fine — `plan` + `onChoose`
+// identity + `projectRoot` are the only fields that change.
+export const PlanConfirm = React.memo(PlanConfirmInner);

src/cli/ui/PlanRefineInput.tsx

@@ -0,0 +1,133 @@
+/**
+ * Inline text input shown after the user picks Approve or Refine in
+ * PlanConfirm. Collects free-form feedback before the loop resumes.
+ *
+ * Why both paths: the plan may contain open questions or risks the
+ * model asked the user to weigh in on. If the user just picks Approve
+ * with no chance to answer, the model implements against its own
+ * guesses. This input lets the user answer questions, pass last-minute
+ * constraints, or (on Refine) request concrete changes. Empty input is
+ * fine for Approve (skip straight to implement) and triggers a
+ * "ask the user clarifying questions" path for Refine.
+ *
+ * Kept minimal: single-line prompt, Enter to submit, Esc to return to
+ * the picker without resuming.
+ */
+
+import { Box, Text } from "ink";
+import React, { useState } from "react";
+import { ModalCard } from "./ModalCard.js";
+import { useKeystroke } from "./keystroke-context.js";
+import { useTick } from "./ticker.js";
+
+export interface PlanRefineInputProps {
+  /**
+   * Which path the user is on. approve = "implement with these last
+   * instructions"; refine = "revise the plan with this feedback";
+   * checkpoint-revise = mid-execution pause, user is tweaking the
+   * remaining plan after seeing a step's result; choice-custom = user
+   * typed an off-list answer to an ask_choice branch. Drives the
+   * header + hint text so users know what kind of message they're
+   * writing.
+   */
+  mode: "approve" | "refine" | "checkpoint-revise" | "choice-custom";
+  /** Called with trimmed feedback. Empty string is allowed. */
+  onSubmit: (feedback: string) => void;
+  /** Called when the user presses Esc to return to the picker. */
+  onCancel: () => void;
+}
+
+export function PlanRefineInput({ mode, onSubmit, onCancel }: PlanRefineInputProps) {
+  const [value, setValue] = useState("");
+
+  useKeystroke((ev) => {
+    if (ev.paste) {
+      // Insert paste content as-is. Multi-line pastes flatten via
+      // newlines becoming spaces because this is a single-line input.
+      setValue((v) => v + ev.input.replace(/\r?\n/g, " "));
+      return;
+    }
+    if (ev.escape) {
+      onCancel();
+      return;
+    }
+    if (ev.return) {
+      onSubmit(value.trim());
+      return;
+    }
+    if (ev.backspace || ev.delete) {
+      setValue((v) => v.slice(0, -1));
+      return;
+    }
+    // Filter out non-printable chars; accept ordinary text + CJK.
+    if (ev.input && !ev.ctrl && !ev.meta) {
+      setValue((v) => v + ev.input);
+    }
+  });
+
+  const tick = useTick();
+  // Slow blink for the cursor block (~480 ms on/off). Same cadence
+  // as the wordmark's brand-mark pulse; reads as "input is alive".
+  const cursorOn = Math.floor(tick / 4) % 2 === 0;
+
+  const meta =
+    mode === "approve"
+      ? {
+          title: "approving — any last instructions?",
+          icon: "📋",
+          accent: "#67e8f9",
+        }
+      : mode === "checkpoint-revise"
+        ? {
+            title: "revising — what should change before the next step?",
+            icon: "✏",
+            accent: "#fbbf24",
+          }
+        : mode === "choice-custom"
+          ? {
+              title: "custom answer — type whatever fits",
+              icon: "🔀",
+              accent: "#f0abfc",
+            }
+          : {
+              title: "refining — what should the model change?",
+              icon: "✏",
+              accent: "#fbbf24",
+            };
+  const hint =
+    mode === "approve"
+      ? "Answer questions the plan raised, add constraints, or just press Enter to approve as-is."
+      : mode === "checkpoint-revise"
+        ? "Scope change, skip steps, alternative approach — the model adjusts the remaining plan."
+        : mode === "choice-custom"
+          ? "Free-form reply. The model reads it verbatim and proceeds — no need to match the listed options."
+          : "Describe what's wrong or missing, or answer questions the plan raised.";
+  const blankHint =
+    mode === "approve"
+      ? " (Enter with blank = approve without extra instructions.)"
+      : mode === "checkpoint-revise"
+        ? " (Enter with blank = continue with the current plan.)"
+        : mode === "choice-custom"
+          ? " (Enter with blank = ask the model what you actually want.)"
+          : " (Enter with blank = ask the model to list concrete questions.)";
+
+  return (
+    <ModalCard accent={meta.accent} icon={meta.icon} title={meta.title}>
+      <Box marginBottom={1}>
+        <Text dimColor>
+          {hint} Enter to send · Esc to return to the picker.
+          {value === "" ? blankHint : ""}
+        </Text>
+      </Box>
+      <Box>
+        <Text color={meta.accent} bold>
+          {"› "}
+        </Text>
+        <Text>{value}</Text>
+        <Text color={meta.accent} bold>
+          {cursorOn ? "▍" : " "}
+        </Text>
+      </Box>
+    </ModalCard>
+  );
+}

src/cli/ui/PlanReviseConfirm.tsx

@@ -0,0 +1,141 @@
+/**
+ * Modal shown when the model proposes a plan revision via
+ * `revise_plan`. Renders a step-level diff between the old remaining
+ * tail and the new proposed tail:
+ *
+ *    ●● ✓ step-2 · Wire middleware           (kept, dim)
+ *  − ●●● ✗ step-3 · Migrate session cookies  (removed, red)
+ *  + ●●  ▶ step-3 · Skip cookie migration    (added, green)
+ *  + ●●  ▶ step-4 · Update cookie tests      (added, green)
+ *
+ * Two buttons: Accept / Reject. Accept replaces the in-memory plan's
+ * remaining steps with the new ones; Reject leaves the original plan
+ * intact and lets the model continue. The picker's border is amber
+ * to distinguish from the green checkpoint picker — revisions are a
+ * different decision point, deserve a different visual lane.
+ */
+
+import { Box, Text } from "ink";
+import React from "react";
+import type { PlanStep } from "../../tools/plan.js";
+import { ModalCard } from "./ModalCard.js";
+import { SingleSelect } from "./Select.js";
+
+export type ReviseChoice = "accept" | "reject";
+
+export interface PlanReviseConfirmProps {
+  reason: string;
+  /** Remaining steps from the current plan (before this revision). */
+  oldRemaining: PlanStep[];
+  /** Remaining steps the model is proposing as a replacement. */
+  newRemaining: PlanStep[];
+  /** Optional updated plan summary. */
+  summary?: string;
+  onChoose: (choice: ReviseChoice) => void;
+}
+
+interface DiffRow {
+  kind: "kept" | "removed" | "added";
+  step: PlanStep;
+}
+
+function computeDiff(oldSteps: PlanStep[], newSteps: PlanStep[]): DiffRow[] {
+  const oldIds = new Set(oldSteps.map((s) => s.id));
+  const newIds = new Set(newSteps.map((s) => s.id));
+  const rows: DiffRow[] = [];
+  // Show removed (in old, not in new) first — preserve original order.
+  for (const s of oldSteps) {
+    if (!newIds.has(s.id)) rows.push({ kind: "removed", step: s });
+  }
+  // Then walk new list. Steps in both lists render as kept; new-only as added.
+  for (const s of newSteps) {
+    rows.push({ kind: oldIds.has(s.id) ? "kept" : "added", step: s });
+  }
+  return rows;
+}
+
+function riskDots(risk: PlanStep["risk"]): { dots: string; color: string } {
+  switch (risk) {
+    case "high":
+      return { dots: "●●●", color: "#f87171" };
+    case "med":
+      return { dots: "●● ", color: "#fbbf24" };
+    case "low":
+      return { dots: "●  ", color: "#4ade80" };
+    default:
+      return { dots: "   ", color: "#94a3b8" };
+  }
+}
+
+function PlanReviseConfirmInner({
+  reason,
+  oldRemaining,
+  newRemaining,
+  summary,
+  onChoose,
+}: PlanReviseConfirmProps) {
+  const rows = computeDiff(oldRemaining, newRemaining);
+  const removedCount = rows.filter((r) => r.kind === "removed").length;
+  const addedCount = rows.filter((r) => r.kind === "added").length;
+  const keptCount = rows.filter((r) => r.kind === "kept").length;
+  return (
+    <ModalCard
+      accent="#fbbf24"
+      icon="✏"
+      title="plan revision proposed"
+      subtitle={`−${removedCount}  +${addedCount}  ·  ${keptCount} kept`}
+    >
+      <Box marginBottom={1}>
+        <Text>{reason}</Text>
+      </Box>
+      {summary ? (
+        <Box marginBottom={1}>
+          <Text dimColor>{`updated summary: ${summary}`}</Text>
+        </Box>
+      ) : null}
+      <Box marginBottom={1} flexDirection="column">
+        {rows.map((row) => {
+          const risk = riskDots(row.step.risk);
+          const prefix = row.kind === "removed" ? "−" : row.kind === "added" ? "+" : " ";
+          const prefixColor =
+            row.kind === "removed" ? "#f87171" : row.kind === "added" ? "#4ade80" : "#94a3b8";
+          const dim = row.kind === "kept";
+          const strike = row.kind === "removed";
+          return (
+            <Box key={`${row.kind}-${row.step.id}`}>
+              <Text color={prefixColor} bold>
+                {`${prefix} `}
+              </Text>
+              <Text color={risk.color} bold dimColor={dim}>
+                {risk.dots}
+              </Text>
+              <Text dimColor={dim} strikethrough={strike}>
+                {` ${row.step.id} · ${row.step.title}`}
+              </Text>
+            </Box>
+          );
+        })}
+      </Box>
+      <SingleSelect
+        initialValue="accept"
+        items={[
+          {
+            value: "accept",
+            label: "Accept revision — apply the new step list",
+            hint: "Replaces the remaining plan with the proposed steps. Done steps are untouched.",
+          },
+          {
+            value: "reject",
+            label: "Reject — keep the original plan",
+            hint: "Drops the proposal. Model continues with the original remaining steps.",
+          },
+        ]}
+        onSubmit={(v) => onChoose(v as ReviseChoice)}
+        onCancel={() => onChoose("reject")}
+        footer="[↑↓] navigate  ·  [Enter] select  ·  [Esc] reject"
+      />
+    </ModalCard>
+  );
+}
+
+export const PlanReviseConfirm = React.memo(PlanReviseConfirmInner);

src/cli/ui/PlanStateBlock.tsx

@@ -0,0 +1,47 @@
+/**
+ * Shared Ink block that renders a TypedPlanState. Used by the live chat
+ * EventLog AND by the RecordView in replay/diff TUIs, so harvest output
+ * looks identical live and on replay.
+ *
+ * Colors are semantic (not decorative):
+ *   - subgoals:       cyan         — structure / plan
+ *   - hypotheses:     green        — current beliefs (like assistant)
+ *   - uncertainties:  yellow       — attention required (like tool)
+ *   - rejected paths: red dim      — ruled out (muted, like error-but-resolved)
+ *
+ * Only the label is colored + bold. The items themselves render in the
+ * terminal's default foreground, so they stay readable on any background —
+ * which is why the old single-magenta block was hard to see on dark themes.
+ */
+
+import { Box, Text } from "ink";
+import React from "react";
+import type { TypedPlanState } from "../../harvest.js";
+
+type FieldColor = string;
+
+export function PlanStateBlock({ planState }: { planState: TypedPlanState }) {
+  const fields: Array<[string, string[], FieldColor, boolean]> = [];
+  if (planState.subgoals.length) fields.push(["subgoals", planState.subgoals, "#67e8f9", false]);
+  if (planState.hypotheses.length)
+    fields.push(["hypotheses", planState.hypotheses, "#86efac", false]);
+  if (planState.uncertainties.length)
+    fields.push(["uncertainties", planState.uncertainties, "#fcd34d", false]);
+  if (planState.rejectedPaths.length)
+    fields.push(["rejected", planState.rejectedPaths, "#94a3b8", true]);
+  if (fields.length === 0) return null;
+
+  return (
+    <Box flexDirection="column" marginBottom={1}>
+      {fields.map(([label, items, color, dim]) => (
+        <Box key={label}>
+          <Text backgroundColor={color} color="black" bold dimColor={dim}>
+            {` ${label} ${items.length} `}
+          </Text>
+          <Text>{"  "}</Text>
+          <Text dimColor={dim}>{items.join(" · ")}</Text>
+        </Box>
+      ))}
+    </Box>
+  );
+}

src/cli/ui/PlanStepList.tsx

@@ -0,0 +1,159 @@
+/**
+ * Shared compact renderer for a plan's structured step list. Used by
+ * PlanConfirm (on approval) and PlanCheckpointConfirm (mid-execution)
+ * so the user always sees the same visual representation of the plan.
+ *
+ * Layout per step:
+ *
+ *    ● ✓ step-1 · Extract tokens into a module
+ *    ●●▶ step-2 · Migrate session cookies
+ *    ●●●  step-3 · Update tests
+ *
+ * The risk gutter (1–3 dots, green/yellow/red) is the signal the user
+ * learns to scan: high-risk steps are what deserves review before
+ * approve; low-risk is noise.
+ */
+
+import { Box, Text } from "ink";
+import React from "react";
+import type { PlanStep, PlanStepRisk } from "../../tools/plan.js";
+
+export type StepStatus = "pending" | "running" | "done" | "skipped";
+
+export interface PlanStepListProps {
+  steps: PlanStep[];
+  /**
+   * Map of stepId → status. Missing ids default to "pending" so a
+   * plan just submitted (no completions yet) renders cleanly.
+   */
+  statuses?: Map<string, StepStatus> | Record<string, StepStatus>;
+  /**
+   * Optional current step — rendered with a `›` gutter mark so the
+   * user sees which one just completed / is about to run.
+   */
+  focusStepId?: string;
+}
+
+function riskDots(risk: PlanStep["risk"]): {
+  dots: string;
+  color: "green" | "yellow" | "red" | "gray";
+} {
+  switch (risk) {
+    case "high":
+      return { dots: "●●●", color: "red" };
+    case "med":
+      return { dots: "●● ", color: "yellow" };
+    case "low":
+      return { dots: "●  ", color: "green" };
+    default:
+      return { dots: "   ", color: "gray" };
+  }
+}
+
+function getStatus(stepId: string, statuses: PlanStepListProps["statuses"]): StepStatus {
+  if (!statuses) return "pending";
+  if (statuses instanceof Map) {
+    return statuses.get(stepId) ?? "pending";
+  }
+  return statuses[stepId] ?? "pending";
+}
+
+function PlanStepListInner({ steps, statuses, focusStepId }: PlanStepListProps) {
+  if (steps.length === 0) return null;
+  const hasAnyRisk = steps.some((s) => s.risk !== undefined);
+  const doneCount = Array.from({ length: steps.length }, (_, i) =>
+    getStatus(steps[i]!.id, statuses),
+  ).filter((s) => s === "done").length;
+  const pct = Math.round((doneCount / steps.length) * 100);
+
+  return (
+    <Box flexDirection="column">
+      <Box>
+        <Text dimColor>
+          {`${steps.length} step${steps.length === 1 ? "" : "s"}`}
+          {doneCount > 0 ? ` · ${doneCount}/${steps.length} done (${pct}%)` : ""}
+          {hasAnyRisk ? " · risk: " : ""}
+        </Text>
+        {hasAnyRisk ? <RiskLegend /> : null}
+      </Box>
+      <Box flexDirection="column" marginTop={1}>
+        {steps.map((step) => {
+          const status = getStatus(step.id, statuses);
+          const focus = focusStepId === step.id;
+          const risk = riskDots(step.risk);
+          const titleDim = status === "done" || status === "skipped";
+          return (
+            <Box key={step.id}>
+              <Text color={focus ? "#67e8f9" : "gray"} bold={focus}>
+                {focus ? "▸ " : "  "}
+              </Text>
+              <Text color={risk.color} bold>
+                {risk.dots}
+              </Text>
+              <Text> </Text>
+              <StatusBadge status={status} />
+              <Text> </Text>
+              <Text dimColor={titleDim} bold={focus}>
+                {`${step.id} · ${step.title}`}
+              </Text>
+            </Box>
+          );
+        })}
+      </Box>
+    </Box>
+  );
+}
+
+/**
+ * Status pill — solid-bg badge per step state. Reads at a glance
+ * better than a glyph + color text: ` DONE `, ` RUN `, ` SKIP `,
+ * ` PEND `. The label widths are normalized so the column under
+ * the badge stays aligned even when statuses mix.
+ */
+function StatusBadge({ status }: { status: StepStatus }) {
+  switch (status) {
+    case "done":
+      return (
+        <Text backgroundColor="#4ade80" color="black" bold>
+          {" ✓ DONE "}
+        </Text>
+      );
+    case "running":
+      return (
+        <Text backgroundColor="#67e8f9" color="black" bold>
+          {" ▶ RUN  "}
+        </Text>
+      );
+    case "skipped":
+      return (
+        <Text backgroundColor="#94a3b8" color="black" bold>
+          {" — SKIP "}
+        </Text>
+      );
+    default:
+      return (
+        <Text color="#94a3b8" dimColor>
+          {" ☐ PEND "}
+        </Text>
+      );
+  }
+}
+
+function RiskLegend() {
+  return (
+    <Box>
+      <Text color="green">●</Text>
+      <Text dimColor> low </Text>
+      <Text color="yellow">●●</Text>
+      <Text dimColor> med </Text>
+      <Text color="red">●●●</Text>
+      <Text dimColor> high</Text>
+    </Box>
+  );
+}
+
+export const PlanStepList = React.memo(PlanStepListInner);
+
+export function riskOf(step: PlanStep): PlanStepRisk | undefined {
+  return step.risk;
+}

src/cli/ui/PromptInput.tsx

@@ -0,0 +1,560 @@
+import { Box, Text, useStdout } from "ink";
+// biome-ignore lint/style/useImportType: tsconfig jsx=react needs React as a runtime value (classic transform compiles JSX to React.createElement)
+import React, { useRef, useState } from "react";
+import { useKeystroke } from "./keystroke-context.js";
+import { type MultilineKey, lineAndColumn, processMultilineKey } from "./multiline-keys.js";
+import {
+  PASTE_SENTINEL_RANGE,
+  type PasteEntry,
+  encodePasteSentinel,
+  expandPasteSentinels,
+  listPasteIdsInBuffer,
+  makePasteEntry,
+} from "./paste-sentinels.js";
+import { type Segment, buildViewport, stringCells } from "./prompt-viewport.js";
+import { GRADIENT } from "./theme.js";
+
+/**
+ * Visual anchor: a left vertical rule (▎ + space) running down every
+ * line of the input. Colored with the accent color so disabled state
+ * dims it; gives the input area a clear "you type here" boundary
+ * without using bordered Boxes (those amplified Ink's eraseLines
+ * miscount on Windows). Length is fixed at 2 so the prefix-cell math
+ * stays trivial.
+ */
+const BAR = "▎ ";
+
+/**
+ * Prompt input v2 — no Ink useInput, no Yoga text wrapping, no
+ * cursor blink. Replaces the bordered-Box / multi-Text approach
+ * that was driving the Windows ghost-row regressions.
+ *
+ * Pipeline:
+ *   - Subscribes to the global keystroke bus (which is fed by our
+ *     own raw stdin parser, NOT Ink's parse-keypress).
+ *   - Pure events: `paste` events go to the paste registry; everything
+ *     else flows through `processMultilineKey` (the existing reducer
+ *     with all the cursor / submit / history-recall semantics).
+ *   - Render: one logical line per <Box> row. Each row renders as
+ *     EXACTLY one visual row — content longer than the visible cell
+ *     budget is clipped via `buildViewport`, with `‹` / `›` markers
+ *     where content is hidden. The cursor moves the viewport so it
+ *     stays visible.
+ *
+ * Cursor blinks at ~480 ms half-period. The ticker that drives the
+ * blink also flows the left-bar gradient and the wordmark, so
+ * we're already paying for re-render every tick — the cursor blink
+ * is free on top of that. Disabled state freezes the cursor solid
+ * so the disabled prompt doesn't compete with the active spinner.
+ */
+
+export interface PromptInputProps {
+  value: string;
+  onChange: (v: string) => void;
+  onSubmit: (v: string) => void;
+  disabled?: boolean;
+  placeholder?: string;
+  /**
+   * History recall. Fired when ↑/↓ hits a buffer boundary (empty
+   * buffer, or cursor already at the first/last line of a multi-line
+   * buffer). Parent walks its prompt history and swaps the value via
+   * `onChange`. Absent → keys are consumed silently.
+   */
+  onHistoryPrev?: () => void;
+  onHistoryNext?: () => void;
+}
+
+export function PromptInput({
+  value,
+  onChange,
+  onSubmit,
+  disabled,
+  placeholder,
+  onHistoryPrev,
+  onHistoryNext,
+}: PromptInputProps) {
+  const [cursor, setCursor] = useState(value.length);
+
+  // Paste registry — keyed by sentinel id, holds original content.
+  const pastesRef = useRef<Map<number, PasteEntry>>(new Map());
+  const nextPasteIdRef = useRef<number>(0);
+
+  // Track external value replacement (history recall, slash completion).
+  // When the parent swaps `value` we snap cursor to end.
+  const lastLocalValueRef = useRef(value);
+  if (value !== lastLocalValueRef.current) {
+    lastLocalValueRef.current = value;
+    if (cursor !== value.length) setCursor(value.length);
+  }
+
+  /**
+   * Register one paste blob and insert its sentinel at the current
+   * cursor. Used both by `paste` events from the stdin reader (the
+   * normal path on terminals that support DECSET 2004) and by the
+   * fallback path inside `processMultilineKey` for chunks that
+   * arrived without bracketed-paste markers.
+   */
+  const registerPaste = (content: string) => {
+    const v = lastLocalValueRef.current;
+    const c = cursor;
+    const id = nextPasteIdRef.current % PASTE_SENTINEL_RANGE;
+    nextPasteIdRef.current = id + 1;
+    pastesRef.current.set(id, makePasteEntry(id, content));
+    const sentinel = encodePasteSentinel(id);
+    const next = v.slice(0, c) + sentinel + v.slice(c);
+    lastLocalValueRef.current = next;
+    onChange(next);
+    setCursor(c + 1);
+  };
+
+  useKeystroke((ev) => {
+    if (disabled) return;
+    if (ev.paste) {
+      // Bracketed-paste content delivered by the stdin reader.
+      // Insert as one sentinel regardless of length.
+      if (ev.input.length > 0) registerPaste(ev.input);
+      return;
+    }
+    const key: MultilineKey = {
+      input: ev.input,
+      return: ev.return,
+      shift: ev.shift,
+      ctrl: ev.ctrl,
+      meta: ev.meta,
+      backspace: ev.backspace,
+      delete: ev.delete,
+      tab: ev.tab,
+      upArrow: ev.upArrow,
+      downArrow: ev.downArrow,
+      leftArrow: ev.leftArrow,
+      rightArrow: ev.rightArrow,
+      escape: ev.escape,
+      pageUp: ev.pageUp,
+      pageDown: ev.pageDown,
+    };
+    const action = processMultilineKey(value, cursor, key);
+    if (action.pasteRequest) {
+      registerPaste(action.pasteRequest.content);
+      return;
+    }
+    if (action.next !== null) {
+      lastLocalValueRef.current = action.next;
+      onChange(action.next);
+    }
+    if (action.cursor !== null) {
+      setCursor(action.cursor);
+    }
+    if (action.submit) {
+      const raw = action.submitValue ?? value;
+      const expanded = expandPasteSentinels(raw, pastesRef.current);
+      // GC unreachable paste entries — anything backspace'd out of
+      // the buffer before submit. Keeps the registry from growing
+      // unbounded across many turns.
+      const reachable = new Set(listPasteIdsInBuffer(raw));
+      for (const id of pastesRef.current.keys()) {
+        if (!reachable.has(id)) pastesRef.current.delete(id);
+      }
+      onSubmit(expanded);
+    }
+    if (action.historyHandoff === "prev") onHistoryPrev?.();
+    if (action.historyHandoff === "next") onHistoryNext?.();
+  }, !disabled);
+
+  // ── Render ──────────────────────────────────────────────────────
+
+  const { stdout } = useStdout();
+  const cols = stdout?.columns ?? 80;
+  const narrow = cols <= 90;
+  const promptBody = narrow ? "› " : "you › ";
+  const promptPrefix = BAR + promptBody;
+  const continuationIndent = BAR + " ".repeat(promptBody.length);
+  const prefixCells = promptPrefix.length;
+  // Reserve 2 cells for the surrounding `paddingX={1}` plus 1 cell
+  // for the cursor block when at end-of-line. Net visible budget per
+  // line.
+  const visibleCells = Math.max(8, cols - prefixCells - 3);
+
+  const placeholderActive = narrow
+    ? "type a message, or /command"
+    : "type a message, or /command  ·  [Ctrl+J] newline  ·  [Ctrl+P/N] history";
+  const effectivePlaceholder = disabled
+    ? (placeholder ?? "…waiting for response…")
+    : (placeholder ?? placeholderActive);
+
+  const lines = value.length > 0 ? value.split("\n") : [""];
+  const accentColor = disabled ? "gray" : "cyan";
+  // Static bar + static cursor. Earlier versions flowed the bar
+  // gradient and blinked the cursor via the global ticker; both
+  // drove per-tick re-renders that interleaved badly with terminal
+  // resize (Ink's eraseLines miscounts logical vs visual rows on
+  // wrap, ghost frames stack). The bar still gets a gradient — just
+  // a fixed sweep based on row index, no time component.
+  const barColorAt = (rowIdx: number): string =>
+    disabled ? "gray" : GRADIENT[((rowIdx % GRADIENT.length) + GRADIENT.length) % GRADIENT.length]!;
+  const cursorVisible = true;
+  const { line: cursorLine, col: cursorCol } = lineAndColumn(value, cursor);
+
+  // Big-buffer mitigation: if the buffer has many logical lines,
+  // collapse middle rows so Ink isn't redrawing 500+ rows per
+  // keystroke.
+  const renderItems = collapseLinesForDisplay(lines, cursorLine);
+  const showHugeBufferHints = lines.length > 20;
+
+  return (
+    <Box flexDirection="column" paddingX={1}>
+      {renderItems.map((item, renderIdx) => {
+        if (item.kind === "skip") {
+          return (
+            // biome-ignore lint/suspicious/noArrayIndexKey: stable — collapse markers derive from a fixed sliding window
+            <Box key={`skip-${renderIdx}`}>
+              <Text color={barColorAt(renderIdx)}>{BAR}</Text>
+              <Text dimColor>{continuationIndent.slice(BAR.length)}</Text>
+              <Text dimColor>
+                {`[… ${item.linesHidden} line${item.linesHidden === 1 ? "" : "s"} hidden — full content kept, submitted on Enter …]`}
+              </Text>
+            </Box>
+          );
+        }
+        const i = item.originalIndex;
+        const line = item.line;
+        const isFirst = i === 0;
+        const isCursorLine = i === cursorLine;
+        const showPlaceholder = isFirst && value.length === 0;
+        return (
+          <PromptLine
+            key={`ln-${i}`}
+            line={line}
+            isFirst={isFirst}
+            isCursorLine={isCursorLine && !disabled}
+            cursorCol={isCursorLine ? cursorCol : null}
+            cursorVisible={cursorVisible}
+            showPlaceholder={showPlaceholder}
+            placeholderText={effectivePlaceholder}
+            promptPrefix={promptPrefix}
+            continuationIndent={continuationIndent}
+            visibleCells={visibleCells}
+            accentColor={accentColor}
+            barColor={barColorAt(i)}
+            pastes={pastesRef.current}
+            disabled={disabled === true}
+          />
+        );
+      })}
+      {showHugeBufferHints && !disabled ? (
+        <Box>
+          <Text color={barColorAt(0)}>{BAR}</Text>
+          <Text dimColor>{continuationIndent.slice(BAR.length)}</Text>
+          <Text dimColor>
+            {`[${lines.length} lines · PageUp/PageDown jump to top/bottom · Ctrl+U clear · Ctrl+W del word]`}
+          </Text>
+        </Box>
+      ) : null}
+      {!disabled && !narrow && value.length > 0 && !value.includes("\n") ? (
+        <Box>
+          <Text color={barColorAt(0)}>{BAR}</Text>
+          <Text dimColor>{continuationIndent.slice(BAR.length)}</Text>
+          <Text dimColor>
+            [Ctrl+J] newline · [Enter] submit · ends with \ for line continuation
+          </Text>
+        </Box>
+      ) : null}
+      {disabled ? (
+        <Box>
+          <Text color={barColorAt(0)}>{BAR}</Text>
+          <Text dimColor>{continuationIndent.slice(BAR.length)}</Text>
+          <Text dimColor>[Esc] to stop</Text>
+        </Box>
+      ) : null}
+    </Box>
+  );
+}
+
+// ── PromptLine ────────────────────────────────────────────────────
+
+interface PromptLineProps {
+  line: string;
+  isFirst: boolean;
+  isCursorLine: boolean;
+  cursorCol: number | null;
+  /** True when the cursor block / inverse char should be drawn this tick. */
+  cursorVisible: boolean;
+  showPlaceholder: boolean;
+  placeholderText: string;
+  promptPrefix: string;
+  continuationIndent: string;
+  visibleCells: number;
+  accentColor: "cyan" | "gray";
+  /** Animated gradient color for the leading ▎ bar. Differs per row + tick. */
+  barColor: string;
+  pastes: ReadonlyMap<number, PasteEntry>;
+  disabled: boolean;
+}
+
+function PromptLine({
+  line,
+  isFirst,
+  isCursorLine,
+  cursorCol,
+  cursorVisible,
+  showPlaceholder,
+  placeholderText,
+  promptPrefix,
+  continuationIndent,
+  visibleCells,
+  accentColor,
+  barColor,
+  pastes,
+  disabled,
+}: PromptLineProps) {
+  // The leading BAR cells of every prefix/continuation are the left
+  // anchor bar — render them as a separate span colored by the
+  // animated gradient so the bar appears to flow vertically.
+  const barText = promptPrefix.slice(0, BAR.length);
+  const bodyPrefix = promptPrefix.slice(BAR.length);
+  const bodyContinuation = continuationIndent.slice(BAR.length);
+  if (showPlaceholder) {
+    return (
+      <Box>
+        <Text color={barColor}>{barText}</Text>
+        <Text bold color={accentColor}>
+          {bodyPrefix}
+        </Text>
+        {!disabled ? <Text color={accentColor}>{cursorVisible ? "▌" : " "}</Text> : null}
+        <Text dimColor>{placeholderText}</Text>
+      </Box>
+    );
+  }
+
+  const viewport = buildViewport(line, isCursorLine ? cursorCol : null, visibleCells, pastes);
+
+  // Render: prefix + (left marker?) + segments-with-cursor + (right marker?)
+  return (
+    <Box>
+      <Text color={barColor}>{barText}</Text>
+      {isFirst ? (
+        <Text bold color={accentColor}>
+          {bodyPrefix}
+        </Text>
+      ) : (
+        <Text dimColor>{bodyContinuation}</Text>
+      )}
+      {viewport.hiddenLeft ? (
+        <Text color="gray" dimColor>
+          ‹
+        </Text>
+      ) : null}
+      <ViewportContent
+        segments={viewport.segments}
+        cursorCell={isCursorLine ? viewport.cursorCell : null}
+        accentColor={accentColor}
+        cursorVisible={cursorVisible}
+      />
+      {viewport.hiddenRight ? (
+        <Text color="gray" dimColor>
+          ›
+        </Text>
+      ) : null}
+    </Box>
+  );
+}
+
+// ── ViewportContent ────────────────────────────────────────────────
+
+/**
+ * Render a viewport's segments with a cursor block at `cursorCell`.
+ * Walks segments in order; the cursor splits at most one segment
+ * (the one containing the cursor cell), producing an inverted char
+ * at that position.
+ *
+ * End-of-line cursor (cursorCell points past the last cell of the
+ * last segment): emit a trailing block.
+ */
+function ViewportContent({
+  segments,
+  cursorCell,
+  accentColor,
+  cursorVisible,
+}: {
+  segments: Segment[];
+  cursorCell: number | null;
+  accentColor: "cyan" | "gray";
+  cursorVisible: boolean;
+}) {
+  // No cursor on this line — straight render.
+  if (cursorCell === null) {
+    return <>{segments.map((seg, i) => renderSegment(seg, i, false))}</>;
+  }
+
+  // Walk segments tallying cells; once we reach `cursorCell`, split
+  // the segment to insert the cursor block.
+  const out: React.ReactNode[] = [];
+  let cells = 0;
+  let placed = false;
+  for (let i = 0; i < segments.length; i++) {
+    const seg = segments[i]!;
+    const segCells = segmentCells(seg);
+    if (placed) {
+      out.push(renderSegment(seg, i, false));
+      continue;
+    }
+    if (cursorCell >= cells + segCells) {
+      // Cursor isn't in this segment.
+      out.push(renderSegment(seg, i, false));
+      cells += segCells;
+      continue;
+    }
+    // Cursor lands inside this segment.
+    if (seg.kind === "paste") {
+      // The cursor is "on" the paste sentinel — render the paste
+      // block inversed so the user sees they're at it. Inverse
+      // toggles with the blink so the paste sentinel stays
+      // legible during the cursor's "off" half-cycle.
+      out.push(
+        <Text key={`p-${i}-cursor`} color="magenta" bold inverse={cursorVisible}>
+          {seg.label}
+        </Text>,
+      );
+      placed = true;
+      cells += segCells;
+      continue;
+    }
+    // text segment — split before/at-cursor/after by cell offset.
+    const offsetIntoSeg = cursorCell - cells;
+    const split = splitTextByCells(seg.text, offsetIntoSeg);
+    if (split.before.length > 0) {
+      out.push(<Text key={`t-${i}-b`}>{split.before}</Text>);
+    }
+    if (split.atCursor.length > 0) {
+      out.push(
+        <Text key={`t-${i}-c`} inverse={cursorVisible} color={accentColor}>
+          {split.atCursor}
+        </Text>,
+      );
+    } else {
+      // Cursor sits past the segment's last char (end-of-text in this
+      // segment). Render block here, blinking with the tick.
+      out.push(
+        <Text key={`t-${i}-c-eol`} color={accentColor}>
+          {cursorVisible ? "▌" : " "}
+        </Text>,
+      );
+    }
+    if (split.after.length > 0) {
+      out.push(<Text key={`t-${i}-a`}>{split.after}</Text>);
+    }
+    placed = true;
+    cells += segCells;
+  }
+
+  // Cursor sits past every segment (end of line).
+  if (!placed) {
+    out.push(
+      <Text key="cursor-eol" color={accentColor}>
+        {cursorVisible ? "▌" : " "}
+      </Text>,
+    );
+  }
+
+  return <>{out}</>;
+}
+
+function segmentCells(seg: Segment): number {
+  if (seg.kind === "paste") return seg.label.length;
+  return stringCells(seg.text);
+}
+
+/**
+ * Split a text string at a cell offset, returning the chars before
+ * the offset, the char AT the offset (the cursor block highlights
+ * it), and the chars after. A wide char that straddles the offset
+ * is treated as the cursor's char.
+ */
+function splitTextByCells(
+  text: string,
+  cellOffset: number,
+): { before: string; atCursor: string; after: string } {
+  let cells = 0;
+  for (let i = 0; i < text.length; i++) {
+    const ch = text[i]!;
+    const cw = charCellsForText(ch);
+    if (cells === cellOffset) {
+      return { before: text.slice(0, i), atCursor: ch, after: text.slice(i + 1) };
+    }
+    if (cells + cw > cellOffset) {
+      // The wide char straddles the offset — show it as the cursor char.
+      return { before: text.slice(0, i), atCursor: ch, after: text.slice(i + 1) };
+    }
+    cells += cw;
+  }
+  // Cursor at end of text.
+  return { before: text, atCursor: "", after: "" };
+}
+
+/**
+ * Local cell-counting helper — duplicates `charCells` from
+ * prompt-viewport but inlined to avoid a back-and-forth import (this
+ * function is hot per-keystroke). Keep in sync.
+ */
+function charCellsForText(ch: string): number {
+  const code = ch.charCodeAt(0);
+  if (code < 0x20 || code === 0x7f) return 0;
+  if (code < 0x1100) return 1;
+  if (code >= 0x1100 && code <= 0x115f) return 2;
+  if (code >= 0x2e80 && code <= 0x303e) return 2;
+  if (code >= 0x3041 && code <= 0x33ff) return 2;
+  if (code >= 0x3400 && code <= 0x4dbf) return 2;
+  if (code >= 0x4e00 && code <= 0x9fff) return 2;
+  if (code >= 0xa000 && code <= 0xa4cf) return 2;
+  if (code >= 0xac00 && code <= 0xd7a3) return 2;
+  if (code >= 0xf900 && code <= 0xfaff) return 2;
+  if (code >= 0xfe30 && code <= 0xfe4f) return 2;
+  if (code >= 0xff00 && code <= 0xff60) return 2;
+  if (code >= 0xffe0 && code <= 0xffe6) return 2;
+  return 1;
+}
+
+function renderSegment(seg: Segment, key: number, _inverse: boolean): React.ReactNode {
+  if (seg.kind === "text") {
+    return <Text key={`s-${key}`}>{seg.text}</Text>;
+  }
+  // Paste sentinels render as a fuchsia bg-pill so they're visually
+  // distinct from typed text — the user can see "this is the
+  // collapsed paste, not 47 lines of code I typed". Matches the
+  // bg-pill idiom used elsewhere (mode bars, tool names).
+  return (
+    <Text key={`s-${key}`} backgroundColor="#f0abfc" color="black" bold>
+      {seg.label}
+    </Text>
+  );
+}
+
+// ── collapse helper (preserved from v1) ────────────────────────────
+
+type RenderItem =
+  | { kind: "line"; line: string; originalIndex: number }
+  | { kind: "skip"; linesHidden: number };
+
+const COLLAPSE_THRESHOLD = 20;
+const COLLAPSE_HEAD_LINES = 3;
+const COLLAPSE_TAIL_LINES = 2;
+
+export function collapseLinesForDisplay(lines: string[], cursorLine: number): RenderItem[] {
+  if (lines.length <= COLLAPSE_THRESHOLD) {
+    return lines.map((line, i) => ({ kind: "line" as const, line, originalIndex: i }));
+  }
+  const keep = new Set<number>();
+  for (let i = 0; i < COLLAPSE_HEAD_LINES && i < lines.length; i++) keep.add(i);
+  for (let i = Math.max(0, lines.length - COLLAPSE_TAIL_LINES); i < lines.length; i++) keep.add(i);
+  if (cursorLine >= 0 && cursorLine < lines.length) keep.add(cursorLine);
+  const sorted = [...keep].sort((a, b) => a - b);
+  const out: RenderItem[] = [];
+  let prev = -1;
+  for (const idx of sorted) {
+    if (idx - prev > 1) {
+      out.push({ kind: "skip", linesHidden: idx - prev - 1 });
+    }
+    out.push({ kind: "line", line: lines[idx] ?? "", originalIndex: idx });
+    prev = idx;
+  }
+  return out;
+}

src/cli/ui/RecordView.tsx

@@ -0,0 +1,133 @@
+/**
+ * Shared renderer for a single TranscriptRecord. Used by ReplayApp and
+ * DiffApp — both need the same visual grammar (user cyan, assistant green,
+ * tool yellow, error red, cache badge colored by threshold) so transcripts
+ * look consistent wherever they're displayed.
+ *
+ * Kept small on purpose: no streaming/branch/planState paths (those are
+ * live-chat concerns and never appear in replayed transcripts).
+ */
+
+import { Box, Text } from "ink";
+import React from "react";
+import type { TranscriptRecord } from "../../transcript.js";
+import { PlanStateBlock } from "./PlanStateBlock.js";
+
+export interface RecordViewProps {
+  rec: TranscriptRecord;
+  /**
+   * When rendering side-by-side in diff mode, shorter truncation limits
+   * keep long tool results from dominating the pane. Passes through
+   * untouched when undefined.
+   */
+  compact?: boolean;
+}
+
+export function RecordView({ rec, compact = false }: RecordViewProps) {
+  const toolArgsMax = compact ? 120 : 200;
+  const toolContentMax = compact ? 200 : 400;
+
+  if (rec.role === "user") {
+    // Continuation indent of 6 spaces matches the `you › ` prefix width
+    // so wrapped multi-line user messages align under the body text
+    // instead of jumping to column 0.
+    const content = rec.content.includes("\n")
+      ? rec.content.split("\n").join("\n      ")
+      : rec.content;
+    return (
+      <Box marginTop={1}>
+        <Text bold color="cyan">
+          you ›{" "}
+        </Text>
+        <Text>{content}</Text>
+      </Box>
+    );
+  }
+  if (rec.role === "assistant_final") {
+    return (
+      <Box flexDirection="column" marginTop={1}>
+        <Box>
+          <Text bold color="green">
+            assistant
+          </Text>
+          {rec.cost !== undefined ? (
+            <Text dimColor>
+              {"  $"}
+              {rec.cost.toFixed(6)}
+            </Text>
+          ) : null}
+          {rec.usage ? <CacheBadge usage={rec.usage} /> : null}
+        </Box>
+        {rec.planState ? <PlanStateBlock planState={rec.planState} /> : null}
+        {rec.content ? (
+          <Text>{rec.content}</Text>
+        ) : (
+          <Text dimColor italic>
+            (tool-call response only)
+          </Text>
+        )}
+      </Box>
+    );
+  }
+  if (rec.role === "tool") {
+    return (
+      <Box flexDirection="column" marginTop={1}>
+        <Text color="yellow">
+          {"tool<"}
+          {rec.tool ?? "?"}
+          {">"}
+        </Text>
+        {rec.args ? (
+          <Text dimColor>
+            {"  args: "}
+            {truncate(rec.args, toolArgsMax)}
+          </Text>
+        ) : null}
+        <Text dimColor>
+          {"  → "}
+          {truncate(rec.content, toolContentMax)}
+        </Text>
+      </Box>
+    );
+  }
+  if (rec.role === "error") {
+    return (
+      <Box marginTop={1}>
+        <Text color="red" bold>
+          error{" "}
+        </Text>
+        <Text color="red">{rec.error ?? rec.content}</Text>
+      </Box>
+    );
+  }
+  if (rec.role === "done" || rec.role === "assistant_delta") {
+    // Noise in replay; skip.
+    return null;
+  }
+  return (
+    <Box>
+      <Text dimColor>
+        [{rec.role}] {rec.content}
+      </Text>
+    </Box>
+  );
+}
+
+function CacheBadge({ usage }: { usage: NonNullable<TranscriptRecord["usage"]> }) {
+  const hit = usage.prompt_cache_hit_tokens ?? 0;
+  const miss = usage.prompt_cache_miss_tokens ?? 0;
+  const total = hit + miss;
+  if (total === 0) return null;
+  const pct = (hit / total) * 100;
+  const color = pct >= 70 ? "green" : pct >= 40 ? "yellow" : "red";
+  return (
+    <Text>
+      <Text dimColor>{"  · cache "}</Text>
+      <Text color={color}>{pct.toFixed(1)}%</Text>
+    </Text>
+  );
+}
+
+function truncate(s: string, max: number): string {
+  return s.length <= max ? s : `${s.slice(0, max)}… (+${s.length - max} chars)`;
+}

src/cli/ui/ReplayApp.tsx

@@ -0,0 +1,118 @@
+/**
+ * Ink TUI for `reasonix replay`. Read-only: no input box, no loop.
+ * j/k navigation across turn-pages, cumulative stats sidebar updates
+ * as you move through time.
+ *
+ * The navigation logic (grouping records into pages, computing cumulative
+ * stats) lives in src/replay.ts as pure functions; this file is just
+ * presentation + key bindings.
+ */
+
+import { Box, Static, Text, useApp, useInput } from "ink";
+import React, { useMemo, useState } from "react";
+import { type TurnPage, computeCumulativeStats } from "../../replay.js";
+import type { TranscriptMeta } from "../../transcript.js";
+import { RecordView } from "./RecordView.js";
+import { StatsPanel } from "./StatsPanel.js";
+
+export interface ReplayAppProps {
+  meta: TranscriptMeta | null;
+  pages: TurnPage[];
+}
+
+export function ReplayApp({ meta, pages }: ReplayAppProps) {
+  const { exit } = useApp();
+  const maxIdx = Math.max(0, pages.length - 1);
+  // Start at the last page — more useful than "start from the beginning"
+  // in practice: users mostly want to see the summary + last turn first.
+  const [idx, setIdx] = useState(maxIdx);
+
+  useInput((input, key) => {
+    if (input === "q" || (key.ctrl && input === "c")) {
+      exit();
+      return;
+    }
+    if (input === "j" || key.downArrow || input === " " || key.return) {
+      setIdx((i) => Math.min(maxIdx, i + 1));
+    } else if (input === "k" || key.upArrow) {
+      setIdx((i) => Math.max(0, i - 1));
+    } else if (input === "g") {
+      setIdx(0);
+    } else if (input === "G") {
+      setIdx(maxIdx);
+    } else if (input === "h" || key.leftArrow) {
+      setIdx(0);
+    } else if (input === "l" || key.rightArrow) {
+      setIdx(maxIdx);
+    }
+  });
+
+  const cumStats = useMemo(() => computeCumulativeStats(pages, idx), [pages, idx]);
+
+  const summary = {
+    turns: cumStats.turns,
+    totalCostUsd: cumStats.totalCostUsd,
+    totalInputCostUsd: cumStats.totalInputCostUsd,
+    totalOutputCostUsd: cumStats.totalOutputCostUsd,
+    claudeEquivalentUsd: cumStats.claudeEquivalentUsd,
+    savingsVsClaudePct: cumStats.savingsVsClaudePct,
+    cacheHitRatio: cumStats.cacheHitRatio,
+    // Replay is read-only — no live last-turn prompt tokens to show.
+    lastPromptTokens: 0,
+    lastTurnCostUsd: 0,
+  };
+
+  const prefixHash =
+    cumStats.prefixHashes.length === 1
+      ? cumStats.prefixHashes[0]!.slice(0, 16)
+      : cumStats.prefixHashes.length === 0
+        ? "(untracked)"
+        : `(churned ×${cumStats.prefixHashes.length})`;
+
+  const currentPage = pages[idx];
+  const progressLabel =
+    pages.length === 0 ? "empty transcript" : `turn ${idx + 1} / ${pages.length}`;
+
+  return (
+    <Box flexDirection="column">
+      <StatsPanel
+        summary={summary}
+        model={cumStats.models[0] ?? meta?.model ?? "?"}
+        prefixHash={prefixHash}
+      />
+
+      <Box flexDirection="column" marginTop={1} paddingX={1}>
+        <Box justifyContent="space-between">
+          <Text color="cyan" bold>
+            {progressLabel}
+          </Text>
+          {meta ? (
+            <Text dimColor>
+              {meta.source}
+              {meta.task ? ` · ${meta.task}` : ""}
+              {meta.mode ? ` · ${meta.mode}` : ""}
+            </Text>
+          ) : null}
+        </Box>
+
+        {currentPage ? (
+          <Static items={currentPage.records.map((rec, i) => ({ key: `${idx}-${i}`, rec }))}>
+            {({ key, rec }) => <RecordView key={key} rec={rec} />}
+          </Static>
+        ) : (
+          <Text dimColor italic>
+            no records
+          </Text>
+        )}
+      </Box>
+
+      <Box marginTop={1} paddingX={1} borderStyle="single" borderColor="gray">
+        <Text dimColor>
+          <Text bold>j</Text>/<Text bold>↓</Text>/<Text bold>space</Text> next · <Text bold>k</Text>
+          /<Text bold>↑</Text> prev · <Text bold>g</Text> first · <Text bold>G</Text> last ·{" "}
+          <Text bold>q</Text> quit
+        </Text>
+      </Box>
+    </Box>
+  );
+}

src/cli/ui/Select.tsx

@@ -0,0 +1,198 @@
+/**
+ * Minimal arrow-key list components for Ink — single-select and
+ * multi-select. No external deps beyond Ink's `useInput`.
+ *
+ * Why hand-roll: `ink-select-input` exists, but it defaults to
+ * Enter-only interaction (no space-to-toggle for multi-select), doesn't
+ * expose the "hint / footer" slot we want under each item, and would be
+ * another dep for ~60 lines of UI code. Reasonix already has one React
+ * rendering quirk bundled (`ink-text-input`); adding more is low value.
+ */
+
+import { Box, Text } from "ink";
+import React, { useState } from "react";
+import { useKeystroke } from "./keystroke-context.js";
+
+export interface SelectItem<V extends string = string> {
+  /** Stable identifier — returned to caller on submit. */
+  value: V;
+  /** First-row label. */
+  label: string;
+  /** Optional second row rendered dimmed. */
+  hint?: string;
+  /** If true, item is not selectable (rendered dimmed, skipped on nav). */
+  disabled?: boolean;
+}
+
+export interface SingleSelectProps<V extends string> {
+  items: SelectItem<V>[];
+  initialValue?: V;
+  onSubmit: (value: V) => void;
+  onCancel?: () => void;
+  /**
+   * Optional footer rendered dim beneath the list, e.g.
+   * `"[↑↓] navigate · [Enter] select · [Esc] cancel"`. Makes keyboard
+   * affordances discoverable — otherwise new users hit `y`/`n` and
+   * wonder why nothing happens.
+   */
+  footer?: string;
+}
+
+export function SingleSelect<V extends string>({
+  items,
+  initialValue,
+  onSubmit,
+  onCancel,
+  footer,
+}: SingleSelectProps<V>) {
+  const initialIndex = Math.max(
+    0,
+    items.findIndex((i) => i.value === initialValue && !i.disabled),
+  );
+  const [index, setIndex] = useState(initialIndex === -1 ? 0 : initialIndex);
+
+  useKeystroke((ev) => {
+    if (ev.paste) return;
+    if (ev.upArrow) {
+      setIndex((i) => findNextEnabled(items, i, -1));
+    } else if (ev.downArrow) {
+      setIndex((i) => findNextEnabled(items, i, +1));
+    } else if (ev.return) {
+      const chosen = items[index];
+      if (chosen && !chosen.disabled) onSubmit(chosen.value);
+    } else if (ev.escape && onCancel) {
+      onCancel();
+    }
+  });
+
+  return (
+    <Box flexDirection="column">
+      {items.map((item, i) => (
+        <SelectRow
+          key={item.value}
+          item={item}
+          active={i === index}
+          marker={i === index ? "▸" : " "}
+        />
+      ))}
+      {footer ? (
+        <Box marginTop={1}>
+          <Text dimColor>{footer}</Text>
+        </Box>
+      ) : null}
+    </Box>
+  );
+}
+
+export interface MultiSelectProps<V extends string> {
+  items: SelectItem<V>[];
+  initialSelected?: V[];
+  onSubmit: (values: V[]) => void;
+  onCancel?: () => void;
+  /** Footer hint under the list — e.g. "[Space] toggle · [Enter] confirm". */
+  footer?: string;
+}
+
+export function MultiSelect<V extends string>({
+  items,
+  initialSelected = [],
+  onSubmit,
+  onCancel,
+  footer,
+}: MultiSelectProps<V>) {
+  const [index, setIndex] = useState(() => {
+    const first = items.findIndex((i) => !i.disabled);
+    return first === -1 ? 0 : first;
+  });
+  const [selected, setSelected] = useState<Set<V>>(new Set(initialSelected));
+
+  useKeystroke((ev) => {
+    if (ev.paste) return;
+    if (ev.upArrow) {
+      setIndex((i) => findNextEnabled(items, i, -1));
+    } else if (ev.downArrow) {
+      setIndex((i) => findNextEnabled(items, i, +1));
+    } else if (ev.input === " ") {
+      const item = items[index];
+      if (!item || item.disabled) return;
+      setSelected((prev) => {
+        const next = new Set(prev);
+        if (next.has(item.value)) next.delete(item.value);
+        else next.add(item.value);
+        return next;
+      });
+    } else if (ev.return) {
+      // Preserve catalog order rather than insertion order, so reruns
+      // produce the same spec list for the same checkbox set — makes the
+      // `config.json` diff trivially stable.
+      const ordered = items.filter((i) => selected.has(i.value)).map((i) => i.value);
+      onSubmit(ordered);
+    } else if (ev.escape && onCancel) {
+      onCancel();
+    }
+  });
+
+  return (
+    <Box flexDirection="column">
+      {items.map((item, i) => {
+        const checked = selected.has(item.value);
+        const marker = checked ? "[x]" : "[ ]";
+        return (
+          <SelectRow
+            key={item.value}
+            item={item}
+            active={i === index}
+            marker={`${i === index ? "▸" : " "} ${marker}`}
+          />
+        );
+      })}
+      {footer ? (
+        <Box marginTop={1}>
+          <Text dimColor>{footer}</Text>
+        </Box>
+      ) : null}
+    </Box>
+  );
+}
+
+// ---------- internals ----------
+
+function SelectRow<V extends string>({
+  item,
+  active,
+  marker,
+}: {
+  item: SelectItem<V>;
+  active: boolean;
+  marker: string;
+}) {
+  const color = item.disabled ? "gray" : active ? "cyan" : undefined;
+  return (
+    <Box flexDirection="column">
+      <Box>
+        <Text color={color}>
+          {marker} {item.label}
+        </Text>
+      </Box>
+      {item.hint ? (
+        <Box paddingLeft={marker.length + 1}>
+          <Text dimColor>{item.hint}</Text>
+        </Box>
+      ) : null}
+    </Box>
+  );
+}
+
+function findNextEnabled<V extends string>(
+  items: SelectItem<V>[],
+  from: number,
+  step: -1 | 1,
+): number {
+  if (items.length === 0) return 0;
+  let i = from;
+  for (let tries = 0; tries < items.length; tries++) {
+    i = (i + step + items.length) % items.length;
+    if (!items[i]?.disabled) return i;
+  }
+  return from;
+}

src/cli/ui/SessionPicker.tsx

@@ -0,0 +1,72 @@
+import { Box, Text } from "ink";
+import React from "react";
+import { SingleSelect } from "./Select.js";
+
+export type SessionChoice = "resume" | "new" | "delete";
+
+export interface SessionPickerProps {
+  sessionName: string;
+  messageCount: number;
+  /** mtime of the session file; used to render "last active Nh ago". */
+  lastActive: Date;
+  onChoose: (choice: SessionChoice) => void;
+}
+
+export function SessionPicker({
+  sessionName,
+  messageCount,
+  lastActive,
+  onChoose,
+}: SessionPickerProps) {
+  return (
+    <Box flexDirection="column" marginY={1}>
+      <Box marginBottom={1}>
+        <Text bold color="cyan">
+          {`Session "${sessionName}" has ${messageCount} prior message${messageCount === 1 ? "" : "s"}`}
+        </Text>
+        <Text dimColor>{` · last active ${relativeTime(lastActive)}`}</Text>
+      </Box>
+      <SingleSelect
+        initialValue="new"
+        items={[
+          {
+            value: "new",
+            label: "Start new conversation",
+            hint: "Previous messages kept on disk; your turn starts fresh.",
+          },
+          {
+            value: "resume",
+            label: "Resume",
+            hint: `Continue where you left off (${messageCount} messages in context).`,
+          },
+          {
+            value: "delete",
+            label: "Delete and start new",
+            hint: "Wipes the session file irreversibly. Other sessions untouched.",
+          },
+        ]}
+        onSubmit={(v) => onChoose(v as SessionChoice)}
+      />
+      <Box marginTop={1}>
+        <Text dimColor>[↑↓] navigate · [Enter] select</Text>
+      </Box>
+    </Box>
+  );
+}
+
+/**
+ * "Nh ago" / "Nm ago" / "yesterday" style relative time. Deliberately
+ * coarse — the picker just needs a sense of "how stale is this session".
+ */
+function relativeTime(date: Date): string {
+  const ms = Date.now() - date.getTime();
+  const mins = Math.floor(ms / 60_000);
+  if (mins < 1) return "just now";
+  if (mins < 60) return `${mins}m ago`;
+  const hours = Math.floor(mins / 60);
+  if (hours < 24) return `${hours}h ago`;
+  const days = Math.floor(hours / 24);
+  if (days === 1) return "yesterday";
+  if (days < 7) return `${days}d ago`;
+  return date.toISOString().slice(0, 10);
+}

src/cli/ui/Setup.tsx

@@ -0,0 +1,71 @@
+import { Box, Text, useApp } from "ink";
+import TextInput from "ink-text-input";
+import React, { useState } from "react";
+import { defaultConfigPath, isPlausibleKey, redactKey, saveApiKey } from "../../config.js";
+
+export interface SetupProps {
+  onReady: (apiKey: string) => void;
+}
+
+export function Setup({ onReady }: SetupProps) {
+  const [value, setValue] = useState("");
+  const [error, setError] = useState<string | null>(null);
+  const { exit } = useApp();
+
+  const handleSubmit = (raw: string) => {
+    const trimmed = raw.trim();
+    if (trimmed === "/exit" || trimmed === "/quit") {
+      exit();
+      return;
+    }
+    if (!isPlausibleKey(trimmed)) {
+      setError("Doesn't look like a DeepSeek key. They start with 'sk-' and are 30+ chars.");
+      setValue("");
+      return;
+    }
+    try {
+      saveApiKey(trimmed);
+    } catch (err) {
+      setError(`Could not save key: ${(err as Error).message}`);
+      return;
+    }
+    onReady(trimmed);
+  };
+
+  return (
+    <Box flexDirection="column" borderStyle="round" borderColor="cyan" paddingX={1}>
+      <Text bold color="cyan">
+        Welcome to Reasonix.
+      </Text>
+      <Box marginTop={1}>
+        <Text>Paste your DeepSeek API key to get started.</Text>
+      </Box>
+      <Text dimColor>Get one (free credit on signup): https://platform.deepseek.com/api_keys</Text>
+      <Text dimColor>Saved locally to {defaultConfigPath()}</Text>
+      <Box marginTop={1}>
+        <Text bold color="cyan">
+          {"key › "}
+        </Text>
+        <TextInput
+          value={value}
+          onChange={setValue}
+          onSubmit={handleSubmit}
+          mask="•"
+          placeholder="sk-..."
+        />
+      </Box>
+      {error ? (
+        <Box marginTop={1}>
+          <Text color="red">{error}</Text>
+        </Box>
+      ) : value ? (
+        <Box marginTop={1}>
+          <Text dimColor>preview: {redactKey(value)}</Text>
+        </Box>
+      ) : null}
+      <Box marginTop={1}>
+        <Text dimColor>(Type /exit to abort.)</Text>
+      </Box>
+    </Box>
+  );
+}

src/cli/ui/ShellConfirm.tsx

@@ -0,0 +1,117 @@
+import { Box, Text } from "ink";
+import React from "react";
+import { ModalCard } from "./ModalCard.js";
+import { SingleSelect } from "./Select.js";
+
+export type ShellConfirmChoice = "run_once" | "always_allow" | "deny";
+
+export interface ShellConfirmProps {
+  command: string;
+  /**
+   * The prefix that would be persisted if the user picks
+   * "always allow". Typically the first 1-2 tokens of `command`.
+   */
+  allowPrefix: string;
+  /**
+   * Which tool is asking. `run_background` spawns via JobRegistry and
+   * returns early; `run_command` (default) blocks until the process
+   * exits. Shown as a hint in the modal so the user knows whether
+   * approving will block the TUI or not.
+   */
+  kind?: "run_command" | "run_background";
+  onChoose: (choice: ShellConfirmChoice) => void;
+}
+
+/**
+ * Modal-style approval for a shell command the model wants to run.
+ * Three choices:
+ *   1. Run once — execute this invocation, prefix NOT remembered.
+ *   2. Always allow — persist the prefix to `~/.reasonix/config.json`
+ *      under this project so every future invocation with that prefix
+ *      auto-runs.
+ *   3. Deny — tell the model the user refused.
+ * Arrow keys + Enter. No y/n hotkey — too easy to trigger by accident
+ * when the user was mid-typing a response.
+ */
+export function ShellConfirm({ command, allowPrefix, kind, onChoose }: ShellConfirmProps) {
+  const isBackground = kind === "run_background";
+  const subtitle = isBackground
+    ? "long-running process — keeps running after approval, /kill to stop"
+    : "model wants to run a shell command";
+  return (
+    <ModalCard
+      accent="#f87171"
+      icon={isBackground ? "⏱" : "⚡"}
+      title={isBackground ? "background process" : "shell command"}
+      subtitle={subtitle}
+    >
+      <Box marginBottom={1}>
+        <Text dimColor>{"$ "}</Text>
+        <Text color="#67e8f9" bold>
+          {command}
+        </Text>
+      </Box>
+      <SingleSelect
+        initialValue="run_once"
+        items={[
+          {
+            value: "run_once",
+            label: "Run once",
+            hint: "Execute this command, don't remember it.",
+          },
+          {
+            value: "always_allow",
+            label: `Always allow "${allowPrefix}" in this project`,
+            hint: "Save the prefix to ~/.reasonix/config.json; future matches auto-run.",
+          },
+          {
+            value: "deny",
+            label: "Deny",
+            hint: "Tell the model the user refused; it will continue without this command.",
+          },
+        ]}
+        onSubmit={(v) => onChoose(v as ShellConfirmChoice)}
+        onCancel={() => onChoose("deny")}
+        footer="[↑↓] navigate  ·  [Enter] select  ·  [Esc] deny"
+      />
+    </ModalCard>
+  );
+}
+
+/**
+ * Pick the "always allow" prefix from a full command. Heuristic:
+ *   - one-token commands ("ls", "pytest") → the token itself
+ *   - multi-token → first two tokens for well-known wrappers
+ *     (`npm install`, `git commit`, `cargo add`, `docker run` …)
+ *     otherwise just the first token (covers `node <script>` where the
+ *     second token is usually a file path specific to this invocation).
+ * Exported so tests can pin the heuristic.
+ */
+export function derivePrefix(command: string): string {
+  const tokens = command.trim().split(/\s+/).filter(Boolean);
+  if (tokens.length === 0) return "";
+  if (tokens.length === 1) return tokens[0]!;
+  const first = tokens[0]!;
+  const TWO_TOKEN_WRAPPERS = new Set([
+    "npm",
+    "npx",
+    "pnpm",
+    "yarn",
+    "bun",
+    "git",
+    "cargo",
+    "go",
+    "docker",
+    "kubectl",
+    "python",
+    "python3",
+    "deno",
+    "pip",
+    "pip3",
+    "make",
+    "rake",
+    "bundle",
+    "gem",
+  ]);
+  return TWO_TOKEN_WRAPPERS.has(first) ? `${first} ${tokens[1]}` : first;
+}

src/cli/ui/SlashArgPicker.tsx

@@ -0,0 +1,108 @@
+import { Box, Text } from "ink";
+// biome-ignore lint/style/useImportType: tsconfig.jsx = "react" needs React in value scope for JSX compilation
+import React from "react";
+import type { SlashCommandSpec } from "./slash.js";
+
+export interface SlashArgPickerProps {
+  /**
+   * When set, render a picker with these matches (filter already
+   * applied upstream). Null → not in picker mode; check `hintSpec`
+   * for a usage hint instead.
+   */
+  matches: readonly string[] | null;
+  /** Highlighted row within `matches`. */
+  selectedIndex: number;
+  /**
+   * Spec of the command the user is typing args for. Used to render
+   * the header label ("/edit <file>") even when matches is empty or
+   * the caller wants a hint instead of a picker.
+   */
+  spec: SlashCommandSpec;
+  /** What kind of arg guidance to render. */
+  kind: "picker" | "hint";
+  /** The user's partial input — shown in the "no matches" hint. */
+  partial: string;
+}
+
+/**
+ * Argument-level picker for a slash command. Mirrors the visual
+ * layout of SlashSuggestions / AtMentionSuggestions so the UI stays
+ * consistent across all three picker surfaces.
+ */
+export function SlashArgPicker({
+  matches,
+  selectedIndex,
+  spec,
+  kind,
+  partial,
+}: SlashArgPickerProps): React.ReactElement | null {
+  // Hint mode: a single dim row explaining the argsHint + summary.
+  if (kind === "hint") {
+    return (
+      <Box paddingX={1} marginTop={1}>
+        <Text dimColor>
+          {"  "}
+          <Text bold>/{spec.cmd}</Text>
+          {spec.argsHint ? ` ${spec.argsHint}` : ""} — {spec.summary}
+        </Text>
+      </Box>
+    );
+  }
+
+  if (matches === null) return null;
+  if (matches.length === 0) {
+    return (
+      <Box flexDirection="column" paddingX={1} marginTop={1}>
+        <Text dimColor>
+          {"  "}
+          <Text bold>/{spec.cmd}</Text>
+          {spec.argsHint ? ` ${spec.argsHint}` : ""} — {spec.summary}
+        </Text>
+        <Text color="yellow"> no match for "{partial}" — keep typing, or Backspace to edit</Text>
+      </Box>
+    );
+  }
+
+  const MAX = 8;
+  const total = matches.length;
+  const windowStart =
+    total <= MAX ? 0 : Math.max(0, Math.min(selectedIndex - Math.floor(MAX / 2), total - MAX));
+  const shown = matches.slice(windowStart, windowStart + MAX);
+  const hiddenAbove = windowStart;
+  const hiddenBelow = total - windowStart - shown.length;
+  return (
+    <Box flexDirection="column" paddingX={1} marginTop={1}>
+      <Text dimColor>
+        {"  "}
+        <Text bold>/{spec.cmd}</Text>
+        {spec.argsHint ? ` ${spec.argsHint}` : ""} — {spec.summary}
+      </Text>
+      {hiddenAbove > 0 ? <Text dimColor> ↑ {hiddenAbove} more above</Text> : null}
+      {shown.map((value, i) => (
+        <ArgRow key={value} value={value} isSelected={windowStart + i === selectedIndex} />
+      ))}
+      {hiddenBelow > 0 ? <Text dimColor> ↓ {hiddenBelow} more below</Text> : null}
+      <Text dimColor> [↑↓] navigate · [Tab]/[Enter] pick</Text>
+    </Box>
+  );
+}
+
+function ArgRow({ value, isSelected }: { value: string; isSelected: boolean }) {
+  const marker = isSelected ? "▸" : " ";
+  if (isSelected) {
+    return (
+      <Box>
+        <Text bold color="cyan">
+          {marker} {value}
+        </Text>
+      </Box>
+    );
+  }
+  return (
+    <Box>
+      <Text dimColor>
+        {marker} {value}
+      </Text>
+    </Box>
+  );
+}

src/cli/ui/SlashSuggestions.tsx

@@ -0,0 +1,79 @@
+import { Box, Text } from "ink";
+// biome-ignore lint/style/useImportType: tsconfig.jsx = "react" needs React in value scope for JSX compilation
+import React from "react";
+import type { SlashCommandSpec } from "./slash.js";
+
+export interface SlashSuggestionsProps {
+  /**
+   * Current matching suggestions, computed by the parent. `null` means
+   * "not in slash-prefix mode" — render nothing. Empty array means "in
+   * slash mode but no matches" — render the "no matches" hint.
+   */
+  matches: SlashCommandSpec[] | null;
+  /** Index (within `matches`) of the currently highlighted row. */
+  selectedIndex: number;
+}
+
+/**
+ * Floating slash-command panel. Rendered below the input box when
+ * the user is typing a `/…` prefix. Navigation state lives in the
+ * parent (App.tsx owns `slashSelected`) so ↑/↓/Tab/Enter stay
+ * consistent with the useInput handler. This component is pure
+ * display: `matches` and `selectedIndex` come in, rows go out.
+ */
+export function SlashSuggestions({
+  matches,
+  selectedIndex,
+}: SlashSuggestionsProps): React.ReactElement | null {
+  if (matches === null) return null;
+  if (matches.length === 0) {
+    return (
+      <Box paddingX={1} marginTop={1}>
+        <Text color="yellow">no slash command matches that prefix</Text>
+        <Text dimColor> — Backspace to edit, or /help for the full list</Text>
+      </Box>
+    );
+  }
+  // Limit rows so the suggestion list never dwarfs the rest of the
+  // UI. Keep the currently-selected row in view by sliding the
+  // window when the selection is near either edge.
+  const MAX = 8;
+  const total = matches.length;
+  const windowStart =
+    total <= MAX ? 0 : Math.max(0, Math.min(selectedIndex - Math.floor(MAX / 2), total - MAX));
+  const shown = matches.slice(windowStart, windowStart + MAX);
+  const hiddenAbove = windowStart;
+  const hiddenBelow = total - windowStart - shown.length;
+  return (
+    <Box flexDirection="column" paddingX={1} marginTop={1}>
+      {hiddenAbove > 0 ? <Text dimColor> ↑ {hiddenAbove} more above</Text> : null}
+      {shown.map((spec, i) => (
+        <SuggestionRow key={spec.cmd} spec={spec} isSelected={windowStart + i === selectedIndex} />
+      ))}
+      {hiddenBelow > 0 ? <Text dimColor> ↓ {hiddenBelow} more below</Text> : null}
+      <Text dimColor> [↑↓] navigate · [Tab]/[Enter] pick</Text>
+    </Box>
+  );
+}
+
+function SuggestionRow({ spec, isSelected }: { spec: SlashCommandSpec; isSelected: boolean }) {
+  const name = `/${spec.cmd}`;
+  const argsSuffix = spec.argsHint ? ` ${spec.argsHint}` : "";
+  // Selected row gets a solid-bg highlight (cyan) so it pops like
+  // an editor's focused autocomplete entry. Non-selected rows stay
+  // dim with a leading bullet for vertical rhythm.
+  if (isSelected) {
+    return (
+      <Box>
+        <Text backgroundColor="#67e8f9" color="black" bold>
+          {` ▸ ${name.padEnd(12)}${argsSuffix.padEnd(16)}  ${spec.summary} `}
+        </Text>
+      </Box>
+    );
+  }
+  return (
+    <Box>
+      <Text color="#94a3b8">{`   ${name.padEnd(12)}${argsSuffix.padEnd(16)} ${spec.summary}`}</Text>
+    </Box>
+  );
+}

src/cli/ui/StatsPanel.tsx

@@ -0,0 +1,582 @@
+import { Box, Text, useStdout } from "ink";
+import React from "react";
+import type { EditMode } from "../../config.js";
+import { DEEPSEEK_CONTEXT_TOKENS, DEFAULT_CONTEXT_TOKENS } from "../../telemetry.js";
+import type { SessionSummary } from "../../telemetry.js";
+import { VERSION } from "../../version.js";
+import { COLOR, GRADIENT } from "./theme.js";
+
+const WORDMARK_LETTERS: ReadonlyArray<string> = ["R", "E", "A", "S", "O", "N", "I", "X"];
+
+/**
+ * Gradient-flowing wordmark. Every tick the gradient shifts one
+ * position so the colors visibly travel across the letters — like
+ * a neon sign. Brand mark `◈` rides the same flow but also pulses
+ * bold on/off (slow when idle, fast when busy) so a glance at the
+ * top of the screen tells you whether the app is thinking.
+ *
+ * Tick is ~120 ms. `rotateEvery=4` ticks → one shift every ~480 ms
+ * idle, ~240 ms when busy. Slow enough to be ambient, fast enough
+ * to feel alive. Truecolor terminals get the smooth flow; 8-color
+ * fallbacks just see all-cyan, which is still legible.
+ */
+function Wordmark({
+  busy: _busy,
+  animate: _animate,
+}: {
+  busy: boolean;
+  animate: boolean;
+}) {
+  // Static gradient. The brand sweep teal → fuchsia is precomputed
+  // once per render — no useTick subscription, no per-tick
+  // re-render. Earlier versions flowed the colors over time, but
+  // the per-tick re-render interleaved badly with terminal resize
+  // (Ink's eraseLines misjudges row count when bars / wide text
+  // wrap, ghost frames stack). Keeping this static eliminates the
+  // multiplier; resize artifacts at most leave a single stale
+  // frame instead of N.
+  return (
+    <Text>
+      <Text color={GRADIENT[0]} bold>
+        ◈
+      </Text>
+      <Text> </Text>
+      {WORDMARK_LETTERS.map((letter, i) => (
+        <Text key={letter} color={GRADIENT[i % GRADIENT.length]} bold>
+          {letter}
+        </Text>
+      ))}
+    </Text>
+  );
+}
+
+export interface StatsPanelProps {
+  summary: SessionSummary;
+  model: string;
+  prefixHash: string;
+  harvestOn?: boolean;
+  branchBudget?: number;
+  /**
+   * Current `reasoning_effort` cap. Shown as a green "· max" / yellow
+   * "· high" tag in the header so the user always sees which tier the
+   * next turn will use. Absent/undefined hides the tag (e.g. before
+   * the loop is constructed).
+   */
+  reasoningEffort?: "high" | "max";
+  /**
+   * True when `reasonix code` is currently running in read-only Plan
+   * Mode. Surfaced as a red "PLAN" tag in the panel header so the user
+   * can tell at a glance that edits are gated behind submit_plan +
+   * approval.
+   */
+  planMode?: boolean;
+  /**
+   * Edit-gate mode. Surfaced as a small pill in the header so the user
+   * can see at a glance whether edits will be queued for review or
+   * applied immediately. Omitted in chat (non-code) mode.
+   */
+  editMode?: EditMode;
+  /**
+   * Account balance fetched once at launch (and optionally refreshed
+   * per-turn by the TUI). `null` or absent hides the balance cell
+   * entirely — /user/balance failed or the user ran with `--no-config`.
+   * The top-up warning fires below 1.0 unit of whatever currency
+   * the endpoint reports so a Chinese user with CNY and a U.S. user
+   * with USD both see "getting low."
+   */
+  balance?: { currency: string; total: number } | null;
+  /**
+   * Published npm version newer than VERSION. Rendered as a yellow
+   * "· update: X" nudge in the panel header. `null` / `undefined`
+   * hides the nudge (offline launch, already up to date, or check
+   * still in flight).
+   */
+  updateAvailable?: string | null;
+  /**
+   * True when the loop is currently mid-turn — drives the wordmark's
+   * "busy breathing" animation. Visual signal that the app is thinking,
+   * visible at a glance from anywhere on screen.
+   */
+  busy?: boolean;
+  /**
+   * /pro is queued — the next turn will run on v4-pro regardless of
+   * `model`. Rendered as a yellow `⇧ pro armed` pill in the header so
+   * the user has a clear "this turn will be expensive" signal before
+   * submitting their message.
+   */
+  proArmed?: boolean;
+  /**
+   * The CURRENT turn is running on v4-pro because the failure-
+   * escalation threshold fired mid-turn. Rendered as a red `⇧ pro
+   * escalated` pill. Clears at turn end.
+   */
+  escalated?: boolean;
+}
+
+/**
+ * Terminal width under which we switch from one-line metrics to a
+ * stacked layout. Below 120 cols the wide version wraps mid-number
+ * and the parens ("in $X · out $Y") get split across lines — which
+ * looks broken. Stacking costs one row but stays readable on every
+ * SSH / split-pane case we've hit.
+ */
+const NARROW_BREAKPOINT = 120;
+
+/**
+ * Cache-hit ratio is always zero on turn 1 (there's literally no cache
+ * to hit yet). Showing that as red "0.0%" is a false alarm — new users
+ * read it as "something is broken." We suppress the gradient until a
+ * few turns have landed; by turn 4 the cache has had time to warm up.
+ */
+const COLD_START_TURNS = 3;
+
+export function StatsPanel({
+  summary,
+  model,
+  prefixHash,
+  harvestOn,
+  branchBudget,
+  reasoningEffort,
+  planMode,
+  editMode,
+  balance,
+  updateAvailable,
+  busy,
+  proArmed,
+  escalated,
+}: StatsPanelProps) {
+  const branchOn = (branchBudget ?? 1) > 1;
+  const ctxMax = DEEPSEEK_CONTEXT_TOKENS[model] ?? DEFAULT_CONTEXT_TOKENS;
+  const ctxRatio = summary.lastPromptTokens / ctxMax;
+  const { stdout } = useStdout();
+  const columns = stdout?.columns ?? 80;
+  const narrow = columns < NARROW_BREAKPOINT;
+
+  // Cold-start: first few turns render cache+cost muted so a 0.0% hit
+  // rate on turn 1 doesn't look like an error. Once the cache has
+  // actually had a chance to build, we flip to the live gradient.
+  const coldStart = summary.turns <= COLD_START_TURNS;
+
+  // No gradient bars, no animation. Earlier versions had truecolor
+  // gradient rules top+bottom and a tick-driven wordmark/bar flow,
+  // but those are exactly the elements Ink's eraseLines miscounts
+  // on resize: ~100-char gradient strings wrap 2-3 visual rows at
+  // narrow widths, the per-tick re-render writes new frames before
+  // the stale rows are erased, and ghost panels stack vertically
+  // (the user-reported "刷屏" / multi-frame artifact). Fixed-row
+  // panel + no per-tick churn keeps Ink's row math honest.
+  return (
+    <Box flexDirection="column" paddingX={1} marginBottom={1}>
+      <Header
+        model={model}
+        prefixHash={prefixHash}
+        harvestOn={harvestOn}
+        branchOn={branchOn}
+        branchBudget={branchBudget ?? 1}
+        reasoningEffort={reasoningEffort}
+        planMode={planMode}
+        editMode={editMode}
+        turns={summary.turns}
+        updateAvailable={updateAvailable}
+        narrow={narrow}
+        busy={busy ?? false}
+        proArmed={proArmed ?? false}
+        escalated={escalated ?? false}
+        animate={false}
+      />
+      {narrow ? (
+        <StackedMetrics
+          summary={summary}
+          ctxRatio={ctxRatio}
+          ctxMax={ctxMax}
+          balance={balance}
+          coldStart={coldStart}
+        />
+      ) : (
+        <InlineMetrics
+          summary={summary}
+          ctxRatio={ctxRatio}
+          ctxMax={ctxMax}
+          balance={balance}
+          coldStart={coldStart}
+        />
+      )}
+    </Box>
+  );
+}
+
+function Header({
+  model,
+  prefixHash,
+  harvestOn,
+  branchOn,
+  branchBudget,
+  reasoningEffort,
+  planMode,
+  editMode,
+  turns,
+  updateAvailable,
+  narrow,
+  busy,
+  proArmed,
+  escalated,
+  animate,
+}: {
+  model: string;
+  prefixHash: string;
+  harvestOn?: boolean;
+  branchOn: boolean;
+  branchBudget: number;
+  reasoningEffort?: "high" | "max";
+  planMode?: boolean;
+  editMode?: EditMode;
+  turns: number;
+  updateAvailable?: string | null;
+  narrow: boolean;
+  busy: boolean;
+  proArmed: boolean;
+  escalated: boolean;
+  /** When false, suppress optional pills + animation to avoid wraps. */
+  animate: boolean;
+}) {
+  // Mode pill — pick the most informative one to surface in the
+  // header. PLAN beats AUTO/review beats nothing. Pro armed/escalated
+  // gets its own pill alongside.
+  const modePill = planMode
+    ? { label: "PLAN", bg: "red" as const }
+    : editMode === "auto"
+      ? { label: "AUTO", bg: "magenta" as const }
+      : editMode === "review"
+        ? { label: "REVIEW", bg: "cyan" as const }
+        : null;
+  const proPill = escalated
+    ? { label: "⇧ PRO", bg: "red" as const }
+    : proArmed
+      ? { label: "⇧ PRO", bg: "yellow" as const }
+      : null;
+  // Narrow / non-animate mode hides the secondary pills (harvest,
+  // branch, reasoning effort) so the header always fits on one
+  // visual row. Wrapping the header is the main amplifier of the
+  // eraseLines miscount that produces the "screen flashing" effect.
+  const showSecondary = animate && !narrow;
+  return (
+    <Box justifyContent="space-between">
+      <Box>
+        <Wordmark busy={busy} animate={animate} />
+        <Text dimColor>{`  ${VERSION}`}</Text>
+        <Text dimColor>{"   "}</Text>
+        <Text color="yellow" bold>
+          {model.replace(/^deepseek-/, "")}
+        </Text>
+        {modePill ? (
+          <>
+            <Text>{"  "}</Text>
+            <Pill label={modePill.label} bg={modePill.bg} />
+          </>
+        ) : null}
+        {proPill ? (
+          <>
+            <Text>{"  "}</Text>
+            <Pill label={proPill.label} bg={proPill.bg} />
+          </>
+        ) : null}
+        {showSecondary && harvestOn ? (
+          <Text dimColor>
+            <Text>{"  "}</Text>
+            <Text color="magenta">harvest</Text>
+          </Text>
+        ) : null}
+        {showSecondary && branchOn ? (
+          <Text dimColor>
+            <Text>{"  "}</Text>
+            <Text color="blue">{`branch×${branchBudget}`}</Text>
+          </Text>
+        ) : null}
+        {showSecondary && reasoningEffort === "max" ? (
+          <>
+            <Text>{"  "}</Text>
+            <Text color="green" dimColor>
+              max
+            </Text>
+          </>
+        ) : null}
+        {showSecondary && reasoningEffort === "high" ? (
+          <>
+            <Text>{"  "}</Text>
+            <Text color="yellow" dimColor>
+              high
+            </Text>
+          </>
+        ) : null}
+      </Box>
+      <Text>
+        {updateAvailable ? <Text color="yellow" bold>{`↑ ${updateAvailable}   `}</Text> : null}
+        <Text dimColor>{narrow ? `t${turns}` : `turn ${turns} · /help`}</Text>
+      </Text>
+    </Box>
+  );
+}
+
+/** Solid-background tag, used for primary mode + pro indicators. */
+function Pill({ label, bg }: { label: string; bg: "red" | "magenta" | "cyan" | "yellow" }) {
+  return (
+    <Text backgroundColor={bg} color="white" bold>
+      {` ${label} `}
+    </Text>
+  );
+}
+
+/**
+ * Wide-terminal layout (≥120 cols): single metrics row. Matches the
+ * original panel, just with calmer spacing and the cold-start
+ * treatment folded in.
+ */
+function InlineMetrics({
+  summary,
+  ctxRatio,
+  ctxMax,
+  balance,
+  coldStart,
+}: {
+  summary: SessionSummary;
+  ctxRatio: number;
+  ctxMax: number;
+  balance?: { currency: string; total: number } | null;
+  coldStart: boolean;
+}) {
+  return (
+    <Box marginTop={1} gap={3}>
+      <ContextCell ratio={ctxRatio} promptTokens={summary.lastPromptTokens} ctxMax={ctxMax} />
+      <CacheCell hitRatio={summary.cacheHitRatio} coldStart={coldStart} turns={summary.turns} />
+      <CostCell summary={summary} coldStart={coldStart} />
+      {balance ? <BalanceCell balance={balance} /> : null}
+    </Box>
+  );
+}
+
+/**
+ * Narrow-terminal layout (<120 cols): one metric per line, in priority
+ * order (ctx → balance → cache → cost). Order matters because users
+ * scanning a cramped terminal want "am I about to hit a wall?" answered
+ * first; dollars spent comes later.
+ */
+function StackedMetrics({
+  summary,
+  ctxRatio,
+  ctxMax,
+  balance,
+  coldStart,
+}: {
+  summary: SessionSummary;
+  ctxRatio: number;
+  ctxMax: number;
+  balance?: { currency: string; total: number } | null;
+  coldStart: boolean;
+}) {
+  return (
+    <Box marginTop={1} flexDirection="column">
+      <ContextCell
+        ratio={ctxRatio}
+        promptTokens={summary.lastPromptTokens}
+        ctxMax={ctxMax}
+        showBar
+      />
+      {balance ? <BalanceCell balance={balance} /> : null}
+      <CacheCell hitRatio={summary.cacheHitRatio} coldStart={coldStart} turns={summary.turns} />
+      <CostCell summary={summary} coldStart={coldStart} />
+    </Box>
+  );
+}
+
+function ContextCell({
+  ratio,
+  promptTokens,
+  ctxMax,
+  showBar,
+}: {
+  ratio: number;
+  promptTokens: number;
+  ctxMax: number;
+  showBar?: boolean;
+}) {
+  if (promptTokens === 0) {
+    return (
+      <Text>
+        <Text color={COLOR.info} dimColor>
+          {"▣ ctx "}
+        </Text>
+        <Text dimColor>— (no turns yet)</Text>
+      </Text>
+    );
+  }
+  const color = ratio >= 0.8 ? COLOR.err : ratio >= 0.6 ? COLOR.warn : COLOR.ok;
+  const pct = Math.round(ratio * 100);
+  return (
+    <Text>
+      <Text color={COLOR.info}>{"▣ ctx  "}</Text>
+      <Bar ratio={ratio} color={color} cells={showBar ? 14 : 10} />
+      <Text> </Text>
+      <Text color={color} bold>
+        {formatTokens(promptTokens)}/{formatTokens(ctxMax)}
+      </Text>
+      <Text dimColor> ({pct}%)</Text>
+      {ratio >= 0.8 ? (
+        <Text color={COLOR.err} bold>
+          {"  ·  /compact"}
+        </Text>
+      ) : null}
+    </Text>
+  );
+}
+
+function CacheCell({
+  hitRatio,
+  coldStart,
+  turns,
+}: {
+  hitRatio: number;
+  coldStart: boolean;
+  turns: number;
+}) {
+  const pct = (hitRatio * 100).toFixed(1);
+  if (turns === 0) {
+    return (
+      <Text>
+        <Text color={COLOR.info} dimColor>
+          {"⌬ cache "}
+        </Text>
+        <Text dimColor>—</Text>
+      </Text>
+    );
+  }
+  if (coldStart) {
+    return (
+      <Text>
+        <Text color={COLOR.info} dimColor>
+          {"⌬ cache "}
+        </Text>
+        <Text dimColor>{pct}% </Text>
+        <Text dimColor italic>
+          (cold start)
+        </Text>
+      </Text>
+    );
+  }
+  const color = hitRatio >= 0.7 ? COLOR.ok : hitRatio >= 0.4 ? COLOR.warn : COLOR.err;
+  return (
+    <Text>
+      <Text color={COLOR.info}>{"⌬ cache  "}</Text>
+      <Text color={color} bold>
+        {pct}%
+      </Text>
+    </Text>
+  );
+}
+
+/**
+ * Color thresholds. Per-turn and session cumulative scale roughly 10×
+ * apart — a $0.20 single turn should feel just as warn-worthy as a $2
+ * session total. Values are rough "notice this" points, not hard caps.
+ */
+function turnCostColor(cost: number): string | undefined {
+  if (cost <= 0) return undefined;
+  if (cost >= 0.2) return COLOR.err;
+  if (cost >= 0.05) return COLOR.warn;
+  return COLOR.ok;
+}
+function sessionCostColor(cost: number): string | undefined {
+  if (cost <= 0) return undefined;
+  if (cost >= 5) return COLOR.err;
+  if (cost >= 0.5) return COLOR.warn;
+  return COLOR.ok;
+}
+
+function CostCell({
+  summary,
+  coldStart,
+}: {
+  summary: SessionSummary;
+  coldStart: boolean;
+}) {
+  if (summary.turns === 0) {
+    return (
+      <Text>
+        <Text color={COLOR.info} dimColor>
+          {"◴ cost "}
+        </Text>
+        <Text dimColor>—</Text>
+      </Text>
+    );
+  }
+  // The first turn is unavoidably a cache-miss (nothing to hit),
+  // so the dollar figure is front-loaded. Muting it during the
+  // cold-start window keeps the "expensive first turn" from
+  // reading as "something is wrong."
+  const turnColor = coldStart ? undefined : turnCostColor(summary.lastTurnCostUsd);
+  const sessionColor = coldStart ? undefined : sessionCostColor(summary.totalCostUsd);
+  return (
+    <Text>
+      <Text color={COLOR.info}>{"◴ turn  "}</Text>
+      <Text color={turnColor} bold={!coldStart} dimColor={coldStart}>
+        ${summary.lastTurnCostUsd.toFixed(4)}
+      </Text>
+      <Text dimColor>{" · session "}</Text>
+      <Text color={sessionColor} bold={!coldStart} dimColor={coldStart}>
+        ${summary.totalCostUsd.toFixed(4)}
+      </Text>
+    </Text>
+  );
+}
+
+function BalanceCell({ balance }: { balance: { currency: string; total: number } }) {
+  const color = balance.total < 1 ? COLOR.err : balance.total < 5 ? COLOR.warn : COLOR.ok;
+  return (
+    <Text>
+      <Text color={COLOR.info}>{"◐ balance  "}</Text>
+      <Text color={color} bold>
+        {balance.currency === "USD" ? "$" : ""}
+        {balance.total.toFixed(2)}
+        {balance.currency !== "USD" ? ` ${balance.currency}` : ""}
+      </Text>
+    </Text>
+  );
+}
+
+/**
+ * Truecolor progress bar. Filled cells use the threshold color (green
+ * → amber → rose) so the bar communicates pressure at a glance;
+ * empty cells use a dim shade so the empty portion is visible
+ * without dominating. ▰/▱ have distinct shapes (filled vs hollow)
+ * so the boundary is clear even when colors snap to 8-color slots
+ * on legacy terminals.
+ */
+function Bar({
+  ratio,
+  color,
+  cells = 14,
+}: {
+  ratio: number;
+  color: string;
+  cells?: number;
+}) {
+  const filled = Math.max(0, Math.min(cells, Math.round(ratio * cells)));
+  return (
+    <Text>
+      <Text color={color}>{"▰".repeat(filled)}</Text>
+      <Text dimColor>{"▱".repeat(cells - filled)}</Text>
+    </Text>
+  );
+}
+
+/**
+ * Compact token formatter using binary K (÷1024): 1234 → "1.2K",
+ * 131072 → "128K". Matches DeepSeek's marketing label of "128K context
+ * length" — showing "131k" confused users (the actual limit is
+ * 128×1024 = 131,072 tokens, but the doc consistently says "128K").
+ * Uppercase K signals binary-K to anyone who notices.
+ */
+function formatTokens(n: number): string {
+  if (n < 1024) return String(n);
+  const k = n / 1024;
+  return k >= 100 ? `${k.toFixed(0)}K` : `${k.toFixed(1)}K`;
+}

src/cli/ui/WelcomeBanner.tsx

@@ -0,0 +1,113 @@
+/**
+ * Welcome card on the empty session. The first thing a user sees
+ * after launching `reasonix code` — needs to communicate, in the
+ * ~5 seconds before they type, three things: brand, what to type,
+ * how to escape. Card framing uses a gradient top rule + left-side
+ * accent bar + sectioned hints so it reads as a designed surface
+ * rather than a bare list. No bordered Boxes — those amplified
+ * Ink's Windows eraseLines miscount.
+ */
+
+import { Box, Text, useStdout } from "ink";
+// biome-ignore lint/style/useImportType: tsconfig jsx=react needs React in value scope
+import React from "react";
+import { COLOR, gradientCells } from "./theme.js";
+
+export interface WelcomeBannerProps {
+  /** True when running `reasonix code`. Surfaces code-mode hints. */
+  inCodeMode?: boolean;
+}
+
+export function WelcomeBanner({ inCodeMode }: WelcomeBannerProps): React.ReactElement {
+  const { stdout } = useStdout();
+  const cols = stdout?.columns ?? 80;
+  const ruleWidth = Math.min(60, Math.max(28, cols - 4));
+  return (
+    <Box flexDirection="column" paddingX={1} marginY={1}>
+      <GradientRule width={ruleWidth} />
+      <BarRow>
+        <Text bold color={COLOR.brand}>
+          ◈ welcome
+        </Text>
+        <Text dimColor>{"  ·  type a message to start"}</Text>
+      </BarRow>
+      <BarRow />
+      <BarRow>
+        <Text bold color={COLOR.primary}>
+          quick start
+        </Text>
+      </BarRow>
+      <Hint cmd="/help" desc="every command + keyboard shortcut" />
+      <Hint cmd="/skill" desc="invoke a stored playbook" />
+      {inCodeMode ? (
+        <>
+          <Hint cmd="@path" desc="inline a file in your message" />
+          <Hint cmd="!cmd" desc="run a shell command, output goes to context" />
+        </>
+      ) : null}
+      <Hint cmd="/exit" desc="quit (Ctrl+C also works)" />
+      <BarRow />
+      <BarRow>
+        <Text dimColor italic>
+          tip:
+        </Text>
+        <Text dimColor>{"  Ctrl+J inserts a newline · trailing \\ also continues"}</Text>
+      </BarRow>
+      <Box marginTop={1}>
+        <GradientRule width={ruleWidth} thin />
+      </Box>
+    </Box>
+  );
+}
+
+/**
+ * One-line gradient rule. `thin` swaps the half-block top/bottom so
+ * the top of the card reads as a "header band" (▄ — bottom-half
+ * filled) and the bottom as "section close" (▁ — minimal pixel
+ * row). Same primitive the StatsPanel uses, kept consistent.
+ */
+function GradientRule({ width, thin }: { width: number; thin?: boolean }) {
+  const cells = gradientCells(width, thin ? "▁" : "▄");
+  return (
+    <Box>
+      {cells.map((c, i) => (
+        // biome-ignore lint/suspicious/noArrayIndexKey: fixed-width gradient row, never reordered
+        <Text key={`wrule-${i}`} color={c.color}>
+          {c.ch}
+        </Text>
+      ))}
+    </Box>
+  );
+}
+
+/**
+ * Card row — left-side accent bar followed by content. Children
+ * optional so we can use this for blank spacer rows (bar only).
+ */
+function BarRow({ children }: { children?: React.ReactNode }) {
+  return (
+    <Box>
+      <Text color={COLOR.brand} bold>
+        ▎
+      </Text>
+      <Text> </Text>
+      {children}
+    </Box>
+  );
+}
+
+/**
+ * Single hint row — bold accent cmd token + dim description.
+ * Padded so all cmd tokens line up regardless of length, like a
+ * man-page synopsis.
+ */
+function Hint({ cmd, desc }: { cmd: string; desc: string }) {
+  return (
+    <BarRow>
+      <Text bold color={COLOR.accent}>
+        {cmd.padEnd(8)}
+      </Text>
+      <Text dimColor>{`  ${desc}`}</Text>
+    </BarRow>
+  );
+}

src/cli/ui/Wizard.tsx

@@ -0,0 +1,447 @@
+/**
+ * First-run / re-configure wizard.
+ *
+ * Walks a new user through: API key → preset pick → MCP server pick →
+ * per-server args → save. Saved output lives in `~/.reasonix/config.json`
+ * so the next `reasonix chat` starts with everything already wired.
+ *
+ * The wizard is the antidote to "too many CLI flags" — a new user should
+ * never have to read `--help` to get MCP + a sensible model combo
+ * working. Everything a user could set via `--mcp`, `--harvest`,
+ * `--branch`, etc. can be picked here in a few arrow-key presses.
+ */
+
+import { Box, Text, useApp, useInput } from "ink";
+import TextInput from "ink-text-input";
+// biome-ignore lint/style/useImportType: JSX (jsx: "react") needs React as a value at runtime
+import React, { useState } from "react";
+import {
+  type PresetName,
+  type ReasonixConfig,
+  defaultConfigPath,
+  isPlausibleKey,
+  readConfig,
+  redactKey,
+  writeConfig,
+} from "../../config.js";
+import { type CatalogEntry, MCP_CATALOG } from "../../mcp/catalog.js";
+import { MultiSelect, type SelectItem, SingleSelect } from "./Select.js";
+import { PRESET_DESCRIPTIONS } from "./presets.js";
+
+export interface WizardProps {
+  /** Called once the config has been saved. */
+  onComplete: (cfg: ReasonixConfig) => void;
+  /** Called if the user presses Esc to abort. */
+  onCancel?: () => void;
+  /** Skip the API-key step if a key already exists (env or config). */
+  existingApiKey?: string;
+  /** Pre-fill selections when re-running (reconfigure flow). */
+  initial?: {
+    preset?: PresetName;
+    mcp?: string[];
+  };
+}
+
+type Step = "apiKey" | "preset" | "mcp" | "mcpArgs" | "review" | "saved";
+
+interface WizardData {
+  apiKey: string;
+  preset: PresetName;
+  selectedCatalog: string[]; // entries from MCP_CATALOG by `name`
+  /** Captured user inputs per catalog entry that has `userArgs` (e.g. fs dir). */
+  catalogArgs: Record<string, string>;
+}
+
+const CATALOG_BY_NAME = new Map(MCP_CATALOG.map((e) => [e.name, e]));
+
+export function Wizard({ onComplete, onCancel, existingApiKey, initial }: WizardProps) {
+  const { exit } = useApp();
+  const [step, setStep] = useState<Step>(existingApiKey ? "preset" : "apiKey");
+  const [data, setData] = useState<WizardData>({
+    apiKey: existingApiKey ?? "",
+    preset: initial?.preset ?? "fast",
+    selectedCatalog: deriveInitialCatalog(initial?.mcp ?? []),
+    catalogArgs: {},
+  });
+  const [error, setError] = useState<string | null>(null);
+
+  // Global Esc → cancel. Disabled once we've started saving to avoid
+  // ejecting out of a half-written state.
+  useInput((_input, key) => {
+    if (key.escape && step !== "saved" && onCancel) onCancel();
+  });
+
+  if (step === "apiKey") {
+    return (
+      <ApiKeyStep
+        onSubmit={(key) => {
+          setData((d) => ({ ...d, apiKey: key }));
+          setError(null);
+          setStep("preset");
+        }}
+        error={error}
+        onError={setError}
+      />
+    );
+  }
+
+  if (step === "preset") {
+    return (
+      <StepFrame title="Pick a preset" step={1} total={3}>
+        <SingleSelect<PresetName>
+          items={presetItems()}
+          initialValue={data.preset}
+          onSubmit={(preset) => {
+            setData((d) => ({ ...d, preset }));
+            setStep("mcp");
+          }}
+        />
+        <Box marginTop={1}>
+          <Text dimColor>[↑↓] navigate · [Enter] confirm · [Esc] cancel</Text>
+        </Box>
+      </StepFrame>
+    );
+  }
+
+  if (step === "mcp") {
+    return (
+      <StepFrame title="Which MCP servers should Reasonix wire up for you?" step={2} total={3}>
+        <MultiSelect
+          items={mcpItems()}
+          initialSelected={data.selectedCatalog}
+          onSubmit={(selected) => {
+            setData((d) => ({ ...d, selectedCatalog: selected }));
+            // Only advance to the args step if any selected entry needs args.
+            const needsArgs = selected.some((name) => CATALOG_BY_NAME.get(name)?.userArgs);
+            setStep(needsArgs ? "mcpArgs" : "review");
+          }}
+          footer="[↑↓] navigate  ·  [Space] toggle  ·  [Enter] confirm  ·  [Esc] cancel  ·  empty = skip"
+        />
+      </StepFrame>
+    );
+  }
+
+  if (step === "mcpArgs") {
+    const pending = data.selectedCatalog.filter((name) => {
+      const entry = CATALOG_BY_NAME.get(name);
+      return entry?.userArgs && !data.catalogArgs[name];
+    });
+    if (pending.length === 0) {
+      setStep("review");
+      return null;
+    }
+    const currentName = pending[0]!;
+    const entry = CATALOG_BY_NAME.get(currentName)!;
+    return (
+      <McpArgsStep
+        entry={entry}
+        error={error}
+        onSubmit={(value) => {
+          setData((d) => ({
+            ...d,
+            catalogArgs: { ...d.catalogArgs, [currentName]: value },
+          }));
+          setError(null);
+        }}
+        onError={setError}
+      />
+    );
+  }
+
+  if (step === "review") {
+    const specs = data.selectedCatalog.map((name) => buildSpec(name, data.catalogArgs));
+    return (
+      <StepFrame title="Ready to save" step={3} total={3}>
+        <Box flexDirection="column">
+          <SummaryLine label="API key" value={redactKey(data.apiKey)} />
+          <SummaryLine label="Preset" value={data.preset} />
+          <SummaryLine
+            label="MCP"
+            value={specs.length === 0 ? "(none)" : `${specs.length} server(s)`}
+          />
+          {specs.map((spec, i) => (
+            // biome-ignore lint/suspicious/noArrayIndexKey: review-only render, order fixed
+            <Box key={i} paddingLeft={14}>
+              <Text dimColor>· {spec}</Text>
+            </Box>
+          ))}
+          <Box marginTop={1}>
+            <Text>Saves to {defaultConfigPath()}</Text>
+          </Box>
+          {error ? (
+            <Box marginTop={1}>
+              <Text color="red">{error}</Text>
+            </Box>
+          ) : null}
+          <Box marginTop={1}>
+            <Text dimColor>[Enter] save · [Esc] cancel</Text>
+          </Box>
+        </Box>
+        <ReviewConfirm
+          onConfirm={() => {
+            try {
+              const specsNow = data.selectedCatalog.map((name) =>
+                buildSpec(name, data.catalogArgs),
+              );
+              const prev = readConfig();
+              const next: ReasonixConfig = {
+                ...prev,
+                apiKey: data.apiKey,
+                preset: data.preset,
+                mcp: specsNow,
+                setupCompleted: true,
+              };
+              writeConfig(next);
+              setStep("saved");
+              onComplete(next);
+            } catch (e) {
+              setError(`Could not save config: ${(e as Error).message}`);
+            }
+          }}
+        />
+      </StepFrame>
+    );
+  }
+
+  // saved
+  return (
+    <Box flexDirection="column" borderStyle="round" borderColor="green" paddingX={1}>
+      <Text bold color="green">
+        ▸ Saved.
+      </Text>
+      <Box marginTop={1}>
+        <Text>Run `reasonix` any time to start chatting — your settings are remembered.</Text>
+      </Box>
+      <Box marginTop={1}>
+        <Text dimColor>[Enter] to exit</Text>
+      </Box>
+      <ExitOnEnter onExit={exit} />
+    </Box>
+  );
+}
+
+// ---------- step components ----------
+
+function ApiKeyStep({
+  onSubmit,
+  error,
+  onError,
+}: {
+  onSubmit: (key: string) => void;
+  error: string | null;
+  onError: (e: string | null) => void;
+}) {
+  const [value, setValue] = useState("");
+  return (
+    <Box flexDirection="column" borderStyle="round" borderColor="cyan" paddingX={1}>
+      <Text bold color="cyan">
+        Welcome to Reasonix.
+      </Text>
+      <Box marginTop={1}>
+        <Text>Paste your DeepSeek API key to get started.</Text>
+      </Box>
+      <Text dimColor>Get one (free credit on signup): https://platform.deepseek.com/api_keys</Text>
+      <Text dimColor>Saved locally to {defaultConfigPath()}</Text>
+      <Box marginTop={1}>
+        <Text bold color="cyan">
+          {"key › "}
+        </Text>
+        <TextInput
+          value={value}
+          onChange={setValue}
+          onSubmit={(raw) => {
+            const trimmed = raw.trim();
+            if (!isPlausibleKey(trimmed)) {
+              onError("Doesn't look like a DeepSeek key. They start with 'sk-' and are 30+ chars.");
+              setValue("");
+              return;
+            }
+            onSubmit(trimmed);
+          }}
+          mask="•"
+          placeholder="sk-..."
+        />
+      </Box>
+      {error ? (
+        <Box marginTop={1}>
+          <Text color="red">{error}</Text>
+        </Box>
+      ) : value ? (
+        <Box marginTop={1}>
+          <Text dimColor>preview: {redactKey(value)}</Text>
+        </Box>
+      ) : null}
+    </Box>
+  );
+}
+
+function McpArgsStep({
+  entry,
+  error,
+  onSubmit,
+  onError,
+}: {
+  entry: CatalogEntry;
+  error: string | null;
+  onSubmit: (value: string) => void;
+  onError: (e: string | null) => void;
+}) {
+  const [value, setValue] = useState("");
+  return (
+    <StepFrame title={`Configure ${entry.name}`} step={2} total={3}>
+      <Box flexDirection="column">
+        <Text>{entry.summary}</Text>
+        {entry.note ? (
+          <Box marginTop={1}>
+            <Text dimColor>{entry.note}</Text>
+          </Box>
+        ) : null}
+        <Box marginTop={1}>
+          <Text>Required parameter: </Text>
+          <Text bold>{entry.userArgs}</Text>
+        </Box>
+        <Box marginTop={1}>
+          <Text bold color="cyan">
+            {entry.userArgs}
+            {" › "}
+          </Text>
+          <TextInput
+            value={value}
+            onChange={setValue}
+            onSubmit={(raw) => {
+              const trimmed = raw.trim();
+              if (!trimmed) {
+                onError(`${entry.name} needs a value — got an empty string.`);
+                return;
+              }
+              onSubmit(trimmed);
+              setValue("");
+            }}
+            placeholder={placeholderFor(entry)}
+          />
+        </Box>
+        {error ? (
+          <Box marginTop={1}>
+            <Text color="red">{error}</Text>
+          </Box>
+        ) : null}
+      </Box>
+    </StepFrame>
+  );
+}
+
+function ReviewConfirm({ onConfirm }: { onConfirm: () => void }) {
+  useInput((_i, key) => {
+    if (key.return) onConfirm();
+  });
+  return null;
+}
+
+function ExitOnEnter({ onExit }: { onExit: () => void }) {
+  useInput((_i, key) => {
+    if (key.return) onExit();
+  });
+  return null;
+}
+
+// ---------- small bits ----------
+
+function StepFrame({
+  title,
+  step,
+  total,
+  children,
+}: {
+  title: string;
+  step: number;
+  total: number;
+  children: React.ReactNode;
+}) {
+  return (
+    <Box flexDirection="column" borderStyle="round" borderColor="cyan" paddingX={1}>
+      <Box>
+        <Text dimColor>
+          Step {step}/{total} ·{" "}
+        </Text>
+        <Text bold color="cyan">
+          {title}
+        </Text>
+      </Box>
+      <Box marginTop={1} flexDirection="column">
+        {children}
+      </Box>
+    </Box>
+  );
+}
+
+function SummaryLine({ label, value }: { label: string; value: string }) {
+  return (
+    <Box>
+      <Text>{label.padEnd(12)}</Text>
+      <Text bold>{value}</Text>
+    </Box>
+  );
+}
+
+// ---------- data helpers ----------
+
+function presetItems(): SelectItem<PresetName>[] {
+  return (["fast", "smart", "max"] as PresetName[]).map((name) => ({
+    value: name,
+    label: `${name} — ${PRESET_DESCRIPTIONS[name].headline}`,
+    hint: PRESET_DESCRIPTIONS[name].cost,
+  }));
+}
+
+function mcpItems(): SelectItem<string>[] {
+  return MCP_CATALOG.map((entry) => {
+    const hintParts: string[] = [entry.summary];
+    if (entry.userArgs) hintParts.push(`(you'll provide ${entry.userArgs})`);
+    if (entry.note) hintParts.push(entry.note);
+    return {
+      value: entry.name,
+      label: entry.name,
+      hint: hintParts.join(" · "),
+    };
+  });
+}
+
+function placeholderFor(entry: CatalogEntry): string {
+  if (entry.name === "filesystem") return "e.g. /tmp/reasonix-sandbox";
+  if (entry.name === "sqlite") return "e.g. ./notes.sqlite";
+  return entry.userArgs ?? "";
+}
+
+function deriveInitialCatalog(existingSpecs: string[]): string[] {
+  // Best-effort recovery: if the user previously picked catalog entries,
+  // the spec strings look like `name=npx -y <pkg> ...`. Match by package
+  // so reconfigure pre-checks the same boxes.
+  const packageToName = new Map(MCP_CATALOG.map((e) => [e.package, e.name]));
+  const out: string[] = [];
+  for (const spec of existingSpecs) {
+    for (const [pkg, name] of packageToName) {
+      if (spec.includes(pkg)) {
+        out.push(name);
+        break;
+      }
+    }
+  }
+  return out;
+}
+
+/**
+ * Build the `--mcp` spec string for a catalog entry. Same format
+ * `mcpCommandFor` produces for `reasonix mcp list`, minus the leading
+ * `--mcp "..."` wrapper — we store the inner spec directly.
+ */
+export function buildSpec(name: string, argsByName: Record<string, string>): string {
+  const entry = CATALOG_BY_NAME.get(name);
+  if (!entry) return name; // shouldn't happen; fall back gracefully
+  const userArg = entry.userArgs ? argsByName[name] : undefined;
+  const tail = userArg ? ` ${quoteIfNeeded(userArg)}` : "";
+  return `${entry.name}=npx -y ${entry.package}${tail}`;
+}
+
+function quoteIfNeeded(s: string): string {
+  return /\s|"/.test(s) ? `"${s.replace(/"/g, '\\"')}"` : s;
+}

src/cli/ui/bang.ts

@@ -0,0 +1,39 @@
+/**
+ * Bash-mode (`!cmd`) prefix parsing.
+ *
+ * A `!` at the start of the user's input means "run this as a shell
+ * command in the sandbox root, and put both the command and its output
+ * into the conversation so the model sees it next turn." Same idea as
+ * Claude Code's `!` prefix — faster than round-tripping through the
+ * model just to cat a file or check git status.
+ *
+ * Design choice: user-typed `!` commands skip the allowlist. The
+ * allowlist exists to bound what the MODEL can do with run_command;
+ * the user typing `!git push` by hand is explicit consent. If a user
+ * wants stricter gating they can set `REASONIX_BANG_CONFIRM=1` in a
+ * future iteration.
+ */
+
+/**
+ * Return the command portion of a `!`-prefixed input, or `null` if
+ * the text isn't a bang invocation. Trims leading/trailing whitespace
+ * from the command body. `!` alone (or `!` followed by only whitespace)
+ * returns `null` — no command to run.
+ */
+export function detectBangCommand(text: string): string | null {
+  if (!text.startsWith("!")) return null;
+  const body = text.slice(1).trim();
+  if (!body) return null;
+  return body;
+}
+
+/**
+ * Format a bang command + its output into a single user-role message
+ * body that the model will see on the next turn. The `[!cmd]` header
+ * marks the run explicitly so the model can distinguish
+ * user-typed shell output from its own `run_command` tool results
+ * (which are `role: tool`, different message shape entirely).
+ */
+export function formatBangUserMessage(cmd: string, output: string): string {
+  return `[!${cmd}]\n${output}`;
+}

src/cli/ui/edit-history.ts

@@ -0,0 +1,109 @@
+import { formatAllBlockDiffs } from "../../code/diff-preview.js";
+import type { ApplyResult, EditBlock, EditSnapshot } from "../../code/edit-blocks.js";
+
+/**
+ * One batch of edits that actually landed on disk — durable enough for
+ * `/undo`, `/history`, and `/show` within a session. Not persisted
+ * across restarts: restoring pre-apply content from a process that
+ * crashed last week is git's job, not ours.
+ */
+export interface EditHistoryEntry {
+  /** Sequence number within the session, stable for `/show <id>`. */
+  id: number;
+  /** Epoch ms when the entry was opened (first edit landed). */
+  at: number;
+  /**
+   * Short tag for what produced the batch — "auto" (auto-mode tool
+   * call), "auto-text" (auto-mode text SEARCH/REPLACE at turn end),
+   * "review-apply" (user-approved modal edit or /apply flush).
+   */
+  source: string;
+  /** Edit blocks included in this batch, in arrival order. */
+  blocks: EditBlock[];
+  /** Per-block outcome — some may be "not-found" if SEARCH drifted. */
+  results: ApplyResult[];
+  /**
+   * First-snapshot-per-path wins: this is what `/undo` restores to.
+   * Deduped so multi-edit turns still roll back to pre-turn state.
+   */
+  snapshots: EditSnapshot[];
+  /**
+   * Paths within this entry that have already been reverted (via
+   * `/undo <id>`, `/undo <id> <path>`, or the newest-non-undone /undo
+   * shortcut). Per-path instead of entry-level so a batch can be
+   * partially undone — user reverts src/foo.ts out of a 3-file batch
+   * without rolling back the other two.
+   */
+  undoneFiles: Set<string>;
+}
+
+/** True when every path in the entry has been undone. */
+export function isEntryFullyUndone(e: EditHistoryEntry): boolean {
+  return e.snapshots.length > 0 && e.snapshots.every((s) => e.undoneFiles.has(s.path));
+}
+
+/** Per-entry three-state status label for display. */
+export function entryStatus(e: EditHistoryEntry): "applied" | "UNDONE" | "PARTIAL" {
+  if (e.undoneFiles.size === 0) return "applied";
+  if (isEntryFullyUndone(e)) return "UNDONE";
+  return "PARTIAL";
+}
+
+/**
+ * Render a batch of SEARCH/REPLACE application results as one
+ * human-scannable info line per edit. Prefixes denote status so the
+ * line reads well even without color (e.g. when piped to a log file
+ * or stripped for screenshots):
+ *   ✓ applied  src/foo.ts
+ *   ✓ created  src/new.ts
+ *   ✗ not-found  src/bar.ts (SEARCH text does not match…)
+ */
+export function formatEditResults(results: ApplyResult[]): string {
+  const lines = results.map((r) => {
+    const mark = r.status === "applied" || r.status === "created" ? "✓" : "✗";
+    const detail = r.message ? ` (${r.message})` : "";
+    return `  ${mark} ${r.status.padEnd(11)} ${r.path}${detail}`;
+  });
+  const ok = results.filter((r) => r.status === "applied" || r.status === "created").length;
+  const total = results.length;
+  const header = `▸ edit blocks: ${ok}/${total} applied — /undo to roll back, or \`git diff\` to review`;
+  return [header, ...lines].join("\n");
+}
+
+/**
+ * Pending-edits preview shown after each assistant turn that proposed
+ * changes. Per-block path header + ±line-count, then a unified-diff-
+ * style preview (context trimmed to 2 lines each side, total capped
+ * at 20 lines per block). Users can eyeball what's about to land
+ * BEFORE pressing `y` — the old summary-only view was a common
+ * mistake surface.
+ */
+export function formatPendingPreview(blocks: EditBlock[]): string {
+  const header = `▸ ${blocks.length} pending edit block(s) — /apply (or y) to commit · /discard (or n) to drop`;
+  const diffLines = formatAllBlockDiffs(blocks);
+  return [header, ...diffLines].join("\n");
+}
+
+/**
+ * Per-file rows for the multi-level `/undo` output, without the
+ * single-batch header (the caller prepends its own).
+ */
+export function formatUndoRows(results: ApplyResult[]): string[] {
+  return results.map((r) => {
+    const mark = r.status === "applied" ? "✓" : "✗";
+    const detail = r.message ? ` (${r.message})` : "";
+    return `  ${mark} ${r.path}${detail}`;
+  });
+}
+
+export function describeRepair(repair: {
+  scavenged: number;
+  truncationsFixed: number;
+  stormsBroken: number;
+}): string {
+  const parts: string[] = [];
+  if (repair.scavenged) parts.push(`scavenged ${repair.scavenged}`);
+  if (repair.truncationsFixed) parts.push(`repaired ${repair.truncationsFixed} truncation`);
+  if (repair.stormsBroken) parts.push(`broke ${repair.stormsBroken} storm`);
+  return parts.length ? `[repair] ${parts.join(", ")}` : "";
+}

src/cli/ui/key-normalize.ts

@@ -0,0 +1,144 @@
+/**
+ * CSI sequence recovery for Ink's `useInput`.
+ *
+ * Why this exists. Ink delivers keyboard events through `parse-keypress`,
+ * which reads stdin and recognises ANSI control-sequence-introducer
+ * (CSI) sequences with a state machine plus a short timeout. On most
+ * terminals this works: the byte stream `\x1b [ A` arrives in one
+ * read, parse-keypress emits `{key.upArrow:true, input:""}`, life is
+ * good.
+ *
+ * On Windows PowerShell + ConPTY (and a handful of embedded shells)
+ * the bytes don't always arrive together. parse-keypress's timeout
+ * expires between chunks, so it dispatches the lone `\x1b` as
+ * `key.escape:true` and then dispatches the trailing `[A` as a
+ * regular character event — `input:"[A", key.upArrow:undefined`. The
+ * useInput consumer sees `[A` as plain text, inserts it into the
+ * buffer, and the cursor never moves. Same shape on `[C` (right
+ * arrow), `[Z` (Shift+Tab), `[5~` (PgUp), `[201~` (bracketed-paste
+ * end), etc.
+ *
+ * Every Reasonix UI component that calls `useInput` is exposed to
+ * this. Patching each one to re-recognise the bare CSI tail was
+ * fragile — every release a new symptom appeared (cursor stuck,
+ * paste markers leaking, Shift+Tab not toggling). So this module is
+ * the single source of truth for CSI recovery: every input handler
+ * runs the raw event through `recoverCsiTail` before reading
+ * structured key flags.
+ *
+ * Recovery is conservative. We only rewrite when:
+ *   1. None of the structured key flags Ink already populated for
+ *      this event is set (so a real upArrow press isn't second-
+ *      guessed).
+ *   2. `input` exactly matches a recognised tail in either form —
+ *      the full `\x1b[X` sequence (in case the timeout merged it)
+ *      or the bare `[X` ConPTY-stripped variant.
+ *
+ * Anything else passes through unchanged.
+ */
+
+/**
+ * Subset of Ink's `Key` interface that contains the structured flags
+ * we know how to recover. Optional everywhere because callers from
+ * different Ink versions may not populate every field.
+ */
+export interface CsiKeyFlags {
+  upArrow?: boolean;
+  downArrow?: boolean;
+  leftArrow?: boolean;
+  rightArrow?: boolean;
+  pageUp?: boolean;
+  pageDown?: boolean;
+  delete?: boolean;
+  shift?: boolean;
+  tab?: boolean;
+}
+
+/**
+ * CSI tails we recognise. Each maps the printable bytes of a CSI
+ * tail (the part after the `\x1b`) to the structured key flags they
+ * should set. Bracketed-paste markers `[200~` / `[201~` are
+ * intentionally absent — they're handled by PromptInput's paste
+ * accumulator, which has different semantics (collect content
+ * between markers rather than emit one keystroke).
+ */
+const CSI_TAIL_TO_FLAGS: ReadonlyArray<{ tail: string; flags: CsiKeyFlags }> = [
+  // Arrow keys — the most common ConPTY victim.
+  { tail: "[A", flags: { upArrow: true } },
+  { tail: "[B", flags: { downArrow: true } },
+  { tail: "[C", flags: { rightArrow: true } },
+  { tail: "[D", flags: { leftArrow: true } },
+  // Page navigation.
+  { tail: "[5~", flags: { pageUp: true } },
+  { tail: "[6~", flags: { pageDown: true } },
+  // Forward-delete (the key labelled Delete on most keyboards).
+  { tail: "[3~", flags: { delete: true } },
+  // Shift+Tab — terminal sends `\x1b[Z` rather than tab-with-shift.
+  { tail: "[Z", flags: { shift: true, tab: true } },
+];
+
+/**
+ * Did Ink already give us a structured key for this event? When
+ * `true`, recovery is unnecessary and would risk overriding a real
+ * keypress that happens to share `input` with a CSI tail.
+ */
+function alreadyStructured(flags: CsiKeyFlags): boolean {
+  return Boolean(
+    flags.upArrow ||
+      flags.downArrow ||
+      flags.leftArrow ||
+      flags.rightArrow ||
+      flags.pageUp ||
+      flags.pageDown ||
+      flags.delete ||
+      (flags.tab && flags.shift),
+  );
+}
+
+/**
+ * If `input` is a recognisable CSI tail (with or without the leading
+ * `\x1b`), return the structured flags it should produce. Otherwise
+ * `null`. Bracketed-paste markers always return `null` here — those
+ * are handled by their own accumulator.
+ *
+ * Pure function. Pass already-structured events through (they
+ * short-circuit) so a real arrow press doesn't get rewritten.
+ */
+export function recoverCsiTail(input: string, existing: CsiKeyFlags = {}): CsiKeyFlags | null {
+  if (alreadyStructured(existing)) return null;
+  for (const entry of CSI_TAIL_TO_FLAGS) {
+    if (input === entry.tail || input === `\x1b${entry.tail}`) {
+      return entry.flags;
+    }
+  }
+  return null;
+}
+
+/**
+ * Tail forms (with and without the leading `\x1b`) that should never
+ * end up as literal text in a user's prompt buffer. Used as a final
+ * defensive pass before treating input as printable — if a CSI
+ * fragment slipped past structured-key recovery (e.g. arrived
+ * embedded inside a paste burst), at least drop the raw bytes
+ * rather than insert them as garbage text.
+ *
+ * Includes the bracketed-paste markers `[200~` / `[201~` because a
+ * paste whose start/end markers got chunked across reads can leave
+ * those bytes in the printable input.
+ */
+export const STRIPPABLE_CSI_FRAGMENTS: readonly string[] = [
+  "\u001b[200~",
+  "\u001b[201~",
+  "[200~",
+  "[201~",
+  ...CSI_TAIL_TO_FLAGS.flatMap((e) => [`\u001b${e.tail}`, e.tail]),
+];
+
+/** Remove every recognised CSI fragment from a string. */
+export function stripCsiFragments(input: string): string {
+  let out = input;
+  for (const frag of STRIPPABLE_CSI_FRAGMENTS) {
+    if (out.includes(frag)) out = out.replaceAll(frag, "");
+  }
+  return out;
+}

src/cli/ui/keystroke-context.tsx

@@ -0,0 +1,120 @@
+/**
+ * KeystrokeContext — React surface in front of the raw stdin reader.
+ *
+ * Replaces Ink's `useInput` chain. Reasonix's components no longer
+ * import `useInput` from "ink"; they call `useKeystroke(handler,
+ * isActive)` from this module. The provider mounted once at App
+ * level owns a `StdinReader`, subscribes a single fan-out function
+ * to it, and dispatches each parsed `KeyEvent` to every active
+ * consumer.
+ *
+ * Why a Context instead of a singleton import: the provider can be
+ * disabled in tests / replay mode without touching the components,
+ * and the lifecycle (start/stop on mount/unmount) is tied to the
+ * React tree rather than a global side effect.
+ *
+ * Why not just keep Ink's useInput: Ink's parse-keypress uses a
+ * 100 ms intra-CSI timeout that's too short for Windows ConPTY,
+ * leaking arrow-key bytes / paste markers into the buffer. Our
+ * reader uses 250 ms and recognises the ESC-stripped variants too
+ * — see `stdin-reader.ts`.
+ */
+
+// biome-ignore lint/style/useImportType: tsconfig jsx=react needs React as a runtime value
+import React, { createContext, useContext, useEffect, useRef } from "react";
+import { type KeyEvent, type StdinReader, getStdinReader } from "./stdin-reader.js";
+
+interface KeystrokeBus {
+  /** Subscribe — returns an unsubscribe function. */
+  subscribe(handler: KeystrokeHandler): () => void;
+}
+
+export type KeystrokeHandler = (ev: KeyEvent) => void;
+
+const KeystrokeContext = createContext<KeystrokeBus | null>(null);
+
+export interface KeystrokeProviderProps {
+  children: React.ReactNode;
+  /**
+   * Optional reader override. Tests inject a synthetic reader so
+   * they can `feed()` chunks instead of touching real stdin. Production
+   * callers leave this unset and get the singleton.
+   */
+  reader?: StdinReader;
+}
+
+export function KeystrokeProvider({
+  children,
+  reader: providedReader,
+}: KeystrokeProviderProps): React.ReactElement {
+  const handlersRef = useRef<Set<KeystrokeHandler>>(new Set());
+  // Ref so the bus value's identity is stable across re-renders —
+  // consumers don't accidentally re-subscribe every render.
+  const busRef = useRef<KeystrokeBus | null>(null);
+  if (busRef.current === null) {
+    busRef.current = {
+      subscribe(handler) {
+        handlersRef.current.add(handler);
+        return () => {
+          handlersRef.current.delete(handler);
+        };
+      },
+    };
+  }
+
+  useEffect(() => {
+    const reader = providedReader ?? getStdinReader();
+    reader.start();
+    const unsubscribe = reader.subscribe((ev) => {
+      // Snapshot the handler set so handlers added/removed during
+      // dispatch don't perturb iteration. Cheap — typical N=1-3.
+      for (const fn of [...handlersRef.current]) fn(ev);
+    });
+    return () => {
+      unsubscribe();
+      // Don't `stop()` the singleton on every unmount — multiple
+      // mounts (test reruns, hot-reload) must not tear down stdin.
+      // The singleton's own start() is idempotent; stop() is the
+      // process-exit handler's job.
+    };
+  }, [providedReader]);
+
+  return <KeystrokeContext.Provider value={busRef.current}>{children}</KeystrokeContext.Provider>;
+}
+
+/**
+ * Subscribe to keystroke events. Mirrors Ink's `useInput` shape —
+ * `handler(ev)` runs on every event while `isActive` is truthy
+ * (default true). Set `isActive=false` to suspend the handler
+ * (e.g. while a modal is up and shouldn't respond to global keys).
+ *
+ * Handler identity changes are tolerated — we re-subscribe via
+ * useEffect on every render. Wrap your handler in `useCallback` if
+ * you want to avoid that.
+ */
+export function useKeystroke(handler: KeystrokeHandler, isActive = true): void {
+  const bus = useContext(KeystrokeContext);
+  // Latest-handler ref so we can subscribe ONCE per active toggle
+  // and still call the freshest closure on each event.
+  const handlerRef = useRef(handler);
+  handlerRef.current = handler;
+
+  useEffect(() => {
+    if (!bus || !isActive) return undefined;
+    return bus.subscribe((ev) => handlerRef.current(ev));
+  }, [bus, isActive]);
+}
+
+/**
+ * Lower-level hook for components that need a stable subscription
+ * across the lifetime of the consumer (typically StdinReader-aware
+ * unit tests).
+ */
+export function useKeystrokeBus(): KeystrokeBus | null {
+  return useContext(KeystrokeContext);
+}
+
+/** Test helper — assemble a KeyEvent with sensible defaults. */
+export function makeKeyEvent(overrides: Partial<KeyEvent> = {}): KeyEvent {
+  return { input: "", ...overrides };
+}