feat(ux): tool-row elapsed + args · reasoning tail · /think (0.4.2)

Three small improvements surfaced from real-session feedback:

1. Tool-running row was just a spinner + raw-JSON args; user said
   "看不到任何的输出,就只知道再转圈". Added elapsed seconds counter
   and per-tool argument summarizer. Instead of
     tool<filesystem_edit_file> running... {"path":"..."...}
   you now see
     tool<filesystem_edit_file> running... 3s
       path: F:\testtest\index.html (2 edits)
   Summarizers for read_file / write_file / edit_file /
   list_directory / directory_tree / search_files / move_file /
   get_file_info, matching by suffix so bridgeMcpTools name prefix
   (e.g. "filesystem_") works too. Unknown tools fall back to a
   truncated raw preview.

2. ReasoningBlock showed the first 220 chars with "(+N chars)"
   elided at the end. R1 opens every turn with the same scaffolding
   ("let me look at the structure...") so the preview looked
   identical across turns and hid the actual decision in the
   truncated tail. Switched to showing the LAST ~260 chars —
   which is where R1 commits to an action.

3. /think slash command dumps the full reasoning text from
   loop.scratch.reasoning when the tail preview isn't enough.
   Alias: /reasoning. Graceful "no reasoning cached" message when
   the current model is deepseek-chat (no reasoning_content) or a
   turn hasn't completed yet.

Tests: +3 in slash.test.ts (/think empty + populated + help).
Suite: 319 -> 322.

Bumps to 0.4.2.

.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

@@ -1,13 +0,0 @@
-.gitattributes text eol=lf
-.gitignore text eol=lf
-*.astro text eol=lf
-*.css text eol=lf
-*.html text eol=lf
-*.js text eol=lf
-*.json text eol=lf
-*.md text eol=lf
-*.mjs text eol=lf
-*.sh 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/pages.yml

@@ -1,66 +0,0 @@
-name: Deploy website
-run-name: Deploy site ${{ inputs.release_version && format('v{0}', inputs.release_version) || github.sha }}${{ inputs.release_request && format(' [{0}]', inputs.release_request) || '' }}
-
-on:
-  push:
-    branches: [website]
-  workflow_dispatch:
-    inputs:
-      release_version:
-        description: "Optional product release version associated with this publication"
-        required: false
-        default: ""
-        type: string
-      release_request:
-        description: "Optional release workflow correlation ID"
-        required: false
-        default: ""
-        type: string
-      studio_version:
-        description: "Studio version that must be present in the generated changelog"
-        required: false
-        default: ""
-        type: string
-
-permissions:
-  contents: read
-  pages: write
-  id-token: write
-
-concurrency:
-  group: reasonix-website-production
-  cancel-in-progress: false
-
-jobs:
-  build:
-    if: github.ref == 'refs/heads/website'
-    runs-on: ubuntu-latest
-    steps:
-      - uses: actions/checkout@3d3c42e5aac5ba805825da76410c181273ba90b1 # v7
-      - uses: actions/setup-node@820762786026740c76f36085b0efc47a31fe5020 # v7
-        with:
-          node-version: "22"
-          cache: npm
-          cache-dependency-path: site/package-lock.json
-      - name: Validate and build
-        working-directory: site
-        env:
-          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
-          STUDIO_RELEASE_VERSION: ${{ inputs.studio_version }}
-        run: |
-          npm ci
-          npm test
-          npm run build
-      - uses: actions/upload-pages-artifact@fc324d3547104276b827a68afc52ff2a11cc49c9 # v5
-        with:
-          path: site/dist
-
-  deploy:
-    needs: build
-    runs-on: ubuntu-latest
-    environment:
-      name: github-pages
-      url: ${{ steps.deploy.outputs.page_url }}
-    steps:
-      - id: deploy
-        uses: actions/deploy-pages@368f82528645a54fb793d4d04e342629a3f51346 # v5

.github/workflows/prepare-release-notes.yml

@@ -1,106 +0,0 @@
-name: Prepare release
-
-on:
-  workflow_dispatch:
-    inputs:
-      version:
-        description: "Official version without a tag prefix (for example 1.20.0)"
-        required: true
-        type: string
-
-permissions:
-  contents: write
-  pull-requests: write
-
-jobs:
-  draft:
-    name: generate reviewable bilingual draft
-    if: github.ref == 'refs/heads/website'
-    runs-on: ubuntu-latest
-    steps:
-      - uses: actions/checkout@3d3c42e5aac5ba805825da76410c181273ba90b1 # v7
-        with:
-          fetch-depth: 0
-
-      - uses: actions/setup-node@820762786026740c76f36085b0efc47a31fe5020 # v7
-        with:
-          node-version: "22"
-
-      - name: Select the review branch
-        env:
-          GH_TOKEN: ${{ github.token }}
-          VERSION: ${{ inputs.version }}
-        run: |
-          set -euo pipefail
-          git config user.name "github-actions[bot]"
-          git config user.email "41898282+github-actions[bot]@users.noreply.github.com"
-          git fetch origin main-v2 website
-
-          if [[ ! "$VERSION" =~ ^(0|[1-9][0-9]*)\.(0|[1-9][0-9]*)\.(0|[1-9][0-9]*)$ ]]; then
-            echo "::error::version must be MAJOR.MINOR.PATCH"
-            exit 1
-          fi
-          branch="website-release-notes/v${VERSION}"
-          if git ls-remote --exit-code --heads origin "$branch" >/dev/null 2>&1; then
-            git fetch origin "refs/heads/$branch:refs/remotes/origin/$branch"
-            git checkout -b "$branch" --track "origin/$branch"
-            git merge-base --is-ancestor origin/website HEAD
-          else
-            git checkout -b "$branch"
-          fi
-          source_sha="$(git rev-parse origin/main-v2)"
-          echo "RELEASE_NOTES_BRANCH=$branch" >> "$GITHUB_ENV"
-          echo "RELEASE_NOTES_SOURCE_SHA=$source_sha" >> "$GITHUB_ENV"
-
-      - name: Generate and validate release notes
-        env:
-          DEEPSEEK_API_KEY: ${{ secrets.DEEPSEEK_API_KEY }}
-          DEEPSEEK_MODEL: deepseek-v4-pro
-          GH_TOKEN: ${{ github.token }}
-          VERSION: ${{ inputs.version }}
-        run: |
-          set -euo pipefail
-          # The first preparation fixes the product range. Reruns update the
-          # draft without silently absorbing unrelated main-v2 merges.
-          node site/scripts/releases/generate-release-notes.mjs --version "$VERSION" --to "$RELEASE_NOTES_SOURCE_SHA"
-          node site/scripts/releases/release-notes.mjs validate
-          node --test site/scripts/releases/release-notes.test.mjs
-          node site/scripts/releases/release-notes.mjs render --version "$VERSION" --output /tmp/release-notes.md
-          {
-            echo "## Review draft for v${VERSION#v}"
-            echo
-            cat /tmp/release-notes.md
-          } >> "$GITHUB_STEP_SUMMARY"
-
-      - name: Open or update the review PR
-        env:
-          GH_TOKEN: ${{ github.token }}
-          VERSION: ${{ inputs.version }}
-        run: |
-          set -euo pipefail
-          git add site/src/data/releases.json
-          if ! git diff --cached --quiet; then
-            git commit -m "docs(release): prepare v${VERSION#v} notes" \
-              -m "Summary:
-          Generate a bilingual, product-focused draft from merged pull request metadata. Reuse the selected release-bound PR when one is available.
-
-          Verification:
-          Validate the catalog, citations, bilingual fields, and rendered GitHub release notes before committing."
-          fi
-          git push -u origin "$RELEASE_NOTES_BRANCH"
-          if ! gh pr list --head "$RELEASE_NOTES_BRANCH" --state open --json number --jq 'length > 0' | grep -q true; then
-            if ! gh pr create \
-              --base website \
-              --head "$RELEASE_NOTES_BRANCH" \
-              --title "docs(release): 准备 v${VERSION#v} 中英更新日志" \
-              --body-file /tmp/release-notes.md; then
-              echo "::warning::GitHub Actions could not open the PR; the reviewed branch is preserved."
-              {
-                echo "## Manual PR handoff"
-                echo
-                echo '```sh'
-                echo "gh pr create --repo ${{ github.repository }} --base website --head $RELEASE_NOTES_BRANCH --fill"
-                echo '```'
-              } >> "$GITHUB_STEP_SUMMARY"
-            fi
-          fi

.github/workflows/release-notes.yml

@@ -1,27 +0,0 @@
-name: Release notes
-
-on:
-  pull_request:
-    branches: [website]
-    paths:
-      - "site/src/data/releases.json"
-      - "site/scripts/releases/**"
-      - "site/scripts/release-event.mjs"
-      - "site/src/pages/changelog/**"
-      - "site/src/components/ChangelogPage.astro"
-      - "site/src/data/releases.ts"
-      - "site/src/styles/changelog.css"
-
-permissions:
-  contents: read
-
-jobs:
-  validate:
-    runs-on: ubuntu-latest
-    steps:
-      - uses: actions/checkout@3d3c42e5aac5ba805825da76410c181273ba90b1 # v7
-      - uses: actions/setup-node@820762786026740c76f36085b0efc47a31fe5020 # v7
-        with:
-          node-version: "22"
-      - run: node site/scripts/releases/release-notes.mjs validate
-      - run: node --test site/scripts/releases/*.test.mjs

.github/workflows/site-ci.yml

@@ -1,33 +0,0 @@
-name: Website CI
-
-on:
-  push:
-    branches: [website]
-  pull_request:
-    branches: [website]
-
-permissions:
-  contents: read
-
-concurrency:
-  group: website-ci-${{ github.ref }}
-  cancel-in-progress: true
-
-jobs:
-  website:
-    runs-on: ubuntu-latest
-    defaults:
-      run:
-        working-directory: site
-    steps:
-      - uses: actions/checkout@3d3c42e5aac5ba805825da76410c181273ba90b1 # v7
-      - uses: actions/setup-node@820762786026740c76f36085b0efc47a31fe5020 # v7
-        with:
-          node-version: "22"
-          cache: npm
-          cache-dependency-path: site/package-lock.json
-      - run: npm ci
-      - run: npm test
-      - run: npm run build
-        env:
-          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}

.gitignore

@@ -1,15 +1,26 @@
 node_modules/
-.npm/
-.wrangler/
-site/dist/
-site/.astro/
-site/.generated/
-site/public/av/
+dist/
+coverage/
 .env
-.env.*
-*.local
+.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

CHANGELOG.md

@@ -0,0 +1,941 @@
+# Changelog
+
+All notable changes to Reasonix. The format follows [Keep a Changelog](https://keepachangelog.com/en/1.1.0/);
+this project uses [Semantic Versioning](https://semver.org/spec/v2.0.0.html).
+
+## [0.4.2] — 2026-04-21
+
+**Headline:** Three small but visible UX improvements from a real
+session: tool-call spinner now shows elapsed time + meaningful args
+(not raw JSON), reasoning preview shows the *tail* instead of the
+head (where the decision actually lives), and a `/think` slash
+command dumps the full R1 reasoning for the most recent turn.
+
+### Changed
+
+- **Tool-running row surfaces elapsed seconds + per-tool argument
+  summary.** Instead of `⠋ tool<filesystem_edit_file> running… 
+  {"path":"F:\\testtest\\index.html","edits":[…]}`, you now see:
+    ```
+    ⠋ tool<filesystem_edit_file> running… 3s
+      path: F:\testtest\index.html (2 edits)
+    ```
+  Per-tool summarizers for `read_file`, `write_file`, `edit_file`,
+  `list_directory`, `directory_tree`, `search_files`, `move_file`,
+  `get_file_info`. Matches on suffix (`_read_file`) so namespaced
+  servers (`filesystem_read_file`) and anonymous servers both work.
+  Unknown tools fall back to a truncated raw-JSON preview — better
+  than nothing.
+- **Reasoning preview shows the tail, not the head.** R1 opens every
+  turn with the same "let me look at the structure…" scaffolding, so
+  previously the `↳ thinking: …` line repeated across turns and hid
+  the real content in `(+N chars)`. Now the preview window shows the
+  last ~260 chars — which is where the model actually decides what
+  to do next. Users reported the head-only preview made R1 turns
+  look identical; this fixes the underlying information-hiding bug.
+
+### Added
+
+- **`/think` slash command.** Dumps the full raw reasoning text from
+  the most recent turn (read from `loop.scratch.reasoning`). Intended
+  for when the 260-char tail isn't enough and you want to see R1's
+  actual chain. Reports a helpful message if no reasoning is cached
+  (e.g. the current model is `deepseek-chat`, which doesn't produce
+  `reasoning_content`). Also listed as an alias `/reasoning`.
+
+### Tests (+3, suite 319→322)
+
+- `tests/slash.test.ts` (+3) — `/think` with empty scratch prints
+  "no reasoning cached", with populated scratch dumps the content,
+  help listing includes it.
+
+---
+
+## [0.4.1] — 2026-04-21
+
+**Headline:** `reasonix code` grows `/undo`, `/commit`, `.gitignore`
+awareness — and, **critically, stops auto-writing edits to disk.** A
+real-session bug ("I asked to analyze the project, it silently edited
+a file") exposed that v0.4.0's auto-apply was the wrong default.
+Edits now sit as **pending** until the user says `/apply`. This
+release also replaces the fixed iter-count budget with a
+token-context guard, which you were right to call out as the correct
+abstraction from the start.
+
+### Fixed (behavior change for code-mode users)
+
+- **Edits are now gated behind `/apply`.** Each assistant turn's
+  SEARCH/REPLACE blocks are parsed and shown as a preview line
+  (`▸ N pending edit block(s) — /apply to commit, /discard to drop`)
+  with per-block `path  (-N +M lines)`. Nothing touches disk without
+  explicit `/apply`. Pending state survives across user messages —
+  you can keep chatting and land the batch later. Aider's model, which
+  we should have picked from the start.
+- **Forced-summary events are tagged `forcedSummary: true` on
+  `LoopEvent`.** The code-mode edit applier ignores tagged events
+  entirely. Without this, a budget / abort / context-guard summary
+  could dump SEARCH/REPLACE blocks into output and silently turn
+  "analysis" into "edit". This was the root-cause bug for the
+  real-session report.
+- **Token-context guard replaces iter count as the primary stop.**
+  After every model response, if `promptTokens / contextWindow > 0.8`
+  the loop emits a yellow warning, skips executing the tool calls the
+  model just proposed, and diverts to the no-tools summary path
+  (`reason: "context-guard"`). Iter cap bumped 24 → 64 as a
+  last-resort backstop — the real constraint is the 131k-token
+  window, not a magic iteration count.
+- **Stray `EditSummary` / `summarizeEdit` reverted** from
+  `src/code/edit-blocks.ts`. v0.4.0's auto-apply let the model write
+  it during a failed forced-summary run. Nothing referenced it.
+  Removed.
+- **SEARCH/REPLACE blocks render as a real diff, not mangled prose.**
+  Previously the Markdown renderer fed SEARCH/REPLACE content through
+  the paragraph path — which joined lines with spaces and let the
+  inline bold/italic regex eat `*` characters inside JSDoc `/** … */`
+  comments. Output looked like `/** Edit landed on disk. /` with
+  trailing `*` consumed and newlines flattened. Now the parser
+  recognizes the `<filename>` / `<<<<<<< SEARCH` / `=======` /
+  `>>>>>>> REPLACE` envelope and emits a dedicated `edit-block` block
+  kind, rendered as `- ` / `+ ` diff rows with the filename on top
+  and (new file) tagged for empty-SEARCH creations. No inline
+  markdown inside — content is shown verbatim.
+- **"Reasoning before it speaks" UX no longer looks frozen.** Under
+  `deepseek-reasoner`, R1 streams `reasoning_content` first and
+  `content` only after — often 20-90 seconds of silence from the
+  user's perspective. The streaming preview used to show
+  `(waiting for first token…)` during that window, making the app
+  look hung. Now:
+    - A cyan braille-spinner pulse ticks at 500 ms so the heartbeat
+      is visible regardless of stream bursts.
+    - Label switches `streaming` → `reasoning` while body is empty.
+    - The "waiting" line is replaced with an explicit
+      `R1 is thinking before it speaks — body text starts when
+      reasoning completes (typically 20-90s)` so the user knows to
+      wait, not to bail.
+- **Tool calls now show a spinner while dispatching.** The loop
+  gains a new `tool_start` event yielded *before* `await
+  tools.dispatch(...)`, separate from the existing `tool` event
+  yielded with the result. The TUI renders a
+  `⠋ tool<filesystem_edit_file> running…` row (with a short args
+  preview) while the Promise is pending. Without this, a multi-KB
+  edit could sit for a full second with no visual feedback — the
+  streaming block was already cleared on `assistant_final` and the
+  input was disabled. Transcripts still only record the `tool`
+  result event (not `tool_start`), so replay/diff output is
+  unchanged.
+
+### Added (code mode)
+
+- **`/apply`** — commits pending edit blocks, snapshots for `/undo`,
+  per-block status.
+- **`/discard`** — forgets pending edits without writing.
+- **`/undo`** — roll back the *last applied* edit batch. Restores
+  files to their pre-`/apply` content, deletes any file the batch had
+  just created. One level of history for now, Aider-style.
+- **`/commit "msg"`** — `git add -A && git commit -m "msg"` inside
+  the code-mode rootDir. Surfaces git's stderr on failure (hooks,
+  nothing staged, detached HEAD, etc.).
+- **.gitignore awareness** — `reasonix code` reads the project's
+  `.gitignore` on launch and injects it into the system prompt as
+  "don't traverse or edit these paths unless asked". Hard-coded
+  baseline ignores (`node_modules`, `dist`, `.git`, `.venv`, etc.) are
+  also baked into the base prompt for projects without a `.gitignore`.
+  Stops the model wasting 5 tool calls listing `node_modules`.
+
+### Tightened
+
+- **`CODE_SYSTEM_PROMPT` gains a "when to edit vs. when to explore"
+  section.** Explicitly tells the model: only propose edits when the
+  user asks to change / fix / add / remove / refactor. For analyze /
+  explain / describe, stay read-only. Belt-and-braces with the
+  `/apply` gate below.
+
+### Tests (+35, suite 292→318)
+
+- `tests/edit-blocks.test.ts` (+5) — `snapshotBeforeEdits` +
+  `restoreSnapshots` round-trip: restore modified file, delete
+  newly-created file on undo, de-dup per path in batches, refuse
+  path-escape in snapshots.
+- `tests/code-prompt.test.ts` (+4 new file) — `.gitignore` injection:
+  no-file case, happy path, truncation over 2KB, base prompt still
+  names the built-in ignores.
+- `tests/slash.test.ts` (+13) — `/apply`, `/discard`, `/undo`,
+  `/commit`: inside vs. outside code mode, usage hint on empty
+  message, double-quote stripping, help listing all of them.
+- `tests/loop.test.ts` (+1) — context-guard warning + forced-summary
+  flag when prompt tokens exceed 80% of the window.
+- `tests/markdown.test.ts` (+5) — `parseBlocks` extracts SEARCH/
+  REPLACE into `edit-block` blocks, preserves multi-line JSDoc
+  verbatim, handles new-file (empty SEARCH), rejects stray markers
+  without close, multi-block responses interleaved with prose.
+- `tests/loop.test.ts` (+1) — `tool_start` precedes `tool` for each
+  dispatch, so UI consumers can pair them.
+
+### Notes
+
+- If you relied on 0.4.0's auto-apply behavior in scripts, that's
+  gone. For automation, call `applyEditBlocks` directly from the
+  library — the CLI TUI is for interactive use where the new gate
+  is correct.
+
+---
+
+## [0.4.0] — 2026-04-21
+
+**Headline:** `reasonix code` — a new subcommand that turns Reasonix
+into a coding assistant. Auto-bridges the filesystem MCP at your
+working directory, teaches the model to emit Aider-style
+SEARCH/REPLACE blocks, applies them to disk after each turn. The
+"cheap Claude Code" pitch becomes real.
+
+### Added
+
+- **`npx reasonix code [dir]`** — opinionated wrapper around chat:
+  - Filesystem MCP auto-bridged at `[dir]` (default CWD). No wizard,
+    no config merge. Out-of-box ready.
+  - Code-specialized system prompt that teaches SEARCH/REPLACE.
+  - Reasoner + harvest on by default (coding tasks repay R1 thinking).
+  - Per-directory session name (`code-<basename>`) so different
+    projects don't share history.
+- **SEARCH/REPLACE edit blocks** (`src/code/edit-blocks.ts`). The
+  model emits:
+    ```
+    path/to/file.ts
+    <<<<<<< SEARCH
+    (exact existing lines)
+    =======
+    (replacement)
+    >>>>>>> REPLACE
+    ```
+  Reasonix parses them from `assistant_final`, applies them under
+  the root dir, reports each result (`✓ applied`, `✓ created`,
+  `✗ not-found`, `✗ path-escape`, …) as an info line in the TUI.
+  Empty SEARCH creates a new file (Aider convention). SEARCH must
+  match byte-for-byte; we never fuzzy-match, because a silently wrong
+  edit is worse than a loud rejection.
+- **New public API** on the library: `parseEditBlocks`,
+  `applyEditBlock`, `applyEditBlocks`, `CODE_SYSTEM_PROMPT`, and the
+  types `EditBlock` / `ApplyResult` / `ApplyStatus`. Anyone building
+  their own code-assistant UX can compose from these.
+- **`ChatOptions.codeMode`** — opt-in flag to enable edit-block
+  processing inside the existing TUI event loop. Plain `reasonix chat`
+  leaves it off.
+
+### Why 0.4.0 (minor, not patch)
+
+This is a new user-facing primitive, not a bug fix or UX polish. The
+library exports grow; the `ChatOptions` interface gains a field.
+Nothing breaks for existing 0.3.x users — `reasonix chat` behaves
+exactly as before when `codeMode` is absent. But the SemVer convention
+is: additive new surface = minor bump.
+
+### Tests (+13, suite 279→292)
+
+- `tests/edit-blocks.test.ts` (+13 new file). `parseEditBlocks`
+  round-trips single + multi + multi-line + empty-SEARCH blocks, and
+  ignores stray 7-char runs in arbitrary prose. `applyEditBlock`
+  covers happy path, new-file creation, not-found rejection,
+  file-missing, path-escape defense, first-occurrence semantics.
+  Batch `applyEditBlocks` confirms failures don't cascade.
+
+### Notes
+
+- v1 scope is deliberately narrow: no `/commit`, no `/undo`, no
+  .gitignore filtering, no diff preview. The user's own `git diff` +
+  `git checkout` is the review + undo surface — and we run inside a
+  git repo by convention.
+- The ctx gauge + Esc + /compact safety net from 0.3.1/0.3.2 applies
+  equally to code mode. Exploring a large repo now has visible
+  progress and a hard off-switch.
+
+---
+
+## [0.3.2] — 2026-04-21
+
+**Headline:** Long exploration sessions are now interruptible and
+self-announcing. 0.3.1's forced-summary was a terminal safety net;
+this release turns it into an interactive budget with a visible warning
+at 70% and `Esc` to cash out early. Plus a README rewrite so new users
+actually know the new UX exists.
+
+### Added
+
+- **Esc while thinking → force a summary now.** `CacheFirstLoop` grows
+  an `abort()` method; the TUI's `useInput` wires Esc to it during
+  busy state (guarded by a once-per-turn flag). The loop checks the
+  abort flag at each iteration boundary, lets any in-flight tool call
+  complete, then diverts to the same no-tools summary path introduced
+  in 0.3.1 — prefixed `[aborted by user (Esc) — summarizing what I
+  found so far]`.
+- **Yellow warning at 70% of tool-call budget.** New `"warning"`
+  `EventRole` + `DisplayRole`, yielded once per step when tool-iter
+  count reaches `Math.floor(maxToolIters * 0.7)`. TUI renders it
+  yellow in the event log with the "Press Esc to summarize now" hint.
+  The command strip under the prompt also advertises the Esc hotkey.
+- **README hero rewrite.** `npx reasonix` (no flags) is now the first
+  code block, with the wizard story in prose; `--mcp`/`--preset`
+  moved to an "Advanced — CLI subcommands and flags" section.
+  What-you-get table gains *Setup wizard*, *Context safety net*
+  (tool-result cap + heal-on-load + `/compact` + ctx gauge + Esc),
+  and merges the MCP transports into one row. Non-goals and
+  configuration sections trimmed to match the new flow.
+
+### Tests (+2, suite 277→279)
+
+- `tests/loop.test.ts` (+2) — warning fires exactly once at the 70%
+  threshold and the content carries `N/budget tool calls used` +
+  `Esc`. `abort()` mid-step pulls the loop into the summary path,
+  surfacing an `aborted by user` prefix on the final event.
+
+---
+
+## [0.3.1] — 2026-04-21
+
+**Fixes a silent stop** that surfaced on the first real MCP exploration
+task after 0.3.0 shipped: the reasoner chained 8 filesystem tool calls
+against a project and the loop quietly exited at the `maxToolIters`
+ceiling without showing the user any answer — no error, no summary,
+just a hung-looking terminal.
+
+### Fixed
+
+- **Tool-call budget now produces a summary instead of stopping silent.**
+  When `maxToolIters` is exhausted with tool calls still pending, the
+  loop now makes one final call *with tools disabled*, forcing the
+  model to produce a text answer from everything it gathered. Yielded
+  as a normal `assistant_final` event prefixed with
+  `[tool-call budget (N) reached — forcing summary from what I found]`.
+- **Default `maxToolIters` raised from 8 → 24.** Eight was never enough
+  for real filesystem / MCP work (read_file → list → read_file chains
+  easily top that). Twenty-four is a workable ceiling that still caps
+  the damage from a confused model. Pass a number to
+  `new CacheFirstLoop({ maxToolIters: N })` to tune per call site.
+
+### Tests
+
+- `tests/loop.test.ts` (+1) — tight `maxToolIters: 2` scenario where
+  every step still wants to call tools, proves the summary call fires,
+  the annotated `assistant_final` contains the fallback text, and the
+  stream still ends with `done`.
+- Suite: **277 passing** (was 276).
+
+---
+
+## [0.3.0] — 2026-04-21
+
+**Stable.** MCP (stdio + SSE, multi-server) + first-run wizard +
+context-safety (result cap + auto-heal + `/compact`). The `0.3.0-alpha.*`
+series graduates — `npm install reasonix@latest` now pulls this.
+
+### Added — since 0.2.2
+
+- **MCP client**: stdio + HTTP+SSE transports, tools/list + tools/call,
+  repeatable `--mcp` flag with `name=` namespacing, curated catalog
+  (`reasonix mcp list`), bundled demo server.
+- **`reasonix setup` wizard**: API key → preset pick → MCP multi-select
+  → per-server args → `~/.reasonix/config.json`. `npx reasonix` with
+  no args launches this on first run and drops into chat afterward.
+- **Config-backed defaults**: `preset`, `mcp`, `session` persist across
+  launches; CLI flags override; `--no-config` escape hatch.
+- **Context gauge in StatsPanel** (NEW this release): `ctx 42k/131k
+  (32%)` next to cache/cost. Turns yellow at 50%, red at 80%, adds a
+  `· /compact` nudge at red.
+- **`/compact` slash** (NEW this release): shrinks every oversized
+  tool result in the log with a tighter 4k cap (configurable via
+  `/compact <chars>`), rewrites the session file on disk. Reports
+  `▸ compacted N tool result(s), saved M chars (~T tokens)`.
+- **`/mcp` and `/setup` slashes**: inspect attached servers, point at
+  the reconfigure command.
+
+### Fixed — since 0.2.2
+
+- `shellSplit` no longer mangles Windows paths outside quotes.
+- Windows `--mcp "npx ..."` works via automatic `.cmd`/`.bat` resolution.
+- `@modelcontextprotocol/server-fetch` and `server-sqlite` removed from
+  the catalog (Python-only reference impls, not on npm).
+- One broken MCP server no longer kills the chat — per-spec failures
+  print `▸ MCP setup SKIPPED` and the session continues.
+- Tool results capped at 32k chars by default (override via
+  `bridgeMcpTools(client, { maxResultChars: N })`). Sessions from
+  pre-alpha.6 clients auto-heal on load — `▸ session "X": healed N
+  oversized tool result(s)…`.
+- DeepSeek 400 `maximum context length` errors now decorate with
+  actionable advice + pretty-printed token figure.
+
+### Tests
+
+- Suite: **276 passing** (was 224 at 0.2.2).
+- New files this release: `tests/resolve.test.ts`, `tests/wizard.test.ts`,
+  `tests/loop-error.test.ts`, `tests/mcp-sse.test.ts`.
+
+### Breaking changes
+
+None against a 0.2.2 user. The config schema grew, but missing fields
+fall through to defaults. MCP-specific API additions (`McpSpec` is now
+a discriminated union, `FlattenOptions`, `DEFAULT_MAX_RESULT_CHARS`)
+are all new surface.
+
+### Deprecated
+
+None.
+
+---
+
+## [0.3.0-alpha.6] — 2026-04-21
+
+**Headline:** A single oversized tool result (e.g. `read_file` on a big
+file) used to silently poison a session — the 3 MB payload landed in
+history and every subsequent turn 400'd with *"maximum context length
+is 131072 tokens. However, you requested 929,452 tokens."* Fixed at
+both ends: prevent it, and diagnose it.
+
+### Fixed
+
+- **MCP tool results are now capped at 32,000 chars by default.**
+  Oversized results are sliced head + 1 KB tail and separated by a
+  `[…truncated N chars…]` marker so the model still sees both ends
+  (common case: error messages appended after a stack trace). Override
+  via `bridgeMcpTools(client, { maxResultChars: N })`. Rationale: ~8k
+  English tokens or ~16k CJK tokens — fits with headroom across 5–10
+  tool calls even at the context limit.
+- **Heal-on-load: poisoned sessions from older clients auto-repair.**
+  On session resume, every tool-role message whose content exceeds the
+  cap is truncated with the same head + tail policy. A stderr line
+  `▸ session "X": healed N oversized tool result(s)…` names the scope
+  of the repair. User and assistant messages are untouched — the
+  conversation flow is preserved, only the bloat from a past
+  `read_file` (etc.) shrinks. Without this, any session built with
+  pre-alpha.6 clients would tip over the 131k-token limit *on the very
+  first new prompt*, before the new 32k cap could matter.
+- **`DeepSeek 400: maximum context length` errors now show actionable
+  advice** instead of a raw JSON blob. The decorated message points at
+  the heal-on-load behaviour, `/forget` (nuke the session file) and
+  `/clear` (drop the display history), and pretty-prints the
+  requested-token figure.
+
+### Added
+
+- `DEFAULT_MAX_RESULT_CHARS` (= 32,000) export for callers that want
+  to raise or lower the cap programmatically.
+- `truncateForModel(s, maxChars)` helper export — same head + tail
+  policy, usable by non-MCP tool adapters that want the same protection.
+- `FlattenOptions` type export (just `{ maxChars? }` today).
+- `formatLoopError(err)` export — the error-decorator used by the loop,
+  exposed so library callers get the same advice when catching errors
+  outside the TUI.
+- `healLoadedMessages(messages, maxChars)` export — the session-heal
+  helper, exposed so library callers who build their own resume flows
+  can apply the same policy.
+
+### Tests (+9, suite 262→271)
+
+- `tests/mcp.test.ts` (+3) — truncation with head + tail preserved,
+  no-op below cap, end-to-end `bridgeMcpTools` dispatch capped by
+  default.
+- `tests/loop-error.test.ts` (+6 new file) — overflow annotation with
+  token figure, non-overflow passthrough, overflow without a figure,
+  heal-on-load truncating tool-role messages while leaving user and
+  assistant messages intact, no-op when all messages fit, multi-hit
+  healing across several oversized rows.
+
+### Migration note
+
+This is a silent behaviour change for any library user whose MCP tool
+was counting on >32k-char results making it to the model verbatim. If
+that's you, pass `maxResultChars: Infinity` (or a higher explicit
+value) to `bridgeMcpTools`.
+
+---
+
+## [0.3.0-alpha.5] — 2026-04-21
+
+**Headline:** `reasonix setup` replaces the CLI-flag maze. New users run
+one command, pick from an arrow-key checklist, and every later launch
+remembers what they chose. The `--mcp "name=npx -y @scope/pkg /path"`
+syntax still works for scripts and power users — it's just no longer
+the *only* way to turn MCP on.
+
+### Added
+
+- **`reasonix setup`** — interactive Ink wizard:
+  1. Paste API key (skipped if already set via env or previous run)
+  2. Pick a preset: `fast` / `smart` / `max` (bundles of model +
+     harvest + branch budget — no more "what's the right model id?")
+  3. Multi-select MCP servers from the curated catalog (space to
+     toggle, enter to confirm). Per-server parameters (filesystem
+     directory, sqlite path) are prompted inline.
+  4. Review + save to `~/.reasonix/config.json`.
+  Re-run any time to reconfigure — existing selections are pre-checked.
+- **`reasonix` with no subcommand** — launches the wizard on first run,
+  drops straight into chat afterwards using saved defaults. Designed
+  so a brand-new user can `npx reasonix` and be chatting in 30s
+  without reading `--help`.
+- **`--preset <fast|smart|max>`** on both `chat` and `run`. Picks the
+  same bundles the wizard offers. Individual flags (`--model`,
+  `--harvest`, `--branch`) still override when you want to be specific.
+- **`--no-config`** escape hatch on `chat` and `run` — ignore
+  `~/.reasonix/config.json` entirely (useful for CI, reproducing
+  a bug report against default settings, or isolating shared boxes).
+- **`/mcp` slash command** — shows the spec strings attached to the
+  current session and the tool registry (handy mid-chat when you want
+  to remember what a tool is called).
+- **`/setup` slash command** — prints instructions to exit and re-run
+  `reasonix setup`. Live reconfiguration mid-session is out of scope:
+  changing the tool set would reset the byte-stable prefix and
+  invalidate the cache-first guarantees that define Reasonix.
+
+### Changed
+
+- **`ReasonixConfig` schema** grows: `preset`, `mcp` (spec strings),
+  `session`, `setupCompleted`. Previous configs (apiKey-only) still
+  load; missing fields fall through to hardcoded defaults.
+- `reasonix chat` / `reasonix run`: when a flag is not passed, the
+  value comes from `~/.reasonix/config.json`. Explicit flags still
+  win. `--no-config` short-circuits this.
+- Slash handler signature: `handleSlash(cmd, args, loop, ctx?)` — the
+  new `ctx` carries per-session state like `mcpSpecs`. Old callers
+  that passed three args continue to compile.
+
+### Tests (+21)
+
+- `tests/resolve.test.ts` (+11) — precedence order: flag → --preset
+  → config.preset → fast defaults; `--no-config`, `--no-session`,
+  `--branch` cap and off cases.
+- `tests/config.test.ts` (+2) — full `ReasonixConfig` round-trip,
+  `session: null` interpreted as ephemeral.
+- `tests/slash.test.ts` (+4) — `/mcp` empty + populated, `/setup`
+  prints the reconfigure hint, help lists both.
+- `tests/wizard.test.ts` (+4) — `buildSpec` → `parseMcpSpec`
+  round-trip on filesystem / memory / spaces-in-path / unknown-entry
+  degrade-gracefully.
+- Suite: **262 passing** (was 241).
+
+### Fixed
+
+- **Catalog no longer lists Python-only servers.** `fetch` and `sqlite`
+  reference MCP servers are distributed as `pip install
+  mcp-server-fetch` / `mcp-server-sqlite`, not npm packages. They
+  were in the catalog by mistake, which meant picking them in the
+  wizard produced a spec that always 404'd on `npm install` when the
+  child was spawned. Removed. The remaining five entries
+  (`filesystem`, `memory`, `github`, `puppeteer`, `everything`) are
+  verified-on-npm as of this release.
+- **One broken MCP server no longer kills the whole chat/run.** Before:
+  any spawn or initialize failure on any server called
+  `process.exit(1)`, losing the session and the other working servers.
+  Now: each failure prints a `▸ MCP setup SKIPPED` line pointing at
+  `reasonix setup` and the session continues with whatever succeeded.
+
+### Notes
+
+- The wizard's Ink rendering is verified manually — unit-testing
+  arrow-key handling would mean pulling in `ink-testing-library`
+  (another dev dep) to exercise mechanically obvious `setState`
+  calls. The pure data layer (what gets written to config.json) is
+  tested end-to-end via `buildSpec → parseMcpSpec`.
+- Existing `npm publish --tag alpha` users: if you published
+  alpha.4 already, alpha.5 is a *pure additive* upgrade — config
+  files written by alpha.4 continue to work; `setupCompleted: false`
+  is assumed on migration so the wizard offers itself on first launch.
+
+---
+
+## [0.3.0-alpha.4] — 2026-04-21
+
+**Headline:** MCP over HTTP+SSE. Bridge *remote* / hosted MCP servers,
+not just local subprocesses. Pass a URL to `--mcp` and Reasonix opens
+an SSE stream and POSTs JSON-RPC to the endpoint the server advertises.
+
+### Added
+
+- **`SseTransport`** (`src/mcp/sse.ts`) — 2024-11-05 HTTP+SSE wire:
+  GET the SSE URL, wait for `event: endpoint`, POST every outgoing
+  JSON-RPC frame to that URL, read responses off the SSE channel.
+  Headers are passthrough, so `Authorization: Bearer ...` works for
+  hosted servers behind auth.
+- **`--mcp` now accepts URLs.** The parser routes anything starting
+  with `http://` or `https://` to `SseTransport`; everything else is
+  stdio as before. Both namespaced and anonymous forms work:
+    ```
+    reasonix chat --mcp "kb=https://mcp.example.com/sse"
+    reasonix run  --mcp "http://127.0.0.1:9000/sse" --task "..."
+    ```
+- `McpSpec` is now a discriminated union:
+  `{ transport: "stdio", command, args } | { transport: "sse", url }`.
+  Callers who inspected `spec.command` / `spec.args` need to branch on
+  `spec.transport` first — not a concern for `--mcp` CLI users.
+- `src/index.ts` exports `SseTransport`, `SseTransportOptions`,
+  `parseMcpSpec`, and the `McpSpec` union types.
+
+### Tests
+
+- `tests/mcp-sse.test.ts` (+4) — in-process `http.Server` fake that
+  implements the SSE wire. Covers: relative-path endpoint resolution,
+  absolute endpoint URLs, a full `McpClient.initialize` →
+  `listTools` round-trip over SSE, and handshake-failure propagation.
+- `parseMcpSpec` SSE cases (+4) — anonymous URL, namespaced URL,
+  case-insensitive scheme, and `ws://` staying routed to stdio (no
+  surprise detection beyond the two supported schemes).
+- Suite: **241 passing** (was 233).
+
+### Notes
+
+- Still targeting MCP protocol `2024-11-05`. The 2025-03-26 spec's
+  "Streamable HTTP" transport (single endpoint, no separate SSE GET)
+  is a separate body of work — deferred until there's a server in
+  the wild worth testing against.
+
+---
+
+## [0.3.0-alpha.3] — 2026-04-22
+
+**Headline:** multi-server MCP + discovery command. Bridge two or more
+MCP servers into one chat session, and stop guessing what servers exist
+— `reasonix mcp list` prints a curated catalog with copy-paste commands.
+
+### Added
+
+- **Repeatable `--mcp`** — pass the flag multiple times to bridge
+  multiple MCP servers into the same `ToolRegistry`. New spec syntax:
+    `"name=cmd args..."`   → tools land namespaced as `name_toolname`
+    `"cmd args..."`        → anonymous (tools keep native names)
+  Example:
+    ```
+    reasonix chat \
+      --mcp "fs=npx -y @modelcontextprotocol/server-filesystem /tmp/safe" \
+      --mcp "mem=npx -y @modelcontextprotocol/server-memory"
+    ```
+  Tools show up as `fs_read_file`, `mem_set`, etc.
+- **`reasonix mcp list`** — curated catalog of popular official MCP
+  servers (filesystem / fetch / github / memory / sqlite / puppeteer /
+  everything) with ready-to-paste `--mcp` commands. Hardcoded because
+  the list changes slowly; fetching over the network would make it
+  flaky offline. `--json` prints the machine-readable form.
+- `src/mcp/spec.ts::parseMcpSpec` — small helper exposed if library
+  callers want the same `name=cmd` parsing. Not exported from the
+  barrel yet; can be promoted when there's demand.
+- `src/mcp/catalog.ts::MCP_CATALOG` — the curated list.
+
+### Fixed
+
+- **`shellSplit` mangled Windows paths outside quotes.** Backslashes
+  were being treated as POSIX escape chars, so `C:\path\to\dir` turned
+  into `C:pathtodir`. Now backslashes only escape inside double
+  quotes; outside, they pass through literally. Matches user
+  expectation on Windows; POSIX users who want escape-a-space should
+  quote the arg instead.
+
+### Tests
+
+- `parseMcpSpec` (+8) — name=cmd form, anonymous form, Windows drive
+  letters (must not look like namespace), identifier edge cases,
+  empty / malformed input.
+- Multi-server integration test (+1) — spawn two demo subprocesses
+  concurrently with different prefixes, dispatch to each, verify no
+  cross-talk.
+- `shellSplit` Windows-path behavior (+1).
+- Suite: **233 passing** (was 224).
+
+---
+
+## [0.3.0-alpha.2] — 2026-04-22
+
+**Headline:** Windows `--mcp` actually works now, plus a second live
+data point through the *official* `@modelcontextprotocol/server-filesystem`.
+
+### Fixed
+
+- **Windows `npx`/`pnpm` MCP launch**. `StdioTransport` now defaults to
+  `shell: true` on win32 so `.cmd` shims (npx.cmd, pnpm.cmd) resolve.
+  Previously `--mcp "npx -y ..."` failed with EPIPE on Windows because
+  `spawn("npx")` couldn't find `npx.cmd` without a shell. POSIX behavior
+  unchanged.
+- **Silenced Node's `DEP0190` deprecation warning.** Under `shell: true`
+  with an args array, Node concatenates args without quoting — unsafe
+  if any arg contains shell metacharacters. We now build a quoted
+  command line ourselves (command bare so PATH lookup works, args
+  platform-quoted) and pass it as a single string. No more warning on
+  `--mcp` runs.
+
+### Added
+
+- **`StdioTransportOptions.shell?: boolean`** — explicit opt-in/out of
+  shell-mode spawning. Platform default still wins when omitted.
+- **Second reference transcript** —
+  `benchmarks/tau-bench/transcripts/mcp-filesystem.jsonl`. Live run
+  through `@modelcontextprotocol/server-filesystem` (14 external tools,
+  code we don't control): **5 turns, 4 tool calls, cache 96.7%,
+  cost $0.00124, 97% cheaper than Claude** at equivalent tokens. The
+  run includes a deliberate permission-denied recovery to show
+  cache-first holds under realistic agent messiness.
+- README table now shows both MCP data points side-by-side (bundled
+  demo vs official external server).
+
+### Tests
+
+- Integration tests explicitly set `shell: false` (they spawn `node.exe`
+  by absolute path — no shim needed). Suite still 224/224.
+
+---
+
+## [0.3.0-alpha.1] — 2026-04-22
+
+**Headline:** MCP client lands. Any
+[Model Context Protocol](https://spec.modelcontextprotocol.io/) server's
+tools now flow through the Cache-First Loop automatically — cache-hit and
+repair benefits extend to the entire MCP ecosystem.
+
+Verified end-to-end on live DeepSeek: `reasonix run --mcp "..."` spawns an
+MCP server, bridges its tools, calls them from the model. The follow-up
+turn after the tool call hit **96.6% cache**, 94% cheaper than Claude at
+same token counts. Reference transcript committed at
+`benchmarks/tau-bench/transcripts/mcp-demo.add.jsonl`.
+
+### Added
+
+- **`reasonix chat --mcp "<cmd>"`** and **`reasonix run --mcp "<cmd>"`** —
+  spawn an MCP server and bridge its tools into the Cache-First Loop.
+  Shell-quoted command; use `--mcp-prefix` to namespace tool names when
+  mixing servers.
+- **Hand-rolled MCP client** (`src/mcp/`) — zero runtime deps. JSON-RPC
+  2.0 + MCP initialize / tools/list / tools/call over stdio NDJSON.
+  Official `@modelcontextprotocol/sdk` deliberately not used; see
+  `src/mcp/README.md` for the reasoning.
+- **`bridgeMcpTools(client)`** — walk an MCP server's tools/list result
+  and register each into a Reasonix `ToolRegistry`. MCP tools become
+  indistinguishable from native tools to the loop, inheriting
+  Cache-First + repair (scavenge / flatten / storm) automatically.
+- **Bundled demo MCP server** — `examples/mcp-server-demo.ts`, ~160
+  lines, zero deps. Exposes `echo` / `add` / `get_time`. Lets any user
+  try the whole integration locally with no external install.
+- **`shellSplit()`** — small shell-style command parser used by the
+  `--mcp` flag. Respects single/double quotes, backslash escapes,
+  tab-space runs. Throws on unterminated quotes.
+- Library exports: `McpClient`, `StdioTransport`, `bridgeMcpTools`,
+  `flattenMcpResult`, `MCP_PROTOCOL_VERSION`, and related types.
+
+### Tests
+
+- **+21 tests**:
+  - `tests/mcp.test.ts` (10) — in-process fake transport covering
+    handshake, list, call, errors, bridge, name prefixing, result
+    flattening.
+  - `tests/mcp-shell-split.test.ts` (9) — quote handling, escapes,
+    unterminated-quote error, whitespace-only input.
+  - `tests/mcp-integration.test.ts` (2) — real subprocess against
+    the bundled demo server via `node --import tsx …` (cross-platform,
+    avoids Windows `.cmd` resolution).
+- Suite: **224 passing** (was 203 at v0.2.2).
+
+### Known limits (next alpha)
+
+- No SSE transport — stdio only.
+- No resources / prompts methods — tool-use only.
+- No progress notifications — tool calls are assumed complete on first
+  response.
+- No streaming tool results.
+
+### Also in this release
+
+- **harvest-bench 18-run data + findings** (no release on its own —
+  data was illuminating, conclusion was "V3 is strong enough that
+  harvest doesn't differentiate on common math", see
+  `benchmarks/harvest/report.md`). Informed the decision to ship MCP as
+  the v0.3 headline rather than a harvest-accuracy claim.
+- **`--timeout` flag** on harvest-bench runner, default 300s. Fixes
+  120s-default client timeout on long R1 + harvest runs.
+
+---
+
+## [0.2.2] — 2026-04-21
+
+**Headline:** 48-run bench data (3 repeats × 8 tasks × 2 modes). Reasonix
+now scores **100% pass rate (24/24)** against 96% baseline; cache-hit
+delta holds at **+47.7pp** with variance well under the last single-run
+numbers.
+
+### Fixed
+
+- **t05 predicate relaxed** (`benchmarks/tau-bench/tasks.ts`). The task
+  required "no refund on a processing order" and formerly also required
+  status to stay `processing`, penalizing an agent who offered
+  cancellation as a helpful alternative. The new predicate passes iff
+  no refund row is written AND the order ends in `{processing, cancelled}`
+  — either refusal or helpful substitution counts. Cancellation was
+  marking reasonix as fail on its single run in v0.1; with this fix
+  reasonix now passes every refusal task in every repeat.
+
+### Changed
+
+- **README headline numbers updated** to the 48-run set. Baseline shows
+  one failure out of 24 (a `t07_wrong_identity` run where baseline
+  skipped identity verification); Reasonix held the guardrail on every
+  run.
+- **`benchmarks/tau-bench/report.md`** regenerated from the 48-run
+  results. Cost estimate vs Claude Sonnet 4.6 stays at ~96% cheaper
+  per task.
+- **`benchmarks/tau-bench/results.json`** replaced with the 48-run data.
+
+### Tests
+
+- +3 tests pinning the three t05 outcomes (refuse / cancel / illegally
+  refund). Suite: **172 passing** (was 169).
+
+---
+
+## [0.2.1] — 2026-04-21
+
+**Headline:** v0.2 grows eyes. `reasonix replay` and `reasonix diff` now
+open interactive Ink TUIs by default. The stdout paths still work when
+piped, so CI / `less` / markdown-export workflows aren't disturbed.
+
+### Added
+
+- **Interactive `reasonix replay <transcript>`** — Ink TUI with
+  per-turn navigation (`j`/`k`/space/arrows, `g`/`G` for jump-to-edge,
+  `q` to quit). Sidebar re-renders cumulative cost / cache / prefix
+  stability as the cursor moves, so "how did the cache hit rate climb
+  over the conversation?" is answered visually instead of in
+  aggregate.
+- **Interactive `reasonix diff <a> <b>`** — split-pane Ink TUI. Both
+  sides scroll together; `n` / `N` jump the cursor to the next / prev
+  divergent turn (the whole point of a diff tool). Cursor defaults to
+  the first divergence so you skip the "identical setup turns".
+- **Shared `RecordView` component** (`src/cli/ui/RecordView.tsx`)
+  used by both TUIs — consistent visual grammar (user cyan, assistant
+  green with cache badge, tool yellow, error red). Replaces the
+  inline renderer in `ReplayApp`.
+- **Pure navigation helpers** in `src/diff.ts`:
+  `findNextDivergence(pairs, fromIdx)` and
+  `findPrevDivergence(pairs, fromIdx)`. Unit-testable without Ink.
+  Both guard against out-of-bounds `fromIdx`.
+- **Pure replay nav helpers** in `src/replay.ts`:
+  `groupRecordsByTurn(records)` and `computeCumulativeStats(pages, upToIdx)`.
+  Used by the TUI sidebar; also individually testable.
+- **New CLI flags** on both commands:
+  - `reasonix replay --print` — force stdout pretty-print (auto when
+    stdout isn't a TTY, or when `--head` / `--tail` is passed).
+  - `reasonix diff --print` — force stdout table.
+  - `reasonix diff --tui` — force Ink TUI even when piped (rare
+    escape hatch).
+
+### Changed
+
+- **`reasonix replay` default** is now the TUI. Old stdout behavior
+  reachable via `--print` or by piping. Non-TTY detection
+  automatically flips to stdout mode, so shell pipelines behave as
+  they did in 0.2.0.
+- **`reasonix diff` default** picks itself from context:
+  - `--md <path>` → write markdown + print summary (unchanged).
+  - `--print` or piped stdout → stdout summary table.
+  - TTY, no `--md`, no `--print` → TUI.
+
+### Tests
+
+- +10 new tests (`replay.test.ts` +6: `groupRecordsByTurn` +
+  `computeCumulativeStats`; `diff.test.ts` +4: divergence navigation).
+  Suite: **169 passing** (was 159).
+
+---
+
+## [0.2.0] — 2026-04-21
+
+**Headline:** v0.2 makes the v0.1 cache-hit claim *auditable*. Any reader
+can now verify the 94.3% / −42% numbers from committed JSONL transcripts
+— no API key required.
+
+### Added
+
+- **`reasonix replay <transcript>`** — pretty-print a past transcript and
+  rebuild its full session summary (turns, tool calls, cache hit, cost,
+  prefix stability) offline. No API calls.
+- **`reasonix diff <a> <b>`** — compare two transcripts: aggregate deltas,
+  first divergence (with Levenshtein similarity for text + exact match
+  for tool-name / args), prefix-stability story. Optional `--md <path>`
+  writes a blog-ready markdown report.
+- **`benchmarks/tau-bench/transcripts/`** — committed reference transcripts
+  (baseline + reasonix on `t01_address_happy`) so anyone can clone the
+  repo and run `reasonix replay` / `diff` immediately, without running
+  the bench.
+- **Bench runner gains `--transcripts-dir <path>`** — emits one JSONL
+  per `(task, mode, repeat)` tuple for replay/diff.
+- New library exports: `computeReplayStats`, `replayFromFile`,
+  `diffTranscripts`, `renderDiffSummary`, `renderDiffMarkdown`,
+  `parseTranscript`, `recordFromLoopEvent`, `writeRecord`.
+
+### Changed
+
+- **Transcript format bumped (backward-compatible)**. Records now carry
+  `usage`, `cost`, `model`, `prefixHash` (reasonix only), and `toolArgs`.
+  All fields optional on read — v0.1 transcripts still parse (cost/cache
+  shown as n/a). A `_meta` line at the top records source/model/task
+  metadata.
+- **Baseline bench runner now emits per-sub-call transcripts**. Previously
+  wrote one aggregated record per user turn, which made diff's
+  apples-to-apples "model calls" count off. Now both modes emit at the
+  same granularity.
+- **Diff rendering label change**: "turns (assistant)" → "model calls",
+  with "user turns" as a separate row in the summary table. Removes the
+  ambiguity that hit when comparing baseline vs reasonix.
+- **Top-level README**: `validated numbers` table now shows the 16-run
+  τ-bench-lite results (94.3% cache, −42% cost) and links to the
+  committed reference transcripts.
+- **Exposed `LoopEvent.toolArgs`** so transcript writers can persist
+  *what* the model sent to each tool, not just the result.
+
+### Fixed
+
+- Windows-only entrypoint bug in the bench runner
+  (`import.meta.url === file://${argv[1]}`) — replaced with
+  `pathToFileURL(argv[1]).href` so `main()` actually runs on Windows.
+
+### Tests
+
+- 17 new tests across `transcript.test.ts` (3), `replay.test.ts` (3),
+  and `diff.test.ts` (11). Total suite: 159 passing.
+
+---
+
+## [0.1.0] — 2026-04-21
+
+**Headline:** first reproducible evidence for Pillar 1 (Cache-First Loop).
+
+### Added
+
+- **`benchmarks/tau-bench/`** — τ-bench-lite harness. 8 retail-flavored
+  multi-turn tool-use tasks with a DeepSeek V3 user simulator,
+  deterministic DB-end-state success predicates (no LLM judge), and a
+  cache-hostile naive baseline runner. Schema mirrors Sierra's τ-bench
+  so upstream tasks can drop in.
+- **`benchmarks/tau-bench/runner.ts`** — orchestrator with
+  `--task` / `--mode` / `--repeats` / `--dry` / `--verbose` flags.
+- **`benchmarks/tau-bench/report.ts`** — renders results JSON into a
+  blog-ready markdown summary with explicit scope caveats.
+- **Live bench numbers** published in `benchmarks/tau-bench/report.md`:
+  - cache hit: baseline 43.9% → reasonix **94.3%** (+50.3pp)
+  - cost/task: baseline $0.00278 → reasonix **$0.00162** (−42%)
+  - vs Claude Sonnet 4.6 (token-count estimate): **~96% cheaper**
+  - pass rate: 100% (baseline) vs 88% (reasonix; 1 predicate too strict,
+    documented)
+
+### Tests
+
+- 8 new tests in `tests/benchmarks.test.ts` covering DB isolation,
+  check-predicate satisfiability, and tool guards — all runnable without
+  an API key. Total suite at this release: 143 passing.
+
+---
+
+Earlier `0.0.x` versions covered Pillar 1 + Pillar 3 internals, retry
+layer, first-run API key prompt, harvest MVP, self-consistency
+branching, and session persistence. They're not reflected as individual
+entries above because the `0.1.0` bench harness is what first produced
+*externally verifiable* evidence for their value.
+
+[0.3.0-alpha.3]: https://github.com/esengine/reasonix/releases/tag/v0.3.0-alpha.3
+[0.3.0-alpha.2]: https://github.com/esengine/reasonix/releases/tag/v0.3.0-alpha.2
+[0.3.0-alpha.1]: https://github.com/esengine/reasonix/releases/tag/v0.3.0-alpha.1
+[0.2.2]: https://github.com/esengine/reasonix/releases/tag/v0.2.2
+[0.2.1]: https://github.com/esengine/reasonix/releases/tag/v0.2.1
+[0.2.0]: https://github.com/esengine/reasonix/releases/tag/v0.2.0
+[0.1.0]: https://github.com/esengine/reasonix/releases/tag/v0.1.0

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

@@ -1,34 +1,320 @@
-# Reasonix Website
+# Reasonix
 
-This branch contains only the public Reasonix website and documentation portal.
+[![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)
 
-- Website source: `site/`
-- Website validation: `.github/workflows/site-ci.yml`
-- Production publication: `.github/workflows/pages.yml`
+**A DeepSeek-native AI coding assistant in your terminal.** Ink TUI. MCP
+first-class. No LangChain.
 
-Product clients live on `main-v2` and `studio`. Shared APIs, identity, telemetry,
-and registry services live on `platform`.
-
-## Local development
-
-```sh
-cd site
-npm ci
-npm test
-npm run dev
+```bash
+npx reasonix
 ```
 
-Production publication runs on pushes to `website` or manual dispatch from that branch.
+One command. First run walks you through a 30-second wizard (API key →
+preset → pick MCP servers from a checklist); every run after that drops
+straight into chat with your tools wired up. Inside the chat, type `/help`.
 
-Production builds synchronize both CLI 1.x and Studio 2.x changelogs from
-published GitHub tags. CLI notes come from the tag's reviewed
-`release-notes/releases.json`; Studio notes come from its versioned Markdown.
-Synchronization needs GitHub read access (`gh auth login` locally or
-`GITHUB_TOKEN` in CI), not a model API key. Missing source notes fail the build.
-The existing CLI publication-marker check still controls public visibility.
+Why bother with yet another agent framework? Because every abstraction
+here earns its weight against a DeepSeek-specific property — dirt-cheap
+tokens, R1 reasoning traces, automatic prefix caching, JSON mode.
+Generic wrappers treat DeepSeek as "OpenAI with a different base URL"
+and leave these advantages on the table. Reasonix leans into them:
+on the same τ-bench-lite workload,
+[**94.4% cache hit, ~40% cheaper tokens, 100% pass rate**](#validated-numbers)
+vs. a cache-hostile baseline.
 
-生产构建会从已发布的 GitHub 标签同步 CLI 1.x 和 Studio 2.x 更新日志。
-CLI 读取标签中已审核的 `release-notes/releases.json`，Studio 读取对应版本的
-Markdown。同步只需要 GitHub 读取权限（本地使用 `gh auth login`，CI 使用
-`GITHUB_TOKEN`），不需要模型 API 密钥。缺失源日志时构建失败；CLI 是否公开
-仍由原有的发布完成标记校验决定。
+---
+
+## What you get
+
+| Feature | How it works | Opt in |
+|---|---|---|
+| **Setup wizard** | First run of `npx reasonix`: pick preset, multi-select MCP servers from a curated catalog, saved to config so the next run just launches chat | always on (first run) |
+| **MCP (stdio + SSE)** | Multi-server bridge — every MCP tool inherits Cache-First + repair + context-safety automatically. `reasonix mcp list` shows the catalog | always on |
+| **Cache-First Loop** | Immutable prefix + append-only log = prefix byte-stable across turns → DeepSeek's automatic prefix cache hits at 70–95% | always on |
+| **Context safety net** | Tool results capped at 32k chars · oversized sessions auto-heal on load · `/compact` to shrink further · ctx gauge in the status bar · Esc to abort exploration and get a forced summary | always on |
+| **R1 Thought Harvesting** | Parses `reasoning_content` into typed `{ subgoals, hypotheses, uncertainties, rejectedPaths }` via a cheap V3 call | `/preset smart` |
+| **Self-Consistency Branching** | Runs N parallel samples at spread temperatures; picks the one with the fewest flagged uncertainties | `/preset max` / `/branch N` |
+| **Tool-Call Repair** | Auto-flattens deep/wide schemas, scavenges tool calls leaked into `<think>`, repairs truncated JSON, breaks call-storms | always on |
+| **Retry layer** | Exponential backoff + jitter on 408/429/500/502/503/504 and network errors. 4xx auth errors don't retry | always on |
+| **Ink TUI** | Live cache-hit / cost / context panel. Streams R1 thinking to a compact preview. Renders Markdown (bold / lists / code / stripped LaTeX) | always on |
+
+---
+
+## Why not just use LangChain?
+
+Even on the default `fast` preset (no harvest, no branching), Reasonix bakes
+in five DeepSeek-specific defences that generic agent frameworks leave to you:
+
+| | Reasonix default | generic frameworks |
+|---|---|---|
+| Prefix-stable loop (→ 85–95% cache hit) | ✅ | ❌ prompts rebuilt each turn |
+| Auto-flatten deep tool schemas | ✅ | ❌ DeepSeek drops args |
+| Retry with jittered backoff (429/503) | ✅ | ❌ custom callbacks |
+| Scavenge tool calls leaked into `<think>` | ✅ | ❌ |
+| Call-storm breaker on identical-arg repeats | ✅ | ❌ |
+| Live cache-hit / cost / vs-Claude panel | ✅ | ❌ |
+| First-run config prompt + Markdown TUI | ✅ | ❌ |
+
+Harvest and self-consistency branching are bonuses on top. The everyday
+win is that **a plain chat with Reasonix already pays for ~40% less tokens
+than the same chat through a naive LangChain setup**, because the prefix
+actually stays byte-stable.
+
+## Validated numbers
+
+**τ-bench-lite** — 8 multi-turn tool-use tasks × 3 repeats = 48 runs per
+side. Same tools / same prompt / same client on both sides, sole variable
+is prefix stability. Measured on live DeepSeek `deepseek-chat`:
+
+| metric | baseline (cache-hostile) | Reasonix | delta |
+|---|---:|---:|---:|
+| runs | 24 | 24 | — |
+| **cache hit** | 46.6% | **94.4%** | **+47.7pp** |
+| cost / task | $0.002599 | $0.001579 | **−39% (×0.61)** |
+| vs Claude Sonnet 4.6 (token-count estimate) | — | — | **~96% cheaper** |
+| pass rate | 96% (23/24) | **100% (24/24)** | Reasonix held the guardrail on every run |
+
+**Verify it yourself — no API key, zero cost:**
+
+```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 JSONL transcripts committed in `benchmarks/tau-bench/transcripts/`
+carry per-turn `usage`, `cost`, and `prefixHash`. Reasonix's prefix hash
+stays byte-stable across every model call; baseline's prefix 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`][r]. Reproduce
+with your own API key: `npx tsx benchmarks/tau-bench/runner.ts --repeats 3`.
+
+[r]: ./benchmarks/tau-bench/report.md
+
+### MCP — works out of the box
+
+Any [MCP](https://spec.modelcontextprotocol.io/) server's tools inherit
+Cache-First + repair + context-safety automatically. The wizard (`npx
+reasonix`) lets you multi-select from a curated catalog — no flags, no
+JSON-by-hand. Three live reference runs:
+
+| server | turns | tool calls | cache hit | cost | vs Claude |
+|---|---:|---:|---:|---:|---:|
+| bundled demo (`add` / `echo` / `get_time`) | 2 | 1 | **96.6%** (turn 2) | $0.000254 | −94.0% |
+| official `@modelcontextprotocol/server-filesystem` | 5 | 4 | **96.7%** overall | $0.001235 | −97.0% |
+| **both concurrently** (`demo_add` + `fs_write_file`) | 5 | 4 | **81.1%** | $0.001852 | −95.9% |
+
+The third row is the ecosystem proof: two MCP servers running as
+separate subprocesses, tools from both exercised in one conversation.
+**One single prefix hash across all 5 turns** — byte-stability survives
+concurrent MCP subprocesses.
+
+Reproduce without an API key (replay the committed transcripts):
+
+```bash
+npx reasonix replay benchmarks/tau-bench/transcripts/mcp-demo.add.jsonl
+npx reasonix replay benchmarks/tau-bench/transcripts/mcp-filesystem.jsonl
+```
+
+Supported transports: **stdio** (local `npx` or binary) and **HTTP+SSE**
+(remote / hosted servers, MCP 2024-11-05 spec). Pass an `http(s)://`
+URL to `--mcp` and Reasonix opens the SSE stream and POSTs JSON-RPC
+to the endpoint the server advertises.
+
+[mcp]: ./benchmarks/tau-bench/transcripts/mcp-demo.add.jsonl
+
+---
+
+## Usage
+
+### One command
+
+```bash
+npx reasonix
+```
+
+First run: a wizard asks for your API key, lets you pick a preset
+(fast / smart / max), then offers a multi-select checklist of MCP
+servers — filesystem, memory, github, puppeteer, everything. Everything
+is saved to `~/.reasonix/config.json`. Subsequent runs drop straight
+into chat.
+
+### Inside the chat
+
+A status bar at the top shows cache hit %, cost, Claude-equivalent, and
+the **context gauge** (`ctx 42k/131k (32%)` — yellow at 50%, red + a
+`/compact` nudge at 80%). A command strip under the input lists the
+slash commands:
+
+```
+/help                   full list + hints
+/preset <fast|smart|max> one-tap bundles (model + harvest + branch)
+/mcp                    list attached MCP servers and tools
+/compact [cap]          shrink oversized tool results in history
+/sessions · /forget     list / delete saved sessions
+/setup                  reconfigure (exits and tells you to run `reasonix setup`)
+/clear · /exit
+```
+
+**Esc while thinking** — abort the current exploration and force the
+model to summarize what it already found. No more "model ran 24 tool
+calls and gave up" — you get an answer every time.
+
+Sessions live as JSONL under `~/.reasonix/sessions/<name>.jsonl` —
+every message appended atomically, so killing the CLI never loses
+context. Oversized tool results auto-heal on load, so poisoning a
+session with one giant `read_file` doesn't brick your history.
+
+### Code mode — `npx reasonix code`
+
+A thin opinionated layer on top of chat: filesystem MCP bridged at
+`cwd`, coding system prompt, reasoner preset, per-directory session.
+The model proposes edits as **SEARCH/REPLACE blocks**:
+
+```
+src/foo.ts
+<<<<<<< SEARCH
+const x = 1;
+=======
+const x = 2;
+>>>>>>> REPLACE
+```
+
+Reasonix parses them out of each turn, applies them to disk, reports
+`✓ applied src/foo.ts` in the TUI. SEARCH must match byte-for-byte;
+we never fuzzy-match (silent wrong edits are worse than loud
+rejections). Run `git diff` to review, `git checkout .` to undo.
+
+```bash
+cd my-project
+npx reasonix code           # default: cwd, reasoner, per-dir session
+npx reasonix code src/      # scope the filesystem sandbox tighter
+npx reasonix code --no-session   # ephemeral
+```
+
+First-run sandbox: because code mode uses the filesystem MCP from
+`@modelcontextprotocol/server-filesystem`, the model can only read
+and write inside the directory you pointed at. It literally can't
+touch files above that root.
+
+### Advanced — CLI subcommands and flags
+
+```bash
+npx reasonix setup                       # reconfigure any time
+npx reasonix chat --session work         # a different named session
+npx reasonix chat --no-session           # ephemeral — nothing persisted
+npx reasonix run "ask anything"          # one-shot, streams to stdout
+npx reasonix stats session.jsonl         # summarize a transcript
+npx reasonix replay chat.jsonl           # scrub a transcript + rebuild cost/cache
+npx reasonix diff a.jsonl b.jsonl --md   # compare two transcripts
+npx reasonix mcp list                    # curated MCP server catalog
+```
+
+Power users can still bypass config and drive Reasonix with flags:
+
+```bash
+npx reasonix chat \
+  --preset max \
+  --mcp "filesystem=npx -y @modelcontextprotocol/server-filesystem /tmp/safe" \
+  --mcp "kb=https://mcp.example.com/sse" \
+  --transcript session.jsonl \
+  --no-config   # ignore ~/.reasonix/config.json (for CI / reproducing issues)
+```
+
+### Library
+
+```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, // self-consistency budget
+});
+
+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());
+```
+
+### Configuration
+
+The wizard handles everything on first run. If you'd rather use env vars
+(CI, shared boxes, etc.):
+
+```bash
+export DEEPSEEK_API_KEY=sk-...        # wins over ~/.reasonix/config.json
+export DEEPSEEK_BASE_URL=https://...  # optional alternate endpoint
+```
+
+Get a key (free credit on signup): <https://platform.deepseek.com/api_keys>
+
+Re-run `npx reasonix setup` any time to add/remove MCP servers or switch
+preset — your existing selections are pre-checked.
+
+---
+
+## Non-goals
+
+- Multi-agent orchestration (use LangGraph).
+- RAG / vector stores (use LlamaIndex or do it yourself).
+- Multi-provider abstraction (use LiteLLM).
+- Web UI / SaaS.
+
+Reasonix does DeepSeek, deeply.
+
+---
+
+## Development
+
+```bash
+git clone https://github.com/esengine/reasonix.git
+cd reasonix
+npm install
+npm run dev chat        # run CLI from source via tsx
+npm run build           # tsup to dist/
+npm test                # vitest (279 tests)
+npm run lint            # biome
+npm run typecheck       # tsc --noEmit
+```
+
+See [docs/ARCHITECTURE.md](docs/ARCHITECTURE.md) for internals.
+
+---
+
+## License
+
+MIT

REASONIX.md

@@ -1,12 +0,0 @@
-# Reasonix Website instructions
-
-- This branch owns the public website and public documentation portal only.
-  Do not add product client or backend service code here.
-- Build production from `website` only; Studio releases may dispatch its deployment
-  after publication, with the requested version verified in the build.
-- Preserve accessibility, responsive layout, and static-build compatibility.
-- Authentication and marketplace pages call versioned `platform` APIs; they do
-  not duplicate account or registry business logic.
-- Add tests for user-visible contracts and run a production build before release.
-- Never commit credentials, tokens, private analytics, 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 +1,147 @@
+# 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 three 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. This is the user-visible proof of Pillar 1's value.
+
+### Pillar 2 — R1 Thought Harvesting *(v0.0.3, opt-in)*
+
+**Problem.** R1 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 (V3, cheap) → TypedPlanState
+                                     ├─ subgoals: string[]
+                                     ├─ hypotheses: string[]
+                                     ├─ uncertainties: string[]
+                                     └─ rejectedPaths: string[]
+```
+
+The harvester is a cheap V3 call with a strict JSON schema. Output is
+validated at runtime. The typed state is queryable by the orchestrator — e.g.
+"if `uncertainties.length > 2`, trigger branch sampling."
+
+### Branch-and-Select *(v0.0.5, opt-in, builds on Pillar 2)*
+
+**Why now.** DeepSeek is cheap enough that running N=3 R1 samples is still
+cheaper than a single Claude call. What was research luxury (self-consistency
+sampling) becomes a practical default.
+
+**How.** When `--branch N` (or `{ branch: N }` in code) is passed:
+
+1. The turn is forced non-streaming (N samples must complete before we can
+   compare).
+2. `runBranches` fires N `client.chat` calls in parallel, spreading
+   temperatures across `[0, 1]` to diversify reasoning paths.
+3. Each sample's `reasoning_content` is piped through Pillar 2's harvest.
+4. The default selector picks the sample with the fewest `uncertainties`;
+   ties are broken by shorter answer length (Occam).
+5. The loop emits a `branch_summary` alongside the winning `assistant_final`.
+
+**Cost.** 3× R1 on a hard math problem ≈ \$0.02 — still dominates Claude on
+cost/quality for agentic work.
+
+### Pillar 3 — Tool-Call Repair *(v0.0.1 ships complete)*
+
+**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`.
+   Opt out with `new ToolRegistry({ autoFlatten: false })`.
+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.
+
+## Module layout
+
+```
+src/
+├── client.ts          # httpx-equivalent DeepSeek client (fetch + SSE)
+├── loop.ts            # Pillar 1: Cache-First Loop (async iterator)
+├── harvest.ts         # Pillar 2 stub (v0.0.1 surface only)
+├── repair/
+│   ├── index.ts       # Pillar 3 pipeline
+│   ├── scavenge.ts
+│   ├── flatten.ts
+│   ├── truncation.ts
+│   └── storm.ts
+├── tools.ts           # Tool registry + dispatch
+├── memory.ts          # Prefix / Log / Scratch primitives
+├── telemetry.ts       # Cost & cache-hit accounting
+├── types.ts           # Shared type definitions
+├── index.ts           # Library barrel export
+└── cli/
+    ├── index.ts       # commander entry
+    ├── commands/      # chat, run, stats, version
+    └── ui/            # Ink React components (App, StatsPanel, EventLog, PromptInput)
+```
+
+## Roadmap
+
+- **v0.0.1** — Pillar 1 end-to-end, Pillar 3 complete, Ink TUI, τ-bench scaffold.
+- **v0.0.2** — First-run key prompt, saved to `~/.reasonix/config.json`.
+- **v0.0.3** — Pillar 2 MVP (opt-in harvest), retry layer, TextInput fix.
+- **v0.0.4** — Schema flatten auto-applied in ToolRegistry (closes Pillar 3).
+- **v0.0.5** — Self-consistency branching (`--branch N`) driven by Pillar 2
+  plan-state uncertainty count.
+- **v0.0.6** — Named session persistence (`--session <name>`), JSONL log
+  stored under `~/.reasonix/sessions/`, restored into the append-only log
+  on resume.
+- **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, session persistence.
+
+## Explicit non-goals
+
+- Multi-agent orchestration.
+- RAG / vector retrieval.
+- Support for non-DeepSeek backends.
+- Web UI / SaaS.

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 +1,177 @@
+/**
+ * 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: {} },
+  },
+];
+
+function send(msg: JsonRpcSuccess | JsonRpcError): void {
+  // Stdio MCP framing: one JSON per line.
+  process.stdout.write(`${JSON.stringify(msg)}\n`);
+}
+
+function handleRequest(req: JsonRpcRequest): 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> };
+      const name = params.name ?? "";
+      const args = params.arguments ?? {};
+      const out = callTool(name, args);
+      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}` },
+      };
+  }
+}
+
+function callTool(
+  name: string,
+  args: Record<string, unknown>,
+): { 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() };
+  }
+  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;
+    }
+    const resp = handleRequest(req);
+    if (resp) send(resp);
+  });
+  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 +1,75 @@
+{
+  "name": "reasonix",
+  "version": "0.4.2",
+  "description": "DeepSeek-native agent framework: cache-first loop, R1 thought harvesting, 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",
+    "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"
+  }
+}

site/astro.config.mjs

@@ -1,16 +0,0 @@
-import { defineConfig } from 'astro/config';
-import sitemap from '@astrojs/sitemap';
-
-// Served from the custom domain reasonix.io at the site root.
-export default defineConfig({
-  site: 'https://reasonix.io',
-  // Documentation code samples intentionally use source newlines as content.
-  // Astro 7's JSX-style compression removes those newlines unless disabled.
-  compressHTML: false,
-  build: { assets: 'static' },
-  integrations: [sitemap({
-    filter: (page) => !/\/changelog\/(?:stable|preview|studio)\/?$/.test(page) &&
-      !/\/changelog\/v\d+\.\d+\.\d+-/.test(page) &&
-      !/\/(?:login|register|forgot|reset|account|device|u)\/?$/.test(page),
-  })],
-});

site/package.json

@@ -1,25 +0,0 @@
-{
-  "name": "reasonix-site",
-  "type": "module",
-  "private": true,
-  "scripts": {
-    "dev": "astro dev",
-    "prebuild": "node scripts/releases/sync-releases.mjs && node scripts/fetch-community.mjs && node scripts/fetch-publications.mjs",
-    "build": "astro build",
-    "preview": "astro preview",
-    "test": "node --test src/scripts/*.test.mjs scripts/releases/*.test.mjs",
-    "release:validate": "node scripts/releases/release-notes.mjs validate"
-  },
-  "dependencies": {
-    "@astrojs/sitemap": "^3.7.4",
-    "@fontsource-variable/inter": "^5.3.0",
-    "@fontsource-variable/jetbrains-mono": "^5.3.0",
-    "astro": "^7.3.1"
-  },
-  "devDependencies": {
-    "sharp": "^0.35.3"
-  },
-  "overrides": {
-    "esbuild": "0.28.1"
-  }
-}

site/public/community/qq-group.svg

@@ -1 +0,0 @@
-<svg xmlns="http://www.w3.org/2000/svg" width="296" height="296" viewBox="0 0 296 296" class="segno"><title>QQ group 1093562660 join QR code</title><g transform="scale(8)"><path fill="#fff" d="M0 0h37v37h-37z"/><path class="qrline" stroke="#000" d="M4 4.5h7m2 0h1m1 0h1m2 0h1m2 0h1m1 0h2m1 0h7m-29 1h1m5 0h1m5 0h1m3 0h2m2 0h1m1 0h1m5 0h1m-29 1h1m1 0h3m1 0h1m2 0h4m1 0h2m1 0h1m2 0h1m1 0h1m1 0h3m1 0h1m-29 1h1m1 0h3m1 0h1m6 0h1m2 0h1m1 0h3m1 0h1m1 0h3m1 0h1m-29 1h1m1 0h3m1 0h1m11 0h1m1 0h1m1 0h1m1 0h3m1 0h1m-29 1h1m5 0h1m1 0h5m2 0h3m1 0h1m2 0h1m5 0h1m-29 1h7m1 0h1m1 0h1m1 0h1m1 0h1m1 0h1m1 0h1m1 0h1m1 0h7m-20 1h1m1 0h3m1 0h3m-18 1h1m2 0h1m1 0h2m1 0h1m1 0h2m2 0h1m1 0h1m1 0h2m1 0h1m1 0h1m-21 1h1m1 0h1m1 0h2m1 0h1m2 0h1m1 0h4m1 0h1m1 0h1m2 0h1m2 0h1m-29 1h4m1 0h4m1 0h2m1 0h3m2 0h2m3 0h5m-28 1h4m4 0h1m3 0h2m2 0h1m9 0h2m-28 1h2m2 0h1m1 0h1m1 0h5m1 0h2m1 0h1m1 0h2m1 0h2m1 0h1m1 0h2m-28 1h1m1 0h2m3 0h1m2 0h1m1 0h4m1 0h2m1 0h1m-22 1h2m1 0h2m1 0h1m1 0h1m1 0h1m1 0h3m3 0h1m1 0h2m1 0h1m1 0h4m-28 1h2m1 0h2m2 0h1m1 0h1m4 0h1m1 0h1m1 0h1m1 0h2m1 0h2m1 0h1m-28 1h4m2 0h2m1 0h3m1 0h1m3 0h3m1 0h1m5 0h1m-27 1h2m2 0h1m1 0h1m2 0h1m1 0h5m1 0h1m2 0h2m2 0h1m2 0h1m-29 1h1m1 0h2m1 0h6m3 0h5m3 0h3m2 0h2m-27 1h2m4 0h1m1 0h2m2 0h1m2 0h1m1 0h2m3 0h1m2 0h2m-29 1h1m2 0h1m2 0h1m2 0h1m5 0h3m1 0h6m1 0h1m-19 1h2m1 0h2m1 0h2m1 0h4m3 0h1m1 0h3m-29 1h7m2 0h1m2 0h1m4 0h2m1 0h1m1 0h1m1 0h1m2 0h1m-28 1h1m5 0h1m1 0h2m1 0h1m2 0h2m3 0h2m3 0h5m-29 1h1m1 0h3m1 0h1m2 0h2m1 0h1m3 0h3m1 0h5m2 0h1m-28 1h1m1 0h3m1 0h1m1 0h2m2 0h2m1 0h2m1 0h2m2 0h5m1 0h1m-29 1h1m1 0h3m1 0h1m2 0h2m1 0h1m1 0h1m2 0h4m3 0h3m1 0h1m-29 1h1m5 0h1m2 0h1m2 0h1m1 0h1m2 0h1m1 0h2m1 0h1m4 0h1m-28 1h7m1 0h1m3 0h2m2 0h2m2 0h3m1 0h1m2 0h1"/></g></svg>

site/public/favicon.svg

@@ -1,16 +0,0 @@
-<?xml version="1.0" encoding="UTF-8"?>
-<svg id="_图层_1" data-name=" 图层 1" xmlns="http://www.w3.org/2000/svg" viewBox="0 0 64 64">
-  <defs>
-    <style>
-      .cls-1 {
-        fill: #fff;
-      }
-
-      .cls-2 {
-        fill: #0153e5;
-      }
-    </style>
-  </defs>
-  <rect class="cls-2" y="0" width="64" height="64" rx="20.22" ry="20.22"/>
-  <path class="cls-1" d="M40.53,37.67h0c2.26-.67,4.24-1.86,5.83-3.59h0c1.73-1.94,2.82-4.29,3.2-6.87.86-5.64-1.94-10.79-7.21-12.97-1.85-.74-3.76-1.06-5.78-1.04h-19.6v37.56h9.64v-12.68c1.05.34,2.16.52,3.29.52l3.15,4.35,5.73,7.83,11.44-.02-9.7-13.1h0ZM40.14,35.94c-1.31.43-2.72.37-4.06-.02-2.3-1.74-3.55-3.6-5.52-5.37-2.52-2.27-5.84-3.84-9.25-3.69.27-.74.66-1.45,1.17-2.11,1.76-2.2,4.16-2.9,6.92-2.51,1.02.14,2.11-1.05,4.18-.82.14.02.28.12.29.2.05.28-.75.44-.75,1.21,0,.32.15.7.45.92,1.06.74,1.97,1.57,2.93,2.43.47.42,2.04,1.59,2.44.64.24-.56.39-1.14.54-1.74.08-.29-.09-.47-.32-.61-1.63-.96-2.24-2.97-1.6-4.75.06-.17.22-.25.36-.26.55-.02.25.99,1.61,1.4,1.28.4,1.32,1.46,1.94,1.04,1.45-.99,1.97-.18,3.32-1.45.14-.13.38-.14.52-.04.09.06.17.22.16.41-.04,1.07-.46,2.1-1.19,2.88-1.39,1.49-2.55.77-2.62,1.82-.22,3.06-1.22,6.11-3.39,8.33-.07.07-.11.17-.1.24.01.07.1.14.19.17l1.83.62c.26.09.45.32.41.57-.03.22-.2.41-.45.49h0Z"/>
-</svg>

site/public/logo.svg

@@ -1,21 +0,0 @@
-<?xml version="1.0" encoding="UTF-8"?>
-<svg id="_图层_1" data-name=" 图层 1" xmlns="http://www.w3.org/2000/svg" width="1151.55" height="217.07" viewBox="0 0 1151.55 217.07">
-  <defs>
-    <style>
-      .cls-1 {
-        fill: #0153e5;
-      }
-    </style>
-  </defs>
-  <circle class="cls-1" cx="972.16" cy="33.55" r="23.88"/>
-  <g>
-    <path class="cls-1" d="M488.72,211.37c-12.37,1.71-24.96.46-38.13.63l-1.23-16.27c-12.87,14.9-29.84,21.97-49.07,19.87-24.58-2.69-44.41-19.38-53.2-42.6-7.32-19.32-6.99-40.86.81-60.12,9.5-23.46,30.72-40.21,55.73-42.02,18.41-1.33,34.33,4.84,45.96,18.54l1.13-15.37,37.63-.22.36,137.56h.01ZM451.41,143.22c0-19.82-16.06-35.88-35.88-35.88s-35.88,16.06-35.88,35.88,16.06,35.88,35.88,35.88,35.88-16.06,35.88-35.88Z"/>
-    <path class="cls-1" d="M294.69,165.71c11.08,4.99,20.6,11.87,31.28,18.31-14.54,22.26-39.3,32.78-65.14,31.91-42.29-1.42-73.12-35.5-70.7-77.31,2.1-36.29,28.66-64.56,65.17-67.92,26.31-2.42,52.01,8.19,66.02,30.99,9.52,15.5,11.55,33.39,9.76,50.92l-101,.13c1.4,14.77,13.51,25.01,25.92,27.74,14.72,3.24,29.02-.82,38.69-14.77h0ZM294.02,127.16c-4.12-16.52-17.68-24.4-32.5-24.13-13.74.25-27.5,9.07-30.5,24.11l63,.02h0Z"/>
-    <path class="cls-1" d="M780.3,143.31c0,40.74-33.02,73.76-73.76,73.76s-73.76-33.02-73.76-73.76,33.02-73.76,73.76-73.76,73.76,33.02,73.76,73.76ZM742.63,143.26c0-19.97-16.19-36.16-36.16-36.16s-36.16,16.19-36.16,36.16,16.19,36.16,36.16,36.16,36.16-16.19,36.16-36.16Z"/>
-    <path class="cls-1" d="M865.82,106.67c-16.4-.48-30.2,10.42-30.32,26.41l-.59,78.88-38.91-.18.06-137.83,38.15.35c.41,5.66-1.03,9.97,1.45,15.75,19.54-26.51,63.34-25.07,82.95-1.16,9.2,11.23,13.46,25.62,13.45,40.38l-.06,82.62-38.94.14-.69-79.28c-.13-14.92-10.82-25.64-26.54-26.1v.02h-.01Z"/>
-    <path class="cls-1" d="M1151.55,211.51l-44.84.51-29.9-41.82-30.52,41.81-43.29-.52,50.71-70.03-48.12-67.06c16.29-1.81,30.31-.14,45.42-.02l26.06,38.81,27.14-39.29c14.85-.38,28.79-.61,44.5.69l-47.96,66.65,50.79,70.28h0Z"/>
-    <path class="cls-1" d="M595.11,210.55c-30.01,11.52-78.69,6.96-94.37-27.63l29.88-14.4c4.49,1.96,5.5,6.8,9.44,9.49,16.43,11.17,43.99,9.75,44.36-4.61.12-4.72-3.46-8.89-8.58-10.29l-36.51-9.95c-11.77-3.21-22.59-9.81-28.13-21.2-10.25-21.06.12-45.53,21.63-54.96,29.01-12.72,77.53-8.27,89.7,25.13l-29.06,12.62c-10.47-12.8-27.66-16.84-42.64-10.42-3.51,1.5-5.54,6.03-5.28,8.81.35,3.7,3.39,7.71,7.59,8.86l40.46,11.09c9.77,2.68,19.02,7.82,24.29,16.77,13.52,22.96,2.31,51.05-22.78,60.69h0Z"/>
-    <rect class="cls-1" x="902.92" y="123.55" width="138.32" height="38.82" transform="translate(828.4464 1114.9374) rotate(-89.96)"/>
-    <path class="cls-1" d="M134.57,139.75l.02-.02c12.9-3.8,24.24-10.63,33.31-20.48v-.03c9.89-11.07,16.1-24.46,18.25-39.19,4.93-32.21-11.06-61.62-41.17-74.07C134.39,1.71,123.51-.11,111.97,0L0,.03v214.57l55.04-.04v-72.42c6,1.93,12.33,2.97,18.82,2.94l18.02,24.87,32.75,44.72,65.37-.09-55.43-74.84h0ZM132.36,129.86c-7.5,2.48-15.55,2.11-23.21-.12-13.17-9.95-20.3-20.57-31.51-30.7-14.37-12.97-33.39-21.96-52.86-21.08,1.55-4.25,3.78-8.31,6.68-12.03,10.05-12.55,23.77-16.55,39.52-14.34,5.82.82,12.03-6.02,23.86-4.7.79.09,1.6.68,1.67,1.16.27,1.61-4.3,2.49-4.3,6.9,0,1.86.83,4.01,2.59,5.24,6.03,4.23,11.26,8.99,16.72,13.9,2.66,2.39,11.66,9.1,13.95,3.64,1.34-3.19,2.22-6.53,3.11-9.93.44-1.68-.49-2.68-1.85-3.48-9.29-5.51-12.79-16.96-9.16-27.12.35-.98,1.26-1.46,2.03-1.49,3.12-.13,1.46,5.65,9.18,8.03,7.32,2.26,7.54,8.34,11.1,5.92,8.29-5.65,11.28-1.02,18.98-8.27.79-.74,2.15-.8,2.97-.22.51.35.95,1.26.91,2.33-.22,6.12-2.61,11.97-6.8,16.46-7.91,8.49-14.56,4.43-14.99,10.38-1.26,17.46-6.97,34.9-19.37,47.58-.4.41-.63.99-.57,1.38.07.41.56.82,1.1.99l10.44,3.55c1.47.5,2.55,1.83,2.35,3.24-.17,1.23-1.15,2.32-2.55,2.79h.01Z"/>
-  </g>
-</svg>

site/public/robots.txt

@@ -1,4 +0,0 @@
-User-agent: *
-Allow: /
-
-Sitemap: https://reasonix.io/sitemap-index.xml

site/scripts/fetch-community.mjs

@@ -1,63 +0,0 @@
-// Prebuild: fetch live community stats + bake contributor avatars into public/av/.
-// Never fails the build — falls back to the committed snapshot on any error.
-import { mkdir, readFile, rm, writeFile } from 'node:fs/promises';
-import sharp from 'sharp';
-
-const repo = 'esengine/DeepSeek-Reasonix';
-const api = `https://api.github.com/repos/${repo}`;
-const headers = { 'User-Agent': 'reasonix-site', Accept: 'application/vnd.github+json' };
-if (process.env.GITHUB_TOKEN) headers.Authorization = `Bearer ${process.env.GITHUB_TOKEN}`;
-
-const fallback = JSON.parse(await readFile('src/data/contributors.json', 'utf8'));
-let { stars, mergedPrs, contributors, list } = fallback;
-
-try {
-  const r = await fetch(`${api}/contributors?per_page=100`, { headers });
-  if (r.ok) {
-    const humans = (await r.json())
-      .filter((c) => c.type === 'User')
-      .map((c) => ({ login: c.login, avatar: String(c.avatar_url).split('?')[0], url: c.html_url, c: c.contributions }));
-    if (humans.length) { list = humans; contributors = humans.length; }
-  }
-} catch {}
-try {
-  const r = await fetch(api, { headers });
-  if (r.ok) { const d = await r.json(); if (typeof d.stargazers_count === 'number') stars = d.stargazers_count; }
-} catch {}
-try {
-  const r = await fetch(`https://api.github.com/search/issues?q=repo:${repo}+is:pr+is:merged&per_page=1`, { headers });
-  if (r.ok) { const d = await r.json(); if (typeof d.total_count === 'number') mergedPrs = d.total_count; }
-} catch {}
-
-// 64px is the largest rendered avatar; bake at 2x. GitHub honours ?s= for its
-// own CDN but serves some custom avatars unscaled and in whatever format was
-// uploaded, so re-encode rather than trusting the response.
-const AVATAR_PX = 128;
-
-await rm('public/av', { recursive: true, force: true });
-await mkdir('public/av', { recursive: true });
-let baked = 0;
-let bakedBytes = 0;
-const out = await Promise.all(list.map(async (c) => {
-  const remote = `${c.avatar}?s=${AVATAR_PX}`;
-  try {
-    const r = await fetch(remote);
-    if (!r.ok) throw new Error(String(r.status));
-    const webp = await sharp(Buffer.from(await r.arrayBuffer()))
-      .resize(AVATAR_PX, AVATAR_PX, { fit: 'cover' })
-      .webp({ quality: 80 })
-      .toBuffer();
-    await writeFile(`public/av/${c.login}.webp`, webp);
-    baked++;
-    bakedBytes += webp.byteLength;
-    return { ...c, avatar: `/av/${c.login}.webp` };
-  } catch {
-    return { ...c, avatar: remote };
-  }
-}));
-
-await writeFile('src/data/community.json', JSON.stringify({ stars, mergedPrs, contributors, list: out }, null, 2) + '\n');
-console.log(
-  `community: ${contributors} contributors · ${stars} stars · ${mergedPrs} merged PRs · ` +
-    `${baked}/${out.length} avatars baked (${(bakedBytes / 1024).toFixed(0)} KB)`,
-);

site/scripts/fetch-publications.mjs

@@ -1,49 +0,0 @@
-import { mkdir, readFile, writeFile } from "node:fs/promises";
-import { resolve } from "node:path";
-import { validateReleaseEvent } from "./release-event.mjs";
-
-const siteRoot = resolve(import.meta.dirname, "..");
-const catalog = JSON.parse(await readFile(resolve(siteRoot, "src/data/releases.json"), "utf8"));
-const output = resolve(siteRoot, ".generated/publications.json");
-const headers = {
-  Accept: "application/vnd.github+json",
-  "User-Agent": "reasonix-site-publications",
-};
-if (process.env.GITHUB_TOKEN) headers.Authorization = `Bearer ${process.env.GITHUB_TOKEN}`;
-
-const publications = [];
-for (const release of catalog.releases) {
-  // Legacy entries predate publication markers and remain public. Every new
-  // reviewed entry fails closed until its exact CLI release carries the marker
-  // uploaded by the all-surface postflight.
-  if (!release.status || release.status === "published") {
-    publications.push(release.version);
-    continue;
-  }
-  const tag = `v${release.version}`;
-  try {
-    const response = await fetch(
-      `https://api.github.com/repos/esengine/DeepSeek-Reasonix/releases/tags/${encodeURIComponent(tag)}`,
-      { headers, signal: AbortSignal.timeout(20_000) },
-    );
-    if (!response.ok) continue;
-    const githubRelease = await response.json();
-    const marker = githubRelease.assets?.find((asset) => asset.name === "release-event.json" && asset.size > 0);
-    if (!marker?.browser_download_url) continue;
-    const markerResponse = await fetch(marker.browser_download_url, {
-      headers,
-      signal: AbortSignal.timeout(20_000),
-    });
-    if (!markerResponse.ok) continue;
-    const event = await markerResponse.json();
-    validateReleaseEvent(event, release);
-    publications.push(release.version);
-  } catch {
-    // A reviewed release must never become public because an upstream lookup
-    // failed. The next Pages build retries after the release postflight.
-  }
-}
-
-await mkdir(resolve(siteRoot, ".generated"), { recursive: true });
-await writeFile(output, `${JSON.stringify({ schemaVersion: 1, publications }, null, 2)}\n`);
-console.log(`Resolved ${publications.length} public release note(s).`);

site/scripts/release-event.mjs

@@ -1,27 +0,0 @@
-function invariant(condition, message) {
-  if (!condition) throw new Error(message);
-}
-
-export function validateReleaseEvent(event, release) {
-  invariant(event && typeof event === "object" && !Array.isArray(event), "release event must be an object");
-  invariant(event.schemaVersion === 1, "release event schemaVersion must be 1");
-  invariant(event.releaseId === release.version, "release event releaseId does not match reviewed notes");
-  invariant(
-    event.channel === (release.channel === "prerelease" ? "preview" : "stable"),
-    "release event channel does not match reviewed notes",
-  );
-  invariant(/^[0-9a-f]{40}$/.test(event.candidateSha), "release event candidateSha must be a full commit SHA");
-  if (release.candidateSha) {
-    invariant(event.candidateSha === release.candidateSha, "release event candidateSha does not match reviewed notes");
-  }
-  invariant(/^\d{4}-\d{2}-\d{2}T/.test(event.publishedAt), "release event publishedAt must be an ISO timestamp");
-  invariant(event.releaseNotesUrl === `https://reasonix.io/changelog/v${release.version}/`, "release event URL is invalid");
-  invariant(event.builds && typeof event.builds === "object", "release event builds are required");
-  for (const surface of ["cli", "desktop", "npm"]) {
-    invariant(typeof event.builds[surface] === "string" && event.builds[surface], `release event builds.${surface} is required`);
-    if (release.builds?.[surface]) {
-      invariant(event.builds[surface] === release.builds[surface], `release event builds.${surface} does not match reviewed notes`);
-    }
-  }
-  return event;
-}

site/scripts/releases/generate-release-notes.mjs

@@ -1,349 +0,0 @@
-#!/usr/bin/env node
-
-import { execFileSync } from "node:child_process";
-import { resolve } from "node:path";
-import { fileURLToPath } from "node:url";
-import { dirname } from "node:path";
-import { withoutOwner } from "../../src/lib/repository-owner.mjs";
-import { compareVersionsDesc, loadCatalog, upsertRelease, validateCatalog } from "./release-notes.mjs";
-
-const repoRoot = resolve(dirname(fileURLToPath(import.meta.url)), "../../..");
-const apiBase = process.env.DEEPSEEK_API_BASE || "https://api.deepseek.com";
-const model = process.env.DEEPSEEK_MODEL || "deepseek-v4-pro";
-const releaseTargetOrder = ["desktop", "cli", "site", "service"];
-
-export const releaseOutputBudgets = Object.freeze({
-  standard: Object.freeze({ highlights: 6, changes: 15, guides: 6, upgrade: 4, risks: 4, bodyChars: 280 }),
-  compact: Object.freeze({ highlights: 4, changes: 9, guides: 4, upgrade: 2, risks: 2, bodyChars: 220 }),
-});
-
-export function editorialLimitInstruction(compact = false) {
-  const budget = compact ? releaseOutputBudgets.compact : releaseOutputBudgets.standard;
-  return `Editorial budget: at most ${budget.highlights} highlights, ${budget.changes} total change items across new/improved/fixed, ${budget.guides} guides, ${budget.upgrade} upgrade notes, and ${budget.risks} risks. Keep every English and Chinese body within ${budget.bodyChars} characters. Select the most important user outcomes across the supplied PRs, combine related work, and avoid repeating the same outcome in highlights and changes. Always return a complete JSON object within this budget.`;
-}
-
-function parseArgs(argv) {
-  const values = {};
-  for (let index = 0; index < argv.length; index += 1) {
-    const arg = argv[index];
-    if (!arg.startsWith("--")) throw new Error(`unexpected argument ${arg}`);
-    values[arg.slice(2)] = argv[++index];
-  }
-  return values;
-}
-
-function runGit(args) {
-  return execFileSync("git", args, { cwd: repoRoot, encoding: "utf8" }).trim();
-}
-
-function normalizeVersion(version) {
-  return String(version || "").replace(/^(?:desktop-|npm-)?v/, "");
-}
-
-function repositoryName() {
-  if (process.env.GITHUB_REPOSITORY) return process.env.GITHUB_REPOSITORY;
-  const remote = runGit(["remote", "get-url", "origin"]);
-  const match = remote.match(/github\.com[/:]([^/]+\/[^/.]+)(?:\.git)?$/);
-  if (!match) throw new Error("cannot determine GitHub repository; set GITHUB_REPOSITORY");
-  return match[1];
-}
-
-function commitRange(from, to) {
-  return runGit(["log", "--first-parent", "--format=%H%x09%s%x09%b%x00", `${from}..${to}`])
-    .split("\0")
-    .map((record) => record.trim())
-    .filter(Boolean)
-    .map((record) => {
-      const [sha, subject, ...body] = record.split("\t");
-      return { sha, subject, body: body.join("\t").trim() };
-    });
-}
-
-function prNumbersFromCommits(commits) {
-  const refs = new Set();
-  for (const commit of commits) {
-    for (const match of `${commit.subject}\n${commit.body}`.matchAll(/#(\d+)/g)) refs.add(Number(match[1]));
-  }
-  return [...refs];
-}
-
-async function githubJson(path, { allowMissing = false } = {}) {
-  const headers = { Accept: "application/vnd.github+json", "User-Agent": "reasonix-release-notes" };
-  if (process.env.GITHUB_TOKEN || process.env.GH_TOKEN) {
-    headers.Authorization = `Bearer ${process.env.GITHUB_TOKEN || process.env.GH_TOKEN}`;
-  }
-  const response = await fetch(`https://api.github.com${path}`, { headers, signal: AbortSignal.timeout(30_000) });
-  if (allowMissing && response.status === 404) return null;
-  if (!response.ok) throw new Error(`GitHub API ${path} failed: ${response.status}`);
-  return response.json();
-}
-
-async function githubList(path) {
-  const items = [];
-  for (let page = 1; ; page += 1) {
-    const separator = path.includes("?") ? "&" : "?";
-    const batch = await githubJson(`${path}${separator}per_page=100&page=${page}`);
-    items.push(...batch);
-    if (batch.length < 100) return items;
-  }
-}
-
-export function inferPullTargetHints(labels, files) {
-  const labelSet = new Set(labels);
-  const targets = new Set();
-  const add = (target) => targets.add(target);
-  const hasPath = (pattern) => files.some((path) => pattern.test(path));
-
-  const explicitlyDesktop = labelSet.has("desktop");
-  const explicitlyCLI = labelSet.has("tui") || labelSet.has("cli");
-  if (explicitlyDesktop) add("desktop");
-  if (explicitlyCLI) add("cli");
-  if (hasPath(/^desktop\//)) add("desktop");
-  if (hasPath(/^(?:internal\/cli\/|cmd\/)/)) add("cli");
-  if (hasPath(/^site\//)) add("site");
-  if (hasPath(/^(?:workers\/|\.github\/|scripts\/|release-notes\/)/)) add("service");
-
-  const hasSharedProductCode = files.some((path) =>
-    /^(?:internal\/|sdk\/|npm\/)/.test(path) &&
-    !/^internal\/cli\//.test(path) &&
-    !/^internal\/telemetry\//.test(path),
-  );
-  if (!explicitlyDesktop && !explicitlyCLI && hasSharedProductCode) {
-    add("desktop");
-    add("cli");
-  }
-  if (!targets.size) {
-    add("desktop");
-    add("cli");
-  }
-  return releaseTargetOrder.filter((target) => targets.has(target));
-}
-
-async function collectPullRequests(repository, commits) {
-  const numbers = new Set(prNumbersFromCommits(commits));
-  const associated = await Promise.all(
-    commits.map((commit) => githubJson(`/repos/${repository}/commits/${commit.sha}/pulls`, { allowMissing: true })),
-  );
-  for (const pulls of associated) for (const pull of pulls || []) numbers.add(pull.number);
-  const pulls = await Promise.all([...numbers].map((number) => githubJson(`/repos/${repository}/pulls/${number}`, { allowMissing: true })));
-  return Promise.all(pulls.filter(Boolean).map(async (pull) => {
-    const labels = (pull.labels || []).map((label) => label.name);
-    const files = (await githubList(`/repos/${repository}/pulls/${pull.number}/files`)).map((file) => file.filename);
-    return {
-      number: pull.number,
-      title: pull.title,
-      body: String(pull.body || "").slice(0, 2000),
-      author: pull.user?.login || "",
-      labels,
-      changedFileCount: files.length,
-      files: files.slice(0, 200),
-      targetHints: inferPullTargetHints(labels, files),
-    };
-  }));
-}
-
-function releaseItems(release) {
-  return [
-    ...(release.highlights || []),
-    ...["new", "improved", "fixed"].flatMap((kind) => release.changes?.[kind] || []),
-    ...(release.upgrade || []),
-    ...(release.risks || []),
-  ];
-}
-
-function normalizeReleaseTargets(release) {
-  for (const item of releaseItems(release)) {
-    if (!Array.isArray(item.targets)) continue;
-    item.targets.sort((a, b) => releaseTargetOrder.indexOf(a) - releaseTargetOrder.indexOf(b));
-  }
-  const targets = new Set(releaseItems(release).flatMap((item) => item.targets || []));
-  release.surfaces = [
-    ...releaseTargetOrder.filter((target) => targets.has(target)),
-    ...[...targets].filter((target) => !releaseTargetOrder.includes(target)).sort(),
-  ];
-}
-
-function collectDocLinks(from, repository, to) {
-  const linkRef = runGit(["rev-parse", to]);
-  const paths = runGit(["diff", "--name-only", `${from}..${to}`])
-    .split("\n")
-    .filter((path) => /^(?:docs|README)[/\w.-]*\.(?:md|mdx)$/i.test(path));
-  return paths.map((path) => `https://github.com/${repository}/blob/${linkRef}/${path}`);
-}
-
-function assertGroundedRefs(value, allowedRefs, path = "release") {
-  if (Array.isArray(value)) {
-    value.forEach((item, index) => assertGroundedRefs(item, allowedRefs, `${path}[${index}]`));
-    return;
-  }
-  if (!value || typeof value !== "object") return;
-  if (Array.isArray(value.refs)) {
-    for (const ref of value.refs) {
-      if (!allowedRefs.has(ref)) throw new Error(`${path}.refs contains PR #${ref}, which is outside the release range`);
-    }
-  }
-  for (const [key, child] of Object.entries(value)) assertGroundedRefs(child, allowedRefs, `${path}.${key}`);
-}
-
-function extractJson(content) {
-  if (!content?.trim()) throw new Error("DeepSeek returned empty content");
-  const parsed = JSON.parse(content);
-  return parsed.release || parsed;
-}
-
-async function askDeepSeek(payload, attempt = 0) {
-  const key = process.env.DEEPSEEK_API_KEY;
-  if (!key) throw new Error("DEEPSEEK_API_KEY is required");
-  const compact = attempt > 0;
-  const response = await fetch(`${apiBase.replace(/\/$/, "")}/chat/completions`, {
-    method: "POST",
-    headers: { Authorization: `Bearer ${key}`, "Content-Type": "application/json" },
-    body: JSON.stringify({
-      model,
-      // Release notes need deterministic structured output, not hidden chain of
-      // thought. Thinking tokens share the generation budget with content and
-      // can otherwise leave response_format JSON empty or truncated.
-      thinking: { type: "disabled" },
-      temperature: 0,
-      max_tokens: 8000,
-      response_format: { type: "json_object" },
-      messages: [
-        {
-          role: "system",
-          content: `You are Reasonix's release editor. Return one JSON object with a \"release\" property. Write factual, user-facing product release notes in equivalent English and Simplified Chinese. Group changes by user outcome, not by commit. Never invent capabilities, migrations, risks, PR numbers, contributors, URLs, or metrics. Every highlight and change must cite one or more supplied PR numbers. Use this exact release shape:
-{
-  \"version\": \"semver\", \"date\": \"YYYY-MM-DD\", \"channel\": \"stable|prerelease\", \"targetingVersion\": 1,
-  \"title\": {\"en\":\"\",\"zh\":\"\"}, \"summary\": {\"en\":\"\",\"zh\":\"\"},
-  \"surfaces\": [\"desktop\",\"cli\"],
-  \"guides\": [{\"title\":{\"en\":\"\",\"zh\":\"\"},\"body\":{\"en\":\"\",\"zh\":\"\"},\"href\":\"https://...\"}],
-  \"highlights\": [{\"kind\":\"new|improved|fixed|security\",\"targets\":[\"desktop\",\"cli\"],\"title\":{\"en\":\"\",\"zh\":\"\"},\"body\":{\"en\":\"\",\"zh\":\"\"},\"refs\":[123]}],
-  \"changes\": {\"new\":[],\"improved\":[],\"fixed\":[]},
-  \"upgrade\": [{\"level\":\"info|warning\",\"targets\":[\"desktop\"],\"title\":{\"en\":\"\",\"zh\":\"\"},\"body\":{\"en\":\"\",\"zh\":\"\"},\"refs\":[123]}],
-  \"risks\": [{\"targets\":[\"cli\"],\"title\":{\"en\":\"\",\"zh\":\"\"},\"body\":{\"en\":\"\",\"zh\":\"\"},\"refs\":[123]}],
-  \"contributors\": [], \"links\": {\"github\":\"https://...\",\"compare\":\"https://...\",\"download\":\"https://...\"}
-}
-Every highlight, change, upgrade note, and risk must have a non-empty \"targets\" array using only this canonical order: desktop, cli, site, service. Use each PR's targetHints as deterministic candidates, then choose the user-visible delivery target supported by its labels, changed files, title, and body. Shared product-core behavior belongs to both desktop and cli. Website-only work belongs to site; hosted workers and release infrastructure belong to service and must not be marked as a client update merely because a client file accompanies the server change. Set top-level surfaces to the canonical union of all item targets. Return guides only for supplied documentation URLs. Mention upgrade action or risk only when explicitly supported; otherwise use empty arrays. ${editorialLimitInstruction(compact)} Output JSON only.`,
-        },
-        {
-          role: "user",
-          content: `${compact ? "The previous response was invalid or truncated. Produce a smaller complete record and obey the compact editorial budget.\n" : ""}Create the release record from these public GitHub sources:\n${JSON.stringify(payload)}`,
-        },
-      ],
-    }),
-  });
-  if (!response.ok) throw new Error(`DeepSeek API failed: ${response.status} ${await response.text()}`);
-  const data = await response.json();
-  const choice = data.choices?.[0];
-  if (choice?.finish_reason === "length") {
-    if (compact) throw new Error("DeepSeek response exceeded the compact editorial budget (finish_reason=length)");
-    return askDeepSeek(payload, attempt + 1);
-  }
-  try {
-    return extractJson(choice?.message?.content);
-  } catch (error) {
-    if (compact) {
-      throw new Error(`${error.message} (finish_reason=${choice?.finish_reason || "unknown"})`);
-    }
-    return askDeepSeek(payload, attempt + 1);
-  }
-}
-
-export function contributorsOf(pulls) {
-  return withoutOwner([...new Set(pulls.map((pull) => pull.author).filter(Boolean))]);
-}
-
-export function previousCLIRelease(catalog, version) {
-  return catalog.releases.find((release) =>
-    release.product !== "studio" && release.channel === "stable" &&
-    compareVersionsDesc(release.version, version) > 0,
-  );
-}
-
-async function main() {
-  const args = parseArgs(process.argv.slice(2));
-  if (!args.version) throw new Error("--version is required");
-  const version = normalizeVersion(args.version);
-  const catalog = await loadCatalog();
-  const channel = version.includes("-") ? "prerelease" : "stable";
-  const baseVersion = version.split("-")[0];
-  const previousRecord = channel === "stable"
-    ? previousCLIRelease(catalog, version)
-    : catalog.releases.find(
-        (release) =>
-          release.version !== version &&
-          release.channel === "prerelease" &&
-          release.baseVersion === baseVersion,
-      ) || catalog.releases.find((release) => release.product !== "studio" && release.channel === "stable");
-  const previous = args.from || previousRecord?.version;
-  if (!previous) throw new Error("--from is required when no previous release exists");
-  const previousVersion = normalizeVersion(previous);
-  const previousIsPreview = previousVersion.includes("-");
-  const from = previous.match(/^(?:desktop-|npm-)?v/)
-    ? previous
-    : previousIsPreview
-      ? `v${previousVersion}`
-      : `desktop-v${previousVersion}`;
-  const to = args.to || "HEAD";
-  const repository = repositoryName();
-  const commits = commitRange(from, to);
-  if (!commits.length) throw new Error(`no commits found in ${from}..${to}`);
-  const pulls = await collectPullRequests(repository, commits);
-  if (!pulls.length) throw new Error(`no pull requests found in ${from}..${to}`);
-  const docLinks = collectDocLinks(from, repository, to);
-  const date = args.date || new Date().toISOString().slice(0, 10);
-  const tag = args.tag || (channel === "prerelease" ? `v${version}` : `desktop-v${version}`);
-  const source = {
-    version,
-    date,
-    channel,
-    range: `${from}..${to}`,
-    pullRequests: pulls,
-    documentationUrls: docLinks,
-  };
-  const release = await askDeepSeek(source);
-  release.product = "cli";
-  release.targetingVersion = 1;
-  release.version = version;
-  release.releaseId = version;
-  release.baseVersion = baseVersion;
-  release.date = date;
-  release.channel = source.channel;
-  release.status = "reviewed";
-  release.previousRelease = previousVersion;
-  const previewOrdinal = version.match(/-preview\.([1-9][0-9]*)$/)?.[1];
-  if (channel === "prerelease") {
-    if (!previewOrdinal) throw new Error("Preview release version must use MAJOR.MINOR.PATCH-preview.N");
-    release.builds = {
-      cli: `v${version}`,
-      desktop: `v${baseVersion}-preview.${previewOrdinal}`,
-      npm: `${baseVersion}-canary.${previewOrdinal}`,
-    };
-  } else {
-    release.builds = {
-      cli: `v${version}`,
-      desktop: `v${version}`,
-      npm: version,
-    };
-  }
-  release.contributors = contributorsOf(pulls);
-  release.links = {
-    github: `https://github.com/${repository}/releases/tag/${tag}`,
-    compare: `https://github.com/${repository}/compare/${from}...${tag}`,
-    download: channel === "prerelease"
-      ? "https://reasonix.io/?download=desktop&channel=preview#start"
-      : "https://reasonix.io/?download=desktop&channel=stable#start",
-  };
-  release.guides = (release.guides || []).filter((guide) => docLinks.includes(guide.href));
-  normalizeReleaseTargets(release);
-  assertGroundedRefs(release, new Set(pulls.map((pull) => pull.number)));
-  validateCatalog({ schemaVersion: 1, releases: [release] });
-  await upsertRelease(release);
-  console.log(`Generated bilingual release notes for v${version} from ${pulls.length} pull request(s).`);
-}
-
-if (process.argv[1] && resolve(process.argv[1]) === fileURLToPath(import.meta.url)) {
-  main().catch((error) => {
-    console.error(error.message);
-    process.exitCode = 1;
-  });
-}

site/scripts/releases/release-notes-pr-kick.sh

@@ -1,63 +0,0 @@
-#!/usr/bin/env bash
-# Start CI on a Notes PR that the Actions bot opened. Events raised with
-# GITHUB_TOKEN never start workflows, so such a PR shows action_required with
-# zero jobs until a human-authenticated close/reopen re-emits pull_request.
-set -euo pipefail
-
-if [ "$#" -ne 1 ] || [[ ! "$1" =~ ^(0|[1-9][0-9]*)\.(0|[1-9][0-9]*)\.(0|[1-9][0-9]*)$ ]]; then
-	echo "usage: site/scripts/releases/release-notes-pr-kick.sh MAJOR.MINOR.PATCH" >&2
-	exit 2
-fi
-
-version="$1"
-repository="${RELEASE_REPOSITORY:-esengine/DeepSeek-Reasonix}"
-branch="website-release-notes/v$version"
-wait_seconds="${RELEASE_NOTES_KICK_WAIT_SECONDS:-120}"
-
-for command in gh jq; do
-	command -v "$command" >/dev/null || {
-		echo "required command is unavailable: $command" >&2
-		exit 2
-	}
-done
-
-prs="$(gh pr list --repo "$repository" --head "$branch" --state open --json number,headRefOid --limit 2)"
-count="$(jq 'length' <<<"$prs")"
-if [ "$count" -ne 1 ]; then
-	echo "expected exactly one open PR for $branch, found $count" >&2
-	exit 1
-fi
-number="$(jq -r '.[0].number' <<<"$prs")"
-head="$(jq -r '.[0].headRefOid' <<<"$prs")"
-
-check_runs() {
-	gh api "repos/$repository/commits/$head/check-runs" --jq '.total_count'
-}
-
-if [ "$(check_runs)" -gt 0 ]; then
-	echo "PR #$number already has check runs on $head; nothing to kick"
-	exit 0
-fi
-
-# Only the recorded-but-never-started shape is safe to kick. Anything else
-# with zero check runs needs a look, not a reopen.
-stalled="$(gh api "repos/$repository/actions/runs?event=pull_request&head_sha=$head&per_page=20" \
-	--jq "[.workflow_runs[] | select(.head_sha == \"$head\" and .conclusion == \"action_required\")] | length")"
-if [ "$stalled" -eq 0 ]; then
-	echo "PR #$number has no check runs and no action_required run on $head; inspect before kicking" >&2
-	exit 1
-fi
-
-echo "PR #$number: $stalled recorded-but-unstarted run(s) on $head; closing and reopening"
-gh pr close "$number" --repo "$repository"
-gh pr reopen "$number" --repo "$repository"
-
-deadline=$((SECONDS + wait_seconds))
-while [ "$(check_runs)" -eq 0 ]; do
-	if [ "$SECONDS" -ge "$deadline" ]; then
-		echo "no check runs appeared on $head within ${wait_seconds}s" >&2
-		exit 1
-	fi
-	sleep 5
-done
-echo "CI started on PR #$number ($head)"

site/scripts/releases/release-notes.mjs

@@ -1,459 +0,0 @@
-#!/usr/bin/env node
-
-import { readFile, writeFile } from "node:fs/promises";
-import { dirname, resolve } from "node:path";
-import { fileURLToPath } from "node:url";
-import { withoutOwner } from "../../src/lib/repository-owner.mjs";
-
-const siteRoot = resolve(dirname(fileURLToPath(import.meta.url)), "../..");
-export const defaultCatalogPath = resolve(siteRoot, "src/data/releases.json");
-
-const localizedFields = ["title", "body"];
-const changeKinds = ["new", "improved", "fixed"];
-const itemKinds = new Set(["new", "improved", "fixed", "security"]);
-const releaseChannels = new Set(["stable", "prerelease"]);
-const releaseStatuses = new Set(["reviewed", "published"]);
-const releaseTargetOrder = ["desktop", "cli", "site", "service"];
-const releaseTargets = new Set(releaseTargetOrder);
-const releaseTargetingRequiredFrom = "1.31.4";
-
-function invariant(condition, message) {
-  if (!condition) throw new Error(message);
-}
-
-function isObject(value) {
-  return value !== null && typeof value === "object" && !Array.isArray(value);
-}
-
-function validateLocalized(value, path) {
-  invariant(isObject(value), `${path} must be an object`);
-  for (const lang of ["en", "zh"]) {
-    invariant(typeof value[lang] === "string" && value[lang].trim(), `${path}.${lang} must be a non-empty string`);
-  }
-}
-
-function validateRefs(refs, path) {
-  if (refs === undefined) return;
-  invariant(Array.isArray(refs), `${path} must be an array`);
-  for (const ref of refs) invariant(Number.isInteger(ref) && ref > 0, `${path} contains invalid PR number ${ref}`);
-}
-
-function validateItem(item, path, { kind = false, href = false, level = false, targets = false } = {}) {
-  invariant(isObject(item), `${path} must be an object`);
-  for (const field of localizedFields) validateLocalized(item[field], `${path}.${field}`);
-  if (kind) invariant(itemKinds.has(item.kind), `${path}.kind is invalid`);
-  if (href) invariant(typeof item.href === "string" && /^https:\/\//.test(item.href), `${path}.href must be HTTPS`);
-  if (level) invariant(item.level === "info" || item.level === "warning", `${path}.level is invalid`);
-  if (targets || item.targets !== undefined) {
-    invariant(Array.isArray(item.targets) && item.targets.length > 0, `${path}.targets must be a non-empty array`);
-    invariant(new Set(item.targets).size === item.targets.length, `${path}.targets contains duplicates`);
-    for (const target of item.targets) invariant(releaseTargets.has(target), `${path}.targets contains invalid target ${target}`);
-    const sorted = releaseTargetOrder.filter((target) => item.targets.includes(target));
-    invariant(sorted.every((target, index) => target === item.targets[index]), `${path}.targets must use canonical order`);
-  }
-  validateRefs(item.refs, `${path}.refs`);
-}
-
-function releaseItems(release) {
-  return [
-    ...release.highlights,
-    ...changeKinds.flatMap((kind) => release.changes[kind]),
-    ...release.upgrade,
-    ...release.risks,
-  ];
-}
-
-function itemTargetsUnion(release) {
-  const targets = new Set(releaseItems(release).flatMap((item) => item.targets || []));
-  return releaseTargetOrder.filter((target) => targets.has(target));
-}
-
-function semverParts(version) {
-  const match = String(version).match(/^(\d+)\.(\d+)\.(\d+)(?:-([0-9A-Za-z.-]+))?$/);
-  invariant(match, `invalid version ${version}`);
-  return [Number(match[1]), Number(match[2]), Number(match[3]), match[4] || ""];
-}
-
-function isCoreVersionAtLeast(version, minimum) {
-  const current = semverParts(version);
-  const floor = semverParts(minimum);
-  for (let index = 0; index < 3; index += 1) {
-    if (current[index] !== floor[index]) return current[index] > floor[index];
-  }
-  return true;
-}
-
-export function compareVersionsDesc(a, b) {
-  const aa = semverParts(a);
-  const bb = semverParts(b);
-  for (let i = 0; i < 3; i += 1) {
-    if (aa[i] !== bb[i]) return bb[i] - aa[i];
-  }
-  if (aa[3] === bb[3]) return 0;
-  if (!aa[3]) return -1;
-  if (!bb[3]) return 1;
-  return String(bb[3]).localeCompare(String(aa[3]), "en", { numeric: true });
-}
-
-export function validateCatalog(catalog) {
-  invariant(isObject(catalog), "catalog must be an object");
-  invariant(catalog.schemaVersion === 1, "catalog.schemaVersion must be 1");
-  invariant(Array.isArray(catalog.releases) && catalog.releases.length > 0, "catalog.releases must not be empty");
-
-  const versions = new Set();
-  for (const [index, release] of catalog.releases.entries()) {
-    const path = `releases[${index}]`;
-    invariant(isObject(release), `${path} must be an object`);
-    semverParts(release.version);
-    invariant(release.product === undefined || ["cli", "studio"].includes(release.product), `${path}.product is invalid`);
-    if (release.product === "studio") {
-      invariant(/^2\.\d+\.\d+$/.test(release.version), `${path}.Studio version must be 2.x`);
-      invariant(release.sourceNotes?.language === "zh", `${path}.sourceNotes.language must be zh`);
-      invariant(typeof release.sourceNotes.markdown === "string" && release.sourceNotes.markdown.trim(), `${path}.sourceNotes.markdown must not be empty`);
-      invariant(/^[0-9a-f]{40}$/.test(release.sourceNotes.sha), `${path}.sourceNotes.sha must be a full commit SHA`);
-      invariant(release.sourceNotes.path === `release-notes/studio/${release.version}.md`, `${path}.sourceNotes.path is invalid`);
-      invariant(release.status === undefined, `${path}.Studio does not use CLI publication markers`);
-    }
-    invariant(!versions.has(release.version), `duplicate version ${release.version}`);
-    versions.add(release.version);
-    invariant(/^\d{4}-\d{2}-\d{2}$/.test(release.date), `${path}.date must use YYYY-MM-DD`);
-    invariant(releaseChannels.has(release.channel), `${path}.channel is invalid`);
-    if (release.releaseId !== undefined) {
-      invariant(release.releaseId === release.version, `${path}.releaseId must equal version`);
-    }
-    if (release.baseVersion !== undefined) {
-      semverParts(release.baseVersion);
-      invariant(!release.baseVersion.includes("-"), `${path}.baseVersion must be stable semver`);
-      invariant(
-        release.version === release.baseVersion || release.version.startsWith(`${release.baseVersion}-`),
-        `${path}.baseVersion does not match version`,
-      );
-    }
-    if (release.status !== undefined) {
-      invariant(releaseStatuses.has(release.status), `${path}.status is invalid`);
-    }
-    if (release.candidateSha !== undefined) {
-      invariant(/^[0-9a-f]{40}$/.test(release.candidateSha), `${path}.candidateSha must be a full commit SHA`);
-    }
-    if (release.previousRelease !== undefined) {
-      semverParts(release.previousRelease);
-      invariant(release.previousRelease !== release.version, `${path}.previousRelease must differ from version`);
-    }
-    if (release.builds !== undefined) {
-      invariant(isObject(release.builds), `${path}.builds must be an object`);
-      for (const surface of ["cli", "desktop", "npm"]) {
-        invariant(
-          typeof release.builds[surface] === "string" && release.builds[surface].trim(),
-          `${path}.builds.${surface} must be a non-empty string`,
-        );
-      }
-    }
-    if (release.status !== undefined) {
-      for (const field of ["releaseId", "baseVersion", "previousRelease", "builds"]) {
-        invariant(release[field] !== undefined, `${path}.${field} is required for managed release records`);
-      }
-      if (release.channel === "stable") {
-        invariant(release.version === release.baseVersion, `${path}.stable version must equal baseVersion`);
-        invariant(release.builds.cli === `v${release.version}`, `${path}.builds.cli does not match Stable version`);
-        invariant(release.builds.desktop === `v${release.version}`, `${path}.builds.desktop does not match Stable version`);
-        invariant(release.builds.npm === release.version, `${path}.builds.npm does not match Stable version`);
-      } else {
-        const preview = release.version.match(/^(\d+\.\d+\.\d+)-preview\.([1-9][0-9]*)$/);
-        invariant(preview, `${path}.managed prerelease must use MAJOR.MINOR.PATCH-preview.N`);
-        invariant(preview[1] === release.baseVersion, `${path}.Preview baseVersion does not match version`);
-        invariant(release.builds.cli === `v${release.version}`, `${path}.builds.cli does not match Preview version`);
-        invariant(release.builds.desktop === `v${release.version}`, `${path}.builds.desktop does not match Preview version`);
-        invariant(
-          release.builds.npm === `${release.baseVersion}-canary.${preview[2]}`,
-          `${path}.builds.npm does not match Preview ordinal`,
-        );
-      }
-    }
-    const targetingRequiredByVersion = release.product !== "studio" && isCoreVersionAtLeast(release.version, releaseTargetingRequiredFrom);
-    if (targetingRequiredByVersion) {
-      invariant(
-        release.targetingVersion === 1,
-        `${path}.targetingVersion must be 1 for v${releaseTargetingRequiredFrom} and newer`,
-      );
-    } else if (release.targetingVersion !== undefined) {
-      invariant(release.targetingVersion === 1, `${path}.targetingVersion is invalid`);
-    }
-    const targetsRequired = release.targetingVersion === 1;
-    validateLocalized(release.title, `${path}.title`);
-    validateLocalized(release.summary, `${path}.summary`);
-    invariant(Array.isArray(release.surfaces) && release.surfaces.length > 0, `${path}.surfaces must not be empty`);
-    invariant(new Set(release.surfaces).size === release.surfaces.length, `${path}.surfaces contains duplicates`);
-    invariant(Array.isArray(release.guides), `${path}.guides must be an array`);
-    release.guides.forEach((item, itemIndex) => validateItem(item, `${path}.guides[${itemIndex}]`, { href: true }));
-    invariant(Array.isArray(release.highlights) && release.highlights.length > 0, `${path}.highlights must not be empty`);
-    release.highlights.forEach((item, itemIndex) =>
-      validateItem(item, `${path}.highlights[${itemIndex}]`, { kind: true, targets: targetsRequired }),
-    );
-    invariant(isObject(release.changes), `${path}.changes must be an object`);
-    for (const changeKind of changeKinds) {
-      invariant(Array.isArray(release.changes[changeKind]), `${path}.changes.${changeKind} must be an array`);
-      release.changes[changeKind].forEach((item, itemIndex) =>
-        validateItem(item, `${path}.changes.${changeKind}[${itemIndex}]`, { targets: targetsRequired }),
-      );
-    }
-    invariant(Array.isArray(release.upgrade), `${path}.upgrade must be an array`);
-    release.upgrade.forEach((item, itemIndex) =>
-      validateItem(item, `${path}.upgrade[${itemIndex}]`, { level: true, targets: targetsRequired }),
-    );
-    invariant(Array.isArray(release.risks), `${path}.risks must be an array`);
-    release.risks.forEach((item, itemIndex) =>
-      validateItem(item, `${path}.risks[${itemIndex}]`, { targets: targetsRequired }),
-    );
-    if (targetsRequired) {
-      const derivedTargets = itemTargetsUnion(release);
-      invariant(
-        derivedTargets.includes("desktop") || derivedTargets.includes("cli"),
-        `${path} must contain at least one Desktop or CLI update`,
-      );
-      invariant(
-        derivedTargets.length === release.surfaces.length &&
-          derivedTargets.every((target, index) => target === release.surfaces[index]),
-        `${path}.surfaces must equal the canonical union of item targets`,
-      );
-    }
-    invariant(Array.isArray(release.contributors), `${path}.contributors must be an array`);
-    invariant(isObject(release.links), `${path}.links must be an object`);
-    for (const link of ["github", "compare", "download"]) {
-      invariant(typeof release.links[link] === "string" && /^https:\/\//.test(release.links[link]), `${path}.links.${link} must be HTTPS`);
-    }
-  }
-
-  const sorted = [...catalog.releases].sort((a, b) => compareVersionsDesc(a.version, b.version));
-  invariant(
-    sorted.every((release, index) => release.version === catalog.releases[index].version),
-    "catalog.releases must be sorted newest first",
-  );
-  return catalog;
-}
-
-export async function loadCatalog(path = defaultCatalogPath) {
-  const catalog = JSON.parse(await readFile(path, "utf8"));
-  return validateCatalog(catalog);
-}
-
-export function releaseForVersion(catalog, version) {
-  const normalized = String(version).replace(/^(?:studio-|desktop-|npm-)?v/, "");
-  const release = catalog.releases.find((entry) => entry.version === normalized);
-  invariant(release, `release notes for v${normalized} are missing`);
-  return release;
-}
-
-function localized(value, lang) {
-  return value[lang] || value.en;
-}
-
-function refsSuffix(refs = []) {
-  if (!refs.length) return "";
-  return ` (${refs.map((ref) => `[#${ref}](https://github.com/esengine/DeepSeek-Reasonix/pull/${ref})`).join(", ")})`;
-}
-
-function targetLabel(target) {
-  return { desktop: "Desktop", cli: "CLI", site: "Site", service: "Service" }[target] || target;
-}
-
-function targetsPrefix(item) {
-  if (!item.targets?.length) return "";
-  return `**[${item.targets.map(targetLabel).join(" · ")}]** `;
-}
-
-function renderItems(items, lang) {
-  return items
-    .map((item) => `- ${targetsPrefix(item)}**${localized(item.title, lang)}** — ${localized(item.body, lang)}${refsSuffix(item.refs)}`)
-    .join("\n");
-}
-
-function hasTarget(item, target) {
-  return item.targets?.includes(target) || false;
-}
-
-function targetItemCount(release, target) {
-  return releaseItems(release).filter((item) => hasTarget(item, target)).length;
-}
-
-function appendTargetSection(lines, release, target, lang) {
-  const isZh = lang === "zh";
-  const title = target === "desktop"
-    ? (isZh ? "桌面端更新" : "Desktop updates")
-    : (isZh ? "CLI 端更新" : "CLI updates");
-  lines.push(`## ${title}`, "");
-
-  const highlights = release.highlights.filter((item) => hasTarget(item, target));
-  if (highlights.length) {
-    lines.push(`### ${isZh ? "重点内容" : "Highlights"}`, "", renderItems(highlights, lang), "");
-  }
-  const headings = {
-    new: isZh ? "新增" : "New",
-    improved: isZh ? "改进" : "Improved",
-    fixed: isZh ? "修复" : "Fixed",
-  };
-  for (const kind of changeKinds) {
-    const items = release.changes[kind].filter((item) => hasTarget(item, target));
-    if (items.length) lines.push(`### ${headings[kind]}`, "", renderItems(items, lang), "");
-  }
-
-  if (!highlights.length && !changeKinds.some((kind) => release.changes[kind].some((item) => hasTarget(item, target)))) {
-    const noTargetedItems = targetItemCount(release, target) === 0;
-    lines.push(
-      target === "cli" && noTargetedItems
-        ? (isZh ? "本版本没有 CLI 相关功能、改进或修复，CLI 用户可按需跳过。" : "This release has no CLI features, improvements, or fixes; CLI users may skip it if preferred.")
-        : (isZh ? "此板块没有功能或修复条目；相关说明请查看下方升级提醒和风险提示。" : "No feature or fix entries are listed here; see the upgrade and risk notes below."),
-      "",
-    );
-  }
-}
-
-function appendOtherTargetSection(lines, release, lang) {
-  const isZh = lang === "zh";
-  const isOtherOnly = (item) => item.targets?.length && !hasTarget(item, "desktop") && !hasTarget(item, "cli");
-  const highlights = release.highlights.filter(isOtherOnly);
-  const changes = Object.fromEntries(changeKinds.map((kind) => [kind, release.changes[kind].filter(isOtherOnly)]));
-  if (!highlights.length && !changeKinds.some((kind) => changes[kind].length)) return;
-
-  lines.push(`## ${isZh ? "其他项目更新" : "Other project updates"}`, "");
-  if (highlights.length) lines.push(renderItems(highlights, lang), "");
-  for (const kind of changeKinds) {
-    if (changes[kind].length) lines.push(renderItems(changes[kind], lang), "");
-  }
-}
-
-export function renderGitHubRelease(release, lang = "zh") {
-  if (release.product === "studio") return release.sourceNotes.markdown;
-  const isZh = lang === "zh";
-  const isPreview = release.channel === "prerelease";
-  const channelLabel = isPreview ? (isZh ? "预览版" : "Preview") : (isZh ? "稳定版" : "Stable");
-  const lines = [
-    `> ${localized(release.summary, lang)}`,
-    "",
-    `**${isZh ? "发布渠道" : "Release channel"}：${channelLabel} · v${release.version}**`,
-    "",
-    isZh
-      ? `[English →](https://reasonix.io/changelog/v${release.version}/?lang=en) · [网页版完整更新日志 →](https://reasonix.io/changelog/v${release.version}/)`
-      : `[中文 →](https://reasonix.io/changelog/v${release.version}/?lang=zh) · [Full release notes →](https://reasonix.io/changelog/v${release.version}/?lang=en)`,
-    "",
-  ];
-
-  if (release.guides.length) {
-    lines.push(`## ${isZh ? "使用攻略" : "Guides"}`, "");
-    for (const guide of release.guides) {
-      lines.push(`- [**${localized(guide.title, lang)}**](${guide.href}) — ${localized(guide.body, lang)}`);
-    }
-    lines.push("");
-  }
-
-  lines.push(
-    `## ${isZh ? "概览" : "Overview"}`,
-    "",
-    `**Reasonix v${release.version} — ${localized(release.title, lang)}**`,
-    "",
-    localized(release.summary, lang),
-    "",
-    `${isZh ? "发布日期" : "Released"}：${release.date}`,
-    "",
-  );
-
-  if (release.targetingVersion === 1) {
-    lines.push(
-      `**Desktop ${targetItemCount(release, "desktop")} · CLI ${targetItemCount(release, "cli")}**`,
-      "",
-    );
-    appendTargetSection(lines, release, "desktop", lang);
-    appendTargetSection(lines, release, "cli", lang);
-    appendOtherTargetSection(lines, release, lang);
-  } else {
-    lines.push(`## ${isZh ? "重点内容" : "Highlights"}`, "", renderItems(release.highlights, lang), "");
-    const headings = {
-      new: isZh ? "新功能" : "New",
-      improved: isZh ? "改进" : "Improved",
-      fixed: isZh ? "修复" : "Fixed",
-    };
-    for (const kind of changeKinds) {
-      const items = release.changes[kind];
-      if (!items.length) continue;
-      lines.push(`## ${headings[kind]}`, "", renderItems(items, lang), "");
-    }
-  }
-
-  lines.push(`## ${isZh ? "升级提醒" : "Upgrade notes"}`, "");
-  if (release.upgrade.length) lines.push(renderItems(release.upgrade, lang));
-  else lines.push(isZh ? "本版本无需手动迁移。" : "No manual migration is required.");
-  lines.push("");
-
-  lines.push(`## ${isZh ? "风险提示" : "Risk notes"}`, "");
-  if (release.risks.length) lines.push(renderItems(release.risks, lang));
-  else lines.push(isZh ? "当前没有需要额外操作的已知风险。" : "There are no known risks requiring extra action.");
-  lines.push("");
-
-  const thanked = withoutOwner(release.contributors);
-  if (thanked.length) {
-    lines.push(
-      `## ${isZh ? "致谢" : "Thanks"}`,
-      "",
-      `${isZh ? "感谢本版本的贡献者" : "Thanks to the contributors in this release"}：${thanked
-        .map((name) => `[@${name}](https://github.com/${name})`)
-        .join("、")}`,
-      "",
-    );
-  }
-
-  lines.push(
-    `## ${isZh ? "下载与安装" : "Download and install"}`,
-    "",
-    `- [${isZh ? "官网按平台下载" : "Platform downloads"}](${release.links.download})`,
-    `- [${isZh ? "查看完整差异" : "Full comparison"}](${release.links.compare})`,
-    "",
-  );
-  return `${lines.join("\n").trim()}\n`;
-}
-
-export async function upsertRelease(release, path = defaultCatalogPath) {
-  const catalog = await loadCatalog(path);
-  const next = {
-    ...catalog,
-    releases: [release, ...catalog.releases.filter((entry) => entry.version !== release.version)].sort((a, b) =>
-      compareVersionsDesc(a.version, b.version),
-    ),
-  };
-  validateCatalog(next);
-  await writeFile(path, `${JSON.stringify(next, null, 2)}\n`);
-  return next;
-}
-
-function parseArgs(argv) {
-  const [command = "validate", ...rest] = argv;
-  const values = { command };
-  for (let i = 0; i < rest.length; i += 1) {
-    const arg = rest[i];
-    if (!arg.startsWith("--")) throw new Error(`unexpected argument ${arg}`);
-    values[arg.slice(2)] = rest[++i];
-  }
-  return values;
-}
-
-async function main() {
-  const args = parseArgs(process.argv.slice(2));
-  const catalogPath = args.catalog ? resolve(args.catalog) : defaultCatalogPath;
-  const catalog = await loadCatalog(catalogPath);
-  if (args.command === "validate") {
-    console.log(`Validated ${catalog.releases.length} release note(s).`);
-    return;
-  }
-  if (args.command !== "render") throw new Error(`unknown command ${args.command}`);
-  invariant(args.version, "render requires --version");
-  invariant(args.output, "render requires --output");
-  const release = releaseForVersion(catalog, args.version);
-  const output = resolve(args.output);
-  await writeFile(output, renderGitHubRelease(release, args.lang === "en" ? "en" : "zh"));
-  console.log(`Rendered v${release.version} release notes to ${output}`);
-}
-
-if (process.argv[1] && resolve(process.argv[1]) === fileURLToPath(import.meta.url)) {
-  main().catch((error) => {
-    console.error(error.message);
-    process.exitCode = 1;
-  });
-}

site/scripts/releases/release-notes.test.mjs

@@ -1,268 +0,0 @@
-import assert from "node:assert/strict";
-import { test } from "node:test";
-import {
-  editorialLimitInstruction,
-  inferPullTargetHints,
-  releaseOutputBudgets,
-} from "./generate-release-notes.mjs";
-import { loadCatalog, releaseForVersion, renderGitHubRelease, validateCatalog } from "./release-notes.mjs";
-import { validateReleaseEvent } from "../release-event.mjs";
-
-test("the committed release catalog is valid and newest first", async () => {
-  const catalog = await loadCatalog();
-  assert.equal(catalog.schemaVersion, 1);
-  assert.equal(new Set(catalog.releases.map((release) => release.version)).size, catalog.releases.length);
-});
-
-test("tag namespaces resolve to the same product release", async () => {
-  const catalog = await loadCatalog();
-  assert.equal(releaseForVersion(catalog, "v1.17.13").version, "1.17.13");
-  assert.equal(releaseForVersion(catalog, "desktop-v1.17.13").version, "1.17.13");
-  assert.equal(releaseForVersion(catalog, "npm-v1.17.13").version, "1.17.13");
-});
-
-test("GitHub rendering keeps product sections and source PR links", async () => {
-  const catalog = await loadCatalog();
-  const markdown = renderGitHubRelease(releaseForVersion(catalog, "1.17.13"), "zh");
-  assert.match(markdown, /## 使用攻略/);
-  assert.match(markdown, /## 重点内容/);
-  assert.match(markdown, /## 升级提醒/);
-  assert.match(markdown, /## 风险提示/);
-  assert.match(markdown, /## 致谢/);
-  assert.match(markdown, /\/pull\/6460/);
-  assert.match(markdown, /reasonix\.io\/changelog\/v1\.17\.13/);
-});
-
-test("targeted releases render Desktop and CLI sections from one shared item", async () => {
-  const catalog = await loadCatalog();
-  const markdown = renderGitHubRelease(releaseForVersion(catalog, "1.31.4"), "zh");
-  assert.match(markdown, /## 桌面端更新/);
-  assert.match(markdown, /## CLI 端更新/);
-  assert.match(markdown, /## 其他项目更新/);
-  assert.match(markdown, /\*\*\[Service\]\*\* \*\*降低数据库读取成本\*\*/);
-  assert.equal(markdown.match(/更好的数学渲染/g)?.length, 2);
-});
-
-test("targeted release validation requires canonical item targets and matching surfaces", () => {
-  const release = {
-    version: "2.0.0",
-    targetingVersion: 1,
-    date: "2026-01-01",
-    channel: "stable",
-    title: { en: "Targeted", zh: "分类版本" },
-    summary: { en: "Summary", zh: "摘要" },
-    surfaces: ["desktop", "cli"],
-    guides: [],
-    highlights: [{
-      kind: "fixed",
-      targets: ["desktop", "cli"],
-      title: { en: "Shared fix", zh: "共享修复" },
-      body: { en: "A shared fix.", zh: "一项共享修复。" },
-      refs: [1],
-    }],
-    changes: { new: [], improved: [], fixed: [] },
-    upgrade: [],
-    risks: [],
-    contributors: [],
-    links: {
-      github: "https://example.com/release",
-      compare: "https://example.com/compare",
-      download: "https://example.com/download",
-    },
-  };
-  assert.doesNotThrow(() => validateCatalog({ schemaVersion: 1, releases: [release] }));
-  assert.throws(
-    () => validateCatalog({
-      schemaVersion: 1,
-      releases: [{ ...release, highlights: [{ ...release.highlights[0], targets: undefined }] }],
-    }),
-    /targets must be a non-empty array/,
-  );
-  assert.throws(
-    () => validateCatalog({ schemaVersion: 1, releases: [{ ...release, surfaces: ["desktop"] }] }),
-    /surfaces must equal the canonical union/,
-  );
-  assert.throws(
-    () => validateCatalog({
-      schemaVersion: 1,
-      releases: [{ ...release, highlights: [{ ...release.highlights[0], targets: ["cli", "desktop"] }] }],
-    }),
-    /targets must use canonical order/,
-  );
-});
-
-test("targeting adoption boundary preserves historical releases and rejects future legacy records", () => {
-  const release = {
-    version: "1.31.3",
-    date: "2026-01-01",
-    channel: "stable",
-    title: { en: "Legacy", zh: "旧版" },
-    summary: { en: "Summary", zh: "摘要" },
-    surfaces: ["desktop"],
-    guides: [],
-    highlights: [{
-      kind: "fixed",
-      title: { en: "Legacy fix", zh: "旧版修复" },
-      body: { en: "A historical fix.", zh: "一项历史修复。" },
-      refs: [1],
-    }],
-    changes: { new: [], improved: [], fixed: [] },
-    upgrade: [],
-    risks: [],
-    contributors: [],
-    links: {
-      github: "https://example.com/release",
-      compare: "https://example.com/compare",
-      download: "https://example.com/download",
-    },
-  };
-
-  assert.doesNotThrow(() => validateCatalog({ schemaVersion: 1, releases: [release] }));
-  for (const version of ["1.31.4", "1.32.0", "2.0.0-preview.1"]) {
-    assert.throws(
-      () => validateCatalog({ schemaVersion: 1, releases: [{ ...release, version }] }),
-      /targetingVersion must be 1 for v1\.31\.4 and newer/,
-    );
-  }
-});
-
-test("release target hints prefer explicit product labels and identify shared or service paths", () => {
-  assert.deepEqual(inferPullTargetHints(["desktop"], ["internal/sessioncatalog/catalog.go"]), ["desktop"]);
-  assert.deepEqual(inferPullTargetHints(["desktop", "tui"], ["desktop/app.go", "internal/cli/cli.go"]), ["desktop", "cli"]);
-  assert.deepEqual(inferPullTargetHints([], ["internal/agent/agent.go"]), ["desktop", "cli"]);
-  assert.deepEqual(inferPullTargetHints([], ["workers/crash-report/src/index.ts"]), ["service"]);
-});
-
-test("release generation uses bounded output and a tighter truncation retry", () => {
-  assert.ok(releaseOutputBudgets.standard.highlights > releaseOutputBudgets.compact.highlights);
-  assert.ok(releaseOutputBudgets.standard.changes > releaseOutputBudgets.compact.changes);
-  assert.ok(releaseOutputBudgets.standard.bodyChars > releaseOutputBudgets.compact.bodyChars);
-  assert.match(editorialLimitInstruction(), /Always return a complete JSON object/);
-  assert.match(editorialLimitInstruction(true), /at most 4 highlights/);
-  assert.match(editorialLimitInstruction(true), /9 total change items/);
-});
-
-test("validation rejects bilingual drift", () => {
-  assert.throws(
-    () =>
-      validateCatalog({
-        schemaVersion: 1,
-        releases: [
-          {
-            version: "1.0.0",
-            date: "2026-01-01",
-            channel: "stable",
-            title: { en: "Title", zh: "" },
-            summary: { en: "Summary", zh: "摘要" },
-          },
-        ],
-      }),
-    /title\.zh/,
-  );
-});
-
-test("managed Preview records bind every surface to one exact ordinal", () => {
-  const release = {
-    version: "1.19.0-preview.3",
-    releaseId: "1.19.0-preview.3",
-    baseVersion: "1.19.0",
-    date: "2026-07-31",
-    channel: "prerelease",
-    status: "reviewed",
-    previousRelease: "1.19.0-preview.2",
-    builds: {
-      cli: "v1.19.0-preview.3",
-      desktop: "v1.19.0-preview.3",
-      npm: "1.19.0-canary.3",
-    },
-    title: { en: "Preview", zh: "预览版" },
-    summary: { en: "Preview summary", zh: "预览版摘要" },
-    surfaces: ["cli"],
-    guides: [],
-    highlights: [{
-      kind: "fixed",
-      title: { en: "Fix", zh: "修复" },
-      body: { en: "A fix.", zh: "一项修复。" },
-      refs: [1],
-    }],
-    changes: { new: [], improved: [], fixed: [] },
-    upgrade: [],
-    risks: [],
-    contributors: [],
-    links: {
-      github: "https://github.com/esengine/DeepSeek-Reasonix/releases/tag/v1.19.0-preview.3",
-      compare: "https://github.com/esengine/DeepSeek-Reasonix/compare/v1.19.0-preview.2...v1.19.0-preview.3",
-      download: "https://reasonix.io/?download=desktop&channel=preview#start",
-    },
-  };
-
-  assert.doesNotThrow(() => validateCatalog({ schemaVersion: 1, releases: [release] }));
-  assert.throws(
-    () => validateCatalog({
-      schemaVersion: 1,
-      releases: [{ ...release, builds: { ...release.builds, npm: "1.19.0-canary.4" } }],
-    }),
-    /builds\.npm/,
-  );
-});
-
-test("publication marker is bound to reviewed version, channel, SHA, and builds", () => {
-  const release = {
-    version: "1.19.0-preview.3",
-    channel: "prerelease",
-    candidateSha: "a".repeat(40),
-    builds: {
-      cli: "v1.19.0-preview.3",
-      desktop: "v1.19.0-preview.3",
-      npm: "1.19.0-canary.3",
-    },
-  };
-  const event = {
-    schemaVersion: 1,
-    releaseId: release.version,
-    channel: "preview",
-    candidateSha: release.candidateSha,
-    publishedAt: "2026-07-31T00:00:00.000Z",
-    releaseNotesUrl: "https://reasonix.io/changelog/v1.19.0-preview.3/",
-    builds: release.builds,
-  };
-
-  assert.doesNotThrow(() => validateReleaseEvent(event, release));
-  assert.throws(
-    () => validateReleaseEvent({ ...event, candidateSha: "b".repeat(40) }, release),
-    /candidateSha/,
-  );
-});
-
-test("Studio tag lookup and verbatim rendering stay separate from CLI records", async () => {
-  const { studioRecord } = await import('./sync-releases.mjs');
-  const source = '中立发布说明。\n\n## 改进\n\n- 窗口布局\n';
-  const studio = studioRecord({ tag_name: 'studio-v2.24.0', published_at: '2026-09-30T00:00:00Z' }, source, 'a'.repeat(40));
-  const catalog = validateCatalog({ schemaVersion: 1, releases: [studio] });
-  assert.equal(releaseForVersion(catalog, 'studio-v2.24.0').product, 'studio');
-  assert.equal(renderGitHubRelease(studio, 'en'), source);
-});
-
-test("the repository owner is never thanked: not collected, not rendered, case-insensitively", async () => {
-  const { contributorsOf } = await import("./generate-release-notes.mjs");
-  const { withoutOwner, repositoryOwner } = await import("../../src/lib/repository-owner.mjs");
-  assert.equal(repositoryOwner, "esengine");
-  assert.deepEqual(withoutOwner(["alice", "EsEngine", "bob"]), ["alice", "bob"]);
-  assert.deepEqual(contributorsOf([{ author: "esengine" }, { author: "alice" }, { author: "alice" }, { author: null }, { author: "ESENGINE" }]), ["alice"]);
-  assert.deepEqual(contributorsOf([{ author: "esengine" }]), []);
-
-  const catalog = await loadCatalog();
-  const base = catalog.releases.find((release) => release.product !== "studio" && release.contributors.length);
-  const markdown = renderGitHubRelease({ ...base, contributors: ["esengine", "alice"] }, "en");
-  assert.doesNotMatch(markdown, /@esengine/);
-  assert.match(markdown, /\[@alice\]/);
-  const alone = renderGitHubRelease({ ...base, contributors: ["esengine"] }, "en");
-  assert.doesNotMatch(alone, /@esengine|## Thanks/);
-});
-
-test("the changelog page filters contributors through the owner helper", async () => {
-  const { readFile } = await import("node:fs/promises");
-  const page = await readFile(new URL("../../src/components/ChangelogPage.astro", import.meta.url), "utf8");
-  assert.match(page, /withoutOwner\(release\.contributors\)/);
-  assert.doesNotMatch(page, /release\.contributors\.(length|map)/);
-});

site/scripts/releases/sync-releases.mjs

@@ -1,139 +0,0 @@
-#!/usr/bin/env node
-import { execFileSync } from 'node:child_process';
-import { appendFile } from 'node:fs/promises';
-import { resolve } from 'node:path';
-import { fileURLToPath } from 'node:url';
-import { parseStudioNotes } from '../../src/lib/studio-notes.mjs';
-import { compareVersionsDesc, loadCatalog, upsertRelease, validateCatalog } from './release-notes.mjs';
-
-const repository = 'esengine/DeepSeek-Reasonix';
-
-export function missingReleases(published, catalog, { studioOnly = false } = {}) {
-  const existing = new Set(catalog.releases.map((r) => `${r.product || 'cli'}:${r.version}`));
-  // The archive starts after the earliest GitHub tags. Do not require source
-  // catalogs from releases that predate the website's supported history.
-  const oldestCLI = catalog.releases.filter((r) => r.product !== 'studio' && r.channel === 'stable')
-    .map((r) => r.version).sort(compareVersionsDesc).at(-1);
-  const missing = new Map();
-  for (const release of published) {
-    if (release.draft || !release.published_at) continue;
-    const studio = release.tag_name.match(/^studio-v(2\.\d+\.\d+)$/);
-    const cli = release.tag_name.match(/^(?:desktop-|npm-)?v(1\.\d+\.\d+)$/);
-    if (!studio && (!cli || release.prerelease)) continue;
-    const product = studio ? 'studio' : 'cli';
-    if (studioOnly && product !== 'studio') continue;
-    const version = (studio || cli)[1];
-    if (product === 'cli' && oldestCLI && compareVersionsDesc(version, oldestCLI) > 0) continue;
-    const key = `${product}:${version}`;
-    if (existing.has(key)) continue;
-    // Prefer the canonical CLI release over duplicate desktop/package tags.
-    if (!missing.has(key) || release.tag_name === `v${version}`) {
-      missing.set(key, { ...release, product, version });
-    }
-  }
-  return [...missing.values()].sort((a, b) => -compareVersionsDesc(a.version, b.version));
-}
-
-export function studioRecord(release, markdown, sha) {
-  if (!markdown?.trim()) throw new Error(`Missing Studio source for ${release.tag_name}`);
-  const version = release.version || release.tag_name.replace(/^studio-v/, '');
-  const title = { en: `Reasonix Studio v${version}`, zh: `Reasonix Studio v${version}` };
-  const line = parseStudioNotes(markdown).summary || `Reasonix Studio v${version}`;
-  const summary = { en: line, zh: line };
-  return {
-    product: 'studio', version, date: release.published_at.slice(0, 10),
-    channel: 'stable',
-    sourceNotes: { language: 'zh', markdown, sha, path: `release-notes/studio/${version}.md` },
-    title, summary, surfaces: ['desktop'], guides: [],
-    highlights: [{ kind: 'improved', title, body: summary }],
-    changes: { new: [], improved: [], fixed: [] }, upgrade: [], risks: [], contributors: [],
-    links: {
-      github: `https://github.com/${repository}/releases/tag/studio-v${version}`,
-      compare: `https://github.com/${repository}/blob/${sha}/release-notes/studio/${version}.md`,
-      download: 'https://reasonix.io/#start',
-    },
-  };
-}
-
-export function describeFailure(error, secrets = [process.env.DEEPSEEK_API_KEY, process.env.GH_TOKEN, process.env.GITHUB_TOKEN]) {
-  let text = String(error?.message ?? error).split('\n')[0];
-  for (const secret of secrets) if (secret && secret.length > 3) text = text.split(secret).join('[redacted]');
-  text = text.replace(/(Bearer\s+|sk-|ghp_|gho_|ghs_|github_pat_)\S+/g, '$1[redacted]').slice(0, 200);
-  return `${error?.name || 'Error'}: ${text}`;
-}
-
-export async function readStudioSource(release, api) {
-  const { sha } = JSON.parse(await api(`commits/${release.tag_name}`));
-  if (!/^[0-9a-f]{40}$/.test(sha)) throw new Error(`Invalid source commit for ${release.tag_name}`);
-  const version = release.version || release.tag_name.replace(/^studio-v/, '');
-  const markdown = await api(`contents/release-notes/studio/${version}.md?ref=${sha}`, true);
-  return { sha, markdown };
-}
-
-export async function readCLISource(release, api) {
-  const { sha } = JSON.parse(await api(`commits/${release.tag_name}`));
-  if (!/^[0-9a-f]{40}$/.test(sha)) throw new Error(`Invalid source commit for ${release.tag_name}`);
-  const catalog = JSON.parse(await api(`contents/release-notes/releases.json?ref=${sha}`, true));
-  const record = catalog.releases?.find((r) => r.version === release.version && r.product !== 'studio');
-  if (!record) throw new Error(`Missing CLI source for ${release.tag_name}`);
-  validateCatalog({ schemaVersion: catalog.schemaVersion, releases: [record] });
-  // Keep reviewed records gated by fetch-publications.mjs and its all-surface
-  // marker. A GitHub release alone must not promote them to published.
-  return record;
-}
-
-export function requireSync(result) {
-  if (result.pending.length) throw new Error(`Changelog sync incomplete: ${result.pending.join(', ')}`);
-}
-
-export function requireStudioSync(result, catalog, expectedVersion) {
-  if (result.pending.length) throw new Error(`Studio changelog sync incomplete: ${result.pending.join(', ')}`);
-  const version = expectedVersion?.replace(/^v/, '');
-  if (version && !catalog.releases.some((r) => r.product === 'studio' && r.version === version)) {
-    throw new Error(`Studio changelog is missing requested release ${expectedVersion}`);
-  }
-}
-
-export async function syncCatalog({ catalog, published, studioOnly = false, readStudio, readCLI, save }) {
-  const added = [], pending = [], failures = [];
-  for (const release of missingReleases(published, catalog, { studioOnly })) {
-    const key = `${release.product}:${release.version}`;
-    try {
-      if (release.product === 'studio') {
-        const { markdown, sha } = await readStudio(release);
-        await save(studioRecord(release, markdown, sha));
-      } else {
-        await save(await readCLI(release));
-      }
-      added.push(key);
-    } catch (error) {
-      pending.push(key);
-      failures.push({ key, reason: describeFailure(error) });
-    }
-  }
-  return { added, pending, failures };
-}
-
-async function main() {
-  const studioOnly = process.argv.includes('--studio-only');
-  const api = (endpoint, raw = false, paginate = false) => execFileSync('gh', [
-    'api', '--hostname', 'github.com', ...(paginate ? ['--paginate', '--slurp'] : []),
-    ...(raw ? ['-H', 'Accept: application/vnd.github.raw+json'] : []), `repos/${repository}/${endpoint}`,
-  ], { encoding: 'utf8', maxBuffer: 64 * 1024 * 1024, stdio: ['ignore', 'pipe', 'pipe'] });
-  const published = JSON.parse(api('releases?per_page=100', false, true)).flat();
-  const result = await syncCatalog({
-    catalog: await loadCatalog(), published, studioOnly,
-    readStudio: (release) => readStudioSource(release, api),
-    save: (release) => upsertRelease(release),
-    readCLI: (release) => readCLISource(release, api),
-  });
-  const summary = `## Website changelog sync\n\nAdded: ${result.added.join(', ') || 'none'}\n\nPending (retried next run): ${result.pending.join(', ') || 'none'}\n${result.failures.map((f) => `\n- ${f.key}: ${f.reason}`).join('')}\n`;
-  console.log(summary);
-  if (process.env.GITHUB_STEP_SUMMARY) await appendFile(process.env.GITHUB_STEP_SUMMARY, summary);
-  requireSync(result);
-  requireStudioSync(result, await loadCatalog(), process.env.STUDIO_RELEASE_VERSION);
-}
-
-if (process.argv[1] && resolve(process.argv[1]) === fileURLToPath(import.meta.url)) {
-  main().catch((error) => { console.error(error.message); process.exitCode = 1; });
-}

site/scripts/releases/sync-releases.test.mjs

@@ -1,201 +0,0 @@
-import assert from 'node:assert/strict';
-import { readFile } from 'node:fs/promises';
-import { test } from 'node:test';
-import { describeFailure, missingReleases, readCLISource, readStudioSource, requireSync, requireStudioSync, studioRecord, syncCatalog } from './sync-releases.mjs';
-import { loadCatalog, validateCatalog, renderGitHubRelease } from './release-notes.mjs';
-
-const published = (tag, extra = {}) => ({ tag_name: tag, draft: false, prerelease: false, published_at: '2026-09-30T12:00:00Z', ...extra });
-
-test('discovery deduplicates CLI namespaces, includes published Studio previews and ignores drafts and unrelated tags', () => {
-  const found = missingReleases([
-    published('v1.39.3'), published('desktop-v1.39.3'), published('npm-v1.39.3'),
-    published('studio-v2.24.0', { prerelease: true }), published('studio-v2.25.0', { draft: true }),
-    published('v1.39.2'), published('v1.40.0-preview.1', { prerelease: true }), published('other-v3.0.0'),
-  ], { releases: [{ version: '1.39.2', product: 'cli' }] });
-  assert.deepEqual(found.map(({ product, version }) => [product, version]), [['cli', '1.39.3'], ['studio', '2.24.0']]);
-});
-
-const cliOnlyCatalog = async () => {
-  const catalog = await loadCatalog();
-  return { ...catalog, releases: catalog.releases.filter((r) => r.product !== 'studio') };
-};
-
-test('Studio preserves Chinese source verbatim and validates without CLI targeting', async () => {
-  const notes = '中立版本说明。\n\n## 修复\n\n- 改善窗口布局\n';
-  const release = studioRecord(published('studio-v2.24.0', { prerelease: true }), notes, 'a'.repeat(40));
-  assert.equal(release.product, 'studio');
-  assert.equal(release.sourceNotes.language, 'zh');
-  assert.equal(release.sourceNotes.markdown, notes);
-  assert.equal(release.channel, 'stable');
-  assert.doesNotThrow(() => validateCatalog({ schemaVersion: 1, releases: [release] }));
-  assert.equal(renderGitHubRelease(release), notes);
-  const catalog = await loadCatalog();
-  assert.throws(() => validateCatalog({ ...catalog, releases: [{ ...catalog.releases[0], product: 'invalid' }] }));
-  assert.throws(() => validateCatalog({ schemaVersion: 1, releases: [{ ...release, sourceNotes: undefined }] }));
-});
-
-test('batch sync imports reviewed CLI and Studio source without model generation', async () => {
-  const catalog = await cliOnlyCatalog();
-  const saved = [];
-  const result = await syncCatalog({
-    catalog, published: [published('v1.99.0'), published('studio-v2.24.0')],
-    readStudio: async () => ({ sha: 'a'.repeat(40), markdown: '中立更新。\n' }),
-    save: async (release) => saved.push(release),
-    readCLI: async () => ({ version: '1.99.0', status: 'reviewed' }),
-  });
-  assert.deepEqual(saved.map((r) => r.version), ['1.99.0', '2.24.0']);
-  assert.equal(saved[0].status, 'reviewed');
-  assert.deepEqual(result.pending, []);
-  assert.deepEqual(result.added, ['cli:1.99.0', 'studio:2.24.0']);
-});
-
-test('existing catalog entries are never regenerated', async () => {
-  const catalog = await loadCatalog();
-  const result = await syncCatalog({ catalog, published: [published('v1.39.2')], save: () => { throw new Error('unexpected write'); } });
-  assert.deepEqual(result, { added: [], pending: [], failures: [] });
-});
-
-test('batch failures retry independently and never manufacture missing Studio notes', async () => {
-  const result = await syncCatalog({
-    catalog: await cliOnlyCatalog(), published: [published('studio-v2.23.0'), published('studio-v2.24.0')],
-    readStudio: async (release) => ({ sha: 'a'.repeat(40), markdown: release.version === '2.23.0' ? '' : '中立说明。' }),
-    save: async () => {},
-  });
-  assert.deepEqual(result.added, ['studio:2.24.0']);
-  assert.deepEqual(result.pending, ['studio:2.23.0']);
-  assert.match(result.failures[0].reason, /^Error: Missing Studio source/);
-});
-
-test('CLI range selection uses the earlier CLI release even with newer Studio and CLI records', async () => {
-  const { previousCLIRelease } = await import('./generate-release-notes.mjs');
-  assert.equal(previousCLIRelease({ releases: [
-    { version: '2.24.0', product: 'studio', channel: 'stable' },
-    { version: '1.39.6', product: 'cli', channel: 'stable' },
-    { version: '1.39.2', channel: 'stable' },
-  ] }, '1.39.3').version, '1.39.2');
-});
-
-test('an upstream published CLI release preserves its publication-marker gate', async () => {
-  const saved = [];
-  const result = await syncCatalog({
-    catalog: await loadCatalog(), published: [published('v1.99.0')],
-    readCLI: async () => ({ version: '1.99.0', product: 'cli', status: 'reviewed' }),
-    save: async (release) => saved.push(release),
-  });
-  assert.deepEqual(result.added, ['cli:1.99.0']);
-  assert.equal(saved[0].status, 'reviewed');
-});
-
-test('failure reasons carry the error class and a message but never secrets', async () => {
-  const result = await syncCatalog({
-    catalog: await loadCatalog(), published: [published('v1.99.0')],
-    readCLI: async () => { throw new TypeError('request failed with Bearer abc123token and key sk-live-999\nstack line'); },
-    save: async () => {},
-  });
-  assert.deepEqual(result.pending, ['cli:1.99.0']);
-  assert.equal(result.failures[0].reason, 'TypeError: request failed with Bearer [redacted] and key sk-[redacted]');
-  assert.equal(describeFailure(new Error('boom hunter2'), ['hunter2']), 'Error: boom [redacted]');
-});
-
-test('Studio entries take their summary from the first line of the notes', () => {
-  const release = studioRecord(published('studio-v2.24.0'), '本版加入反馈。\n\n## 新增\n\n- 项 (#1)\n', 'a'.repeat(40));
-  assert.equal(release.summary.zh, '本版加入反馈。');
-  assert.equal(release.summary.en, '本版加入反馈。');
-});
-
-test('Studio source is read from its published tag commit, never the moving product branch', async () => {
-  const sha = 'b'.repeat(40);
-  const source = await readStudioSource(published('studio-v2.45.0'), async (endpoint, raw) => {
-    if (endpoint === 'commits/studio-v2.45.0') return JSON.stringify({ sha });
-    assert.equal(endpoint, `contents/release-notes/studio/2.45.0.md?ref=${sha}`);
-    assert.equal(raw, true);
-    return '该版本原始说明。\n';
-  });
-  assert.deepEqual(source, { sha, markdown: '该版本原始说明。\n' });
-});
-
-test('build sync imports all missing Studio releases, leaves CLI alone and is idempotent', async () => {
-  const catalog = { schemaVersion: 1, releases: [] };
-  const releases = [published('v1.99.0'), published('studio-v2.44.0'), published('studio-v2.45.0'), published('studio-v2.46.0', { draft: true })];
-  const run = () => syncCatalog({
-    catalog, published: releases, studioOnly: true,
-    readStudio: async (release) => ({ sha: release.version === '2.44.0' ? 'a'.repeat(40) : 'b'.repeat(40), markdown: `${release.version} 原文。\n` }),
-    save: async (release) => catalog.releases.unshift(release),
-  });
-  const first = await run();
-  assert.deepEqual(first.added, ['studio:2.44.0', 'studio:2.45.0']);
-  assert.deepEqual(first.pending, []);
-  assert.equal(catalog.releases[0].version, '2.45.0');
-  assert.equal(catalog.releases[0].sourceNotes.sha, 'b'.repeat(40));
-  assert.deepEqual((await run()).added, []);
-});
-
-test('a failed or incomplete Studio sync blocks publication of a stale catalog', () => {
-  const catalog = { releases: [{ product: 'studio', version: '2.44.0' }, { version: '2.45.0', product: 'cli' }] };
-  const complete = { pending: [], failures: [] };
-  assert.doesNotThrow(() => requireStudioSync(complete, catalog));
-  assert.doesNotThrow(() => requireStudioSync(complete, catalog, '2.44.0'));
-  assert.doesNotThrow(() => requireStudioSync(complete, catalog, 'v2.44.0'));
-  assert.throws(() => requireStudioSync(complete, catalog, '2.45.0'), /2\.45\.0/);
-  assert.throws(() => requireStudioSync({ pending: ['studio:2.45.0'] }, catalog), /studio:2\.45\.0/);
-});
-
-test('production builds synchronize both products before rendering and deployments require the website branch', async () => {
-  const pkg = JSON.parse(await readFile(new URL('../../package.json', import.meta.url), 'utf8'));
-  assert.ok(pkg.scripts.prebuild.startsWith('node scripts/releases/sync-releases.mjs &&'));
-  const workflow = await readFile(new URL('../../../.github/workflows/pages.yml', import.meta.url), 'utf8');
-  assert.match(workflow, /workflow_dispatch:\n    inputs:/);
-  assert.match(workflow, /if: github\.ref == 'refs\/heads\/website'/);
-  assert.match(workflow, /STUDIO_RELEASE_VERSION: \$\{\{ inputs\.studio_version \}\}/);
-});
-
-test('CLI sources use exact published tag commits and preserve reviewed bilingual content', async () => {
-  const catalog = await loadCatalog();
-  const record = catalog.releases.find((r) => r.version === '1.39.7');
-  const sha = 'c'.repeat(40);
-  for (const tag of ['v1.39.7', 'desktop-v1.39.7']) {
-    const result = await readCLISource({ ...published(tag), version: '1.39.7' }, async (endpoint, raw) => {
-      if (endpoint === `commits/${tag}`) return JSON.stringify({ sha });
-      assert.equal(endpoint, `contents/release-notes/releases.json?ref=${sha}`);
-      assert.equal(raw, true);
-      return JSON.stringify({ schemaVersion: 1, releases: [record] });
-    });
-    assert.deepEqual(result, record);
-  }
-});
-
-test('missing or invalid CLI source fails closed while independent Studio sync continues', async () => {
-  const release = { ...published('v1.99.0'), version: '1.99.0' };
-  const api = async (endpoint) => endpoint.startsWith('commits/')
-    ? JSON.stringify({ sha: 'd'.repeat(40) })
-    : JSON.stringify({ schemaVersion: 1, releases: [] });
-  const result = await syncCatalog({
-    catalog: await cliOnlyCatalog(), published: [release, published('studio-v2.99.0')],
-    readCLI: (r) => readCLISource(r, api),
-    readStudio: async () => ({ sha: 'e'.repeat(40), markdown: '更新说明。' }),
-    save: async () => {},
-  });
-  assert.deepEqual(result.pending, ['cli:1.99.0']);
-  assert.deepEqual(result.added, ['studio:2.99.0']);
-  assert.throws(() => requireSync(result), /cli:1\.99\.0/);
-  await assert.rejects(readCLISource(release, async () => JSON.stringify({ sha: 'invalid' })), /Invalid source commit/);
-  await assert.rejects(readCLISource(release, async (endpoint) => endpoint.startsWith('commits/')
-    ? JSON.stringify({ sha: 'd'.repeat(40) })
-    : JSON.stringify({ schemaVersion: 1, releases: [{ version: '1.99.0' }] })), /date/);
-});
-
-test('build sync respects the archive history boundary and never imports unpublished CLI drafts', async () => {
-  const catalog = { schemaVersion: 1, releases: [{ version: '1.39.7', channel: 'stable' }] };
-  const releases = [published('v1.0.0'), published('v1.39.8'), published('desktop-v1.39.8'),
-    published('v1.39.9'), published('v1.39.10', { draft: true }), published('v1.39.11', { prerelease: true })];
-  const run = () => syncCatalog({
-    catalog, published: releases,
-    readCLI: async (r) => ({ version: r.version, channel: 'stable', status: 'reviewed' }),
-    save: async (r) => catalog.releases.unshift(r),
-  });
-  assert.deepEqual((await run()).added, ['cli:1.39.8', 'cli:1.39.9']);
-  assert.deepEqual(catalog.releases.map((r) => r.version), ['1.39.9', '1.39.8', '1.39.7']);
-  const repeated = await run();
-  assert.deepEqual(repeated, { added: [], pending: [], failures: [] });
-  assert.doesNotThrow(() => requireSync(repeated));
-});

site/src/components/ChangelogPage.astro

@@ -1,445 +0,0 @@
----
-import Base from '../layouts/Base.astro';
-import CommunityJoin from './CommunityJoin.astro';
-import SiteHeader from './SiteHeader.astro';
-import type { ReleaseItem, ReleaseRecord, ReleaseTarget } from '../data/releases';
-import { releasePath, releaseTargetCount } from '../data/releases';
-import { issueHref, parseStudioNotes } from '../lib/studio-notes.mjs';
-import { withoutOwner } from '../lib/repository-owner.mjs';
-import '../styles/changelog.css';
-
-const { release, releases, canonical } = Astro.props as {
-  release: ReleaseRecord;
-  releases: ReleaseRecord[];
-  canonical?: string;
-};
-const thanked = withoutOwner(release.contributors);
-const base = import.meta.env.BASE_URL.replace(/\/$/, '');
-const repo = 'https://github.com/esengine/DeepSeek-Reasonix';
-const prHref = (ref: number) => `${repo}/pull/${ref}`;
-
-const isStudio = release.product === 'studio';
-const isPreview = !isStudio && release.channel === 'prerelease';
-const latestForChannel = releases[0];
-const studioDoc = isStudio && release.sourceNotes ? parseStudioNotes(release.sourceNotes.markdown) : null;
-const studioBlocks = studioDoc ? studioDoc.blocks.filter((block, index) => !(index === 0 && block.type === 'paragraph' && studioDoc.summary === release.summary.zh)) : [];
-const downloadHref = isPreview ? 'https://reasonix.io/?download=desktop#start' : release.links.download;
-
-const kindLabel = (kind: string) => ({
-  new: { en: 'New', zh: '新增' },
-  improved: { en: 'Improved', zh: '改进' },
-  fixed: { en: 'Fixed', zh: '修复' },
-  security: { en: 'Security', zh: '安全' },
-}[kind] ?? { en: kind, zh: kind });
-
-const surfaceLabel = (surface: string) => ({
-  agent: { en: 'Agent', zh: 'Agent' },
-  desktop: { en: 'Desktop', zh: '桌面端' },
-  cli: { en: 'CLI', zh: 'CLI' },
-  mcp: { en: 'MCP', zh: 'MCP' },
-  security: { en: 'Security', zh: '安全' },
-  provider: { en: 'Provider', zh: '模型服务' },
-  plugin: { en: 'Plugins', zh: '插件' },
-  site: { en: 'Site', zh: '网站' },
-  service: { en: 'Service', zh: '服务端' },
-}[surface] ?? { en: surface, zh: surface });
-
-const targetingEnabled = release.targetingVersion === 1;
-const changeKinds = ['new', 'improved', 'fixed'] as const;
-const clientTargets: { id: ReleaseTarget; en: string; zh: string }[] = [
-  { id: 'desktop', en: 'Desktop updates', zh: '桌面端更新' },
-  { id: 'cli', en: 'CLI updates', zh: 'CLI 端更新' },
-];
-const hasTarget = (item: ReleaseItem, target: ReleaseTarget) => item.targets?.includes(target) ?? false;
-const clientHighlights = (target: ReleaseTarget) => release.highlights.filter((item) => hasTarget(item, target));
-const clientChanges = (target: ReleaseTarget, kind: typeof changeKinds[number]) =>
-  release.changes[kind].filter((item) => hasTarget(item, target));
-const hasClientChangeContent = (target: ReleaseTarget) =>
-  clientHighlights(target).length > 0 || changeKinds.some((kind) => clientChanges(target, kind).length > 0);
-const isOtherOnly = (item: ReleaseItem) =>
-  Boolean(item.targets?.length) && !hasTarget(item, 'desktop') && !hasTarget(item, 'cli');
-const otherHighlights = release.highlights.filter(isOtherOnly);
-const otherChanges = Object.fromEntries(
-  changeKinds.map((kind) => [kind, release.changes[kind].filter(isOtherOnly)]),
-) as Record<typeof changeKinds[number], ReleaseItem[]>;
-const hasOtherChanges = otherHighlights.length > 0 || changeKinds.some((kind) => otherChanges[kind].length > 0);
-
-/* Sections render only when they have content; numbering is sequential. */
-const sectionDefs = [
-  ...(release.guides.length ? [{ id: 'guides', en: 'Guides', zh: '使用攻略' }] : []),
-  ...(targetingEnabled
-    ? [
-        ...clientTargets,
-        ...(hasOtherChanges ? [{ id: 'other', en: 'Other project updates', zh: '其他项目更新' }] : []),
-      ]
-    : [
-        { id: 'highlights', en: 'Highlights', zh: '重点内容' },
-        ...changeKinds
-          .filter((kind) => release.changes[kind].length)
-          .map((kind) => ({ id: kind, ...kindLabel(kind) })),
-      ]),
-  ...(release.upgrade.length ? [{ id: 'upgrade', en: 'Upgrade notes', zh: '升级提醒' }] : []),
-  ...(release.risks.length ? [{ id: 'risks', en: 'Risk notes', zh: '风险提示' }] : []),
-  ...(thanked.length ? [{ id: 'thanks', en: 'Thanks', zh: '致谢' }] : []),
-];
-const sectionNum = new Map(sectionDefs.map((s, i) => [s.id, String(i + 1).padStart(2, '0')]));
-const tocItems = [...(isStudio ? [{ id: 'source-notes', en: 'Chinese source notes', zh: '中文原始说明' }] : sectionDefs), { id: 'download', en: 'Download', zh: '下载与安装' }];
-
-/* Version rail: group by minor, show the latest few patches per group,
-   older ones behind a native <details> expander. */
-const minorKey = (v: string) => v.split('.').slice(0, 2).join('.');
-const railGroups: { key: string; items: ReleaseRecord[] }[] = [];
-for (const item of releases) {
-  const key = minorKey(item.version);
-  const last = railGroups[railGroups.length - 1];
-  if (last && last.key === key) last.items.push(item);
-  else railGroups.push({ key, items: [item] });
-}
-const RAIL_VISIBLE = 3;
-
-const titleEn = `Reasonix${isStudio ? ' Studio' : ''} v${release.version} release notes`;
-const titleZh = `Reasonix${isStudio ? ' Studio' : ''} v${release.version} 更新日志`;
-const description = release.summary.en;
----
-
-<Base title={titleEn} titleEn={titleEn} titleZh={titleZh} description={description} canonical={canonical} noindex={isPreview}>
-  <SiteHeader active="changelog" scrolled />
-
-  <main class="release-stage">
-    <nav class="release-product-tabs" aria-label="Products">
-      <a href={`${base}/changelog/cli/`} aria-current={!isStudio ? 'page' : undefined}><span class="l-en">CLI · 1.x (previous)</span><span class="l-zh">CLI · 1.x（上一代）</span></a>
-      <a href={`${base}/changelog/`} aria-current={isStudio ? 'page' : undefined}>Studio · 2.x</a>
-    </nav>
-    <div class="release-mobile-switcher">
-      <label for="release-version"><span class="l-en">Version</span><span class="l-zh">版本</span></label>
-      <select id="release-version" data-release-version>
-        {releases.map((item) => <option value={item.version} selected={item.version === release.version}>v{item.version}</option>)}
-      </select>
-    </div>
-
-    <div class="release-grid">
-      <aside class="release-rail" aria-label="Release versions">
-        <div class="release-rail__eyebrow"><span class="release-rail__mark"></span><span class="l-en">Release ledger</span><span class="l-zh">版本档案</span></div>
-        <nav>
-          {railGroups.map((group) => {
-            const channelItems = group.items;
-            if (!channelItems.length) return null;
-            const visible = channelItems.slice(0, RAIL_VISIBLE);
-            const overflow = channelItems.slice(RAIL_VISIBLE);
-            return (
-              <div class="release-rail__group">
-                <p class="release-rail__minor">{group.key}.x</p>
-                {visible.map((item) => (
-                  <a class:list={["release-version-link", { active: item.version === release.version }]} href={`${base}${releasePath(item.version)}`}>
-                    <span class="release-version-link__line"><strong>v{item.version}</strong>{item === latestForChannel && <em><span class="l-en">Latest</span><span class="l-zh">最新</span></em>}</span>
-                    <small>{item.date}</small>
-                  </a>
-                ))}
-                {overflow.length > 0 && (
-                  <details class="release-rail__more" open={overflow.some((item) => item.version === release.version)}>
-                    <summary>
-                      <span class="when-closed"><span class="l-en">+{overflow.length} more</span><span class="l-zh">还有 {overflow.length} 个</span></span>
-                      <span class="when-open"><span class="l-en">Show less</span><span class="l-zh">收起</span></span>
-                    </summary>
-                    {overflow.map((item) => (
-                      <a class:list={["release-version-link", { active: item.version === release.version }]} href={`${base}${releasePath(item.version)}`}>
-                        <span class="release-version-link__line"><strong>v{item.version}</strong>{item === latestForChannel && <em><span class="l-en">Latest</span><span class="l-zh">最新</span></em>}</span>
-                        <small>{item.date}</small>
-                      </a>
-                    ))}
-                  </details>
-                )}
-              </div>
-            );
-          })}
-        </nav>
-        <a class="release-rail__all" href={`${repo}/releases`}><span class="l-en">All GitHub releases ↗</span><span class="l-zh">全部 GitHub Releases ↗</span></a>
-      </aside>
-
-      <article class="release-paper">
-        <header class="release-hero">
-          <div class="release-hero__meta">
-            {isPreview && <span class="release-channel release-channel--preview"><span class="release-channel__dot"></span><span class="l-en">Historical archive</span><span class="l-zh">历史归档</span></span>}
-            <time datetime={release.date}>{release.date}</time>
-          </div>
-          <h1>Reasonix{isStudio ? ' Studio' : ''} v{release.version}</h1>
-          <div class="release-surfaces">
-            {release.surfaces.map((surface) => {
-              const label = surfaceLabel(surface);
-              return <span><span class="l-en">{label.en}</span><span class="l-zh">{label.zh}</span></span>;
-            })}
-          </div>
-          {release.builds && (
-            <div class="release-builds" aria-label="Published builds">
-              <span><strong>CLI</strong> {release.builds.cli}</span>
-              <span><strong>Desktop</strong> {release.builds.desktop}</span>
-              <span><strong>npm</strong> {release.builds.npm}</span>
-            </div>
-          )}
-          {targetingEnabled && (
-            <div class="release-target-summary" aria-label="Updates by product">
-              <span><strong>Desktop</strong> {releaseTargetCount(release, 'desktop')}</span>
-              <span><strong>CLI</strong> {releaseTargetCount(release, 'cli')}</span>
-            </div>
-          )}
-          <p class="release-lede"><span class="l-en">{release.summary.en}</span><span class="l-zh">{release.summary.zh}</span></p>
-        </header>
-
-        {isStudio && release.sourceNotes && (
-          <section id="source-notes" class="release-section">
-            <div class="release-section__head"><span>01</span><h2><span class="l-en">Chinese source notes</span><span class="l-zh">中文原始说明</span></h2></div>
-            <p class="release-source-link"><a href={release.links.compare}><span class="l-en">View source ↗</span><span class="l-zh">查看原文 ↗</span></a></p>
-            <div class="release-source-notes" lang="zh">
-              {studioBlocks.map((block) => block.type === 'heading' ? (
-                <h3>{block.inline.map((token) => token.type === 'code' ? <code>{token.value}</code> : token.value)}</h3>
-              ) : block.type === 'list' ? (
-                <ul>
-                  {block.items.map((item) => (
-                    <li>{item.map((token) => token.type === 'code' ? <code>{token.value}</code> : token.type === 'ref' ? <a href={issueHref(token.number)} rel="noopener">{token.value}</a> : token.value)}</li>
-                  ))}
-                </ul>
-              ) : (
-                <p>{block.inline.map((token) => token.type === 'code' ? <code>{token.value}</code> : token.type === 'ref' ? <a href={issueHref(token.number)} rel="noopener">{token.value}</a> : token.value)}</p>
-              ))}
-            </div>
-          </section>
-        )}
-        {!isStudio && <>
-        {release.guides.length > 0 && (
-          <section id="guides" class="release-section release-guides">
-            <div class="release-section__head"><span>{sectionNum.get('guides')}</span><h2><span class="l-en">Start here</span><span class="l-zh">使用攻略</span></h2></div>
-            <div class="release-guide-grid">
-              {release.guides.map((guide) => (
-                <a class="release-guide" href={guide.href}>
-                  <span class="release-guide__arrow">↗</span>
-                  <h3><span class="l-en">{guide.title.en}</span><span class="l-zh">{guide.title.zh}</span></h3>
-                  <p><span class="l-en">{guide.body.en}</span><span class="l-zh">{guide.body.zh}</span></p>
-                </a>
-              ))}
-            </div>
-          </section>
-        )}
-
-        {targetingEnabled ? (
-          <>
-            {clientTargets.map((target) => {
-              const highlights = clientHighlights(target.id);
-              const total = releaseTargetCount(release, target.id);
-              return (
-                <section id={target.id} class="release-section release-target-section" data-target={target.id}>
-                  <div class="release-section__head"><span>{sectionNum.get(target.id)}</span><h2><span class="l-en">{target.en}</span><span class="l-zh">{target.zh}</span></h2></div>
-                  <p class="release-target-section__summary">
-                    <span class="l-en">{total} update{total === 1 ? '' : 's'} relevant to {target.id === 'desktop' ? 'Desktop' : 'CLI'}.</span>
-                    <span class="l-zh">与{target.id === 'desktop' ? '桌面端' : ' CLI'}相关的更新共 {total} 项。</span>
-                  </p>
-
-                  {highlights.length > 0 && (
-                    <div class="release-target-group">
-                      <h3 class="release-target-group__title"><span class="l-en">Highlights</span><span class="l-zh">重点内容</span></h3>
-                      <div class="release-highlight-list">
-                        {highlights.map((item, index) => {
-                          const kind = kindLabel(item.kind);
-                          return (
-                            <article class="release-highlight" data-kind={item.kind}>
-                              <div class="release-highlight__index">{String(index + 1).padStart(2, '0')}</div>
-                              <div>
-                                <div class="release-item-meta">
-                                  <div class="release-highlight__kind"><span class="l-en">{kind.en}</span><span class="l-zh">{kind.zh}</span></div>
-                                  <div class="release-item-targets">{item.targets?.map((itemTarget) => {
-                                    const label = surfaceLabel(itemTarget);
-                                    return <span><span class="l-en">{label.en}</span><span class="l-zh">{label.zh}</span></span>;
-                                  })}</div>
-                                </div>
-                                <h3><span class="l-en">{item.title.en}</span><span class="l-zh">{item.title.zh}</span></h3>
-                                <p><span class="l-en">{item.body.en}</span><span class="l-zh">{item.body.zh}</span></p>
-                                {item.refs?.length && <div class="release-refs">{item.refs.map((ref) => <a href={prHref(ref)}>#{ref}</a>)}</div>}
-                              </div>
-                            </article>
-                          );
-                        })}
-                      </div>
-                    </div>
-                  )}
-
-                  {changeKinds.map((kind) => {
-                    const items = clientChanges(target.id, kind);
-                    if (!items.length) return null;
-                    const label = kindLabel(kind);
-                    return (
-                      <div class="release-target-group">
-                        <h3 class="release-target-group__title"><span class="l-en">{label.en}</span><span class="l-zh">{label.zh}</span></h3>
-                        <div class="release-change-list">
-                          {items.map((item: ReleaseItem) => (
-                            <article>
-                              <div class="release-item-targets">{item.targets?.map((itemTarget) => {
-                                const targetLabel = surfaceLabel(itemTarget);
-                                return <span><span class="l-en">{targetLabel.en}</span><span class="l-zh">{targetLabel.zh}</span></span>;
-                              })}</div>
-                              <h3><span class="l-en">{item.title.en}</span><span class="l-zh">{item.title.zh}</span></h3>
-                              <p><span class="l-en">{item.body.en}</span><span class="l-zh">{item.body.zh}</span></p>
-                              {item.refs?.length && <div class="release-refs">{item.refs.map((ref) => <a href={prHref(ref)}>#{ref}</a>)}</div>}
-                            </article>
-                          ))}
-                        </div>
-                      </div>
-                    );
-                  })}
-
-                  {!hasClientChangeContent(target.id) && (
-                    <div class="release-target-empty">
-                      {target.id === 'cli' && total === 0 ? (
-                        <><strong><span class="l-en">No CLI changes in this release.</span><span class="l-zh">本版本没有 CLI 相关改动。</span></strong><p><span class="l-en">CLI users may skip this version if preferred.</span><span class="l-zh">CLI 用户可按需跳过这个版本。</span></p></>
-                      ) : (
-                        <><strong><span class="l-en">No feature or fix entries in this section.</span><span class="l-zh">此板块没有功能或修复条目。</span></strong><p><span class="l-en">See the upgrade and risk notes below for relevant guidance.</span><span class="l-zh">相关说明请查看下方升级提醒和风险提示。</span></p></>
-                      )}
-                    </div>
-                  )}
-                </section>
-              );
-            })}
-
-            {hasOtherChanges && (
-              <section id="other" class="release-section release-target-section" data-target="other">
-                <div class="release-section__head"><span>{sectionNum.get('other')}</span><h2><span class="l-en">Other project updates</span><span class="l-zh">其他项目更新</span></h2></div>
-                <p class="release-target-section__summary"><span class="l-en">Website and service changes that do not require a Desktop or CLI update.</span><span class="l-zh">不要求更新桌面端或 CLI 的网站与服务端变更。</span></p>
-                <div class="release-change-list">
-                  {[...otherHighlights, ...changeKinds.flatMap((kind) => otherChanges[kind])].map((item) => (
-                    <article>
-                      <div class="release-item-targets">{item.targets?.map((itemTarget) => {
-                        const label = surfaceLabel(itemTarget);
-                        return <span><span class="l-en">{label.en}</span><span class="l-zh">{label.zh}</span></span>;
-                      })}</div>
-                      <h3><span class="l-en">{item.title.en}</span><span class="l-zh">{item.title.zh}</span></h3>
-                      <p><span class="l-en">{item.body.en}</span><span class="l-zh">{item.body.zh}</span></p>
-                      {item.refs?.length && <div class="release-refs">{item.refs.map((ref) => <a href={prHref(ref)}>#{ref}</a>)}</div>}
-                    </article>
-                  ))}
-                </div>
-              </section>
-            )}
-          </>
-        ) : (
-          <>
-            <section id="highlights" class="release-section">
-              <div class="release-section__head"><span>{sectionNum.get('highlights')}</span><h2><span class="l-en">Highlights</span><span class="l-zh">重点内容</span></h2></div>
-              <div class="release-highlight-list">
-                {release.highlights.map((item, index) => {
-                  const kind = kindLabel(item.kind);
-                  return (
-                    <article class="release-highlight" data-kind={item.kind}>
-                      <div class="release-highlight__index">{String(index + 1).padStart(2, '0')}</div>
-                      <div>
-                        <div class="release-highlight__kind"><span class="l-en">{kind.en}</span><span class="l-zh">{kind.zh}</span></div>
-                        <h3><span class="l-en">{item.title.en}</span><span class="l-zh">{item.title.zh}</span></h3>
-                        <p><span class="l-en">{item.body.en}</span><span class="l-zh">{item.body.zh}</span></p>
-                        {item.refs?.length && <div class="release-refs">{item.refs.map((ref) => <a href={prHref(ref)}>#{ref}</a>)}</div>}
-                      </div>
-                    </article>
-                  );
-                })}
-              </div>
-            </section>
-
-            {changeKinds.map((kind) => {
-              const items = release.changes[kind];
-              if (!items.length) return null;
-              const label = kindLabel(kind);
-              return (
-                <section id={kind} class="release-section release-change-section">
-                  <div class="release-section__head"><span>{sectionNum.get(kind)}</span><h2><span class="l-en">{label.en}</span><span class="l-zh">{label.zh}</span></h2></div>
-                  <div class="release-change-list">
-                    {items.map((item: ReleaseItem) => (
-                      <article>
-                        <h3><span class="l-en">{item.title.en}</span><span class="l-zh">{item.title.zh}</span></h3>
-                        <p><span class="l-en">{item.body.en}</span><span class="l-zh">{item.body.zh}</span></p>
-                        {item.refs?.length && <div class="release-refs">{item.refs.map((ref) => <a href={prHref(ref)}>#{ref}</a>)}</div>}
-                      </article>
-                    ))}
-                  </div>
-                </section>
-              );
-            })}
-          </>
-        )}
-
-        {release.upgrade.length > 0 && (
-          <section id="upgrade" class="release-section">
-            <div class="release-section__head"><span>{sectionNum.get('upgrade')}</span><h2><span class="l-en">Upgrade notes</span><span class="l-zh">升级提醒</span></h2></div>
-            <div class="release-notice-list">
-              {release.upgrade.map((item) => (
-                <article class:list={["release-notice", `release-notice--${item.level}`]}>
-                  <div class="release-notice__icon">{item.level === 'warning' ? '!' : 'i'}</div>
-                  <div>
-                    {item.targets?.length && <div class="release-item-targets">{item.targets.map((itemTarget) => {
-                      const label = surfaceLabel(itemTarget);
-                      return <span><span class="l-en">{label.en}</span><span class="l-zh">{label.zh}</span></span>;
-                    })}</div>}
-                    <h3><span class="l-en">{item.title.en}</span><span class="l-zh">{item.title.zh}</span></h3>
-                    <p><span class="l-en">{item.body.en}</span><span class="l-zh">{item.body.zh}</span></p>
-                    {item.refs?.length && <div class="release-refs">{item.refs.map((ref) => <a href={prHref(ref)}>#{ref}</a>)}</div>}
-                  </div>
-                </article>
-              ))}
-            </div>
-          </section>
-        )}
-
-        {release.risks.length > 0 && (
-          <section id="risks" class="release-section">
-            <div class="release-section__head"><span>{sectionNum.get('risks')}</span><h2><span class="l-en">Risk notes</span><span class="l-zh">风险提示</span></h2></div>
-            <div class="release-change-list">
-              {release.risks.map((item) => (
-                <article>
-                  {item.targets?.length && <div class="release-item-targets">{item.targets.map((itemTarget) => {
-                    const label = surfaceLabel(itemTarget);
-                    return <span><span class="l-en">{label.en}</span><span class="l-zh">{label.zh}</span></span>;
-                  })}</div>}
-                  <h3><span class="l-en">{item.title.en}</span><span class="l-zh">{item.title.zh}</span></h3>
-                  <p><span class="l-en">{item.body.en}</span><span class="l-zh">{item.body.zh}</span></p>
-                  {item.refs?.length && <div class="release-refs">{item.refs.map((ref) => <a href={prHref(ref)}>#{ref}</a>)}</div>}
-                </article>
-              ))}
-            </div>
-          </section>
-        )}
-
-        {thanked.length > 0 && (
-          <section id="thanks" class="release-section release-thanks">
-            <div class="release-section__head"><span>{sectionNum.get('thanks')}</span><h2><span class="l-en">Thanks</span><span class="l-zh">致谢</span></h2></div>
-            <p><span class="l-en">This release was shaped by:</span><span class="l-zh">感谢本版本的贡献者：</span></p>
-            <div>{thanked.map((name) => <a href={`https://github.com/${name}`}>@{name}</a>)}</div>
-          </section>
-        )}
-
-        </>}
-
-        <section id="download" class="release-section release-download">
-          <div>
-            <p class="release-download__kicker"><span class="l-en">Ready when you are</span><span class="l-zh">准备好即可升级</span></p>
-            <h2><span class="l-en">Ship with a safer Reasonix.</span><span class="l-zh">升级到更可靠的 Reasonix。</span></h2>
-          </div>
-          <div class="release-download__actions">
-          <a class="btn btn-dark" href={downloadHref}><span class="l-en">Download</span><span class="l-zh">下载</span></a>
-            <a class="release-compare" href={release.links.compare}><span class="l-en">{isStudio ? 'Source notes ↗' : 'Full comparison ↗'}</span><span class="l-zh">{isStudio ? '原始说明 ↗' : '完整差异 ↗'}</span></a>
-          </div>
-        </section>
-      </article>
-
-      <aside class="release-toc">
-        <p><span class="l-en">In v{release.version}</span><span class="l-zh">在 v{release.version} 中</span></p>
-        <nav>{tocItems.map((item) => <a href={`#${item.id}`}><span class="l-en">{item.en}</span><span class="l-zh">{item.zh}</span></a>)}</nav>
-      </aside>
-    </div>
-  </main>
-
-  <CommunityJoin />
-  <footer class="release-footer">
-    <a class="brand" href={`${base}/`}><img src={`${base}/logo.svg`} alt="" /><span>Reasonix</span></a>
-    <span>© 2026 Reasonix · MIT</span>
-    <a href={repo}>GitHub ↗</a>
-  </footer>
-
-  <script>
-    import '../scripts/changelog.js';
-  </script>
-</Base>

site/src/components/CommunityJoin.astro

@@ -1,71 +0,0 @@
----
-import { QQ_GROUP, DISCORD_URL, DOUYIN } from '../lib/community-links.mjs';
-
-const base = import.meta.env.BASE_URL.replace(/\/$/, '');
----
-<section class="join" aria-labelledby="join-title" data-community-join>
-  <div class="join-card">
-    <div class="join-head">
-      <h2 id="join-title"><span class="l-en">Join the community</span><span class="l-zh">加入社区</span></h2>
-      <p><span class="l-en">Get setup help, share workflows, and talk to other Reasonix users.</span><span class="l-zh">安装答疑、分享工作流，和其他 Reasonix 用户交流。</span></p>
-    </div>
-    <div class="join-body">
-      <div class="join-qq">
-        <a class="join-qr" href={QQ_GROUP.joinUrl} target="_blank" rel="noreferrer" data-qq-join>
-          <img src={`${base}${QQ_GROUP.qrPath}`} width="132" height="132" alt="QQ group QR code" loading="lazy" decoding="async" />
-        </a>
-        <div class="join-info">
-          <span class="join-label">QQ</span>
-          <strong class="join-name">{QQ_GROUP.name}</strong>
-          <span class="join-num"><span class="l-en">Group</span><span class="l-zh">群号</span> <code>{QQ_GROUP.number}</code></span>
-          <a class="join-link" href={QQ_GROUP.joinUrl} target="_blank" rel="noreferrer"><span class="l-en">Join the QQ group</span><span class="l-zh">加入 QQ 群</span> ↗</a>
-        </div>
-      </div>
-      <div class="join-discord">
-        <span class="join-label">Discord</span>
-        <span class="join-note"><span class="l-en">Bilingual server with help channels and feature ideas.</span><span class="l-zh">双语服务器，有答疑频道和功能讨论。</span></span>
-        <a class="join-link" href={DISCORD_URL} target="_blank" rel="noreferrer" data-discord-join><span class="l-en">Join Discord</span><span class="l-zh">加入 Discord</span> ↗</a>
-      </div>
-    </div>
-    <details class="join-minor" data-douyin>
-      <summary><span class="l-en">Douyin</span><span class="l-zh">抖音</span> · <span class="l-en">ID</span><span class="l-zh">抖音号</span> <code>{DOUYIN.id}</code> <span class="join-minor-name">{DOUYIN.name}</span></summary>
-      <img src={`${base}${DOUYIN.qrPath}`} width="120" height="179" alt="Douyin QR code" loading="lazy" decoding="async" />
-    </details>
-  </div>
-</section>
-
-<style>
-  .join { max-width: 1180px; margin: 0 auto; padding: 36px 40px 8px; }
-  .join-card {
-    background: var(--bg-soft); border: 1px solid var(--line); border-radius: var(--radius);
-    padding: 24px 28px; display: grid; grid-template-columns: minmax(0, 1fr) auto; gap: 28px 40px; align-items: center;
-  }
-  .join-head h2 { font-size: 18px; font-weight: 600; letter-spacing: -0.01em; color: var(--ink); margin: 0 0 6px; }
-  .join-head p { font-size: 13.5px; line-height: 1.6; color: var(--ink-2); margin: 0; max-width: 34ch; }
-  .join-body { display: flex; gap: 32px; align-items: center; flex-wrap: wrap; }
-  .join-qq { display: flex; gap: 18px; align-items: center; }
-  .join-qr { display: block; line-height: 0; border: 1px solid var(--line); border-radius: var(--radius-sm); overflow: hidden; background: #fff; flex: none; }
-  .join-qr img { width: 132px; height: 132px; display: block; }
-  .join-minor { grid-column: 1 / -1; font-size: 12.5px; color: var(--ink-3); }
-  .join-minor summary { cursor: pointer; width: fit-content; }
-  .join-minor code { font-family: var(--font-mono); }
-  .join-minor img { display: block; margin-top: 10px; border-radius: var(--radius-sm); border: 1px solid var(--line); }
-  .join-info, .join-discord { display: flex; flex-direction: column; gap: 5px; align-items: flex-start; font-size: 13.5px; color: var(--ink-2); }
-  .join-label { font-family: var(--font-mono); font-size: 11.5px; letter-spacing: 0.04em; text-transform: uppercase; color: var(--ink-3); }
-  .join-name { font-size: 15px; font-weight: 600; color: var(--ink); }
-  .join-num code { font-family: var(--font-mono); font-size: 14px; color: var(--ink); }
-  .join-note { max-width: 24ch; line-height: 1.5; }
-  .join-link { color: var(--accent-deep); font-weight: 600; text-decoration: none; margin-top: 4px; }
-  .join-link:hover { text-decoration: underline; }
-  @media (max-width: 900px) {
-    .join { padding: 28px 24px 4px; }
-    .join-card { grid-template-columns: 1fr; }
-    .join-head p { max-width: none; }
-  }
-  @media (max-width: 480px) {
-    .join { padding: 24px 16px 4px; }
-    .join-card { padding: 20px 18px; }
-    .join-qq { flex-direction: column; align-items: flex-start; }
-    .join-body { gap: 22px; }
-  }
-</style>

site/src/components/PasswordInput.astro

@@ -1,37 +0,0 @@
----
-interface Props {
-  id: string;
-  name?: string;
-  autocomplete: string;
-  minlength?: number;
-  required?: boolean;
-}
-
-const { id, name, autocomplete, minlength, required = false } = Astro.props;
----
-
-<div class="password-input">
-  <input
-    id={id}
-    name={name}
-    type="password"
-    autocomplete={autocomplete}
-    minlength={minlength}
-    required={required}
-  />
-  <button
-    type="button"
-    class="password-toggle"
-    data-password-toggle
-    aria-controls={id}
-    aria-pressed="false"
-    aria-label="Show password / 显示密码">
-    <svg class="password-eye-open" viewBox="0 0 24 24" aria-hidden="true">
-      <path d="M2.5 12s3.5-6 9.5-6 9.5 6 9.5 6-3.5 6-9.5 6-9.5-6-9.5-6Z" />
-      <circle cx="12" cy="12" r="2.7" />
-    </svg>
-    <svg class="password-eye-closed" viewBox="0 0 24 24" aria-hidden="true">
-      <path d="M3 3l18 18M10.6 6.2A10.9 10.9 0 0 1 12 6c6 0 9.5 6 9.5 6a17 17 0 0 1-2.1 2.7M6.2 6.2C3.8 7.8 2.5 12 2.5 12s3.5 6 9.5 6a9.8 9.8 0 0 0 3.2-.5M9.9 9.9a3 3 0 0 0 4.2 4.2" />
-    </svg>
-  </button>
-</div>

site/src/components/SiteHeader.astro

@@ -1,129 +0,0 @@
----
-type ActiveItem = 'features' | 'surfaces' | 'studio' | 'skills' | 'community' | 'docs' | 'changelog';
-
-const {
-  active,
-  scrolled = false,
-} = Astro.props as {
-  active?: ActiveItem;
-  scrolled?: boolean;
-};
-
-const base = import.meta.env.BASE_URL.replace(/\/$/, '');
-const repo = 'https://github.com/esengine/DeepSeek-Reasonix';
-const items: Array<{
-  id: ActiveItem;
-  href: string;
-  en: string;
-  zh: string;
-  secondary?: boolean;
-}> = [
-  { id: 'features', href: `${base}/#features`, en: 'Features', zh: '特性' },
-  { id: 'surfaces', href: `${base}/#surfaces`, en: 'Surfaces', zh: '使用形态', secondary: true },
-  { id: 'studio', href: `${base}/remote/`, en: 'Web Studio', zh: '网页版 Studio' },
-  { id: 'skills', href: `${base}/skills/`, en: 'Skills', zh: '技能市场' },
-  { id: 'community', href: `${base}/#community`, en: 'Community', zh: '社区', secondary: true },
-  { id: 'docs', href: `${base}/docs/`, en: 'Docs', zh: '文档' },
-  { id: 'changelog', href: `${base}/changelog/`, en: 'Changelog', zh: '更新日志' },
-];
----
-
-<header class:list={['nav', { scrolled }]}>
-  <div class="nav-inner">
-    <a class="brand" href={`${base}/`}>
-      <picture class="brand-picture">
-        <source media="(max-width: 400px)" srcset={`${base}/favicon.svg`} />
-        <img src={`${base}/logo.svg`} alt="Reasonix logo" />
-      </picture>
-    </a>
-    <nav class="nav-links" aria-label="Primary navigation">
-      {items.map((item) => (
-        <a
-          class:list={[{ here: active === item.id, 'nav-link--secondary': item.secondary }]}
-          href={item.href}
-          aria-current={active === item.id ? 'page' : undefined}
-        >
-          <span class="l-en">{item.en}</span>
-          <span class="l-zh">{item.zh}</span>
-        </a>
-      ))}
-    </nav>
-    <a
-      class="nav-github"
-      href={repo}
-      target="_blank"
-      rel="noreferrer"
-      aria-label="Reasonix GitHub repository"
-    >
-      <svg viewBox="0 0 24 24" aria-hidden="true">
-        <path fill="currentColor" d="M12 .7a12 12 0 0 0-3.8 23.4c.6.1.8-.3.8-.6v-2.3c-3.3.7-4-1.4-4-1.4-.5-1.4-1.3-1.8-1.3-1.8-1.1-.7.1-.7.1-.7 1.2.1 1.8 1.2 1.8 1.2 1 1.8 2.8 1.3 3.5 1 .1-.8.4-1.3.8-1.6-2.6-.3-5.4-1.3-5.4-5.9 0-1.3.5-2.4 1.2-3.2-.1-.3-.5-1.5.1-3.1 0 0 1-.3 3.3 1.2a11.5 11.5 0 0 1 6 0c2.3-1.5 3.3-1.2 3.3-1.2.7 1.6.3 2.8.1 3.1.8.8 1.2 1.9 1.2 3.2 0 4.6-2.8 5.6-5.4 5.9.4.4.8 1.1.8 2.2v3.3c0 .3.2.7.8.6A12 12 0 0 0 12 .7Z" />
-      </svg>
-      <span class="nav-github-label">GitHub</span>
-    </a>
-    <div class="lang-switch" role="group" aria-label="Language">
-      <button type="button" data-lang="en" class="active">EN</button>
-      <button type="button" data-lang="zh">中文</button>
-    </div>
-    <div class="theme-switch" role="group" aria-label="Theme">
-      <button type="button" data-theme="system" class="active" aria-label="System theme"><svg width="13" height="13" viewBox="0 0 24 24" fill="none" stroke="currentColor" stroke-width="2" stroke-linecap="round" stroke-linejoin="round" aria-hidden="true"><rect x="2" y="3" width="20" height="14" rx="2"/><line x1="8" y1="21" x2="16" y2="21"/><line x1="12" y1="17" x2="12" y2="21"/></svg></button>
-      <button type="button" data-theme="light" aria-label="Light theme"><svg width="13" height="13" viewBox="0 0 24 24" fill="none" stroke="currentColor" stroke-width="2" stroke-linecap="round" stroke-linejoin="round" aria-hidden="true"><circle cx="12" cy="12" r="4"/><line x1="12" y1="1" x2="12" y2="4"/><line x1="12" y1="20" x2="12" y2="23"/><line x1="4.2" y1="4.2" x2="6.3" y2="6.3"/><line x1="17.7" y1="17.7" x2="19.8" y2="19.8"/><line x1="1" y1="12" x2="4" y2="12"/><line x1="20" y1="12" x2="23" y2="12"/><line x1="4.2" y1="19.8" x2="6.3" y2="17.7"/><line x1="17.7" y1="6.3" x2="19.8" y2="4.2"/></svg></button>
-      <button type="button" data-theme="dark" aria-label="Dark theme"><svg width="13" height="13" viewBox="0 0 24 24" fill="none" stroke="currentColor" stroke-width="2" stroke-linecap="round" stroke-linejoin="round" aria-hidden="true"><path d="M21 12.8A9 9 0 1 1 11.2 3a7 7 0 0 0 9.8 9.8z"/></svg></button>
-    </div>
-    <span class="nav-acct nav-sign-in" data-account-slot aria-busy="true">
-      <a class="btn btn-ghost" href={`${base}/login/`}>
-        <span class="l-en">Sign in</span>
-        <span class="l-zh">登录</span>
-      </a>
-    </span>
-    <a class="btn btn-dark nav-install" href={`${base}/#start`}>
-      <span class="l-en">Install</span>
-      <span class="l-zh">安装</span>
-    </a>
-    <button
-      class="nav-menu-toggle"
-      type="button"
-      data-mobile-nav-toggle
-      aria-controls="site-mobile-nav"
-      aria-expanded="false"
-      aria-label="Open navigation"
-      title="Open navigation"
-    >
-      <svg viewBox="0 0 24 24" aria-hidden="true">
-        <path d="M4 6h16M4 12h16M4 18h16" />
-      </svg>
-    </button>
-  </div>
-  <div class="mobile-nav" id="site-mobile-nav" data-mobile-nav hidden>
-    <button class="mobile-nav-backdrop" type="button" data-mobile-nav-close aria-label="Close navigation"></button>
-    <aside class="mobile-nav-panel" role="dialog" aria-modal="true" aria-labelledby="site-mobile-nav-title">
-      <div class="mobile-nav-head">
-        <span id="site-mobile-nav-title"><span class="l-en">Navigation</span><span class="l-zh">导航</span></span>
-        <button class="mobile-nav-close" type="button" data-mobile-nav-close aria-label="Close navigation" title="Close navigation">
-          <svg viewBox="0 0 24 24" aria-hidden="true"><path d="m6 6 12 12M18 6 6 18" /></svg>
-        </button>
-      </div>
-      <nav class="mobile-nav-links" aria-label="Mobile primary navigation">
-        {items.map((item) => (
-          <a class:list={[{ here: active === item.id }]} href={item.href} aria-current={active === item.id ? 'page' : undefined}>
-            <span class="l-en">{item.en}</span>
-            <span class="l-zh">{item.zh}</span>
-          </a>
-        ))}
-      </nav>
-      <div class="mobile-nav-actions">
-        <a class="mobile-nav-github" href={repo} target="_blank" rel="noreferrer">
-          <svg viewBox="0 0 24 24" aria-hidden="true"><path fill="currentColor" d="M12 .7a12 12 0 0 0-3.8 23.4c.6.1.8-.3.8-.6v-2.3c-3.3.7-4-1.4-4-1.4-.5-1.4-1.3-1.8-1.3-1.8-1.1-.7.1-.7.1-.7 1.2.1 1.8 1.2 1.8 1.2 1 1.8 2.8 1.3 3.5 1 .1-.8.4-1.3.8-1.6-2.6-.3-5.4-1.3-5.4-5.9 0-1.3.5-2.4 1.2-3.2-.1-.3-.5-1.5.1-3.1 0 0 1-.3 3.3 1.2a11.5 11.5 0 0 1 6 0c2.3-1.5 3.3-1.2 3.3-1.2.7 1.6.3 2.8.1 3.1.8.8 1.2 1.9 1.2 3.2 0 4.6-2.8 5.6-5.4 5.9.4.4.8 1.1.8 2.2v3.3c0 .3.2.7.8.6A12 12 0 0 0 12 .7Z" /></svg>
-          GitHub
-        </a>
-        <span class="nav-acct" data-account-slot aria-busy="true">
-          <a class="btn btn-ghost" href={`${base}/login/`}><span class="l-en">Sign in</span><span class="l-zh">登录</span></a>
-        </span>
-        <a class="btn btn-dark" href={`${base}/#start`}><span class="l-en">Install</span><span class="l-zh">安装</span></a>
-      </div>
-    </aside>
-  </div>
-</header>
-
-<script>
-  import '../scripts/account-nav.js';
-</script>

site/src/components/SponsorSlot.astro

@@ -1,31 +0,0 @@
----
-const href = "https://www.packyapi.ai/register?aff=rIbQ";
-const rightCodeHref = "https://www.rightapi.ai/register?aff=e083bf73";
----
-<div class="foot-sponsor">
-  <span class="sp-label"><span class="l-en">Sponsor</span><span class="l-zh">赞助商</span></span>
-  <a class="sp-link" href={rightCodeHref} target="_blank" rel="sponsored noopener noreferrer" aria-label="Right Code">
-    <img src="/sponsor/rightcode.png" alt="" width="18" height="18" />
-    <span class="sp-name">Right Code</span>
-  </a>
-  <a class="sp-link" href={href} target="_blank" rel="sponsored noopener noreferrer" aria-label="PackyCode">
-    <svg viewBox="0 0 145.55 113.29" aria-hidden="true" focusable="false">
-      <path d="M144.68,38.49l-.06-.23c-.88-3.28-2.5-5.94-4.58-8.06.14,5.65-2.96,11.02-6.22,16.66l-.39.68c-2.26,3.91-4.66,7.94-6.57,11.1l-.86,1.38c-3.36,5.44-6.27,10.14-12.18,14.18-8.34,5.87-18.2,5.81-26.92,5.76-2.81-.02-5.48-.03-7.95.14l-.35.02c-3.22.06-5.96,1.57-8.17,4.49l-.14.18c-.86,1.06-1.7,2.26-2.58,3.54-3.43,4.92-7.69,11.04-16.17,12.42-4.37.86-9.98.84-14.94.83h-1.95c-.52,0-1.06,0-1.61,0-6.95,0-16.08-.89-21.94-6.55-.15-.15-.3-.3-.44-.45.5,4.73,2.33,8.64,5.44,11.65,5.86,5.66,14.98,6.55,21.94,6.55.55,0,1.09,0,1.61-.01h1.93c4.96.02,10.58.04,14.96-.83,8.48-1.37,12.74-7.5,16.17-12.42.88-1.27,1.72-2.48,2.58-3.54l.14-.18c2.21-2.92,4.95-4.43,8.17-4.49l.35-.02c2.47-.17,5.13-.16,7.95-.14,8.72.05,18.58.11,26.91-5.76,5.92-4.03,8.82-8.73,12.19-14.17l.86-1.39c1.91-3.15,4.3-7.18,6.57-11.09l.39-.69c3.81-6.6,7.41-12.84,5.86-19.57ZM120.9,23.02c-.28,0-.56,0-.83,0-9.68-.19-24.03-.09-35.57-.01l-2.04.02c-.93.01-1.82.02-2.67.03-8.36.08-14.4.13-23.33,3.82l-.27.12c-10.76,4.68-16.91,12.16-22.83,21.95-5.53,8.76-12.62,20.57-16.32,26.79-.41.69-.77,1.3-1.09,1.84l-.49.84c-1.49,2.53-3.23,5.49-4.21,8.95,3.98,1.9,8.52,2.65,12.71,2.91.27-.77.64-1.56,1.07-2.38.48-.94,1.05-1.9,1.63-2.89l.49-.84c.96-1.62,2.38-3.99,4.05-6.78,3.82-6.36,8.98-14.88,13.19-21.55l.07-.11c5.02-8.31,9.2-13.45,16.91-16.81l.11-.05c6.57-2.7,10.54-2.74,18.43-2.81.87-.01,1.78-.02,2.69-.03l1.99-.02c9.17-.06,20.13-.14,29.01-.07,2.26.01,4.39.04,6.32.08h.12s.11,0,.11,0c1.25-.01,2.91.11,4.61.46,1.03.22,2.08.52,3.05.93.21-.35.41-.71.62-1.06l.39-.68c1.92-3.33,3.79-6.57,4.97-9.82-4.08-1.92-8.7-2.76-12.89-2.82Z"/>
-      <path d="M115.07,11.81c-9.7-.19-24.07-.09-35.62-.01h-1.99c-.93.03-1.82.04-2.67.04-8.36.08-14.4.14-23.33,3.83l-.27.12c-10.76,4.67-16.91,12.16-22.83,21.95-6.13,9.71-14.19,23.21-17.41,28.63l-.5.84c-2.08,3.55-4.68,7.97-4.94,13.39v.2s0,.21,0,.21c.01.81.06,1.61.15,2.38.14.15.29.3.44.45,1.53,1.47,3.28,2.63,5.15,3.52,3.98,1.9,8.52,2.65,12.71,2.91,1.41.09,2.78.12,4.08.12.55,0,1.09-.01,1.61-.01h1.95c4.95.01,10.57.03,14.94-.83,8.48-1.38,12.74-7.5,16.17-12.42.88-1.28,1.72-2.48,2.58-3.54l.14-.18c2.21-2.92,4.95-4.44,8.17-4.49l.35-.02c2.47-.17,5.14-.16,7.95-.14,8.71.05,18.58.1,26.92-5.76,5.91-4.04,8.82-8.74,12.18-14.18l.86-1.39c1.74-2.86,3.87-6.45,5.95-10.03.21-.35.41-.71.62-1.06l.39-.68c1.92-3.33,3.79-6.57,4.97-9.82.82-2.26,1.31-4.53,1.25-6.84-5.18-5.29-13.22-7.25-19.97-7.19ZM122.56,40.37l-.39.67c-2.21,3.81-4.55,7.77-6.39,10.79l-.84,1.36c-3.01,4.87-4.83,7.81-8.48,10.29l-.1.07c-4.94,3.49-11.95,3.45-19.38,3.41-2.88-.02-5.87-.04-8.79.16-7.1.19-13.51,3.58-18.07,9.57-1.13,1.4-2.12,2.83-3.08,4.21-2.92,4.18-4.71,6.57-7.64,7.02l-.31.06c-3.09.63-8.28.61-12.45.6h-2.16c-3.85.07-7.01-.16-9.45-.69-2.24-.48-3.87-1.22-4.89-2.2-.66-.64-1.54-1.81-1.63-4.65.11-1.35.71-2.82,1.52-4.35.48-.94,1.05-1.9,1.63-2.89l.49-.84c3.17-5.33,11.19-18.75,17.24-28.33l.07-.11c5.02-8.32,9.2-13.45,16.92-16.81l.1-.05c6.57-2.7,10.54-2.74,18.43-2.82.87,0,1.78,0,2.69-.03h1.94c11.52-.09,25.86-.19,35.38,0h.23c1.25-.01,2.92.11,4.61.46,3.15.66,6.4,2.12,7.27,5.02.2,1.2-.89,3.62-2.27,6.18-.7,1.31-1.48,2.65-2.2,3.9ZM120.07,23.01c-9.68-.19-24.03-.09-35.57-.01l-2.04.02c-.93.01-1.82.02-2.67.03-8.36.08-14.4.13-23.33,3.82l-.27.12c-10.76,4.68-16.91,12.16-22.83,21.95-5.53,8.76-12.62,20.57-16.32,26.79-.78-.35-1.41-.77-1.9-1.24-.66-.64-1.54-1.81-1.63-4.65.18-2.18,1.62-4.64,3.15-7.25l.49-.83c3.17-5.32,11.18-18.73,17.24-28.33l.07-.12c5.02-8.31,9.2-13.45,16.92-16.81l.1-.04c6.57-2.7,10.54-2.74,18.43-2.82.87-.01,1.78-.01,2.69-.03h1.99c11.5-.09,25.82-.19,35.33,0h.23c3.57-.04,10.55,1.02,11.88,5.48.14.84-.35,2.27-1.13,3.93-.28,0-.56,0-.83,0Z"/>
-      <path d="M134.68,16.09l-.06-.23c-3.07-11.45-15.08-15.33-24.55-15.25-9.68-.19-24.03-.09-35.57-.01h-2.04c-.93.03-1.82.04-2.67.04-8.36.08-14.4.14-23.33,3.83l-.27.12c-10.76,4.67-16.91,12.16-22.83,21.95-6.14,9.73-14.2,23.22-17.41,28.62l-.49.85c-2.09,3.55-4.69,7.96-4.95,13.39v.2s0,.21,0,.21c.09,5.57,1.82,10.13,5.15,13.58.14.15.29.3.44.45,1.53,1.47,3.28,2.63,5.15,3.52,3.98,1.9,8.52,2.65,12.71,2.91,1.41.09,2.78.12,4.08.12.55,0,1.09-.01,1.61-.01h1.95c4.95.01,10.57.03,14.94-.83,8.48-1.38,12.74-7.5,16.17-12.42.88-1.28,1.72-2.48,2.58-3.54l.14-.18c2.21-2.92,4.95-4.44,8.17-4.49l.35-.02c2.47-.17,5.14-.16,7.95-.14,8.71.05,18.58.1,26.92-5.76,5.91-4.04,8.82-8.74,12.18-14.18l.86-1.39c1.74-2.86,3.87-6.45,5.95-10.03.21-.35.41-.71.62-1.06l.39-.68c1.92-3.33,3.79-6.57,4.97-9.82.82-2.26,1.31-4.53,1.25-6.84-.02-.96-.14-1.93-.36-2.91ZM119.76,25.27c-.7,1.31-1.48,2.65-2.2,3.9l-.39.67c-1.19,2.04-2.41,4.13-3.57,6.09-1.01,1.7-1.97,3.31-2.82,4.7l-.84,1.36c-3.01,4.87-4.83,7.81-8.48,10.29l-.1.07c-4.94,3.49-11.96,3.45-19.38,3.41-2.89-.02-5.87-.04-8.79.16-7.1.18-13.51,3.58-18.07,9.57-1.13,1.4-2.12,2.83-3.08,4.21-2.92,4.18-4.71,6.57-7.64,7.02l-.31.06c-3.09.63-8.27.61-12.45.6h-2.16c-3.85.07-7.01-.16-9.45-.69-1.16-.25-2.16-.57-2.99-.96-.78-.35-1.41-.77-1.9-1.24-.66-.64-1.54-1.81-1.63-4.65.18-2.18,1.62-4.64,3.15-7.25l.49-.83c3.17-5.32,11.18-18.73,17.24-28.33l.07-.12c5.02-8.31,9.2-13.45,16.92-16.81l.1-.04c6.57-2.7,10.54-2.74,18.43-2.82.87-.01,1.78-.01,2.69-.03h1.99c11.5-.09,25.82-.19,35.33,0h.23c3.57-.04,10.55,1.02,11.88,5.48.14.84-.35,2.27-1.13,3.93-.34.72-.73,1.48-1.14,2.25Z"/>
-    </svg>
-    <span class="sp-name">PackyCode</span>
-  </a>
-</div>
-<style>
-  .foot-sponsor {
-    max-width: 1180px; margin: 0 auto; padding: 14px 40px 22px;
-    display: flex; flex-wrap: wrap; align-items: center; gap: 8px 14px;
-    border-top: 1px solid var(--line);
-    font-size: 13px; color: var(--ink-3);
-  }
-  .sp-link { display: inline-flex; align-items: center; gap: 8px; color: var(--ink-2); text-decoration: none; font-weight: 600; transition: color 0.2s; }
-  .sp-link:hover { color: var(--ink); }
-  .sp-link img { height: 18px; width: 18px; display: block; }
-  .sp-link svg { height: 18px; width: auto; fill: currentColor; stroke: currentColor; stroke-miterlimit: 10; }
-</style>

site/src/components/StudioChangelog.astro

@@ -1,25 +0,0 @@
----
-import ChangelogPage from './ChangelogPage.astro';
-import Base from '../layouts/Base.astro';
-import SiteHeader from './SiteHeader.astro';
-import { releasePath, studioReleases } from '../data/releases';
-import '../styles/changelog.css';
-const latest = studioReleases[0];
-const base = import.meta.env.BASE_URL.replace(/\/$/, '');
----
-{latest ? <ChangelogPage release={latest} releases={studioReleases} canonical={new URL(`${base}${releasePath(latest.version)}`, Astro.site).href} /> : (
-  <Base title="Reasonix Studio release notes" titleEn="Reasonix Studio release notes" titleZh="Reasonix Studio 更新日志" description="Reasonix Studio release notes">
-    <SiteHeader active="changelog" scrolled />
-    <main class="release-stage">
-      <nav class="release-product-tabs" aria-label="Products">
-        <a href={`${base}/changelog/cli/`}><span class="l-en">CLI · 1.x (previous)</span><span class="l-zh">CLI · 1.x（上一代）</span></a>
-        <a href={`${base}/changelog/`} aria-current="page">Studio · 2.x</a>
-      </nav>
-      <article class="release-paper release-studio-empty">
-        <h1>Reasonix Studio</h1>
-        <p><span class="l-en">Website notes are awaiting review. Published releases remain available on GitHub.</span><span class="l-zh">网站发布说明正在等待审核。已发布版本可在 GitHub 查看。</span></p>
-        <a href="https://github.com/esengine/DeepSeek-Reasonix/releases">GitHub ↗</a>
-      </article>
-    </main>
-  </Base>
-)}

site/src/data/community.json

@@ -1,595 +0,0 @@
-{
-  "stars": 29222,
-  "mergedPrs": 2816,
-  "contributors": 98,
-  "list": [
-    {
-      "login": "SivanCola",
-      "avatar": "/av/SivanCola.webp",
-      "url": "https://github.com/SivanCola",
-      "c": 2311
-    },
-    {
-      "login": "esengine",
-      "avatar": "/av/esengine.webp",
-      "url": "https://github.com/esengine",
-      "c": 518
-    },
-    {
-      "login": "ttmouse",
-      "avatar": "/av/ttmouse.webp",
-      "url": "https://github.com/ttmouse",
-      "c": 121
-    },
-    {
-      "login": "lifu963",
-      "avatar": "/av/lifu963.webp",
-      "url": "https://github.com/lifu963",
-      "c": 105
-    },
-    {
-      "login": "HUQIANTAO",
-      "avatar": "/av/HUQIANTAO.webp",
-      "url": "https://github.com/HUQIANTAO",
-      "c": 74
-    },
-    {
-      "login": "GTC2080",
-      "avatar": "/av/GTC2080.webp",
-      "url": "https://github.com/GTC2080",
-      "c": 61
-    },
-    {
-      "login": "light-front-theory",
-      "avatar": "/av/light-front-theory.webp",
-      "url": "https://github.com/light-front-theory",
-      "c": 56
-    },
-    {
-      "login": "Li-Charles-One",
-      "avatar": "/av/Li-Charles-One.webp",
-      "url": "https://github.com/Li-Charles-One",
-      "c": 49
-    },
-    {
-      "login": "eghrhegpe",
-      "avatar": "/av/eghrhegpe.webp",
-      "url": "https://github.com/eghrhegpe",
-      "c": 28
-    },
-    {
-      "login": "CVEngineer66",
-      "avatar": "/av/CVEngineer66.webp",
-      "url": "https://github.com/CVEngineer66",
-      "c": 16
-    },
-    {
-      "login": "JesonChou",
-      "avatar": "/av/JesonChou.webp",
-      "url": "https://github.com/JesonChou",
-      "c": 15
-    },
-    {
-      "login": "HaoyueQin",
-      "avatar": "/av/HaoyueQin.webp",
-      "url": "https://github.com/HaoyueQin",
-      "c": 14
-    },
-    {
-      "login": "SuMuxi66",
-      "avatar": "/av/SuMuxi66.webp",
-      "url": "https://github.com/SuMuxi66",
-      "c": 11
-    },
-    {
-      "login": "lanshi17",
-      "avatar": "/av/lanshi17.webp",
-      "url": "https://github.com/lanshi17",
-      "c": 11
-    },
-    {
-      "login": "CnsMaple",
-      "avatar": "/av/CnsMaple.webp",
-      "url": "https://github.com/CnsMaple",
-      "c": 9
-    },
-    {
-      "login": "cyq1017",
-      "avatar": "/av/cyq1017.webp",
-      "url": "https://github.com/cyq1017",
-      "c": 9
-    },
-    {
-      "login": "ipanta",
-      "avatar": "/av/ipanta.webp",
-      "url": "https://github.com/ipanta",
-      "c": 8
-    },
-    {
-      "login": "XTLine",
-      "avatar": "/av/XTLine.webp",
-      "url": "https://github.com/XTLine",
-      "c": 8
-    },
-    {
-      "login": "YoungDan-hero",
-      "avatar": "/av/YoungDan-hero.webp",
-      "url": "https://github.com/YoungDan-hero",
-      "c": 8
-    },
-    {
-      "login": "paradoxSCH",
-      "avatar": "/av/paradoxSCH.webp",
-      "url": "https://github.com/paradoxSCH",
-      "c": 8
-    },
-    {
-      "login": "wade19990814-hue",
-      "avatar": "/av/wade19990814-hue.webp",
-      "url": "https://github.com/wade19990814-hue",
-      "c": 7
-    },
-    {
-      "login": "SauronSkywalker",
-      "avatar": "/av/SauronSkywalker.webp",
-      "url": "https://github.com/SauronSkywalker",
-      "c": 7
-    },
-    {
-      "login": "yizeyi18",
-      "avatar": "/av/yizeyi18.webp",
-      "url": "https://github.com/yizeyi18",
-      "c": 6
-    },
-    {
-      "login": "ashishexee",
-      "avatar": "/av/ashishexee.webp",
-      "url": "https://github.com/ashishexee",
-      "c": 6
-    },
-    {
-      "login": "erphenheimer",
-      "avatar": "/av/erphenheimer.webp",
-      "url": "https://github.com/erphenheimer",
-      "c": 6
-    },
-    {
-      "login": "Bernardxu123",
-      "avatar": "/av/Bernardxu123.webp",
-      "url": "https://github.com/Bernardxu123",
-      "c": 6
-    },
-    {
-      "login": "lizhengwu",
-      "avatar": "/av/lizhengwu.webp",
-      "url": "https://github.com/lizhengwu",
-      "c": 6
-    },
-    {
-      "login": "qiaone",
-      "avatar": "/av/qiaone.webp",
-      "url": "https://github.com/qiaone",
-      "c": 5
-    },
-    {
-      "login": "mchenziyi",
-      "avatar": "/av/mchenziyi.webp",
-      "url": "https://github.com/mchenziyi",
-      "c": 4
-    },
-    {
-      "login": "ferstar",
-      "avatar": "/av/ferstar.webp",
-      "url": "https://github.com/ferstar",
-      "c": 4
-    },
-    {
-      "login": "zhangsanouo",
-      "avatar": "/av/zhangsanouo.webp",
-      "url": "https://github.com/zhangsanouo",
-      "c": 4
-    },
-    {
-      "login": "par73e",
-      "avatar": "/av/par73e.webp",
-      "url": "https://github.com/par73e",
-      "c": 4
-    },
-    {
-      "login": "liaoyl830",
-      "avatar": "/av/liaoyl830.webp",
-      "url": "https://github.com/liaoyl830",
-      "c": 3
-    },
-    {
-      "login": "jiaxindeyang-a11y",
-      "avatar": "/av/jiaxindeyang-a11y.webp",
-      "url": "https://github.com/jiaxindeyang-a11y",
-      "c": 3
-    },
-    {
-      "login": "nostalgia296",
-      "avatar": "/av/nostalgia296.webp",
-      "url": "https://github.com/nostalgia296",
-      "c": 3
-    },
-    {
-      "login": "Diarica",
-      "avatar": "/av/Diarica.webp",
-      "url": "https://github.com/Diarica",
-      "c": 3
-    },
-    {
-      "login": "yekern",
-      "avatar": "/av/yekern.webp",
-      "url": "https://github.com/yekern",
-      "c": 3
-    },
-    {
-      "login": "maoxin1234",
-      "avatar": "/av/maoxin1234.webp",
-      "url": "https://github.com/maoxin1234",
-      "c": 3
-    },
-    {
-      "login": "lightfront",
-      "avatar": "/av/lightfront.webp",
-      "url": "https://github.com/lightfront",
-      "c": 3
-    },
-    {
-      "login": "ikelvingo",
-      "avatar": "/av/ikelvingo.webp",
-      "url": "https://github.com/ikelvingo",
-      "c": 3
-    },
-    {
-      "login": "ffff2004",
-      "avatar": "/av/ffff2004.webp",
-      "url": "https://github.com/ffff2004",
-      "c": 3
-    },
-    {
-      "login": "kekexunxun",
-      "avatar": "/av/kekexunxun.webp",
-      "url": "https://github.com/kekexunxun",
-      "c": 3
-    },
-    {
-      "login": "Tatlatat",
-      "avatar": "/av/Tatlatat.webp",
-      "url": "https://github.com/Tatlatat",
-      "c": 3
-    },
-    {
-      "login": "PaulDing98",
-      "avatar": "/av/PaulDing98.webp",
-      "url": "https://github.com/PaulDing98",
-      "c": 3
-    },
-    {
-      "login": "AtmoOmen",
-      "avatar": "/av/AtmoOmen.webp",
-      "url": "https://github.com/AtmoOmen",
-      "c": 3
-    },
-    {
-      "login": "billycat",
-      "avatar": "/av/billycat.webp",
-      "url": "https://github.com/billycat",
-      "c": 2
-    },
-    {
-      "login": "xianyu-sheng",
-      "avatar": "/av/xianyu-sheng.webp",
-      "url": "https://github.com/xianyu-sheng",
-      "c": 2
-    },
-    {
-      "login": "heshuimu",
-      "avatar": "/av/heshuimu.webp",
-      "url": "https://github.com/heshuimu",
-      "c": 2
-    },
-    {
-      "login": "drafish",
-      "avatar": "/av/drafish.webp",
-      "url": "https://github.com/drafish",
-      "c": 2
-    },
-    {
-      "login": "yhemeo613",
-      "avatar": "/av/yhemeo613.webp",
-      "url": "https://github.com/yhemeo613",
-      "c": 2
-    },
-    {
-      "login": "wqshan-cn",
-      "avatar": "/av/wqshan-cn.webp",
-      "url": "https://github.com/wqshan-cn",
-      "c": 2
-    },
-    {
-      "login": "warvyvr",
-      "avatar": "/av/warvyvr.webp",
-      "url": "https://github.com/warvyvr",
-      "c": 2
-    },
-    {
-      "login": "Xio-Shark",
-      "avatar": "/av/Xio-Shark.webp",
-      "url": "https://github.com/Xio-Shark",
-      "c": 2
-    },
-    {
-      "login": "LVGG",
-      "avatar": "/av/LVGG.webp",
-      "url": "https://github.com/LVGG",
-      "c": 2
-    },
-    {
-      "login": "assoyuan",
-      "avatar": "/av/assoyuan.webp",
-      "url": "https://github.com/assoyuan",
-      "c": 2
-    },
-    {
-      "login": "closss",
-      "avatar": "/av/closss.webp",
-      "url": "https://github.com/closss",
-      "c": 2
-    },
-    {
-      "login": "iysun",
-      "avatar": "/av/iysun.webp",
-      "url": "https://github.com/iysun",
-      "c": 2
-    },
-    {
-      "login": "whale-fall-ouo",
-      "avatar": "/av/whale-fall-ouo.webp",
-      "url": "https://github.com/whale-fall-ouo",
-      "c": 2
-    },
-    {
-      "login": "sudoviber",
-      "avatar": "/av/sudoviber.webp",
-      "url": "https://github.com/sudoviber",
-      "c": 2
-    },
-    {
-      "login": "qiukeren",
-      "avatar": "/av/qiukeren.webp",
-      "url": "https://github.com/qiukeren",
-      "c": 2
-    },
-    {
-      "login": "nanami7777777",
-      "avatar": "/av/nanami7777777.webp",
-      "url": "https://github.com/nanami7777777",
-      "c": 2
-    },
-    {
-      "login": "alxbnct",
-      "avatar": "/av/alxbnct.webp",
-      "url": "https://github.com/alxbnct",
-      "c": 1
-    },
-    {
-      "login": "Zhuocheng-Lang",
-      "avatar": "/av/Zhuocheng-Lang.webp",
-      "url": "https://github.com/Zhuocheng-Lang",
-      "c": 1
-    },
-    {
-      "login": "dcs02280653-collab",
-      "avatar": "/av/dcs02280653-collab.webp",
-      "url": "https://github.com/dcs02280653-collab",
-      "c": 1
-    },
-    {
-      "login": "dengbushi",
-      "avatar": "/av/dengbushi.webp",
-      "url": "https://github.com/dengbushi",
-      "c": 1
-    },
-    {
-      "login": "h4rk8s",
-      "avatar": "/av/h4rk8s.webp",
-      "url": "https://github.com/h4rk8s",
-      "c": 1
-    },
-    {
-      "login": "myipanta",
-      "avatar": "/av/myipanta.webp",
-      "url": "https://github.com/myipanta",
-      "c": 1
-    },
-    {
-      "login": "jackijianxa",
-      "avatar": "/av/jackijianxa.webp",
-      "url": "https://github.com/jackijianxa",
-      "c": 1
-    },
-    {
-      "login": "jbts6",
-      "avatar": "/av/jbts6.webp",
-      "url": "https://github.com/jbts6",
-      "c": 1
-    },
-    {
-      "login": "ji-tz",
-      "avatar": "/av/ji-tz.webp",
-      "url": "https://github.com/ji-tz",
-      "c": 1
-    },
-    {
-      "login": "kabaka9527",
-      "avatar": "/av/kabaka9527.webp",
-      "url": "https://github.com/kabaka9527",
-      "c": 1
-    },
-    {
-      "login": "9710willy",
-      "avatar": "/av/9710willy.webp",
-      "url": "https://github.com/9710willy",
-      "c": 1
-    },
-    {
-      "login": "onenewcode",
-      "avatar": "/av/onenewcode.webp",
-      "url": "https://github.com/onenewcode",
-      "c": 1
-    },
-    {
-      "login": "Ninot1Quyi",
-      "avatar": "/av/Ninot1Quyi.webp",
-      "url": "https://github.com/Ninot1Quyi",
-      "c": 1
-    },
-    {
-      "login": "xiaoshuai1024",
-      "avatar": "/av/xiaoshuai1024.webp",
-      "url": "https://github.com/xiaoshuai1024",
-      "c": 1
-    },
-    {
-      "login": "rixzkiye",
-      "avatar": "/av/rixzkiye.webp",
-      "url": "https://github.com/rixzkiye",
-      "c": 1
-    },
-    {
-      "login": "taibai233",
-      "avatar": "/av/taibai233.webp",
-      "url": "https://github.com/taibai233",
-      "c": 1
-    },
-    {
-      "login": "ying-hua",
-      "avatar": "/av/ying-hua.webp",
-      "url": "https://github.com/ying-hua",
-      "c": 1
-    },
-    {
-      "login": "yuanchenglu",
-      "avatar": "/av/yuanchenglu.webp",
-      "url": "https://github.com/yuanchenglu",
-      "c": 1
-    },
-    {
-      "login": "zhuguang-ZFG",
-      "avatar": "/av/zhuguang-ZFG.webp",
-      "url": "https://github.com/zhuguang-ZFG",
-      "c": 1
-    },
-    {
-      "login": "zlwu",
-      "avatar": "/av/zlwu.webp",
-      "url": "https://github.com/zlwu",
-      "c": 1
-    },
-    {
-      "login": "xinrenH",
-      "avatar": "/av/xinrenH.webp",
-      "url": "https://github.com/xinrenH",
-      "c": 1
-    },
-    {
-      "login": "zdjmrq",
-      "avatar": "/av/zdjmrq.webp",
-      "url": "https://github.com/zdjmrq",
-      "c": 1
-    },
-    {
-      "login": "i1j",
-      "avatar": "/av/i1j.webp",
-      "url": "https://github.com/i1j",
-      "c": 1
-    },
-    {
-      "login": "Abysstsuki",
-      "avatar": "/av/Abysstsuki.webp",
-      "url": "https://github.com/Abysstsuki",
-      "c": 1
-    },
-    {
-      "login": "themarchrain",
-      "avatar": "/av/themarchrain.webp",
-      "url": "https://github.com/themarchrain",
-      "c": 1
-    },
-    {
-      "login": "wudiandy",
-      "avatar": "/av/wudiandy.webp",
-      "url": "https://github.com/wudiandy",
-      "c": 1
-    },
-    {
-      "login": "EMEEEEMMMM",
-      "avatar": "/av/EMEEEEMMMM.webp",
-      "url": "https://github.com/EMEEEEMMMM",
-      "c": 1
-    },
-    {
-      "login": "HBLADEH",
-      "avatar": "/av/HBLADEH.webp",
-      "url": "https://github.com/HBLADEH",
-      "c": 1
-    },
-    {
-      "login": "HHHEEEWWW",
-      "avatar": "/av/HHHEEEWWW.webp",
-      "url": "https://github.com/HHHEEEWWW",
-      "c": 1
-    },
-    {
-      "login": "HorusJiang",
-      "avatar": "/av/HorusJiang.webp",
-      "url": "https://github.com/HorusJiang",
-      "c": 1
-    },
-    {
-      "login": "J3y0r",
-      "avatar": "/av/J3y0r.webp",
-      "url": "https://github.com/J3y0r",
-      "c": 1
-    },
-    {
-      "login": "JimmyDaddy",
-      "avatar": "/av/JimmyDaddy.webp",
-      "url": "https://github.com/JimmyDaddy",
-      "c": 1
-    },
-    {
-      "login": "LegGasai",
-      "avatar": "/av/LegGasai.webp",
-      "url": "https://github.com/LegGasai",
-      "c": 1
-    },
-    {
-      "login": "gcoder1991",
-      "avatar": "/av/gcoder1991.webp",
-      "url": "https://github.com/gcoder1991",
-      "c": 1
-    },
-    {
-      "login": "LouF666",
-      "avatar": "/av/LouF666.webp",
-      "url": "https://github.com/LouF666",
-      "c": 1
-    },
-    {
-      "login": "MaitreyeeDeshmukh",
-      "avatar": "/av/MaitreyeeDeshmukh.webp",
-      "url": "https://github.com/MaitreyeeDeshmukh",
-      "c": 1
-    },
-    {
-      "login": "ERroooooR",
-      "avatar": "/av/ERroooooR.webp",
-      "url": "https://github.com/ERroooooR",
-      "c": 1
-    }
-  ]
-}

site/src/data/contributors.json

@@ -1,48 +0,0 @@
-{
-  "stars": 20843,
-  "mergedPrs": 1779,
-  "contributors": 41,
-  "list": [
-    { "login": "esengine", "avatar": "https://avatars.githubusercontent.com/u/18465053", "url": "https://github.com/esengine", "c": 310 },
-    { "login": "SivanCola", "avatar": "https://avatars.githubusercontent.com/u/32437197", "url": "https://github.com/SivanCola", "c": 158 },
-    { "login": "HUQIANTAO", "avatar": "https://avatars.githubusercontent.com/u/58421104", "url": "https://github.com/HUQIANTAO", "c": 73 },
-    { "login": "GTC2080", "avatar": "https://avatars.githubusercontent.com/u/140309575", "url": "https://github.com/GTC2080", "c": 16 },
-    { "login": "CVEngineer66", "avatar": "https://avatars.githubusercontent.com/u/129239603", "url": "https://github.com/CVEngineer66", "c": 10 },
-    { "login": "Li-Charles-One", "avatar": "https://avatars.githubusercontent.com/u/258708209", "url": "https://github.com/Li-Charles-One", "c": 10 },
-    { "login": "SuMuxi66", "avatar": "https://avatars.githubusercontent.com/u/96619914", "url": "https://github.com/SuMuxi66", "c": 9 },
-    { "login": "lanshi17", "avatar": "https://avatars.githubusercontent.com/u/94416777", "url": "https://github.com/lanshi17", "c": 9 },
-    { "login": "paradoxSCH", "avatar": "https://avatars.githubusercontent.com/u/64133628", "url": "https://github.com/paradoxSCH", "c": 7 },
-    { "login": "wade19990814-hue", "avatar": "https://avatars.githubusercontent.com/u/280641290", "url": "https://github.com/wade19990814-hue", "c": 7 },
-    { "login": "YoungDan-hero", "avatar": "https://avatars.githubusercontent.com/u/66891653", "url": "https://github.com/YoungDan-hero", "c": 6 },
-    { "login": "lizhengwu", "avatar": "https://avatars.githubusercontent.com/u/38285521", "url": "https://github.com/lizhengwu", "c": 5 },
-    { "login": "Bernardxu123", "avatar": "https://avatars.githubusercontent.com/u/85089406", "url": "https://github.com/Bernardxu123", "c": 5 },
-    { "login": "CnsMaple", "avatar": "https://avatars.githubusercontent.com/u/92523839", "url": "https://github.com/CnsMaple", "c": 5 },
-    { "login": "AtmoOmen", "avatar": "https://avatars.githubusercontent.com/u/110901588", "url": "https://github.com/AtmoOmen", "c": 3 },
-    { "login": "Tatlatat", "avatar": "https://avatars.githubusercontent.com/u/269959336", "url": "https://github.com/Tatlatat", "c": 3 },
-    { "login": "kekexunxun", "avatar": "https://avatars.githubusercontent.com/u/44473551", "url": "https://github.com/kekexunxun", "c": 3 },
-    { "login": "jiaxindeyang-a11y", "avatar": "https://avatars.githubusercontent.com/u/278341870", "url": "https://github.com/jiaxindeyang-a11y", "c": 3 },
-    { "login": "nostalgia296", "avatar": "https://avatars.githubusercontent.com/u/207565364", "url": "https://github.com/nostalgia296", "c": 2 },
-    { "login": "yhemeo613", "avatar": "https://avatars.githubusercontent.com/u/138780695", "url": "https://github.com/yhemeo613", "c": 2 },
-    { "login": "ttmouse", "avatar": "https://avatars.githubusercontent.com/u/8982044", "url": "https://github.com/ttmouse", "c": 2 },
-    { "login": "iysun", "avatar": "https://avatars.githubusercontent.com/u/102790274", "url": "https://github.com/iysun", "c": 2 },
-    { "login": "closss", "avatar": "https://avatars.githubusercontent.com/u/106432698", "url": "https://github.com/closss", "c": 2 },
-    { "login": "XTLine", "avatar": "https://avatars.githubusercontent.com/u/140948646", "url": "https://github.com/XTLine", "c": 2 },
-    { "login": "LVGG", "avatar": "https://avatars.githubusercontent.com/u/20256205", "url": "https://github.com/LVGG", "c": 2 },
-    { "login": "xinrenH", "avatar": "https://avatars.githubusercontent.com/u/121069519", "url": "https://github.com/xinrenH", "c": 1 },
-    { "login": "lightfront", "avatar": "https://avatars.githubusercontent.com/u/13162893", "url": "https://github.com/lightfront", "c": 1 },
-    { "login": "lifu963", "avatar": "https://avatars.githubusercontent.com/u/56394323", "url": "https://github.com/lifu963", "c": 1 },
-    { "login": "kabaka9527", "avatar": "https://avatars.githubusercontent.com/u/142149737", "url": "https://github.com/kabaka9527", "c": 1 },
-    { "login": "dcs02280653-collab", "avatar": "https://avatars.githubusercontent.com/u/272150807", "url": "https://github.com/dcs02280653-collab", "c": 1 },
-    { "login": "ashishexee", "avatar": "https://avatars.githubusercontent.com/u/144021866", "url": "https://github.com/ashishexee", "c": 1 },
-    { "login": "alxbnct", "avatar": "https://avatars.githubusercontent.com/u/52067352", "url": "https://github.com/alxbnct", "c": 1 },
-    { "login": "PorunC", "avatar": "https://avatars.githubusercontent.com/u/63705582", "url": "https://github.com/PorunC", "c": 1 },
-    { "login": "ERroooooR", "avatar": "https://avatars.githubusercontent.com/u/121479279", "url": "https://github.com/ERroooooR", "c": 1 },
-    { "login": "LegGasai", "avatar": "https://avatars.githubusercontent.com/u/75920107", "url": "https://github.com/LegGasai", "c": 1 },
-    { "login": "JimmyDaddy", "avatar": "https://avatars.githubusercontent.com/u/16460813", "url": "https://github.com/JimmyDaddy", "c": 1 },
-    { "login": "drafish", "avatar": "https://avatars.githubusercontent.com/u/18543527", "url": "https://github.com/drafish", "c": 1 },
-    { "login": "HorusJiang", "avatar": "https://avatars.githubusercontent.com/u/29286555", "url": "https://github.com/HorusJiang", "c": 1 },
-    { "login": "HBLADEH", "avatar": "https://avatars.githubusercontent.com/u/27012363", "url": "https://github.com/HBLADEH", "c": 1 },
-    { "login": "Nahiyi", "avatar": "https://avatars.githubusercontent.com/u/163129774", "url": "https://github.com/Nahiyi", "c": 1 },
-    { "login": "i1j", "avatar": "https://avatars.githubusercontent.com/u/35729767", "url": "https://github.com/i1j", "c": 1 }
-  ]
-}

site/src/data/desktop-download.js

@@ -1,3 +0,0 @@
-// Set this temporarily to an exact vX.Y.Z only during a documented download
-// incident. The production default follows the current Stable manifest.
-export const desktopDownloadVersion = "";

site/src/data/releases.ts

@@ -1,91 +0,0 @@
-import source from './releases.json';
-import { readFileSync } from 'node:fs';
-import { resolve } from 'node:path';
-
-export type LocalizedText = { en: string; zh: string };
-export type ReleaseTarget = 'desktop' | 'cli' | 'site' | 'service';
-
-export type ReleaseItem = {
-  title: LocalizedText;
-  body: LocalizedText;
-  refs?: number[];
-  targets?: ReleaseTarget[];
-};
-
-export type ReleaseHighlight = ReleaseItem & {
-  kind: 'new' | 'improved' | 'fixed' | 'security';
-};
-
-export type ReleaseGuide = ReleaseItem & { href: string };
-export type ReleaseUpgrade = ReleaseItem & { level: 'info' | 'warning' };
-
-export type ReleaseRecord = {
-  version: string;
-  product?: 'cli' | 'studio';
-  sourceNotes?: { language: 'zh'; markdown: string; sha: string; path: string };
-  targetingVersion?: 1;
-  releaseId?: string;
-  baseVersion?: string;
-  date: string;
-  channel: 'stable' | 'prerelease';
-  status?: 'reviewed' | 'published';
-  candidateSha?: string;
-  previousRelease?: string;
-  builds?: { cli: string; desktop: string; npm: string };
-  title: LocalizedText;
-  summary: LocalizedText;
-  surfaces: string[];
-  guides: ReleaseGuide[];
-  highlights: ReleaseHighlight[];
-  changes: { new: ReleaseItem[]; improved: ReleaseItem[]; fixed: ReleaseItem[] };
-  upgrade: ReleaseUpgrade[];
-  risks: ReleaseItem[];
-  contributors: string[];
-  links: { github: string; compare: string; download: string };
-};
-
-export const releaseCatalog = source as { schemaVersion: number; releases: ReleaseRecord[] };
-export const allReleases = releaseCatalog.releases;
-
-let publishedIds = new Set<string>();
-try {
-  const generated = JSON.parse(
-    readFileSync(resolve(process.cwd(), '.generated/publications.json'), 'utf8'),
-  ) as { publications?: string[] };
-  publishedIds = new Set(generated.publications ?? []);
-} catch {
-  // Before prebuild, preserve legacy entries and fail closed for reviewed
-  // releases that require a successful all-surface publication marker.
-}
-
-export const publishedReleases = allReleases.filter(
-  (release) => !release.status || release.status === 'published' || publishedIds.has(release.version),
-);
-// Public navigation contains official releases only. Historical prereleases
-// remain addressable by their exact version URL for compatibility.
-export const studioReleases = publishedReleases.filter((release) => release.product === 'studio');
-export const releases = publishedReleases.filter((release) => release.product !== 'studio' && release.channel === 'stable');
-export const stableReleases = releases;
-export const previewReleases = publishedReleases.filter((release) => release.channel === 'prerelease');
-export const latestStableRelease = stableReleases[0];
-export const latestPreviewRelease = previewReleases[0];
-export const latestRelease = latestStableRelease;
-
-export function releasePath(version: string): string {
-  return `/changelog/v${version}/`;
-}
-
-export function releaseContentItems(release: ReleaseRecord): ReleaseItem[] {
-  return [
-    ...release.highlights,
-    ...release.changes.new,
-    ...release.changes.improved,
-    ...release.changes.fixed,
-    ...release.upgrade,
-    ...release.risks,
-  ];
-}
-
-export function releaseTargetCount(release: ReleaseRecord, target: ReleaseTarget): number {
-  return releaseContentItems(release).filter((item) => item.targets?.includes(target)).length;
-}

site/src/layouts/Account.astro

@@ -1,47 +0,0 @@
----
-import Base from './Base.astro';
-import CommunityJoin from '../components/CommunityJoin.astro';
-import SponsorSlot from '../components/SponsorSlot.astro';
-const base = import.meta.env.BASE_URL.replace(/\/$/, '');
-const repo = 'https://github.com/esengine/DeepSeek-Reasonix';
-const { title, description, titleEn, titleZh, wide, dash } = Astro.props;
----
-<Base title={title} description={description} titleEn={titleEn} titleZh={titleZh}>
-  <Fragment slot="head">
-    <meta name="robots" content="noindex" />
-    <link rel="preconnect" href="https://id.reasonix.io" crossorigin="anonymous" />
-    <link rel="preconnect" href="https://studio.reasonix.io" crossorigin="anonymous" />
-    <link rel="dns-prefetch" href="//id.reasonix.io" />
-    <link rel="dns-prefetch" href="//studio.reasonix.io" />
-  </Fragment>
-  <header class="nav auth-nav scrolled">
-    <div class="nav-inner">
-      <a class="brand" href={`${base}/`}><img src={`${base}/logo.svg`} alt="Reasonix logo" /><span>Reasonix</span></a>
-      <div class="lang-switch" role="group" aria-label="Language" style="margin-left:auto">
-        <button type="button" data-lang="en" class="active">EN</button>
-        <button type="button" data-lang="zh">中文</button>
-      </div>
-    </div>
-  </header>
-
-  <main class="auth-main">
-    <div class={dash ? 'auth-card wide dash' : wide ? 'auth-card wide' : 'auth-card'}>
-      <slot />
-    </div>
-  </main>
-
-  <footer>
-    <CommunityJoin />
-    <div class="foot-sub" style="border-top:none">
-      <a class="brand" href={`${base}/`}><img src={`${base}/logo.svg`} alt="Reasonix logo" /><span>Reasonix</span></a>
-      <nav class="foot-links">
-        <a href={`${base}/`}><span class="l-en">Home</span><span class="l-zh">首页</span></a>
-        <a href={`${base}/docs/`}><span class="l-en">Docs</span><span class="l-zh">文档</span></a>
-        <a href={repo}>GitHub</a>
-      </nav>
-    </div>
-    <SponsorSlot />
-  </footer>
-
-  <script>import '../scripts/auth.js';</script>
-</Base>

site/src/layouts/Base.astro

@@ -1,47 +0,0 @@
----
-import '../styles/global.css';
-const base = import.meta.env.BASE_URL.replace(/\/$/, '');
-const { title, description, titleEn, titleZh, canonical: canonicalOverride, noindex = false } = Astro.props;
-const canonical = canonicalOverride ?? new URL(Astro.url.pathname, Astro.site).href;
-const ogImage = new URL(`${base}/og.png`, Astro.site).href;
----
-<!doctype html>
-<html lang="en">
-<head>
-  <meta charset="utf-8" />
-  <meta name="viewport" content="width=device-width, initial-scale=1" />
-  <title>{title}</title>
-  <meta name="description" content={description} />
-  {noindex && <meta name="robots" content="noindex, nofollow" />}
-  <link rel="canonical" href={canonical} />
-  <link rel="icon" href={`${base}/favicon.svg`} type="image/svg+xml" />
-  <link rel="sitemap" href={`${base}/sitemap-index.xml`} />
-  <meta name="theme-color" content="#ffffff" />
-  <script is:inline>
-    (function(){try{var p=localStorage.getItem("reasonix-theme")||"system";var d=p==="dark"||(p==="system"&&window.matchMedia("(prefers-color-scheme: dark)").matches);document.documentElement.dataset.theme=d?"dark":"light";var m=document.querySelector('meta[name="theme-color"]');if(m)m.content=d?"#1f232b":"#ffffff";}catch(e){}})();
-  </script>
-  <meta property="og:type" content="website" />
-  <meta property="og:site_name" content="Reasonix" />
-  <meta property="og:title" content={title} />
-  <meta property="og:description" content={description} />
-  <meta property="og:url" content={canonical} />
-  <meta property="og:image" content={ogImage} />
-  <meta property="og:image:width" content="1200" />
-  <meta property="og:image:height" content="630" />
-  <meta property="og:image:alt" content="Reasonix — an open-source coding agent for your terminal, desktop, browser and editor" />
-  <meta property="og:locale" content="en_US" />
-  <meta property="og:locale:alternate" content="zh_CN" />
-  <meta name="twitter:card" content="summary_large_image" />
-  <meta name="twitter:title" content={title} />
-  <meta name="twitter:description" content={description} />
-  <meta name="twitter:image" content={ogImage} />
-  <slot name="head" />
-</head>
-<body data-motion="rich" data-lang="en" data-title-en={titleEn ?? title} data-title-zh={titleZh ?? title}>
-  <slot />
-  <script>
-    import '../scripts/site.js';
-    import '../scripts/fx.js';
-  </script>
-</body>
-</html>

site/src/layouts/Community.astro

@@ -1,105 +0,0 @@
----
-import "../styles/community.css";
-import CommunityJoin from "../components/CommunityJoin.astro";
-const { title, description, active } = Astro.props;
-const canonical = new URL(Astro.url.pathname, Astro.site).href;
----
-<!doctype html>
-<html lang="en">
-<head>
-  <meta charset="utf-8" />
-  <meta name="viewport" content="width=device-width, initial-scale=1" />
-  <title>{title}</title>
-  <meta name="description" content={description} />
-  <link rel="canonical" href={canonical} />
-  <link rel="icon" href="/favicon.svg" type="image/svg+xml" />
-  <meta name="theme-color" content="#ffffff" />
-  <script is:inline>
-(function(){try{var p=localStorage.getItem("reasonix-theme")||"system";var d=p==="dark"||(p==="system"&&window.matchMedia("(prefers-color-scheme: dark)").matches);document.documentElement.dataset.theme=d?"dark":"light";var m=document.querySelector('meta[name="theme-color"]');if(m)m.content=d?"#1f232b":"#ffffff";}catch(e){}})();
-</script>
-  <meta property="og:type" content="website" />
-  <meta property="og:site_name" content="Reasonix Community" />
-  <meta property="og:title" content={title} />
-  <meta property="og:description" content={description} />
-</head>
-<body data-lang="en">
-  <header class="nav">
-    <div class="nav-inner">
-      <a class="brand" href="/community/" aria-label="Reasonix Community"><span class="mark" aria-hidden="true">R</span><span class="brand-name">Reasonix</span><span class="ctag"><span class="l-en">Community</span><span class="l-zh">社区</span></span></a>
-      <nav class="nav-links">
-        <a class={active === "discussions" ? "here" : ""} href="/community/"><span class="l-en">Discussions</span><span class="l-zh">讨论</span></a>
-        <a href="/community/?category=skills"><span class="l-en">Skills</span><span class="l-zh">技能</span></a>
-        <a href="/community/?category=show"><span class="l-en">Showcase</span><span class="l-zh">展示</span></a>
-        <a href="/docs/"><span class="l-en">Docs ↗</span><span class="l-zh">文档 ↗</span></a>
-      </nav>
-      <div class="nav-right">
-        <div class="lang-switch" role="group" aria-label="Language">
-          <button type="button" data-lang="en" class="active">EN</button>
-          <button type="button" data-lang="zh">中文</button>
-        </div>
-        <div class="theme-switch" role="group" aria-label="Theme">
-          <button type="button" data-theme="system" class="active" aria-label="System theme"><svg width="13" height="13" viewBox="0 0 24 24" fill="none" stroke="currentColor" stroke-width="2" stroke-linecap="round" stroke-linejoin="round" aria-hidden="true"><rect x="2" y="3" width="20" height="14" rx="2"/><line x1="8" y1="21" x2="16" y2="21"/><line x1="12" y1="17" x2="12" y2="21"/></svg></button>
-          <button type="button" data-theme="light" aria-label="Light theme"><svg width="13" height="13" viewBox="0 0 24 24" fill="none" stroke="currentColor" stroke-width="2" stroke-linecap="round" stroke-linejoin="round" aria-hidden="true"><circle cx="12" cy="12" r="4"/><line x1="12" y1="1" x2="12" y2="4"/><line x1="12" y1="20" x2="12" y2="23"/><line x1="4.2" y1="4.2" x2="6.3" y2="6.3"/><line x1="17.7" y1="17.7" x2="19.8" y2="19.8"/><line x1="1" y1="12" x2="4" y2="12"/><line x1="20" y1="12" x2="23" y2="12"/><line x1="4.2" y1="19.8" x2="6.3" y2="17.7"/><line x1="17.7" y1="6.3" x2="19.8" y2="4.2"/></svg></button>
-          <button type="button" data-theme="dark" aria-label="Dark theme"><svg width="13" height="13" viewBox="0 0 24 24" fill="none" stroke="currentColor" stroke-width="2" stroke-linecap="round" stroke-linejoin="round" aria-hidden="true"><path d="M21 12.8A9 9 0 1 1 11.2 3a7 7 0 0 0 9.8 9.8z"/></svg></button>
-        </div>
-        <span id="nav-account"></span>
-      </div>
-      <button
-        class="nav-menu-toggle"
-        type="button"
-        data-mobile-nav-toggle
-        aria-controls="community-mobile-nav"
-        aria-expanded="false"
-        aria-label="Open navigation"
-        title="Open navigation"
-      >
-        <svg viewBox="0 0 24 24" aria-hidden="true"><path d="M4 6h16M4 12h16M4 18h16" /></svg>
-      </button>
-    </div>
-    <div class="mobile-nav" id="community-mobile-nav" data-mobile-nav hidden>
-      <button class="mobile-nav-backdrop" type="button" data-mobile-nav-close aria-label="Close navigation"></button>
-      <aside class="mobile-nav-panel" role="dialog" aria-modal="true" aria-labelledby="community-mobile-nav-title">
-        <div class="mobile-nav-head">
-          <span id="community-mobile-nav-title"><span class="l-en">Navigation</span><span class="l-zh">导航</span></span>
-          <button class="mobile-nav-close" type="button" data-mobile-nav-close aria-label="Close navigation" title="Close navigation">
-            <svg viewBox="0 0 24 24" aria-hidden="true"><path d="m6 6 12 12M18 6 6 18" /></svg>
-          </button>
-        </div>
-        <nav class="mobile-nav-links" aria-label="Mobile community navigation">
-          <a class:list={[{ here: active === "discussions" }]} href="/community/"><span class="l-en">Discussions</span><span class="l-zh">讨论</span></a>
-          <a href="/community/?category=skills"><span class="l-en">Skills</span><span class="l-zh">技能</span></a>
-          <a href="/community/?category=show"><span class="l-en">Showcase</span><span class="l-zh">展示</span></a>
-          <a href="/docs/"><span class="l-en">Docs ↗</span><span class="l-zh">文档 ↗</span></a>
-        </nav>
-        <div class="mobile-nav-actions">
-          <a class="mobile-nav-github" href="https://github.com/esengine/DeepSeek-Reasonix" target="_blank" rel="noreferrer">
-            <svg viewBox="0 0 24 24" aria-hidden="true"><path fill="currentColor" d="M12 .7a12 12 0 0 0-3.8 23.4c.6.1.8-.3.8-.6v-2.3c-3.3.7-4-1.4-4-1.4-.5-1.4-1.3-1.8-1.3-1.8-1.1-.7.1-.7.1-.7 1.2.1 1.8 1.2 1.8 1.2 1 1.8 2.8 1.3 3.5 1 .1-.8.4-1.3.8-1.6-2.6-.3-5.4-1.3-5.4-5.9 0-1.3.5-2.4 1.2-3.2-.1-.3-.5-1.5.1-3.1 0 0 1-.3 3.3 1.2a11.5 11.5 0 0 1 6 0c2.3-1.5 3.3-1.2 3.3-1.2.7 1.6.3 2.8.1 3.1.8.8 1.2 1.9 1.2 3.2 0 4.6-2.8 5.6-5.4 5.9.4.4.8 1.1.8 2.2v3.3c0 .3.2.7.8.6A12 12 0 0 0 12 .7Z" /></svg>
-            GitHub
-          </a>
-          <span id="mobile-nav-account"></span>
-          <a class="btn btn-primary" href="/community/new/"><span class="l-en">New topic</span><span class="l-zh">发起话题</span></a>
-        </div>
-      </aside>
-    </div>
-  </header>
-
-  <main>
-    <slot />
-  </main>
-
-  <CommunityJoin />
-  <footer class="foot">
-    <div class="foot-inner">
-      <a class="brand" href="/"><span class="mark">R</span>Reasonix</a>
-      <span><span class="l-en">© 2026 · MIT · built to be left running.</span><span class="l-zh">© 2026 · MIT 许可 · 为常驻运行而生。</span></span>
-      <nav class="links">
-        <a href="/community/guidelines/"><span class="l-en">Guidelines</span><span class="l-zh">规范</span></a>
-        <a href="/docs/"><span class="l-en">Docs</span><span class="l-zh">文档</span></a>
-        <a href="https://github.com/esengine/DeepSeek-Reasonix">GitHub</a>
-      </nav>
-    </div>
-  </footer>
-
-  <script>import "../scripts/community.js";</script>
-</body>
-</html>

site/src/lib/account-overview.mjs

@@ -1,115 +0,0 @@
-const TIERS = [
-  ["New", "新成员"],
-  ["Basic", "基础"],
-  ["Member", "成员"],
-  ["Regular", "常客"],
-  ["Leader", "领袖"],
-];
-
-// [en, zh] for a forum trust level; a value outside the known range reads as unknown.
-export function trustName(level) {
-  return Number.isInteger(level) && level >= 0 && level < TIERS.length ? TIERS[level] : null;
-}
-
-export function deviceSummary(payload) {
-  const list = Array.isArray(payload?.devices) ? payload.devices.filter((d) => d && !d.revokedAt) : [];
-  return { total: list.length, online: payload?.presenceAvailable === false ? null : list.filter((d) => d.online === true).length };
-}
-
-export function backupCount(payload) {
-  return Array.isArray(payload?.backups) ? payload.backups.length : null;
-}
-
-const whole = (n) => (Number.isFinite(n) && n >= 0 ? Math.floor(n) : null);
-
-// Only well-formed numbers reach the page; anything else renders as "—".
-export function forumSummary(payload) {
-  const m = payload?.member;
-  const s = payload?.stats;
-  if (!m || !s) return null;
-  return {
-    trust: Number.isInteger(m.trust) ? m.trust : null,
-    role: m.role === "admin" || m.role === "moderator" ? m.role : "member",
-    dailyPostCap: whole(m.dailyPostCap),
-    canPostLinks: m.canPostLinks === true,
-    silencedUntil: typeof m.silencedUntil === "string" ? m.silencedUntil : null,
-    topics: whole(s.topics),
-    posts: whole(s.posts),
-    likesReceived: whole(s.likesReceived),
-    solved: whole(s.solved),
-    recent: Array.isArray(payload.recent)
-      ? payload.recent.filter((r) => Number.isInteger(r?.id) && typeof r.title === "string").slice(0, 5)
-      : [],
-  };
-}
-
-export function initials(handle) {
-  return String(handle || "?").replace(/[^a-zA-Z0-9]/g, "").slice(0, 2).toUpperCase() || "?";
-}
-
-// "empty" is only for an answered request whose counts are all zero; a failed or
-// malformed answer is "unavailable", never a claim that the member has not taken part.
-export function forumState(summary) {
-  if (!summary) return "unavailable";
-  return summary.topics === 0 && summary.posts === 0 ? "empty" : "active";
-}
-
-const LEVELS = [
-  ["New seed", "新种"],
-  ["Sprout", "萌芽"],
-  ["Seedling", "幼苗"],
-  ["Sapling", "小树"],
-  ["Bloom", "繁花"],
-  ["Canopy", "成荫"],
-  ["Grove", "共林"],
-];
-
-// [en, zh] for a feedback level, null outside the known ladder.
-export function levelName(level) {
-  return Number.isInteger(level) && level >= 0 && level < LEVELS.length ? LEVELS[level] : null;
-}
-
-const TRUST = new Set(["active", "legacy_active", "lapsed", "revoked", "none"]);
-const count = (n) => (Number.isInteger(n) && n >= 0 ? n : null);
-
-function standing(p) {
-  if (!p || count(p.level) === null || count(p.adoptedCount) === null || !TRUST.has(p.trustState)) return null;
-  const limits = p.effectiveLimits ?? {};
-  return {
-    level: p.level,
-    adopted: p.adoptedCount,
-    base: count(p.currentThreshold),
-    nextLevel: count(p.nextLevel),
-    nextThreshold: count(p.nextThreshold),
-    remaining: count(p.remaining),
-    trustState: p.trustState,
-    trustExpiresAt: typeof p.trustExpiresAt === "string" ? p.trustExpiresAt : null,
-    perHour: count(limits.reportsPerHour),
-    perDay: count(limits.reportsPerDay),
-    repliesPerHour: count(limits.repliesPerHour),
-  };
-}
-
-// Share of the way to the next level, or null at the top or when the thresholds do not hold together.
-export function levelProgress(s) {
-  if (!s || s.nextThreshold === null || s.base === null || s.nextThreshold <= s.base) return null;
-  return Math.min(1, Math.max(0, (s.adopted - s.base) / (s.nextThreshold - s.base)));
-}
-
-// "unavailable" is a failed or malformed answer; "none" is an answered request with no linked install.
-export function feedbackSummary(payload) {
-  if (!payload || !Array.isArray(payload.installs) || !Array.isArray(payload.items)) return { state: "unavailable" };
-  const installs = payload.installs.map((i) => ({ id: String(i?.id ?? ""), linkedAt: i?.linkedAt, standing: standing(i?.profile) })).filter((i) => /^[0-9a-f]{12}$/.test(i.id));
-  if (installs.length === 0) return { state: "none" };
-  const items = payload.items
-    .filter((it) => typeof it?.receipt === "string" && typeof it.titleSnippet === "string")
-    .slice(0, 5)
-    .map((it) => ({
-      receipt: it.receipt,
-      title: it.titleSnippet,
-      status: typeof it.status === "string" ? it.status : "",
-      issueNumber: count(it.issueNumber),
-      version: typeof it.resolvedVersion === "string" && /^[0-9A-Za-z][0-9A-Za-z.+-]{0,31}$/.test(it.resolvedVersion) ? it.resolvedVersion : null,
-    }));
-  return { state: "linked", headline: standing(payload.profile), installs, items };
-}

site/src/lib/board.mjs

@@ -1,63 +0,0 @@
-// The contributor board's pure parts: what a name may look like on the page, and the
-// rows built from the public answer. Names come from users, so every one is cleaned
-// and set as text; nothing here makes markup.
-
-export const NAME_LIMIT = 60;
-
-// Bidirectional controls and other invisible formatting characters can make a name
-// read as something else (a right-to-left override flips what follows it), so none
-// reaches the page.
-const INVISIBLE = /[\u0000-\u001f\u007f-\u009f­؜᠎​-‏‪-‮⁠--]/gu;
-
-export function cleanName(raw) {
-  const text = String(raw ?? "").normalize("NFKC").replace(/[\t\n\r]+/g, " ").replace(INVISIBLE, "").replace(/\s+/g, " ").trim();
-  const chars = [...text];
-  return chars.length > NAME_LIMIT ? chars.slice(0, NAME_LIMIT - 1).join("") + "…" : text;
-}
-
-export function newestFirst(a, b) {
-  const pa = a.replace(/^v/, "").split(".").map(Number);
-  const pb = b.replace(/^v/, "").split(".").map(Number);
-  for (let i = 0; i < 3; i++) if ((pa[i] ?? 0) !== (pb[i] ?? 0)) return (pb[i] ?? 0) - (pa[i] ?? 0);
-  return 0;
-}
-
-export function versionsOf(entries) {
-  return [...new Set(entries.flatMap((e) => e.releases.map((r) => r.version)))].sort(newestFirst);
-}
-
-// One row as plain parts, whatever the document is: the caller sets each as text.
-export function rowOf(entry, ranked) {
-  return {
-    rank: ranked ? String(entry.rank ?? "") : null,
-    name: cleanName(entry.displayName),
-    credits: Number.isFinite(entry.credits) ? entry.credits : 0,
-    chips: ranked ? [] : (entry.releases ?? []).slice(0, 3).map((r) => (r.count > 1 ? `${r.version} ×${r.count}` : r.version)),
-  };
-}
-
-// buildRow draws a row with the given document. It writes only through
-// textContent, so a name can never become markup.
-export function buildRow(entry, ranked, doc) {
-  const row = rowOf(entry, ranked);
-  const li = doc.createElement("li");
-  const part = (cls, text) => {
-    const el = doc.createElement("span");
-    el.className = cls;
-    el.textContent = text;
-    return el;
-  };
-  if (row.rank !== null) li.append(part("board-rank", row.rank));
-  li.append(part("board-name", row.name));
-  const credits = doc.createElement("span");
-  credits.className = "board-credits";
-  credits.append(part("l-en", `${row.credits} adopted`), part("l-zh", `${row.credits} 条被采纳`));
-  li.append(credits);
-  if (!ranked) {
-    const where = doc.createElement("span");
-    where.className = "board-where";
-    for (const chip of row.chips) where.append(part("board-chip", chip));
-    li.append(where);
-  }
-  return li;
-}

site/src/lib/community-links.mjs

@@ -1,14 +0,0 @@
-export const QQ_GROUP = {
-  name: 'DeepSeek-Reasonix官方群',
-  number: '1093562660',
-  joinUrl: 'https://qm.qq.com/q/i59b0z2R8s',
-  qrPath: '/community/qq-group.svg',
-};
-
-export const DISCORD_URL = 'https://discord.gg/XF78rEME2D';
-
-export const DOUYIN = {
-  name: '做游戏的小鱼',
-  id: '22703872788',
-  qrPath: '/community/douyin.png',
-};

site/src/lib/forum-mirror.mjs

@@ -1,27 +0,0 @@
-// A forum thread with source "github" mirrors a GitHub Discussion, and one with source "feedback" mirrors an in-app report's issue: its text
-// is GitHub's, so the page shows where it lives instead of a reply box.
-export const DISCUSSIONS_URL = "https://github.com/esengine/DeepSeek-Reasonix/discussions";
-export const ISSUES_URL = "https://github.com/esengine/DeepSeek-Reasonix/issues";
-
-export function mirrorOf(topic) {
-  if (!topic || (topic.source !== "github" && topic.source !== "feedback")) return null;
-  const feedback = topic.source === "feedback";
-  const base = feedback ? ISSUES_URL : DISCUSSIONS_URL;
-  const url = Number.isInteger(topic.ghNumber) && topic.ghNumber > 0 ? `${base}/${topic.ghNumber}` : base;
-  const status = ["recorded", "in_progress", "fixed"].includes(topic.ghStatus) ? topic.ghStatus : null;
-  const version = status === "fixed" && typeof topic.fixedIn === "string" && /^[0-9A-Za-z][0-9A-Za-z.+-]{0,31}$/.test(topic.fixedIn) ? topic.fixedIn : null;
-  return { url, status, version, feedback };
-}
-
-const LABELS = {
-  recorded: ["Recorded", "已记录"],
-  in_progress: ["In progress", "处理中"],
-  fixed: ["Fixed", "已修复"],
-};
-
-// [en, zh] for the status badge, with the shipped version when there is one.
-export function statusText(mirror) {
-  if (!mirror?.status) return null;
-  const [en, zh] = LABELS[mirror.status];
-  return mirror.version ? [`${en} in v${mirror.version.replace(/^v/, "")}`, `${zh}于 v${mirror.version.replace(/^v/, "")}`] : [en, zh];
-}

site/src/lib/repository-owner.mjs

@@ -1,7 +0,0 @@
-// The repository owner is never thanked on release pages; change the login here only.
-export const repositoryOwner = "esengine";
-
-export function withoutOwner(logins) {
-  const owner = repositoryOwner.toLowerCase();
-  return logins.filter((login) => String(login).toLowerCase() !== owner);
-}

site/src/lib/studio-notes.mjs

@@ -1,64 +0,0 @@
-const REPO_ISSUES = 'https://github.com/esengine/DeepSeek-Reasonix/issues/';
-const TRAILING_REFS = /(\(?)(#\d{1,9}(?:\s*,\s*#\d{1,9})*)(\)?)\s*$/;
-
-export function issueHref(digits) {
-  if (!/^\d{1,9}$/.test(digits)) throw new Error('issue number must be digits only');
-  return `${REPO_ISSUES}${digits}`;
-}
-
-function codeSpans(text) {
-  const out = [];
-  const pattern = /`([^`\n]+)`/g;
-  let last = 0;
-  for (const match of text.matchAll(pattern)) {
-    if (match.index > last) out.push({ type: 'text', value: text.slice(last, match.index) });
-    out.push({ type: 'code', value: match[1] });
-    last = match.index + match[0].length;
-  }
-  if (last < text.length) out.push({ type: 'text', value: text.slice(last) });
-  return out;
-}
-
-export function parseInline(line) {
-  const trailing = line.match(TRAILING_REFS);
-  const hasBoundary = trailing && (trailing.index === 0 || /\s/.test(line[trailing.index - 1]) || trailing[1] === '(');
-  const insideCode = trailing && (line.slice(0, trailing.index).split('`').length - 1) % 2 === 1;
-  if (!trailing || !hasBoundary || insideCode || (trailing[1] === '(') !== (trailing[3] === ')')) return codeSpans(line);
-  const body = line.slice(0, trailing.index);
-  const tokens = codeSpans(body);
-  tokens.push({ type: 'text', value: trailing[1] });
-  trailing[2].split(/(\s*,\s*)/).forEach((part) => {
-    const ref = part.match(/^#(\d+)$/);
-    tokens.push(ref ? { type: 'ref', number: ref[1], value: part } : { type: 'text', value: part });
-  });
-  if (trailing[3]) tokens.push({ type: 'text', value: trailing[3] });
-  return tokens;
-}
-
-export function parseStudioNotes(markdown) {
-  const blocks = [];
-  let list = null;
-  let summary = '';
-  for (const raw of String(markdown ?? '').split(/\r?\n/)) {
-    const line = raw.trimEnd();
-    if (!line.trim()) { list = null; continue; }
-    const heading = line.match(/^##\s+(\S.*)$/);
-    const bullet = line.match(/^[-*]\s+(\S.*)$/);
-    if (heading) {
-      list = null;
-      blocks.push({ type: 'heading', inline: parseInline(heading[1].trim()) });
-    } else if (bullet) {
-      if (!list) { list = { type: 'list', items: [] }; blocks.push(list); }
-      list.items.push(parseInline(bullet[1]));
-    } else {
-      list = null;
-      if (!summary && blocks.length === 0) summary = line.trim();
-      blocks.push({ type: 'paragraph', inline: parseInline(line.trim()) });
-    }
-  }
-  return { summary, blocks };
-}
-
-export function plainText(tokens) {
-  return tokens.map((t) => t.value).join('');
-}

site/src/pages/404.astro

@@ -1,44 +0,0 @@
----
-import Base from '../layouts/Base.astro';
-import CommunityJoin from '../components/CommunityJoin.astro';
-import SponsorSlot from '../components/SponsorSlot.astro';
-import SiteHeader from '../components/SiteHeader.astro';
-const base = import.meta.env.BASE_URL.replace(/\/$/, '');
----
-<Base
-  title="Page not found — Reasonix"
-  titleEn="Page not found — Reasonix"
-  titleZh="页面不存在 — Reasonix"
-  description="The page you are looking for does not exist.">
-
-  <Fragment slot="head"><meta name="robots" content="noindex" /></Fragment>
-
-  <script is:inline>
-    // Preserve the documented /u/<handle> shape on static hosting by moving it
-    // to the client-rendered public profile page.
-    try {
-      const match = location.pathname.match(/^\/u\/([^/]+)\/?$/);
-      if (match) location.replace(`/u/?handle=${encodeURIComponent(decodeURIComponent(match[1]))}`);
-    } catch {}
-  </script>
-
-  <SiteHeader scrolled />
-
-  <main class="hero" style="padding-bottom:150px">
-    <div class="wrap">
-      <div class="eyebrow">404</div>
-      <h1><span class="l-en">This page went <span class="grad">cold.</span></span><span class="l-zh">这一页<span class="grad">冷掉了</span>。</span></h1>
-      <p class="sub"><span class="l-en">The page you're looking for doesn't exist — but the session is still warm.</span><span class="l-zh">你找的页面不存在——但会话还热着。</span></p>
-      <div class="cold-blocks" aria-hidden="true"><i></i><i></i><i></i><i></i><i></i><i></i><i></i><i class="new"></i></div>
-      <div class="hero-cta">
-        <a class="btn btn-dark" href={`${base}/`}><span class="l-en">Back to home</span><span class="l-zh">回到首页</span></a>
-        <a class="btn btn-ghost" href={`${base}/docs/`}><span class="l-en">Read the docs</span><span class="l-zh">查看文档</span></a>
-      </div>
-    </div>
-  </main>
-
-  <footer>
-    <CommunityJoin />
-    <SponsorSlot />
-  </footer>
-</Base>

site/src/pages/account.astro

@@ -1,125 +0,0 @@
----
-import Account from '../layouts/Account.astro';
-import PasswordInput from '../components/PasswordInput.astro';
----
-<Account
-  wide
-  dash
-  title="Your account — Reasonix"
-  titleEn="Your account — Reasonix"
-  titleZh="我的账号 — Reasonix"
-  description="Manage your Reasonix account.">
-  <div id="account-gate" class="auth-head">
-    <p><span class="l-en">Loading your account…</span><span class="l-zh">正在加载账号…</span></p>
-  </div>
-
-  <div id="account-view" hidden>
-    <div class="acct-id">
-      <span id="acct-avatar" class="acct-avatar" aria-hidden="true"></span>
-      <div class="acct-who">
-        <div id="acct-name" class="acct-name-big"></div>
-        <div id="acct-handle" class="acct-handle"></div>
-        <div id="acct-email" class="acct-email"></div>
-        <div class="acct-chips">
-          <span id="acct-role" class="acct-role"></span>
-          <span id="acct-verified" class="acct-chip"></span>
-          <span id="acct-joined" class="acct-chip"></span>
-        </div>
-      </div>
-      <a id="acct-profile-link" class="btn btn-ghost sm" href="/u/"><span class="l-en">Public profile</span><span class="l-zh">公开主页</span></a>
-    </div>
-
-    <div id="acct-overview" class="acct-grid" role="group" aria-label="Overview">
-      <article class="acct-card" id="card-forum">
-        <h3><span class="l-en">Community</span><span class="l-zh">社区</span></h3>
-        <div class="acct-level"><span id="forum-level" class="acct-lv">—</span><span id="forum-level-note" class="acct-note"></span></div>
-        <dl class="acct-stats">
-          <div><dt><span class="l-en">Topics</span><span class="l-zh">话题</span></dt><dd id="st-topics">—</dd></div>
-          <div><dt><span class="l-en">Replies</span><span class="l-zh">回复</span></dt><dd id="st-posts">—</dd></div>
-          <div><dt><span class="l-en">Likes</span><span class="l-zh">获赞</span></dt><dd id="st-likes">—</dd></div>
-          <div><dt><span class="l-en">Solved</span><span class="l-zh">已解决</span></dt><dd id="st-solved">—</dd></div>
-        </dl>
-        <p id="forum-perms" class="acct-note"></p>
-        <ul id="forum-recent" class="acct-recent"></ul>
-        <a class="acct-more" href="/community/"><span class="l-en">Open the forum →</span><span class="l-zh">进入论坛 →</span></a>
-      </article>
-
-      <article class="acct-card" id="card-feedback">
-        <h3><span class="l-en">Feedback level</span><span class="l-zh">反馈等级</span></h3>
-        <p class="acct-big" id="fb-level">—</p>
-        <div id="fb-track" class="acct-track" hidden><i id="fb-fill"></i></div>
-        <p class="acct-note" id="fb-note"></p>
-        <p class="acct-note" id="fb-limits"></p>
-        <ul id="fb-installs" class="acct-recent"></ul>
-        <ul id="fb-items" class="acct-recent"></ul>
-      </article>
-
-      <article class="acct-card" id="card-devices">
-        <h3><span class="l-en">Devices</span><span class="l-zh">设备</span></h3>
-        <p class="acct-big"><span id="dev-total">—</span> <span class="acct-unit"><span class="l-en">registered</span><span class="l-zh">台已注册</span></span></p>
-        <p class="acct-note" id="dev-online"></p>
-        <a class="acct-more" href="/remote/"><span class="l-en">Open Web Studio →</span><span class="l-zh">进入网页版 Studio →</span></a>
-      </article>
-
-      <article class="acct-card" id="card-backups">
-        <h3><span class="l-en">Config backups</span><span class="l-zh">配置备份</span></h3>
-        <p class="acct-big"><span id="bk-total">—</span> <span class="acct-unit"><span class="l-en">saved</span><span class="l-zh">份</span></span></p>
-        <p class="acct-note"><span class="l-en">Back up and restore your Studio settings from Studio.</span><span class="l-zh">在 Studio 里备份和恢复你的设置。</span></p>
-      </article>
-    </div>
-
-    <div id="verification-wrap" hidden>
-      <h2 class="acct-h2"><span class="l-en">Email verification</span><span class="l-zh">邮箱验证</span></h2>
-      <div id="verification-msg" class="auth-msg" hidden></div>
-      <p class="hint"><span class="l-en">Your email is not confirmed. Some community actions remain locked.</span><span class="l-zh">你的邮箱尚未验证，部分社区操作仍不可用。</span></p>
-      <button id="resend-verification-btn" type="button" class="btn btn-ghost"><span class="l-en">Resend verification email</span><span class="l-zh">重新发送验证邮件</span></button>
-    </div>
-
-    <h2 class="acct-h2"><span class="l-en">Profile</span><span class="l-zh">资料</span></h2>
-    <div id="profile-msg" class="auth-msg" hidden></div>
-    <form id="profile-form" class="auth-form" novalidate>
-      <div class="field">
-        <label for="f-displayName"><span class="l-en">Display name</span><span class="l-zh">显示名</span></label>
-        <input id="f-displayName" type="text" maxlength="80" />
-      </div>
-      <div class="field">
-        <label for="f-handle"><span class="l-en">Handle</span><span class="l-zh">用户名</span></label>
-        <input id="f-handle" type="text" minlength="3" maxlength="30" />
-        <span class="hint"><span class="l-en">Your public profile is linked above.</span><span class="l-zh">你的公开主页链接显示在上方。</span></span>
-      </div>
-      <div class="field">
-        <label for="f-bio"><span class="l-en">Bio</span><span class="l-zh">简介</span></label>
-        <textarea id="f-bio" rows="3" maxlength="500"></textarea>
-      </div>
-      <div class="field">
-        <label for="f-avatarUrl"><span class="l-en">Avatar URL</span><span class="l-zh">头像链接</span></label>
-        <input id="f-avatarUrl" type="url" maxlength="500" />
-      </div>
-      <button type="submit" class="btn btn-dark"><span class="l-en">Save profile</span><span class="l-zh">保存资料</span></button>
-    </form>
-
-    <h2 class="acct-h2"><span class="l-en">Password</span><span class="l-zh">密码</span></h2>
-    <div id="password-msg" class="auth-msg" hidden></div>
-    <form id="password-form" class="auth-form" novalidate>
-      <div class="field">
-        <label for="currentPassword"><span class="l-en">Current password</span><span class="l-zh">当前密码</span></label>
-        <PasswordInput id="currentPassword" autocomplete="current-password" required />
-      </div>
-      <div class="field">
-        <label for="newPassword"><span class="l-en">New password</span><span class="l-zh">新密码</span></label>
-        <PasswordInput id="newPassword" autocomplete="new-password" minlength={8} required />
-      </div>
-      <button type="submit" class="btn btn-ghost"><span class="l-en">Change password</span><span class="l-zh">修改密码</span></button>
-    </form>
-
-    <h2 class="acct-h2"><span class="l-en">Web Studio</span><span class="l-zh">网页版 Studio</span></h2>
-    <p class="hint"><span class="l-en">Use the full Studio interface from this browser and control a computer signed in to the same account.</span><span class="l-zh">在浏览器中使用完整的 Studio 界面，并控制已登录同一账号的电脑。</span></p>
-    <a class="btn btn-ghost acct-remote" href="/remote/"><span class="l-en">Enter Web Studio</span><span class="l-zh">进入网页版 Studio</span></a>
-
-    <div class="acct-foot">
-      <button id="logout-btn" type="button" class="btn btn-ghost"><span class="l-en">Sign out</span><span class="l-zh">退出登录</span></button>
-      <button id="delete-btn" type="button" class="acct-danger"><span class="l-en">Delete account</span><span class="l-zh">注销账号</span></button>
-    </div>
-  </div>
-<script>import "../scripts/account-overview.js";</script>
-</Account>

site/src/pages/changelog/[version].astro

@@ -1,18 +0,0 @@
----
-import ChangelogPage from '../../components/ChangelogPage.astro';
-import { allReleases, publishedReleases, releases, studioReleases } from '../../data/releases';
-
-export function getStaticPaths() {
-  const publishedVersions = new Set(publishedReleases.map((release) => release.version));
-  return allReleases.map((release) => ({
-    params: { version: `v${release.version}` },
-    props: { release, published: publishedVersions.has(release.version) },
-  }));
-}
-
-const { release, published } = Astro.props;
-if (!published) {
-  return Astro.redirect(release.product === 'studio' ? '/changelog/' : '/changelog/cli/');
-}
----
-<ChangelogPage release={release} releases={release.product === 'studio' ? studioReleases : releases} />

site/src/pages/changelog/cli.astro

@@ -1,10 +0,0 @@
----
-import ChangelogPage from '../../components/ChangelogPage.astro';
-import { latestStableRelease, releases, releasePath } from '../../data/releases';
-
-/* /changelog/cli/ renders the latest 1.x release but canonicalizes to its version URL
-   to avoid duplicate content with /changelog/vX.Y.Z/. */
-const canonical = new URL(releasePath(latestStableRelease.version), Astro.site).href;
----
-
-<ChangelogPage release={latestStableRelease} releases={releases} canonical={canonical} />

site/src/pages/changelog/index.astro

@@ -1,5 +0,0 @@
----
-import StudioChangelog from '../../components/StudioChangelog.astro';
----
-
-<StudioChangelog />

site/src/pages/changelog/preview.astro

@@ -1,3 +0,0 @@
----
-return Astro.redirect('/changelog/cli/', 301);
----

site/src/pages/changelog/stable.astro

@@ -1,3 +0,0 @@
----
-return Astro.redirect('/changelog/cli/', 301);
----

site/src/pages/changelog/studio.astro

@@ -1,5 +0,0 @@
----
-import StudioChangelog from '../../components/StudioChangelog.astro';
----
-
-<StudioChangelog />

site/src/pages/community/board.astro

@@ -1,53 +0,0 @@
----
-import Community from "../../layouts/Community.astro";
----
-<Community title="Contributors · Reasonix Community" description="The people whose suggestions shipped in Reasonix, by release." active="board">
-  <div class="wrap board">
-    <header class="board-head">
-      <h1><span class="l-en">Contributors</span><span class="l-zh">贡献榜</span></h1>
-      <p class="board-lead">
-        <span class="l-en">People whose feedback was adopted and shipped in a release. A release has a ranking; all releases together are listed by name, not ranked. Only people who chose to appear are here.</span>
-        <span class="l-zh">反馈被采纳并发布的人。每个版本有名次；全部版本只按名字排序，不比高低。只有自己选择加入的人才会出现。</span>
-      </p>
-      <label class="board-pick">
-        <span class="l-en">Release</span><span class="l-zh">版本</span>
-        <select id="board-release"><option value="" data-l-en="All releases" data-l-zh="全部版本">All releases</option></select>
-      </label>
-    </header>
-    <ol id="board-list" class="board-list" aria-live="polite"></ol>
-    <p id="board-empty" class="board-note" hidden>
-      <span class="l-en">Nobody is listed for this release yet.</span><span class="l-zh">这个版本还没有人上榜。</span>
-    </p>
-    <p id="board-off" class="board-note" hidden>
-      <span class="l-en">The contributor board is not open yet.</span><span class="l-zh">贡献榜还没有开放。</span>
-    </p>
-    <p id="board-error" class="board-note" hidden>
-      <span class="l-en">The board could not be loaded. Try again in a moment.</span><span class="l-zh">榜单暂时读不出来，稍后再试。</span>
-    </p>
-    <p class="board-note">
-      <span class="l-en">A ranking depends on what the maintainers chose to ship: a good report that was declined earns nothing. To appear, link your install to your account and turn the board on in Studio's feedback panel; you can leave at any time.</span>
-      <span class="l-zh">名次取决于维护者选择发布的内容：被婉拒的好反馈不计入。想上榜，在 Studio 的反馈面板里把这台电脑关联到账号并打开贡献榜；随时可以退出。</span>
-    </p>
-  </div>
-  <script>import "../../scripts/board.js";</script>
-</Community>
-
-<style is:global>
-  .board { max-width: 760px; margin: 0 auto; padding: 32px 16px 56px; }
-  .board-head { display: grid; gap: 10px; margin-bottom: 18px; }
-  .board-head h1 { margin: 0; font-size: 28px; letter-spacing: -0.01em; }
-  .board-lead { margin: 0; color: var(--ink-3); line-height: 1.6; }
-  .board-pick { display: inline-flex; align-items: center; gap: 8px; color: var(--ink-3); font-size: 14px; }
-  .board-pick select { min-width: 160px; padding: 5px 8px; border: 1px solid var(--line); border-radius: 6px; background: var(--bg); color: inherit; font: inherit; }
-  .board-list { list-style: none; margin: 0; padding: 0; border: 1px solid var(--line); border-radius: 10px; overflow: hidden; }
-  .board-list li { display: flex; align-items: center; gap: 12px; padding: 11px 16px; border-top: 1px solid var(--line); }
-  .board-list li:first-child { border-top: 0; }
-  .board-rank { flex: none; width: 28px; text-align: right; font: 600 14px ui-monospace, "JetBrains Mono Variable", monospace; color: var(--ink-3); }
-  .board-list[data-ranked] li:nth-child(-n+3) .board-rank { color: var(--accent); }
-  .board-name { flex: 1 1 auto; min-width: 0; overflow: hidden; text-overflow: ellipsis; white-space: nowrap; font-weight: 600; }
-  .board-credits { flex: none; color: var(--ink-3); font-size: 14px; }
-  .board-where { display: flex; flex-wrap: wrap; gap: 4px; justify-content: flex-end; }
-  .board-chip { padding: 1px 8px; border: 1px solid var(--line); border-radius: 999px; font-size: 12px; white-space: nowrap; }
-  .board-note { margin: 14px 2px 0; color: var(--ink-3); font-size: 14px; line-height: 1.6; }
-  @media (max-width: 560px) { .board-where { display: none; } .board-list li { padding: 10px 12px; } }
-</style>

site/src/pages/community/guidelines.astro

@@ -1,14 +0,0 @@
----
-import Community from "../../layouts/Community.astro";
----
-<Community title="Guidelines — Reasonix Community" description="How the Reasonix community forum works.">
-  <div class="wrap" style="padding:36px 32px 80px;max-width:760px">
-    <div class="crumb"><a href="/community/"><span class="l-en">Community</span><span class="l-zh">社区</span></a><span class="sep">/</span><span><span class="l-en">Guidelines</span><span class="l-zh">规范</span></span></div>
-    <h1 style="font-size:32px;font-weight:600;letter-spacing:-0.02em"><span class="l-en">Community guidelines</span><span class="l-zh">社区规范</span></h1>
-    <p style="margin:14px 0 28px;color:var(--ink-2);font-size:16px;line-height:1.7"><span class="l-en">A small forum works when everyone keeps it useful and kind. A few things worth knowing.</span><span class="l-zh">一个小论坛，靠大家保持有用与友善才能运转。几点值得先了解。</span></p>
-
-    <div class="side-card" style="margin-bottom:16px"><h4><span class="l-en">Be kind &amp; on-topic</span><span class="l-zh">友善、切题</span></h4><p style="color:var(--ink-2);line-height:1.7"><span class="l-en">Assume good faith, search before asking, and keep threads focused. Format code in fenced <code>```</code> blocks.</span><span class="l-zh">与人为善、提问前先搜索、保持话题聚焦。代码请放进 <code>```</code> 围栏块。</span></p></div>
-    <div class="side-card" style="margin-bottom:16px"><h4><span class="l-en">Trust levels</span><span class="l-zh">信任等级</span></h4><p style="color:var(--ink-2);line-height:1.7"><span class="l-en">Everyone signs in with their Reasonix account. New accounts start limited — no links, a small daily post cap — and unlock more as they read and contribute. It keeps the forum spam-free without getting in real members' way.</span><span class="l-zh">所有人用 Reasonix 账号登录。新账号有限制——不能发链接、每日发帖上限较低——随着阅读与贡献逐步解锁。既挡住广告，又不妨碍真实成员。</span></p></div>
-    <div class="side-card"><h4><span class="l-en">Moderation</span><span class="l-zh">审核</span></h4><p style="color:var(--ink-2);line-height:1.7"><span class="l-en">Flag anything off — a few flags auto-hide a post for review. Moderators can restrict accounts that abuse the forum. All moderator actions are logged.</span><span class="l-zh">发现不妥就举报——几次举报会自动隐藏帖子待审。版主可限制滥用论坛的账号。所有版主操作都有记录。</span></p></div>
-  </div>
-</Community>

site/src/pages/community/index.astro

@@ -1,53 +0,0 @@
----
-import Community from "../../layouts/Community.astro";
-import { QQ_GROUP, DISCORD_URL, DOUYIN } from "../../lib/community-links.mjs";
----
-<Community title="Reasonix Community" description="Ask questions, share skills, and shape a DeepSeek-native agent." active="discussions">
-  <div class="wrap forum">
-    <aside class="fnav" aria-label="Forum navigation">
-      <a class="btn btn-primary fnew" href="/community/new/"><span class="l-en">✎ New topic</span><span class="l-zh">✎ 发起话题</span></a>
-      <nav class="fmenu" id="sort-tabs" aria-label="Topic lists">
-        <button class="on" data-sort="latest"><span class="l-en">Latest</span><span class="l-zh">最新</span></button>
-        <button data-sort="top"><span class="l-en">Top</span><span class="l-zh">热门</span></button>
-        <button data-sort="unanswered"><span class="l-en">Unanswered</span><span class="l-zh">未回复</span></button>
-      </nav>
-      <h5 class="fh"><span class="l-en">Categories</span><span class="l-zh">分区</span></h5>
-      <nav class="fcats" id="cat-list" aria-label="Categories">
-        <a class="fcat" href="/community/"><i class="dot" data-cat=""></i><span class="nm"><span class="l-en">Loading…</span><span class="l-zh">加载中…</span></span></a>
-      </nav>
-      <h5 class="fh"><span class="l-en">Community</span><span class="l-zh">社区</span></h5>
-      <nav class="flinks">
-        <a href="/community/guidelines/"><span class="l-en">Guidelines</span><span class="l-zh">社区规范</span></a>
-        <a href={QQ_GROUP.joinUrl} target="_blank" rel="noreferrer"><span class="l-en">QQ group</span><span class="l-zh">QQ 群</span> <code>{QQ_GROUP.number}</code></a>
-        <a href={DISCORD_URL} target="_blank" rel="noreferrer">Discord</a>
-        <a href="/docs/"><span class="l-en">Documentation ↗</span><span class="l-zh">文档 ↗</span></a>
-      </nav>
-      <p class="fstat"><span id="s-topics">—</span> <span class="l-en">topics</span><span class="l-zh">话题</span> · <span id="s-cats">—</span> <span class="l-en">categories</span><span class="l-zh">分区</span></p>
-    </aside>
-
-    <main class="fmain">
-      <div class="fbar">
-        <div class="ftitle">
-          <h1 id="f-title"><span class="l-en">All topics</span><span class="l-zh">全部话题</span></h1>
-          <p id="f-desc"></p>
-        </div>
-        <label class="fsearch"><span class="l-en sr">Filter topics</span><span class="l-zh sr">筛选话题</span>
-          <input id="t-search" type="search" autocomplete="off" placeholder="Filter topics…" data-ph-zh="筛选话题…" />
-        </label>
-      </div>
-      <div class="ftable" role="table" aria-label="Topics">
-        <div class="fhead" role="row">
-          <span role="columnheader"><span class="l-en">Topic</span><span class="l-zh">话题</span></span>
-          <span role="columnheader" class="num"><span class="l-en">Replies</span><span class="l-zh">回复</span></span>
-          <span role="columnheader" class="num"><span class="l-en">Views</span><span class="l-zh">浏览</span></span>
-          <span role="columnheader" class="act"><span class="l-en">Activity</span><span class="l-zh">活动</span></span>
-        </div>
-        <div id="topic-list" class="topics" role="rowgroup">
-          <div class="skeleton"><div class="bar"></div><div class="bar short"></div></div>
-          <div class="skeleton"><div class="bar"></div><div class="bar short"></div></div>
-          <div class="skeleton"><div class="bar"></div><div class="bar short"></div></div>
-        </div>
-      </div>
-    </main>
-  </div>
-</Community>

site/src/pages/community/new.astro

@@ -1,28 +0,0 @@
----
-import Community from "../../layouts/Community.astro";
----
-<Community title="New topic — Reasonix Community" description="Start a discussion on the Reasonix community forum.">
-  <div class="wrap" style="padding-top:32px;max-width:820px">
-    <div class="crumb"><a href="/community/">Community</a><span class="sep">/</span><span><span class="l-en">New topic</span><span class="l-zh">发起话题</span></span></div>
-    <h1 style="font-size:28px;font-weight:600;letter-spacing:-0.02em;margin-bottom:6px"><span class="l-en">Start a discussion</span><span class="l-zh">发起讨论</span></h1>
-
-    <div id="new-gate" hidden class="card cta" style="margin-top:18px">
-      <h4><span class="l-en">Sign in to post</span><span class="l-zh">登录后发帖</span></h4>
-      <p class="lead"><span class="l-en">You'll post with your Reasonix account. New here? Signing in creates one.</span><span class="l-zh">用你的 Reasonix 账号发帖。还没有账号？登录即创建。</span></p>
-      <a class="btn btn-primary" id="gate-login" href="#"><span class="l-en">Sign in</span><span class="l-zh">登录</span></a>
-    </div>
-
-    <div id="new-form" hidden>
-      <div class="msg error" id="new-msg" hidden></div>
-      <div class="composer">
-        <input class="title" id="f-title" maxlength="160" data-ph-en="Topic title — be specific" data-ph-zh="话题标题 —— 尽量具体" />
-        <textarea id="f-body" data-ph-en="Write your post… Markdown and ``` code blocks supported." data-ph-zh="写下内容… 支持 Markdown 和 ``` 代码块。"></textarea>
-        <div class="foot">
-          <select id="f-category"><option value="" data-l-en="Choose a category…" data-l-zh="选择分区…">Choose a category…</option></select>
-          <button class="btn btn-primary" id="f-submit"><span class="l-en">Post topic</span><span class="l-zh">发布话题</span></button>
-        </div>
-      </div>
-      <p class="lead" style="margin-top:14px"><span class="l-en">Please search before posting, keep it on-topic, and format code in fenced blocks. New accounts can't post links until they've participated a little.</span><span class="l-zh">发帖前请先搜索、保持切题、代码放进围栏块。新账号需参与一段时间后才能发链接。</span></p>
-    </div>
-  </div>
-</Community>

site/src/pages/community/topic.astro

@@ -1,42 +0,0 @@
----
-import Community from "../../layouts/Community.astro";
----
-<Community title="Discussion — Reasonix Community" description="A discussion on the Reasonix community forum.">
-  <div class="wrap" style="padding-top:28px">
-    <div class="crumb">
-      <a href="/community/"><span class="l-en">Community</span><span class="l-zh">社区</span></a><span class="sep">/</span>
-      <span id="crumb-cat">…</span><span class="sep">/</span>
-      <span id="crumb-title"><span class="l-en">Loading…</span><span class="l-zh">加载中…</span></span>
-    </div>
-    <div class="thread-head">
-      <h1 id="t-title">
-        <div class="skeleton" style="border:none;padding:0"><div class="bar" style="width:70%;height:22px"></div></div>
-      </h1>
-      <div class="meta" id="t-meta"></div>
-    </div>
-  </div>
-
-  <div class="wrap thread-layout">
-    <div>
-      <div id="posts">
-        <div class="skeleton"><div class="bar"></div><div class="bar short"></div></div>
-        <div class="skeleton"><div class="bar"></div><div class="bar short"></div></div>
-      </div>
-
-      <div id="reply-zone"></div>
-    </div>
-
-    <aside class="side">
-      <div class="side-card">
-        <h4><span class="l-en">Participants</span><span class="l-zh">参与者</span></h4>
-        <div class="parti" id="parti"></div>
-      </div>
-      <div class="side-card">
-        <h4><span class="l-en">Actions</span><span class="l-zh">操作</span></h4>
-        <div style="display:flex;flex-direction:column;gap:10px">
-          <a class="link-act" href="/community/"><span class="l-en">← Back to discussions</span><span class="l-zh">← 返回讨论区</span></a>
-        </div>
-      </div>
-    </aside>
-  </div>
-</Community>

site/src/pages/device.astro

@@ -1,37 +0,0 @@
----
-import Account from '../layouts/Account.astro';
----
-<Account
-  title="Authorize a device — Reasonix"
-  titleEn="Authorize a device — Reasonix"
-  titleZh="授权设备 — Reasonix"
-  description="Approve a sign-in request from the Reasonix CLI or desktop app.">
-  <div id="device-gate" class="auth-head">
-    <p><span class="l-en">Checking your session…</span><span class="l-zh">正在检查登录状态…</span></p>
-  </div>
-
-  <div id="device-view" hidden>
-    <div class="auth-head">
-      <h1><span class="l-en">Approve Reasonix sign-in</span><span class="l-zh">批准 Reasonix 登录</span></h1>
-      <p><span class="l-en">Only approve if you started this request.</span><span class="l-zh">仅在这是你本人发起的请求时批准。</span></p>
-    </div>
-
-    <div id="device-msg" class="auth-msg" hidden></div>
-
-    <div id="device-code-step">
-      <div class="field">
-        <label for="device-code"><span class="l-en">Device code</span><span class="l-zh">设备码</span></label>
-        <input id="device-code" class="device-code" type="text" autocomplete="one-time-code" spellcheck="false" placeholder="XXXX-XXXX" />
-      </div>
-      <button id="device-check" type="button" class="btn btn-ghost device-check"><span class="l-en">Continue</span><span class="l-zh">继续</span></button>
-    </div>
-
-    <p id="device-meta" class="device-meta" hidden></p>
-    <p id="device-expiry" class="device-expiry" hidden></p>
-
-    <div id="device-actions" class="device-actions" hidden>
-      <button id="device-approve" type="button" class="btn btn-dark"><span class="l-en">Approve sign-in</span><span class="l-zh">批准登录</span></button>
-      <button id="device-deny" type="button" class="btn btn-ghost"><span class="l-en">Reject</span><span class="l-zh">拒绝</span></button>
-    </div>
-  </div>
-</Account>