ci: the AI provider workflow runs only the provider tests and passes every provider's key

The catalog listed `mistral-large-4` with a 1,000,000-token output
limit, equal to its context window. Mistral rejects a request for more
than 262,144 completion tokens, so a request that left `max_tokens`
unset, or set it higher, failed with a 400 whenever the account's
credit covered more than 262,144 output tokens.

- `max_tokens` for `mistral-large-4` is 262,144. The context window
  stays at 1,000,000 tokens.
- A test sends `mistral-large-4` and `mistral-large-latest` through the
  chat driver with ample credit and checks the cap that reaches
  Mistral.

.github/CODEOWNERS

@@ -2,7 +2,7 @@
 
 # The last matching rule takes precedence.
 
-- @Salazareo
+* @Salazareo
 
 # GUI
 
@@ -18,7 +18,10 @@
 # Backend AI
 
 /src/backend/controllers/puterai/ @404oops @ProgrammerIn-wonderland @Salazareo
-/src/backend/drivers/ai-\*/ @404oops @ProgrammerIn-wonderland @Salazareo
+/src/backend/drivers/ai/ @404oops @ProgrammerIn-wonderland @Salazareo
+/src/backend/util/aiCostFactor* @404oops @ProgrammerIn-wonderland @Salazareo
+/src/backend/util/aiPrices* @404oops @ProgrammerIn-wonderland @Salazareo
+/src/backend/util/aiProviderKey* @404oops @ProgrammerIn-wonderland @Salazareo
 
 # Backend: AI, hosting, workers, networking, and WebDAV
 
@@ -29,7 +32,7 @@
 /src/backend/drivers/workers/ @ProgrammerIn-wonderland @Salazareo
 /src/backend/services/localworker/ @ProgrammerIn-wonderland @Salazareo
 /src/backend/stores/subdomain/ @ProgrammerIn-wonderland @Salazareo
-/extensions/workerSandbox\* @ProgrammerIn-wonderland @Salazareo
+/extensions/workerSandbox* @ProgrammerIn-wonderland @Salazareo
 /src/worker/ @ProgrammerIn-wonderland @Salazareo
 /src/worker-types/ @ProgrammerIn-wonderland @Salazareo
 /src/backend/controllers/peer/ @ProgrammerIn-wonderland @Salazareo
@@ -42,7 +45,7 @@
 /src/backend/services/permission/ @jfcastro92 @Salazareo
 /src/backend/services/acl/ @jfcastro92 @Salazareo
 /src/backend/services/team/ @jfcastro92 @Salazareo
-/src/backend/services/apps/AppPermissionService\* @jfcastro92 @Salazareo
+/src/backend/services/apps/AppPermissionService* @jfcastro92 @Salazareo
 /src/backend/stores/share/ @jfcastro92 @Salazareo
 /src/backend/stores/permission/ @jfcastro92 @Salazareo
 /src/backend/stores/group/ @jfcastro92 @Salazareo
@@ -59,7 +62,7 @@
 /src/puter-js/tests/api/suites/hosting.suite.ts @ProgrammerIn-wonderland @Salazareo
 /src/puter-js/tests/api/suites/workers.suite.ts @ProgrammerIn-wonderland @Salazareo
 /src/puter-js/tests/api/suites/net.suite.ts @ProgrammerIn-wonderland @Salazareo
-/src/puter-js/src/modules/Peer\* @ProgrammerIn-wonderland @Salazareo
+/src/puter-js/src/modules/Peer* @ProgrammerIn-wonderland @Salazareo
 
 # SDK: sharing and permissions
 

.github/workflows/actions.lock

@@ -0,0 +1,106 @@
+# This file is machine-generated by `gh actions-lock`.
+# Do not edit by hand; run `gh actions-lock` to update.
+# Docs: https://gh.io/actions-lockfile
+version: 'v0.0.3'
+workflows:
+    '.github/workflows/ai-provider-integration-tests.yaml':
+        - 'actions/[email protected]'
+        - 'actions/[email protected]'
+    '.github/workflows/backend-tests.yaml':
+        - 'actions/[email protected]'
+        - 'actions/[email protected]'
+        - 'actions/[email protected]'
+        - 'actions/[email protected]'
+        - 'davelosert/[email protected]'
+        - 'dorny/[email protected]'
+    '.github/workflows/dependabot-automerge.yml':
+        - 'dependabot/[email protected]'
+    '.github/workflows/docker-image.yaml':
+        - 'actions/[email protected]'
+        - 'docker/[email protected]'
+        - 'docker/[email protected]'
+        - 'docker/[email protected]'
+        - 'docker/[email protected]'
+        - 'docker/[email protected]'
+        - 'peter-evans/[email protected]'
+    '.github/workflows/docs-build.yml':
+        - 'actions/[email protected]'
+        - 'actions/[email protected]'
+    '.github/workflows/notify-dev.yaml': []
+    '.github/workflows/notify-prod.yaml': []
+    '.github/workflows/puterjs-tests.yaml':
+        - 'actions/[email protected]'
+        - 'actions/[email protected]'
+        - 'actions/[email protected]'
+        - 'actions/[email protected]'
+        - 'davelosert/[email protected]'
+        - 'dorny/[email protected]'
+    '.github/workflows/tag-alias.yaml':
+        - 'docker/[email protected]'
+        - 'docker/[email protected]'
+dependencies:
+    'actions/[email protected]':
+        ref: 'v7.0.1'
+        commit: 'sha1-3d3c42e5aac5ba805825da76410c181273ba90b1'
+        owner_id: 44036562
+        repo_id: 197814629
+    'actions/[email protected]':
+        ref: 'v8.0.2'
+        commit: 'sha1-9000827ccba6bdab643e8b6fd33ac0654aef8333'
+        owner_id: 44036562
+        repo_id: 192626254
+    'actions/[email protected]':
+        ref: 'v7.1.0'
+        commit: 'sha1-949feb2413d6458794dcd2491c4babbbce0c15c1'
+        owner_id: 44036562
+        repo_id: 189476904
+    'actions/[email protected]':
+        ref: 'v7.0.2'
+        commit: 'sha1-cf430e030ddbb5b0abf93d22962f4752f3646cd9'
+        owner_id: 44036562
+        repo_id: 192625955
+    'davelosert/[email protected]':
+        ref: 'v2.13.2'
+        commit: 'sha1-74c2d9210b4fc44c84d8213f61d7ec99837b7aa0'
+        owner_id: 4287128
+        repo_id: 501176456
+    'dependabot/[email protected]':
+        ref: 'v3.1.0'
+        commit: 'sha1-25dd0e34f4fe68f24cc83900b1fe3fe149efef98'
+        owner_id: 27347476
+        repo_id: 371068214
+    'docker/[email protected]':
+        ref: 'v7.4.0'
+        commit: 'sha1-c3c9e263c25d99ce0380d002d59b67737d91b0dc'
+        owner_id: 5429470
+        repo_id: 241092383
+    'docker/[email protected]':
+        ref: 'v4.8.0'
+        commit: 'sha1-8aa5831fb8d48d8f76594c7ddde61ae58019f550'
+        owner_id: 5429470
+        repo_id: 287743349
+    'docker/[email protected]':
+        ref: 'v6.2.0'
+        commit: 'sha1-dc802804100637a589fabce1cb79ff13a1411302'
+        owner_id: 5429470
+        repo_id: 306769011
+    'docker/[email protected]':
+        ref: 'v4.4.1'
+        commit: 'sha1-f87e5991a6d7451dcb8d9637bfbc97413f497069'
+        owner_id: 5429470
+        repo_id: 288485773
+    'docker/[email protected]':
+        ref: 'v4.4.0'
+        commit: 'sha1-99012661954931238ded8c8b007157a8430204e1'
+        owner_id: 5429470
+        repo_id: 288487894
+    'dorny/[email protected]':
+        ref: 'v4.0.3'
+        commit: 'sha1-ceb8a2b8f2d89434be7ff52d3de7ec3738c5cc9d'
+        owner_id: 1588572
+        repo_id: 265601040
+    'peter-evans/[email protected]':
+        ref: 'v5.0.0'
+        commit: 'sha1-1b9a80c056b620d92cedb9d9b5a223409c68ddfa'
+        owner_id: 18365890
+        repo_id: 193685475

.github/workflows/ai-provider-integration-tests.yaml

@@ -17,10 +17,12 @@ jobs:
 
         steps:
             - name: Checkout repository
-              uses: actions/checkout@v7
+              uses: actions/checkout@v7.0.1
+              with:
+                  persist-credentials: false
 
             - name: Set up Node.js
-              uses: actions/setup-node@v7
+              uses: actions/setup-node@v7.1.0
               with:
                   node-version: '26'
                   cache: 'npm'
@@ -29,10 +31,9 @@ jobs:
               run: npm ci
 
             - name: Run AI provider integration tests
-              # Vitest treats positional args as filename substring filters.
-              # The pattern matches every `*.integration.test.ts` file and
-              # nothing else — the regular backend test suite stays out.
-              run: npm run test:backend -- integration.test
+              # Only the provider tests: the other `*.integration.test.ts`
+              # files need no credentials and run with the backend suite.
+              run: npm run test:backend -- $(git ls-files 'src/backend/drivers/ai/**/*.integration.test.ts')
               env:
                   CI: 'true'
                   PUTER_TEST_AI_CLAUDE_API_KEY: ${{ secrets.PUTER_TEST_AI_CLAUDE_API_KEY }}
@@ -47,6 +48,15 @@ jobs:
                   PUTER_TEST_AI_MOONSHOT_API_KEY: ${{ secrets.PUTER_TEST_AI_MOONSHOT_API_KEY }}
                   PUTER_TEST_AI_ZAI_API_KEY: ${{ secrets.PUTER_TEST_AI_ZAI_API_KEY }}
                   PUTER_TEST_AI_ELEVENLABS_API_KEY: ${{ secrets.PUTER_TEST_AI_ELEVENLABS_API_KEY }}
+                  PUTER_TEST_AI_ALIBABA_API_KEY: ${{ secrets.PUTER_TEST_AI_ALIBABA_API_KEY }}
+                  PUTER_TEST_AI_AZURE_OPENAI_API_KEY: ${{ secrets.PUTER_TEST_AI_AZURE_OPENAI_API_KEY }}
+                  PUTER_TEST_AI_AZURE_OPENAI_API_URL: ${{ secrets.PUTER_TEST_AI_AZURE_OPENAI_API_URL }}
+                  PUTER_TEST_AI_BYTEPLUS_API_KEY: ${{ secrets.PUTER_TEST_AI_BYTEPLUS_API_KEY }}
+                  PUTER_TEST_AI_HOONIFY_API_KEY: ${{ secrets.PUTER_TEST_AI_HOONIFY_API_KEY }}
+                  PUTER_TEST_AI_INFRON_API_KEY: ${{ secrets.PUTER_TEST_AI_INFRON_API_KEY }}
+                  PUTER_TEST_AI_KLING_API_KEY: ${{ secrets.PUTER_TEST_AI_KLING_API_KEY }}
+                  PUTER_TEST_AI_META_API_KEY: ${{ secrets.PUTER_TEST_AI_META_API_KEY }}
+                  PUTER_TEST_AI_MINIMAX_API_KEY: ${{ secrets.PUTER_TEST_AI_MINIMAX_API_KEY }}
 
             # Realtime conversations through the SDK against live OpenAI. Builds
             # the SDK bundle these tests load itself, so it runs even when the

.github/workflows/backend-tests.yaml

@@ -23,8 +23,10 @@ jobs:
     outputs:
       backend: ${{ steps.filter.outputs.backend }}
     steps:
-      - uses: actions/checkout@v7
-      - uses: dorny/paths-filter@v4
+      - uses: actions/checkout@v7.0.1
+        with:
+          persist-credentials: false
+      - uses: dorny/[email protected]
         id: filter
         with:
           filters: |
@@ -52,10 +54,12 @@ jobs:
     runs-on: ubuntu-latest
     steps:
       - name: Checkout repository
-        uses: actions/checkout@v7
+        uses: actions/checkout@v7.0.1
+        with:
+          persist-credentials: false
 
       - name: Set up Node.js
-        uses: actions/setup-node@v7
+        uses: actions/setup-node@v7.1.0
         with:
           node-version: '26'
           cache: 'npm'
@@ -80,13 +84,14 @@ jobs:
 
     steps:
       - name: Checkout
-        uses: actions/checkout@v7
+        uses: actions/checkout@v7.0.1
         with:
+          persist-credentials: false
           ref: ${{ github.event.pull_request.head.sha || github.sha }}
           repository: ${{ github.event.pull_request.head.repo.full_name || github.repository }}
 
       - name: Set up Node.js
-        uses: actions/setup-node@v7
+        uses: actions/setup-node@v7.1.0
         with:
           node-version: '26'
           cache: 'npm'
@@ -106,7 +111,7 @@ jobs:
 
       - name: Upload blob report
         if: ${{ !cancelled() }}
-        uses: actions/upload-artifact@v7
+        uses: actions/upload-artifact@v7.0.2
         with:
           name: backend-blob-${{ matrix.shard }}
           path: .vitest-reports/
@@ -146,13 +151,14 @@ jobs:
     runs-on: ubuntu-latest
     steps:
       - name: Checkout
-        uses: actions/checkout@v7
+        uses: actions/checkout@v7.0.1
         with:
+          persist-credentials: false
           ref: ${{ github.event.pull_request.head.sha || github.sha }}
           repository: ${{ github.event.pull_request.head.repo.full_name || github.repository }}
 
       - name: Set up Node.js
-        uses: actions/setup-node@v7
+        uses: actions/setup-node@v7.1.0
         with:
           node-version: '26'
           cache: 'npm'
@@ -161,7 +167,7 @@ jobs:
         run: npm ci
 
       - name: Download blob reports
-        uses: actions/download-artifact@v8
+        uses: actions/download-artifact@v8.0.2
         with:
           pattern: backend-blob-*
           path: .vitest-reports
@@ -173,7 +179,7 @@ jobs:
           CI: 'true'
 
       - name: Upload coverage artifact
-        uses: actions/upload-artifact@v7
+        uses: actions/upload-artifact@v7.0.2
         with:
           name: backend-coverage-${{ github.event_name == 'push' && 'main' || 'pr' }}
           path: src/backend/coverage/
@@ -204,7 +210,7 @@ jobs:
 
       - name: Report coverage on PR
         if: github.event_name == 'pull_request'
-        uses: davelosert/vitest-coverage-report-action@v2
+        uses: davelosert/vitest-coverage-report-action@v2.13.2
         with:
           json-summary-path: src/backend/coverage/coverage-summary.json
           json-final-path: src/backend/coverage/coverage-final.json

.github/workflows/dependabot-automerge.yml

@@ -13,7 +13,7 @@ jobs:
     steps:
       - name: Dependabot metadata
         id: metadata
-        uses: dependabot/fetch-metadata@v3
+        uses: dependabot/fetch-metadata@v3.1.0
         with:
           github-token: "${{ secrets.GITHUB_TOKEN }}"
 

.github/workflows/docker-image.yaml

@@ -45,30 +45,32 @@ jobs:
                   fi
 
             - name: Checkout repository
-              uses: actions/checkout@v7
+              uses: actions/checkout@v7.0.1
+              with:
+                  persist-credentials: false
 
             - name: Log in to GitHub Package Container registry
-              uses: docker/login-action@v4
+              uses: docker/login-action@v4.8.0
               with:
                   registry: ${{ env.REGISTRY }}
                   username: ${{ github.actor }}
                   password: ${{ secrets.GITHUB_TOKEN }}
 
             - name: Log in to Docker Hub
-              uses: docker/login-action@v4
+              uses: docker/login-action@v4.8.0
               with:
                   username: ${{ secrets.DOCKERHUB_USERNAME }}
                   password: ${{ secrets.DOCKERHUB_TOKEN }}
 
             - name: Set up QEMU
-              uses: docker/setup-qemu-action@v4
+              uses: docker/setup-qemu-action@v4.4.0
 
             - name: Set up Docker Buildx
-              uses: docker/setup-buildx-action@v4
+              uses: docker/setup-buildx-action@v4.4.1
 
             - name: Extract metadata (tags, labels) for Docker
               id: meta
-              uses: docker/metadata-action@v6
+              uses: docker/metadata-action@v6.2.0
               with:
                   images: |
                       ${{ env.REGISTRY }}/${{ env.IMAGE_NAME }}
@@ -82,7 +84,7 @@ jobs:
                       type=raw,value=main,enable=${{ github.event_name == 'push' || inputs.push_main }}
 
             - name: Build and push Docker image
-              uses: docker/build-push-action@v7
+              uses: docker/build-push-action@v7.4.0
               with:
                   platforms: linux/amd64,linux/arm64
                   context: .
@@ -95,7 +97,7 @@ jobs:
                   cache-to: type=gha,mode=max
 
             - name: Sync README to Docker Hub
-              uses: peter-evans/dockerhub-description@v5
+              uses: peter-evans/dockerhub-description@v5.0.0
               with:
                   username: ${{ secrets.DOCKERHUB_USERNAME }}
                   password: ${{ secrets.DOCKERHUB_TOKEN }}

.github/workflows/docs-build.yml

@@ -5,16 +5,21 @@ on:
     paths:
       - 'src/docs/**'
 
+permissions:
+  contents: read
+
 jobs:
   build-docs:
     runs-on: ubuntu-latest
 
     steps:
       - name: Checkout repository
-        uses: actions/checkout@v7
+        uses: actions/checkout@v7.0.1
+        with:
+          persist-credentials: false
 
       - name: Set up Node.js
-        uses: actions/setup-node@v7
+        uses: actions/setup-node@v7.1.0
         with:
           node-version: '26'
           cache: 'npm'

.github/workflows/main.yml

@@ -1,40 +0,0 @@
-name: Maintain Release Merge PR
-
-on:
-  push:
-    branches:
-      - main
-
-jobs:
-  update-release-pr:
-    runs-on: ubuntu-latest
-    steps:
-      - uses: actions/checkout@v7
-      - name: Setup Git
-        run: |
-          git config user.name github-actions
-          git config user.email [email protected]
-      - name: Check for existing PR
-        id: find-pr
-        uses: juliangruber/find-pull-request-action@v1
-        with:
-          github-token: ${{ secrets.GITHUB_TOKEN }}
-          branch: release
-      - uses: actions/checkout@v7
-        if: steps.find-pr.outputs.number == ''
-        with:
-          ref: release
-      - name: Reset release branch
-        if: steps.find-pr.outputs.number == ''
-        run: |
-          git fetch origin main:main
-          git reset --hard main
-      - name: Create/Update PR
-        if: steps.find-pr.outputs.number == ''
-        uses: peter-evans/create-pull-request@v8
-        with:
-          token: ${{ secrets.GITHUB_TOKEN }}
-          commit-message: Update release branch
-          title: Merge Release Auto-PR
-          body: Merging this PR will invoke release actions          
-          branch: auto-update/release

.github/workflows/notify-prod.yaml

@@ -5,6 +5,8 @@ on:
     branches:
       - main
 
+permissions: {}
+
 jobs:
   notify:
     runs-on: ubuntu-latest

.github/workflows/puterjs-tests.yaml

@@ -22,8 +22,10 @@ jobs:
     outputs:
       puterjs: ${{ steps.filter.outputs.puterjs }}
     steps:
-      - uses: actions/checkout@v7
-      - uses: dorny/paths-filter@v4
+      - uses: actions/checkout@v7.0.1
+        with:
+          persist-credentials: false
+      - uses: dorny/[email protected]
         id: filter
         with:
           filters: |
@@ -52,10 +54,12 @@ jobs:
 
     steps:
       - name: Checkout
-        uses: actions/checkout@v7
+        uses: actions/checkout@v7.0.1
+        with:
+          persist-credentials: false
 
       - name: Set up Node.js
-        uses: actions/setup-node@v7
+        uses: actions/setup-node@v7.1.0
         with:
           node-version: '26'
           cache: 'npm'
@@ -73,10 +77,12 @@ jobs:
 
     steps:
       - name: Checkout
-        uses: actions/checkout@v7
+        uses: actions/checkout@v7.0.1
+        with:
+          persist-credentials: false
 
       - name: Set up Node.js
-        uses: actions/setup-node@v7
+        uses: actions/setup-node@v7.1.0
         with:
           node-version: '26'
           cache: 'npm'
@@ -130,14 +136,15 @@ jobs:
     steps:
       - name: Checkout ${{ matrix.ref }}
         if: needs.changes.outputs.puterjs == 'true'
-        uses: actions/checkout@v7
+        uses: actions/checkout@v7.0.1
         with:
+          persist-credentials: false
           ref: ${{ matrix.ref }}
           repository: ${{ matrix.repository }}
 
       - name: Set up Node.js
         if: needs.changes.outputs.puterjs == 'true'
-        uses: actions/setup-node@v7
+        uses: actions/setup-node@v7.1.0
         with:
           node-version: '26'
           cache: 'npm'
@@ -161,7 +168,7 @@ jobs:
 
       - name: Upload coverage artifact
         if: needs.changes.outputs.puterjs == 'true' && !cancelled()
-        uses: actions/upload-artifact@v7
+        uses: actions/upload-artifact@v7.0.2
         with:
           name: puterjs-coverage-${{ matrix.artifact }}
           path: src/puter-js/coverage/coverage-*.json
@@ -174,13 +181,15 @@ jobs:
     runs-on: ubuntu-latest
     steps:
       - name: Checkout repository
-        uses: actions/checkout@v7
+        uses: actions/checkout@v7.0.1
+        with:
+          persist-credentials: false
 
       # Missing when the PR leg failed; `coverage (pr)` already reports that.
       - name: Download PR coverage
         id: pr-coverage
         continue-on-error: true
-        uses: actions/download-artifact@v8
+        uses: actions/download-artifact@v8.0.2
         with:
           name: puterjs-coverage-pr
           path: src/puter-js/coverage
@@ -191,14 +200,14 @@ jobs:
         id: base-coverage
         if: steps.pr-coverage.outcome == 'success'
         continue-on-error: true
-        uses: actions/download-artifact@v8
+        uses: actions/download-artifact@v8.0.2
         with:
           name: puterjs-coverage-base
           path: coverage-base
 
       - name: Report coverage on PR
         if: steps.pr-coverage.outcome == 'success' && steps.base-coverage.outcome == 'success'
-        uses: davelosert/vitest-coverage-report-action@v2
+        uses: davelosert/vitest-coverage-report-action@v2.13.2
         with:
           name: puter.js SDK
           json-summary-path: src/puter-js/coverage/coverage-summary.json
@@ -207,7 +216,7 @@ jobs:
 
       - name: Report coverage on PR (no base comparison)
         if: steps.pr-coverage.outcome == 'success' && steps.base-coverage.outcome != 'success'
-        uses: davelosert/vitest-coverage-report-action@v2
+        uses: davelosert/vitest-coverage-report-action@v2.13.2
         with:
           name: puter.js SDK
           json-summary-path: src/puter-js/coverage/coverage-summary.json

.github/workflows/release-please.yml

@@ -1,18 +0,0 @@
-on:
-  push:
-    branches:
-      - main
-
-permissions:
-  contents: write
-  pull-requests: write
-
-name: release-please
-
-jobs:
-  release-please:
-    runs-on: ubuntu-latest
-    steps:
-      - uses: google-github-actions/release-please-action@v4
-        with:
-          release-type: node

.github/workflows/tag-alias.yaml

@@ -45,14 +45,14 @@ jobs:
           fi
 
       - name: Log in to GitHub Package Container registry
-        uses: docker/login-action@v4
+        uses: docker/login-action@v4.8.0
         with:
           registry: ${{ env.REGISTRY }}
           username: ${{ github.actor }}
           password: ${{ secrets.GITHUB_TOKEN }}
 
       - name: Set up Docker Buildx
-        uses: docker/setup-buildx-action@v4
+        uses: docker/setup-buildx-action@v4.4.1
 
       - name: Create alias tag
         env:

AGENTS.md

@@ -9,6 +9,7 @@ Use these as the source of truth before exploring further:
 - [README.md](README.md) — project overview and quickstart.
 - [doc/architecture.md](doc/architecture.md) — backend layered stack (controllers → drivers → services → stores → clients), `PuterServer` wiring, `Context` (ALS), actors, and extensions.
 - [doc/contributing-apis.md](doc/contributing-apis.md) — adding and maintaining public APIs end to end (backend surface → puter.js → types → docs → tests). Follow it for any API work.
+- [doc/ai-drivers.md](doc/ai-drivers.md) — where AI driver code lives (interfaces, providers, protocols, shared), the import rules between those folders, and how to add a provider or an AI interface.
 - [doc/pagination.md](doc/pagination.md) — the one pagination convention for list APIs (limit/cursor/offset/includeTotal, envelope shape, cursor semantics).
 - [doc/alarms.md](doc/alarms.md) — raising alarms and picking a severity (what pages, what only gets recorded), plus the config that routes them.
 - [doc/self-hosting.md](doc/self-hosting.md) — running Puter outside hosted infra.
@@ -70,7 +71,7 @@ Commit messages and PR descriptions never credit anyone or mention a bug report.
 - **Test new behavior.** Every new function, endpoint, driver method, or logic branch gets a test; every bug fix gets a regression test that fails before the fix. If something is genuinely hard to test, skip it but say so in the PR.
 - **Boy Scout Rule, proportional to the change.** In files you're already touching, fix the typo, the dead import, the missing test, the bit you had to read twice. Don't ride a refactor along with a bug fix.
 - **Understand what you commit.** AI assistance is fine; shipping code you couldn't have written, debugged, or defended in review is not.
-- **A limit change is not done until the docs change with it.** Every rate limit, concurrency cap, quota, and allowance in the code is published in [src/docs/src/rate-limits-and-quotas.md](src/docs/src/rate-limits-and-quotas.md) — an undisclosed limit is one developers discover as a service failure. If a PR moves any of these numbers, the same PR updates that page. The numbers live in `src/backend/controllers/fs/limits.ts` (filesystem), `src/backend/drivers/util/aiLimits.ts` (all AI drivers), per-driver `rateLimit`/`concurrent` configs, and `src/backend/data/subPolicies/` (free-tier allowances).
+- **A limit change is not done until the docs change with it.** Every rate limit, concurrency cap, quota, and allowance in the code is published in [src/docs/src/rate-limits-and-quotas.md](src/docs/src/rate-limits-and-quotas.md) — an undisclosed limit is one developers discover as a service failure. If a PR moves any of these numbers, the same PR updates that page. The numbers live in `src/backend/controllers/fs/limits.ts` (filesystem), `src/backend/drivers/ai/shared/aiLimits.ts` (all AI drivers), per-driver `rateLimit`/`concurrent` configs, and `src/backend/data/subPolicies/` (free-tier allowances).
 
 ---
 
@@ -97,6 +98,10 @@ Layer rules:
 - **Drivers and controllers stay thin.** Domain rules a second entry point needs (signup, app CRUD, worker deploy, AI routing/billing) live in a service, not in the first driver or controller that needed them.
 - **Prefer explicit arguments over [`Context`](src/backend/core/context.ts) (ALS).** Use it only for request-scoped values that would otherwise thread through many layers; today that's mostly `actor` and `req`.
 
+### AI drivers
+
+AI drivers live in [src/backend/drivers/ai/](src/backend/drivers/ai/): `interfaces/` holds the Puter-facing drivers, `providers/<vendor>/<interface>/` holds vendor code, `protocols/` holds wire protocols several vendors speak, and `shared/` holds helpers more than one interface uses. Follow [doc/ai-drivers.md](doc/ai-drivers.md) when adding or moving AI code.
+
 ### Extensions
 
 [extensions/](extensions/) is for **non-crucial parts of the system**: Puter must still work with the extension removed. If core needs to call it, it belongs in core ([whoami](extensions/whoami.ts) is the cautionary example). Inside an extension, follow the same layered structure, unless it only needs a few route handlers, in which case the `extension.get/post/...` helpers are enough on their own. The `extension` API is in [doc/architecture.md](doc/architecture.md#extension-api).

config.template.jsonc

@@ -254,6 +254,16 @@
             "user": "",
             "pass": ""
         }
+        // Each send names a stream: "auth", "signup" or "notify". A stream
+        // listed here adds its headers to every message on it, and its "from"
+        // when the sender gives none. Tags are written to "tagsHeader".
+        // "streams": {
+        //     "notify": {
+        //         "from": "\"Puter\" <[email protected]>",
+        //         "headers": { "X-Example-Stream": "notify" },
+        //         "tagsHeader": "X-Example-Tags"
+        //     }
+        // }
     },
 
     // ── Inbound mail (separate process) ─────────────────────────────────

doc/ai-drivers.md

@@ -0,0 +1,153 @@
+# AI Drivers
+
+Where the AI driver code lives under [src/backend/drivers/ai/](../src/backend/drivers/ai/), what each folder owns, and how to add a provider or a new AI interface. The general layer rules are in [architecture.md](architecture.md) and [AGENTS.md](../AGENTS.md#backend). This page covers what is specific to AI.
+
+## Layout
+
+```text
+src/backend/drivers/ai/
+├── interfaces/    Puter-facing drivers, one folder per AI interface
+├── providers/     Vendor code, as providers/<vendor>/<interface>/
+├── protocols/     Wire protocols that several vendors speak
+└── shared/        Helpers that more than one interface uses
+```
+
+| Folder | Owns | Example |
+| --- | --- | --- |
+| `interfaces/<interface>/` | The driver class, the interface's contracts in `types.ts`, its provider base class where one exists, and the helpers and tests that apply to every provider of that interface. | [interfaces/chat/ChatCompletionDriver.ts](../src/backend/drivers/ai/interfaces/chat/ChatCompletionDriver.ts) |
+| `providers/<vendor>/<interface>/` | One vendor's implementation of one interface: the adapter, its model catalog and prices, its fixtures, and its tests. | [providers/gemini/video/](../src/backend/drivers/ai/providers/gemini/video/) |
+| `providers/<vendor>/` | Helpers that several of that vendor's interfaces use. | [providers/gemini/geminiRest.ts](../src/backend/drivers/ai/providers/gemini/geminiRest.ts) |
+| `protocols/openaiCompatible/` | The OpenAI wire protocol: the base provider class, message and usage conversion, and parameter mapping for Chat Completions and Responses. | [protocols/openaiCompatible/OpenAICompatProvider.ts](../src/backend/drivers/ai/protocols/openaiCompatible/OpenAICompatProvider.ts) |
+| `shared/` | Helpers that more than one interface uses: limits, the provider registry, the remote catalog cache, job polling, streamed charging, and media input. | [shared/aiLimits.ts](../src/backend/drivers/ai/shared/aiLimits.ts) |
+
+Helpers that non-AI code also uses stay in [src/backend/drivers/util/](../src/backend/drivers/util/): file input, data URIs, upstream error mapping, and stream piping.
+
+AI code that a service also needs lives in [src/backend/util/](../src/backend/util/), because a service can't import from the driver layer. The realtime relay in `services/realtime/` bills through the same cost factor as the drivers, so these three files are there:
+
+| File | Holds |
+| --- | --- |
+| [aiCostFactor.ts](../src/backend/util/aiCostFactor.ts) | `withAiCostFactor`, the metering view every AI driver and the realtime relay record usage through, and `withAiCreditHold`. |
+| [aiProviderKey.ts](../src/backend/util/aiProviderKey.ts) | `readProviderKey`, which reads an API key from `config.providers` blocks. |
+| [aiPrices.ts](../src/backend/util/aiPrices.ts) | Vendor prices that a driver and a service both bill. |
+
+### Interfaces
+
+| Folder | Driver | `driverInterface` | `driverName` | Key in `puterDrivers` |
+| --- | --- | --- | --- | --- |
+| `interfaces/chat/` | `ChatCompletionDriver` | `puter-chat-completion` | `ai-chat` | `aiChat` |
+| `interfaces/image/` | `ImageGenerationDriver` | `puter-image-generation` | `ai-image` | `aiImage` |
+| `interfaces/video/` | `VideoGenerationDriver` | `puter-video-generation` | `ai-video` | `aiVideo` |
+| `interfaces/textToSpeech/` | `TTSDriver` | `puter-tts` | `ai-tts` | `aiTts` |
+| `interfaces/speechToText/` | `SpeechToTextDriver` | `puter-speech2txt` | `ai-speech2txt` | `aiSpeech2Txt` |
+| `interfaces/speechToSpeech/` | `VoiceChangerDriver` | `puter-speech2speech` | `ai-speech2speech` | `aiSpeech2Speech` |
+| `interfaces/ocr/` | `OCRDriver` | `puter-ocr` | `ai-ocr` | `aiOcr` |
+
+Folder names are not runtime identifiers. `driverInterface`, `driverName`, driver aliases, the keys under `providers` in config, provider ids, model ids, and usage keys are public contracts. Moving or renaming a file never changes them.
+
+## Request flow
+
+A call goes from the interface to a provider, and from there to a shared protocol when the vendor speaks one:
+
+```text
+interfaces/chat/ChatCompletionDriver.ts
+    validates the call, picks the model and provider, holds credits
+  → providers/deepseek/chat/DeepSeekProvider.ts
+        DeepSeek's catalog, endpoint, and request differences
+    → protocols/openaiCompatible/OpenAICompatProvider.ts
+          the OpenAI-compatible request, response, and stream handling
+```
+
+A provider whose vendor has its own API, such as `ClaudeProvider` or `ElevenLabsTTSProvider`, implements the interface's contract directly and uses no protocol.
+
+## Import rules
+
+- `shared/` imports nothing from `interfaces/`, `providers/`, or `protocols/`.
+- Nothing in `services/`, `stores/`, or `clients/` imports from `drivers/ai/`. Code that a service and a driver both need goes in `src/backend/util/`.
+- `providers/` and `protocols/` import an interface's `types.ts` and helpers. They never import a driver class. Their tests can, to drive a provider through the real driver.
+- Only an interface's driver file imports providers, to register them. The interface's helpers don't.
+- An interface doesn't import another interface. When a second interface needs a helper, move the helper to `shared/`, or to `providers/<vendor>/` when it belongs to one vendor.
+- A vendor folder imports another vendor's folder only when it serves that vendor's models. `providers/azure/` reads the OpenAI and xAI catalogs for that reason.
+
+## Where a file goes
+
+| The code is | It goes in |
+| --- | --- |
+| Input validation, gates, routing, credit holds, or anything else every provider of the interface gets | `interfaces/<interface>/` |
+| A request or response contract that providers implement | `interfaces/<interface>/types.ts` |
+| A vendor's endpoint, request shape, catalog, prices, or quirks | `providers/<vendor>/<interface>/` |
+| A vendor's auth, REST plumbing, or constants that two of its interfaces use | `providers/<vendor>/` |
+| Behavior of a wire protocol that several vendors speak | `protocols/<protocol>/` |
+| A helper that two or more interfaces use and that belongs to no vendor | `shared/` |
+| A helper that non-AI drivers or controllers also use | `src/backend/drivers/util/` |
+| AI code that a service also uses | `src/backend/util/`, in a file named `ai<Something>.ts` |
+
+Keep a helper next to its only consumer. Move it up when a second consumer appears, not before.
+
+When one Puter option becomes a different request shape per vendor, the interface reads the option and each dialect maps it. The chat `compaction` option is read in `interfaces/chat/utils/compaction.js`, mapped for OpenAI by `toOpenAiContextManagement` in `protocols/openaiCompatible/openaiParams.ts`, and mapped for Anthropic by `toAnthropicContextManagement` in `providers/claude/chat/contextManagement.ts`. Tools work the same way: `normalize_tools_object` in the interface, then `toolsToWire` for OpenAI and `claudeToolPolicy` for Anthropic.
+
+Tests sit next to the code they test. Fixtures go in a `fixtures/` folder next to the test that reads them.
+
+## Adding a provider
+
+1. Create `providers/<vendor>/<interface>/`. Use the vendor's existing folder if it has one, so all of a vendor's interfaces stay together.
+2. Implement the interface's contract from `interfaces/<interface>/types.ts`:
+
+    | Interface | Contract | Base class |
+    | --- | --- | --- |
+    | chat | `IChatProvider` | `OpenAICompatProvider` for an OpenAI-compatible vendor |
+    | image | `IImageProvider` | none |
+    | video | `IVideoProvider` | `VideoProvider` |
+    | textToSpeech | `ITTSProvider` | none |
+    | speechToText | `ISpeechToTextProvider` | `SpeechToTextProvider` |
+    | ocr | `IOcrProvider` | none |
+
+    Speech to speech has one provider, so `VoiceChangerDriver` uses `ElevenLabsSpeechToSpeechProvider` directly. Add a contract to its `types.ts` when a second provider needs one.
+
+3. Put the model catalog and prices in the same folder, as `models.ts` or `costs.ts`. A provider that loads its catalog from the vendor wraps the fetch in `cachedRemoteCatalog` from `shared/`.
+4. Register the provider in the interface's driver: in `#registerProviders()`, or in `onServerStart()` for OCR and speech to speech. A chat provider built from an API key and an optional base URL is one row in `KEYED_PROVIDERS` instead. Text to speech and speech to text also list the provider id and its aliases in `providerAliases.ts`.
+5. Read credentials from `config.providers[<key>]`. The key is part of the self-hosting config contract, so reuse the vendor's existing key when it has one.
+6. Add tests next to the provider. Mock the vendor SDK or `fetch` at the network boundary and drive the provider through the real driver where you can. A live test is a `*.integration.test.ts` file that skips itself, with `skipUnlessEnv` from [testEnv.ts](../src/backend/testEnv.ts), unless its `PUTER_TEST_AI_*` variable is set. Helpers for provider tests are in [shared/integrationTestUtil.ts](../src/backend/drivers/ai/shared/integrationTestUtil.ts).
+7. For a chat provider, add its static catalog to `CATALOGS` in [modelCatalogs.test.ts](../src/backend/drivers/ai/interfaces/chat/modelCatalogs.test.ts) and the provider to [providerConsistency.test.ts](../src/backend/drivers/ai/interfaces/chat/providerConsistency.test.ts). The catalog test fails when a `providers/*/chat/` file with "model" in its name exports a catalog that isn't listed.
+8. Add the provider's config key to the `providers` config of the interface's [fuzz suite](#fuzz-tests), and its id to the list of providers the suite expects.
+9. Update the published docs for the models and limits the provider adds, following [contributing-apis.md](contributing-apis.md).
+
+### OpenAI-compatible vendors
+
+A vendor that speaks the OpenAI Chat Completions protocol extends `OpenAICompatProvider` and overrides only what differs. It still gets its own `providers/<vendor>/chat/` folder.
+
+Vendors share one constants-only folder only when at least six of them differ in nothing but base URL and model catalog. Each then becomes one data file under `providers/openaiCompatible/providers/`, read by a single implementation. No vendor qualifies today, because every subclass overrides request, catalog, or billing behavior.
+
+## Fuzz tests
+
+Two seeded suites send malformed input through the real drivers and providers. They run with the rest of the backend tests.
+
+| Suite | Covers |
+| --- | --- |
+| [interfaces/chat/ChatCompletionDriver.fuzz.test.ts](../src/backend/drivers/ai/interfaces/chat/ChatCompletionDriver.fuzz.test.ts) | Chat requests with a few values changed, and valid requests against wrong statuses, bodies of the wrong shape, and broken event streams. |
+| [interfaces/mediaDrivers.fuzz.test.ts](../src/backend/drivers/ai/interfaces/mediaDrivers.fuzz.test.ts) | Image, video, speech and OCR requests with a few values changed. Every vendor refuses the request. |
+
+What the suites assert:
+
+- A malformed request never fails with an error that has no status, which `/drivers/call` would report as an unclassified 500.
+- For chat, with the vendors answering, a malformed request also never fails with a 5xx and never marks a route unhealthy.
+- When the upstream misbehaves, chat ends with an answer or an `HttpError`. A stream only has to end: the error line a stream carries isn't checked, so a malformed event can still end one with a 500.
+- Requests reach the vendors, and with the vendors answering some chat requests are answered, so a suite that stops exercising the providers fails.
+
+The vendors are played at the HTTP boundary by `upstream` in [shared/fuzzTestUtil.ts](../src/backend/drivers/ai/shared/fuzzTestUtil.ts), which stands in for global `fetch`, undici `fetch` and axios, and makes `https.request` throw so an SDK with its own client fails the suite. The vendors' SDKs run, except Groq's, which is swapped for the OpenAI SDK, and the AWS clients, whose `send` is stubbed. The media suite calls the drivers as a user with unlimited metering, so a request gets past file input and the credit hold to the vendor. A provider that loads its catalog from the vendor registers no models there, so the suites skip it.
+
+A failure lists each distinct finding with its case number and input. Each case is generated from the seed and its own number, so the same case fails again on the next run. Routes are picked by rendezvous hashing: a model added to a catalog takes only the cases it wins, and every other case keeps its route. To search further, raise the case count:
+
+```sh
+PUTER_FUZZ_CASES=100000 npx vitest run --config src/backend/vitest.config.ts src/backend/drivers/ai/interfaces/chat/ChatCompletionDriver.fuzz.test.ts
+```
+
+When a suite finds a crash, validate the value where the request enters, in the driver or in `normalize_single_message`, so every provider is covered. Reject only what crashed: a value a provider ignored or refused before must still reach it. An option a driver reads as text, a number or a flag goes in the driver's `SCALAR_OPTIONS`, and `assertScalarOptions` from `shared/scalarOptions.ts` answers 400 for a value there that can't be converted to text. Add a unit test for the case next to the fix.
+
+## Adding an interface
+
+1. Create `interfaces/<interface>/` with the driver class and a `types.ts` for the contracts providers implement.
+2. Register the driver in [src/backend/drivers/index.ts](../src/backend/drivers/index.ts).
+3. Use `AI_RATE_LIMIT` and `AI_CONCURRENT` from `shared/aiLimits.ts`, and publish any new limit in [rate-limits-and-quotas.md](../src/docs/src/rate-limits-and-quotas.md).
+4. Meter through `withAiCostFactor` from `src/backend/util/aiCostFactor.ts`, and route between providers with `ProviderRegistry` from `shared/providerRegistry.ts`.
+5. List the options the providers read as text, a number or a flag in a `SCALAR_OPTIONS` array, and call `assertScalarOptions` from `shared/scalarOptions.ts` first in each method. Add the driver to [mediaDrivers.fuzz.test.ts](../src/backend/drivers/ai/interfaces/mediaDrivers.fuzz.test.ts).
+6. Follow [contributing-apis.md](contributing-apis.md) for the puter.js method, types, docs, and tests.

doc/architecture.md

@@ -42,6 +42,19 @@ block-beta
 
 Extensions sit alongside this stack and can register into any layer; see [Extensions](#extensions).
 
+### AI drivers
+
+The AI drivers have their own layout under [src/backend/drivers/ai/](../src/backend/drivers/ai/):
+
+| Folder | Holds |
+| --- | --- |
+| `interfaces/` | The Puter-facing drivers, one folder per AI interface (chat, image, video, text to speech, speech to text, speech to speech, OCR). |
+| `providers/` | Vendor code, as `providers/<vendor>/<interface>/`. |
+| `protocols/` | Wire protocols that several vendors speak, such as the OpenAI-compatible one. |
+| `shared/` | Helpers that more than one interface uses. |
+
+A call goes from an interface's driver to a provider, and from there to a shared protocol when the vendor speaks one. [ai-drivers.md](ai-drivers.md) has the ownership rules, the import rules, and the steps for adding a provider.
+
 ## Entry point: `PuterServer`
 
 `PuterServer` is the bootstrap. It:

doc/push-client.md

@@ -16,7 +16,7 @@ Core subscribes the browser to a push service only when the server also publishe
 
 `uid` is the notification's uid, a later push with the same `group` replaces the one showing, and `target` and `data` reach the app when the user taps it.
 
-When the browser replaces the subscription (`pushsubscriptionchange`), `sw.js` posts `{ type: 'puter-push-subscription-changed' }` to every open window on Puter's origin. The worker has no token or session, so the page's push client registers the new subscription.
+When the browser replaces the subscription (`pushsubscriptionchange`), `sw.js` keeps the new one, or subscribes again with Puter's stored key when the browser gave none and the event, the receipt or an earlier mark names the subscription that went. It writes `puter:subscription-changed:<scope>` to the `puter-push` IndexedDB as `{ at, oldEndpoint }`, the old endpoint kept from an earlier mark no page handled yet, else taken from the event or from the receipt, forgets the receipt kept for that scope, and posts `{ type: 'puter-push-subscription-changed' }` to every open window on Puter's origin. The worker has no token or session, so an open page runs `helpers/pushSync.js` on that message, after any run already in flight, and a later load does the same through the marker.
 
 ## Receipts
 
@@ -59,9 +59,9 @@ Apps on their own origin do the same through `push-sw.js`, which they import int
 
 ```ts
 interface PushClient {
-    enable(): Promise<{ deviceUid: string }>;
+    enable(options?: { background?: boolean }): Promise<{ deviceUid: string }>;
     disable(): Promise<void>;
-    status(): Promise<{
+    status(options?: { cached?: boolean }): Promise<{
         permission: 'default' | 'granted' | 'denied';
         registered: boolean;
         deviceUid?: string;
@@ -69,12 +69,12 @@ interface PushClient {
 }
 ```
 
-- `enable()` may ask for notification permission, so core calls it from a click: Turn on in the Notifications tab, Allow on a permission prompt that includes `notifications:push` while this browser is off, and the "Turn on notifications" button of the `/action/enable-push` popup and the matching desktop dialog (`UIEnablePushDialog`). Core also calls it without a click, from `helpers/pushSync.js`, when `Notification.permission` is already `granted`, `status()` reports the browser as not registered, the user has not turned push off in this browser, and an app holds `notifications:push`; the browser does not prompt then. The built-in client runs `puter.notifications.enable()`, which subscribes with the `/sw.js` registration and registers the browser through the Web Push flow above (`platform: 'webpush'`). It then resolves the `uid` of this browser's `webpush` device from `listDevices()`. It rejects when permission is refused or the browser wasn't registered.
+- `enable()` may ask for notification permission, so core calls it from a click: Turn on in the Notifications tab, Allow on a permission prompt that includes `notifications:push` while this browser is off, and the "Turn on notifications" button of the `/action/enable-push` popup and the matching desktop dialog (`UIEnablePushDialog`). Core also calls it without a click, from `helpers/pushSync.js`, when `Notification.permission` is already `granted`, `status()` reports the browser as not registered, the user has not turned push off in this browser, and an app may push to Puter's devices (`puterDevices` in `GET /push/apps`); the browser does not prompt then. That call passes `{ background: true }`: a browser the user removed in Puter stays removed, and the built-in client rejects with code `push_device_removed`, after which core records the browser as turned off. Before a background call the built-in client asks `POST /push/web/subscriptions/status` about every earlier endpoint it knows: the marker's `oldEndpoint` and the last endpoint the server answered `active` for (`puter.push.last-endpoint:<user uuid>` in `localStorage`). On a 429 it registers nothing and rejects with `too_many_requests`, which the sync reports as `later`, keeping the marker for the next run. When any answer is `removed`, it ends the current subscription in the browser, clears the marker and rejects with `push_device_removed`, so a subscription change or a dropped subscription never brings back a browser removed from another device. A click renews it as before. For a click the built-in client runs `puter.notifications.enable()`, which subscribes with the `/sw.js` registration and registers the browser through the Web Push flow above (`platform: 'webpush'`); in the background it runs the same registration without replacing a removed subscription or opening Puter's sign-in. It then resolves the `uid` of this browser's `webpush` device from `listDevices()` and clears the subscription-changed marker. It rejects when permission is refused or the browser wasn't registered.
 - `disable()` runs `puter.notifications.disable()`, which sends `DELETE /push/web/subscriptions { endpoint }` and ends the browser's subscription. The tab calls it for Turn off, and for Remove on the device marked as this browser. Remove on any other device is `DELETE /push/devices/:uid`.
-- `status()` reports the state without prompting. `permission` is `Notification.permission`. `registered` is true when this browser has a device registered for the signed-in user, and `deviceUid` is that device's `uid`.
+- `status()` reports the state without prompting. `permission` is `Notification.permission`. `registered` is true when this browser has a device registered for the signed-in user and `POST /push/web/subscriptions/status` answers `active` for the current subscription's endpoint, and `deviceUid` is that device's `uid`. A server that can't answer leaves the device match alone, and so does an `unknown` for an endpoint `enable()` registered in this page in the last 5 minutes, since that check can trail a registration. While the subscription-changed marker is set, `registered` is false. With `{ cached: true }` a client may answer with the last registered state it read in this page. Core passes it for the silent registration on app launch and for an app's `puter.notifications.status()`; the Notifications tab and the push dialogs read fresh. The built-in client keeps that state in memory for the same user and subscription for up to 5 minutes, from `enable()` or once the server answered `active` for the endpoint, and answers from it without either request. Reads of the same user and endpoint share one real check while it is in flight. It drops it on `disable()`, a failed `enable()`, an unregistered answer, a set subscription-changed marker, and the worker's `puter-push-subscription-changed` message, so a new page load always asks the server. Whether the calling app may push is checked on every call, against a `GET /push/apps` answer the page reuses for 30 seconds and drops on `enable()`, `disable()`, a grant, a revoke and a user change. When it can't be read, or leaves the app out, the grant alone counts.
 
 After `enable()` resolves, the tab calls `POST /push/devices/:uid/test` and asks the user whether a notification showed up.
 
 The tab also reads `GET /push/apps` and `GET`/`POST /push/preferences`.
 
-Core keeps its own record of a browser the user turned off, `puter.push.browser-off:<user uuid>` in `localStorage`, written by Turn off and by Remove on this browser's device, and cleared when `enable()` resolves. The silent registration above skips a browser with that record, so a device removed here stays removed while one removed from another device, or a new sign-in in a browser that already allows notifications, registers again.
+Core keeps its own record of a browser the user turned off, `puter.push.browser-off:<user uuid>` in `localStorage`, written by Turn off, by Remove on this browser's device, and by a silent registration the server refuses with `push_device_removed`, and cleared when `enable()` resolves. The silent registration above skips a browser with that record, so a device removed here or from another device stays removed until the user turns it on from a click, while a new sign-in in a browser that already allows notifications registers again.

doc/self-hosting.md

@@ -326,6 +326,20 @@ Used for password resets, email confirmation, and notifications. Without it thos
 
 To require email confirmation before login, also set `"strict_email_verification_required": true`.
 
+Account and notification mail is sent on a named stream: `auth` (password, address and 2FA changes), `signup` (address confirmation; a `puter.signup.validate` listener may name another: lowercase letters, digits, `:`, `_` and `-`, up to 64 characters, starting with a letter or digit) and `notify` (share, app feedback and contact form mail). Add `"streams"` inside `"email"` to configure one, for instance to let your mail provider route or report each kind of mail separately:
+
+```json
+"streams": {
+    "notify": {
+        "from": "\"Puter\" <[email protected]>",
+        "headers": { "X-Example-Stream": "notify" },
+        "tagsHeader": "X-Example-Tags"
+    }
+}
+```
+
+`headers` are added to every message on the stream, `from` replaces the default sender, and `tagsHeader` names the header that carries a message's tags as `name=value` pairs joined by `, `. A stream that is not listed adds nothing: the message goes out with the default from address and the caller's headers. `streams` is never handed to the transport.
+
 To read the mail yourself instead of sending it, point the transport at a local SMTP sink — [MailHog](https://github.com/mailhog/MailHog) catches everything and serves it at `http://localhost:8025`. Publish both ports; a container that only exposes them is unreachable from the host:
 
 ```sh

package-lock.json

@@ -897,21 +897,21 @@
       }
     },
     "node_modules/@babel/core": {
-      "version": "7.29.7",
-      "resolved": "https://registry.npmjs.org/@babel/core/-/core-7.29.7.tgz",
-      "integrity": "sha512-RgHBCvtjbOK2gXSNBNIkNoEc9qoVEtau3hj8gEqKQuL3HZAibKarWFEI3Lfm6EYKkLalOh8eSrj9b+ch9H/VBA==",
+      "version": "7.29.13",
+      "resolved": "https://registry.npmjs.org/@babel/core/-/core-7.29.13.tgz",
+      "integrity": "sha512-j1nvOQCZYSgp7HLmisnCXFTpVvFODiijQ9QHkORfGKWH6YDtskTEeCJS7eV545GZ9UBzrq0e2xsOd5QQ5PjIqw==",
       "dev": true,
       "license": "MIT",
       "dependencies": {
         "@babel/code-frame": "^7.29.7",
-        "@babel/generator": "^7.29.7",
-        "@babel/helper-compilation-targets": "^7.29.7",
-        "@babel/helper-module-transforms": "^7.29.7",
-        "@babel/helpers": "^7.29.7",
-        "@babel/parser": "^7.29.7",
+        "@babel/generator": "^7.29.13",
+        "@babel/helper-compilation-targets": "^7.29.13",
+        "@babel/helper-module-transforms": "^7.29.13",
+        "@babel/helpers": "^7.29.13",
+        "@babel/parser": "^7.29.13",
         "@babel/template": "^7.29.7",
-        "@babel/traverse": "^7.29.7",
-        "@babel/types": "^7.29.7",
+        "@babel/traverse": "^7.29.13",
+        "@babel/types": "^7.29.11",
         "@jridgewell/remapping": "^2.3.5",
         "convert-source-map": "^2.0.0",
         "debug": "^4.1.0",
@@ -938,14 +938,14 @@
       }
     },
     "node_modules/@babel/generator": {
-      "version": "7.29.7",
-      "resolved": "https://registry.npmjs.org/@babel/generator/-/generator-7.29.7.tgz",
-      "integrity": "sha512-DkXD5OJQaAQIdZ1bt3UZdEnHAn9Imd3IVBdX03UFe+ony9Ojw5pzr9YVKGDY1jt+Gcn/FnGkNf8r+Vj5NOJWtQ==",
+      "version": "7.29.13",
+      "resolved": "https://registry.npmjs.org/@babel/generator/-/generator-7.29.13.tgz",
+      "integrity": "sha512-T5FRo+RzVHvGjWOuF1Ljc44b+NXAOazodHkGUHp4I3zCkQ4/sNVJm56h1S278LMR0bY5xBhztGziSbli8zObIw==",
       "dev": true,
       "license": "MIT",
       "dependencies": {
-        "@babel/parser": "^7.29.7",
-        "@babel/types": "^7.29.7",
+        "@babel/parser": "^7.29.13",
+        "@babel/types": "^7.29.11",
         "@jridgewell/gen-mapping": "^0.3.12",
         "@jridgewell/trace-mapping": "^0.3.28",
         "jsesc": "^3.0.2"
@@ -955,9 +955,9 @@
       }
     },
     "node_modules/@babel/helper-compilation-targets": {
-      "version": "7.29.7",
-      "resolved": "https://registry.npmjs.org/@babel/helper-compilation-targets/-/helper-compilation-targets-7.29.7.tgz",
-      "integrity": "sha512-wem6WaBj4NaVYVdNhLPPVacES6ZJ+KBBfSkTMD3YZxbP3rm3Di85tJU5ljaUNhaOynt+Aj0xruhYuzQBt8n71g==",
+      "version": "7.29.13",
+      "resolved": "https://registry.npmjs.org/@babel/helper-compilation-targets/-/helper-compilation-targets-7.29.13.tgz",
+      "integrity": "sha512-8WxJ4/Vmes3ghacj8VOJy3NW8eyHiFY/4thU/LSBuBE470+igjR/j1ZTNn8fV5VdNrLx6iXUwig526UdOvfP0w==",
       "dev": true,
       "license": "MIT",
       "dependencies": {
@@ -982,22 +982,15 @@
       }
     },
     "node_modules/@babel/helper-compilation-targets/node_modules/semver": {
-      "version": "6.3.1",
-      "resolved": "https://registry.npmjs.org/semver/-/semver-6.3.1.tgz",
-      "integrity": "sha512-BR7VvDCVHO+q2xBEWskxS6DJE1qRnb7DxzUrogb71CWoSficBxYsiAGd+Kl0mmq/MprG9yArRkyrQxTO6XjMzA==",
+      "version": "6.3.2",
+      "resolved": "https://registry.npmjs.org/semver/-/semver-6.3.2.tgz",
+      "integrity": "sha512-GYrCADwpu6yV5OAvchkQ27Z5wwMxWAEMg5NNWjyHh/5DboFFqbdbvYNIvZouQpxXyeMPoTOh0vdPYKlf0ZswdQ==",
       "dev": true,
       "license": "ISC",
       "bin": {
         "semver": "bin/semver.js"
       }
     },
-    "node_modules/@babel/helper-compilation-targets/node_modules/yallist": {
-      "version": "3.1.1",
-      "resolved": "https://registry.npmjs.org/yallist/-/yallist-3.1.1.tgz",
-      "integrity": "sha512-a4UGQaWPH59mOXUYnAG2ewncQS4i4F43Tv3JoAM+s2VDAmS9NsK8GpDMLrCHPksFT7h3K6TOoUNn2pb7RoXx4g==",
-      "dev": true,
-      "license": "ISC"
-    },
     "node_modules/@babel/helper-globals": {
       "version": "7.29.7",
       "resolved": "https://registry.npmjs.org/@babel/helper-globals/-/helper-globals-7.29.7.tgz",
@@ -1023,15 +1016,15 @@
       }
     },
     "node_modules/@babel/helper-module-transforms": {
-      "version": "7.29.7",
-      "resolved": "https://registry.npmjs.org/@babel/helper-module-transforms/-/helper-module-transforms-7.29.7.tgz",
-      "integrity": "sha512-UPUVSyXbOh627KiCIGQSgwWzGeBKLkaJ9PJEdrngIwMSzxLR4jS4+f1f1jb7VzBbg8nFLaYotvVPFCTqdrmTAg==",
+      "version": "7.29.13",
+      "resolved": "https://registry.npmjs.org/@babel/helper-module-transforms/-/helper-module-transforms-7.29.13.tgz",
+      "integrity": "sha512-/U96wOz+SCoZ7Da/8kjDGltcNY280JPQcRNPK0Hk3PTbdpaiBDQImtC6JsbVwb1HGMr3usZQU2WsWVjhYNmRzw==",
       "dev": true,
       "license": "MIT",
       "dependencies": {
         "@babel/helper-module-imports": "^7.29.7",
         "@babel/helper-validator-identifier": "^7.29.7",
-        "@babel/traverse": "^7.29.7"
+        "@babel/traverse": "^7.29.13"
       },
       "engines": {
         "node": ">=6.9.0"
@@ -1051,9 +1044,9 @@
       }
     },
     "node_modules/@babel/helper-string-parser": {
-      "version": "7.29.7",
-      "resolved": "https://registry.npmjs.org/@babel/helper-string-parser/-/helper-string-parser-7.29.7.tgz",
-      "integrity": "sha512-Pb5ijPrZ89GDH8223L4UP8i6QApWxs04RbPQJTeWDV0/keR2E36MeKnyr6LYmUUvqRRI+Iv87SuF1W6ErINzYw==",
+      "version": "7.29.13",
+      "resolved": "https://registry.npmjs.org/@babel/helper-string-parser/-/helper-string-parser-7.29.13.tgz",
+      "integrity": "sha512-fWegr+WsEsiMVW4KUNdIIzzMTZSzNiqhy0//6+2MRi2d5NFNsL/AYwBQW8eBnRbTBVRnDVzjaJEUqKaCWjMMdQ==",
       "dev": true,
       "license": "MIT",
       "engines": {
@@ -1081,27 +1074,27 @@
       }
     },
     "node_modules/@babel/helpers": {
-      "version": "7.29.7",
-      "resolved": "https://registry.npmjs.org/@babel/helpers/-/helpers-7.29.7.tgz",
-      "integrity": "sha512-1k2lAGRMfHTcwuNYcCNUmaUffmQv8KWMfh2iJUUeRlwlwH4FdNG7mfPI10NPfLHJFThE4Tyr4mv7kTNZOiPuBg==",
+      "version": "7.29.13",
+      "resolved": "https://registry.npmjs.org/@babel/helpers/-/helpers-7.29.13.tgz",
+      "integrity": "sha512-laoRpD/kO/iA4CDlgJbixHekg7oPvWALK0PQyK3Ob2I2njZRvVAD77RfWCIImtqWCq6KijoBoZK7bp/HlTWASQ==",
       "dev": true,
       "license": "MIT",
       "dependencies": {
         "@babel/template": "^7.29.7",
-        "@babel/types": "^7.29.7"
+        "@babel/types": "^7.29.11"
       },
       "engines": {
         "node": ">=6.9.0"
       }
     },
     "node_modules/@babel/parser": {
-      "version": "7.29.7",
-      "resolved": "https://registry.npmjs.org/@babel/parser/-/parser-7.29.7.tgz",
-      "integrity": "sha512-hnORnjP/1P/zFEndoeX+n+t1RwWRJiJpM/jO7FW32Kn9r5+sJB2JWOdYo4L6k78j15eCwY3Gm/7364B1EMwtNg==",
+      "version": "7.29.13",
+      "resolved": "https://registry.npmjs.org/@babel/parser/-/parser-7.29.13.tgz",
+      "integrity": "sha512-fJM50YYjlTiBhgdkGmC1tBpv+FMAyo4annf2X6Aks+0yRlaiVkYW/3f07xAfVVkYIoZ9fFZp+mEThUFnuybhkQ==",
       "dev": true,
       "license": "MIT",
       "dependencies": {
-        "@babel/types": "^7.29.7"
+        "@babel/types": "^7.29.11"
       },
       "bin": {
         "parser": "bin/babel-parser.js"
@@ -1135,18 +1128,18 @@
       }
     },
     "node_modules/@babel/traverse": {
-      "version": "7.29.7",
-      "resolved": "https://registry.npmjs.org/@babel/traverse/-/traverse-7.29.7.tgz",
-      "integrity": "sha512-EhlfNQtZ+NK22w5BM61ciuiq1m58ed33Wr1Xan//ZRTy6hgjnwyCffRYwzsGXdASJSUJ1guZILsErh1eQcl+zw==",
+      "version": "7.29.13",
+      "resolved": "https://registry.npmjs.org/@babel/traverse/-/traverse-7.29.13.tgz",
+      "integrity": "sha512-0ve0xMlFA73dgY1oyJRY6RoW+/bncdcOQqg6jjYcVfXBK90OdLXjm9R6lmRetdZVrPjXkKIoMVBqYFPjcAlZ4Q==",
       "dev": true,
       "license": "MIT",
       "dependencies": {
         "@babel/code-frame": "^7.29.7",
-        "@babel/generator": "^7.29.7",
+        "@babel/generator": "^7.29.13",
         "@babel/helper-globals": "^7.29.7",
-        "@babel/parser": "^7.29.7",
+        "@babel/parser": "^7.29.13",
         "@babel/template": "^7.29.7",
-        "@babel/types": "^7.29.7",
+        "@babel/types": "^7.29.11",
         "debug": "^4.3.1"
       },
       "engines": {
@@ -1154,13 +1147,13 @@
       }
     },
     "node_modules/@babel/types": {
-      "version": "7.29.7",
-      "resolved": "https://registry.npmjs.org/@babel/types/-/types-7.29.7.tgz",
-      "integrity": "sha512-4zBIxpPzowiZpusoFkyGVwakdRJUyuH5PxQ/PrqghfdFWWasvnCdPfQXHrenDai+gyLARulZjZowCOj6fjT4pA==",
+      "version": "7.29.11",
+      "resolved": "https://registry.npmjs.org/@babel/types/-/types-7.29.11.tgz",
+      "integrity": "sha512-WCsemW40Cpc6gouC1SrY6PBaZ+oLRlEVY9XBvZBI7il/HyUrb2nJ505wE1MHEFyDZNnrWDEuy4jL50WVHfTTSQ==",
       "dev": true,
       "license": "MIT",
       "dependencies": {
-        "@babel/helper-string-parser": "^7.29.7",
+        "@babel/helper-string-parser": "^7.29.11",
         "@babel/helper-validator-identifier": "^7.29.7"
       },
       "engines": {
@@ -7460,18 +7453,18 @@
       "license": "MIT"
     },
     "node_modules/body-parser": {
-      "version": "2.3.0",
-      "resolved": "https://registry.npmjs.org/body-parser/-/body-parser-2.3.0.tgz",
-      "integrity": "sha512-2cGmJupaNgg+QUwVLAucDuWuoMZ6EX9iHDRswZ5lsNYEmwPaRknMPCLZz07yTzVq/83p4o/wzbDZbBrTvGGTIw==",
+      "version": "2.4.0",
+      "resolved": "https://registry.npmjs.org/body-parser/-/body-parser-2.4.0.tgz",
+      "integrity": "sha512-Ifk1KcLrxaGt1occQagQNFNNOqRt1LFuehEnHHzB8Z6cRgIxRU1TBaiIsUiCdA+gy5PL7Y1IX31DNKkRmxtXjQ==",
       "license": "MIT",
       "dependencies": {
         "bytes": "^3.1.2",
-        "content-type": "^2.0.0",
+        "content-type": "^2.1.0",
         "debug": "^4.4.3",
         "http-errors": "^2.0.1",
-        "iconv-lite": "^0.7.2",
+        "iconv-lite": "^0.7.3",
         "on-finished": "^2.4.1",
-        "qs": "^6.15.2",
+        "qs": "^6.16.1",
         "raw-body": "^3.0.2",
         "type-is": "^2.1.0"
       },
@@ -7484,9 +7477,9 @@
       }
     },
     "node_modules/body-parser/node_modules/content-type": {
-      "version": "2.0.0",
-      "resolved": "https://registry.npmjs.org/content-type/-/content-type-2.0.0.tgz",
-      "integrity": "sha512-j/O/d7GcZCyNl7/hwZAb606rzqkyvaDctLmckbxLzHvFBzTJHuGEdodATcP3yIRoDrLHkIATJuvzbFlp/ki2cQ==",
+      "version": "2.1.0",
+      "resolved": "https://registry.npmjs.org/content-type/-/content-type-2.1.0.tgz",
+      "integrity": "sha512-mj7UPXE0jaqaOsukNZRUEfEi2AcL7C/vwmwcHV0O97eO1E1pxBZuyjlZrx5seTaNBg1U6+o35wpa35Qfcc+7ag==",
       "license": "MIT",
       "engines": {
         "node": ">=18"
@@ -9581,9 +9574,9 @@
       }
     },
     "node_modules/fastify": {
-      "version": "5.12.5",
-      "resolved": "https://registry.npmjs.org/fastify/-/fastify-5.12.5.tgz",
-      "integrity": "sha512-OB2k1dlxs5/NAABqeKV2FUHkSD2BbENsCak8yULVcymn3fHIPDVa9TI3SDnJSWYSllZmSYuZXy2gTnsT+Sut1A==",
+      "version": "5.12.7",
+      "resolved": "https://registry.npmjs.org/fastify/-/fastify-5.12.7.tgz",
+      "integrity": "sha512-v4pEPsTRPuqlDIYiQFB+BHjVN4SdHX9u0ABk0ZDUKbbdY1vsNryUd1j4Z+jQEZajvYIVk047Kimva9/AJ79GYw==",
       "funding": [
         {
           "type": "github",
@@ -16587,9 +16580,9 @@
       "license": "MIT"
     },
     "node_modules/undici": {
-      "version": "7.30.1",
-      "resolved": "https://registry.npmjs.org/undici/-/undici-7.30.1.tgz",
-      "integrity": "sha512-03KrMbjIFDWQR5RNPrSw3bd1r12JpyFQl9/yxjUbJtqkjmllqC5lFjZh6ujeuJCKr8EOQvRW872Oy/az+nLYxg==",
+      "version": "7.30.2",
+      "resolved": "https://registry.npmjs.org/undici/-/undici-7.30.2.tgz",
+      "integrity": "sha512-mLyPQnHwUxaM/rideoK/+KL8DaAJLRl4aBCfmX444aCSLnIaomqPLtNRe2jdCYcsk5wZzXrDIQC8ZeYNRAYyIA==",
       "license": "MIT",
       "engines": {
         "node": ">=20.18.1"
@@ -18141,6 +18134,13 @@
         "node": ">=10"
       }
     },
+    "node_modules/yallist": {
+      "version": "3.1.1",
+      "resolved": "https://registry.npmjs.org/yallist/-/yallist-3.1.1.tgz",
+      "integrity": "sha512-a4UGQaWPH59mOXUYnAG2ewncQS4i4F43Tv3JoAM+s2VDAmS9NsK8GpDMLrCHPksFT7h3K6TOoUNn2pb7RoXx4g==",
+      "dev": true,
+      "license": "ISC"
+    },
     "node_modules/yaml": {
       "version": "2.9.0",
       "resolved": "https://registry.npmjs.org/yaml/-/yaml-2.9.0.tgz",
@@ -18233,9 +18233,9 @@
       }
     },
     "node_modules/zod": {
-      "version": "4.4.3",
-      "resolved": "https://registry.npmjs.org/zod/-/zod-4.4.3.tgz",
-      "integrity": "sha512-ytENFjIJFl2UwYglde2jchW2Hwm4GJFLDiSXWdTrJQBIN9Fcyp7n4DhxJEiWNAJMV1/BqWfW/kkg71UDcHJyTQ==",
+      "version": "4.6.7",
+      "resolved": "https://registry.npmjs.org/zod/-/zod-4.6.7.tgz",
+      "integrity": "sha512-g8W2D2kU6a8untc053fX1uVBKzM7yqAxW/3zwk83+6RyF2+SKOuV+c0wBDhUwzV1PaGapmZH+rmcUzPf+3CGwg==",
       "license": "MIT",
       "funding": {
         "url": "https://github.com/sponsors/colinhacks"
@@ -18300,7 +18300,7 @@
         "mime-types": "^2.1.35",
         "murmurhash": "^2.0.1",
         "mysql2": "^3.24.6",
-        "nodemailer": "^10.1.4",
+        "nodemailer": "^10.1.7",
         "openai": "^6.34.0",
         "otpauth": "^9.5.2",
         "pg": "^8.21.0",
@@ -18312,10 +18312,10 @@
         "svg-captcha": "^1.4.0",
         "together-ai": "^0.33.0",
         "ua-parser-js": "^1.0.41",
-        "undici": "^7.30.1",
+        "undici": "^7.30.2",
         "uuid": "^14.0.3",
         "validator": "^13.15.35",
-        "ws": "^8.22.0"
+        "ws": "^8.22.2"
       },
       "devDependencies": {
         "@types/bcrypt": "^6.0.0",
@@ -18343,10 +18343,19 @@
       "dev": true,
       "license": "MIT"
     },
+    "src/backend/node_modules/nodemailer": {
+      "version": "10.1.7",
+      "resolved": "https://registry.npmjs.org/nodemailer/-/nodemailer-10.1.7.tgz",
+      "integrity": "sha512-OQa6FDln5fLttmqSbjDiRYvFDOFNrBqfiOwHPlEbURil3b+vPB1v8xpi+Sp46drzNDlsTnNsS502vthmz56r4w==",
+      "license": "MIT-0",
+      "engines": {
+        "node": ">=20.0.0"
+      }
+    },
     "src/backend/node_modules/ws": {
-      "version": "8.22.0",
-      "resolved": "https://registry.npmjs.org/ws/-/ws-8.22.0.tgz",
-      "integrity": "sha512-Ydggc987+RO0AnWtZ/7Wq9FtNvcrL1b/RO0ud9mWjUPgDrsAAwQSF51sm2hm1XofbU/4jkpGEsLFsZZxU+1DOg==",
+      "version": "8.22.2",
+      "resolved": "https://registry.npmjs.org/ws/-/ws-8.22.2.tgz",
+      "integrity": "sha512-/rEZ2ejown2N5gxVTHUu9bVVC7ttu0/Tgzf5hbTOixR3Fs7mbbXgn2DbdbcKgJOmpQMtrIUWivtYuVMnp/W/yA==",
       "license": "MIT",
       "engines": {
         "node": ">=10.0.0"

src/backend/clients/database/DatabaseClient.test.ts

@@ -167,6 +167,38 @@ describe('AbstractDatabaseClient — replica-aware reads', () => {
         expect(client.reads).toEqual(['SELECT 1']);
         expect(client.preads).toEqual([]);
     });
+
+    describe('tryHardReadAll', () => {
+        const reads = [{ query: 'SELECT 1' }, { query: 'SELECT 2' }];
+
+        it('keeps replica rows without reading the primary', async () => {
+            const client = new FixtureDatabaseClient([{ id: 1 }], [{ id: 2 }]);
+            expect(await client.tryHardReadAll(reads)).toEqual([
+                [{ id: 1 }],
+                [{ id: 1 }],
+            ]);
+            expect(client.preads).toEqual([]);
+        });
+
+        it.each([[], new Error('replica unavailable')])(
+            'reads every query on the primary when the replica has none',
+            async (replica) => {
+                const client = new FixtureDatabaseClient(replica, [{ id: 2 }]);
+                expect(await client.tryHardReadAll(reads)).toEqual([
+                    [{ id: 2 }],
+                    [{ id: 2 }],
+                ]);
+                expect(client.preads).toEqual(['SELECT 1', 'SELECT 2']);
+            },
+        );
+
+        it('issues one read per query when there is no replica', async () => {
+            const client = new FixtureDatabaseClient([], [{ id: 2 }], false);
+            expect(await client.tryHardReadAll(reads)).toEqual([[], []]);
+            expect(client.reads).toEqual(['SELECT 1', 'SELECT 2']);
+            expect(client.preads).toEqual([]);
+        });
+    });
 });
 
 describe('AbstractDatabaseClient — SQL generation', () => {

src/backend/clients/database/DatabaseClient.ts

@@ -172,6 +172,34 @@ export class AbstractDatabaseClient extends PuterClient {
         return result.value;
     }
 
+    /** Reads the primary only when every replica read is empty or fails. */
+    @Span('db.tryHardReadAll', (reads: unknown[]) => ({
+        'db.batch_size': reads.length,
+    }))
+    async tryHardReadAll(
+        reads: { query: string; params?: unknown[] }[],
+    ): Promise<Record<string, unknown>[][]> {
+        if (!this.hasReadReplica()) {
+            return Promise.all(
+                reads.map(({ query, params = [] }) => this.read(query, params)),
+            );
+        }
+        const onReplica = await Promise.all(
+            reads.map(async ({ query, params = [] }) => {
+                try {
+                    return await this.replicaRead(query, params);
+                } catch {
+                    // A failed replica read counts as a miss.
+                    return [];
+                }
+            }),
+        );
+        if (onReplica.some((rows) => rows.length > 0)) return onReplica;
+        return Promise.all(
+            reads.map(({ query, params = [] }) => this.pread(query, params)),
+        );
+    }
+
     /**
      * Apply the `.sql` files named `<engineName>*` in each configured migration
      * directory, in filename order. Files must be idempotent: nothing records

src/backend/clients/database/SqliteDatabaseClient.test.ts

@@ -27,7 +27,7 @@ import { DatabaseClientFactory } from './index.js';
 import { SqliteDatabaseClient } from './SqliteDatabaseClient.js';
 
 /** Highest schema version the migration table can reach. */
-const CURRENT_SCHEMA_VERSION = 98;
+const CURRENT_SCHEMA_VERSION = 99;
 
 /**
  * These suites migrate real files on disk. Idle they finish in well under a
@@ -705,6 +705,60 @@ describe('SqliteDatabaseClient — boot and migrations', { timeout: DISK_MIGRATI
         }
     });
 
+    it('fills a share row missing its entry owner from 0103, invites left alone', async () => {
+        const dir = mkdtempSync(join(tmpdir(), 'puter-sqlite-share-owner-'));
+        const path = join(dir, 'puter.sqlite');
+        try {
+            const before = new SqliteDatabaseClient(
+                sqliteConfig({ inMemory: false, path }),
+            );
+            await before.onServerStart();
+            const [user] = (await before.read(
+                'SELECT MIN(`id`) AS id FROM `user`',
+            )) as { id: number }[];
+            await before.write(
+                'INSERT INTO `fsentries` (`uuid`, `name`, `user_id`, `modified`) ' +
+                    'VALUES (?, ?, ?, ?)',
+                ['22222222-2222-4222-8222-222222222222', 'owned.txt', user.id, 0],
+            );
+            const [entry] = (await before.read(
+                'SELECT `id` FROM `fsentries` WHERE `uuid` = ?',
+                ['22222222-2222-4222-8222-222222222222'],
+            )) as { id: number }[];
+            await before.write(
+                'INSERT INTO `share` (`uid`, `issuer_user_id`, ' +
+                    '`recipient_email`, `fsentry_id`) VALUES (?, ?, ?, ?)',
+                ['share-no-owner', user.id, '[email protected]', entry.id],
+            );
+            await before.write(
+                'INSERT INTO `share` (`uid`, `issuer_user_id`, ' +
+                    '`recipient_email`) VALUES (?, ?, ?)',
+                ['share-invite', user.id, '[email protected]'],
+            );
+            // The full schema as it stood before 0103, so only 0103 reruns.
+            await before.write('PRAGMA user_version = 98');
+            before.onServerShutdown();
+
+            const after = new SqliteDatabaseClient(
+                sqliteConfig({ inMemory: false, path }),
+            );
+            await after.onServerStart();
+            await expect(
+                after.read(
+                    'SELECT `uid`, `entry_owner_user_id` FROM `share` ' +
+                        'WHERE `uid` IN (?, ?) ORDER BY `uid`',
+                    ['share-invite', 'share-no-owner'],
+                ),
+            ).resolves.toEqual([
+                { uid: 'share-invite', entry_owner_user_id: null },
+                { uid: 'share-no-owner', entry_owner_user_id: user.id },
+            ]);
+            after.onServerShutdown();
+        } finally {
+            rmSync(dir, { recursive: true, force: true });
+        }
+    });
+
     it('indexes notification.created_at for the retention sweep', async () => {
         const rows = await client.read('PRAGMA index_list(`notification`)');
         expect(rows.map((r) => String(r.name))).toContain(

src/backend/clients/database/SqliteDatabaseClient.ts

@@ -137,6 +137,7 @@ const AVAILABLE_MIGRATIONS: [number, string[]][] = [
     [95, ['0100_notification-send-key.sql']],
     [96, ['0101_user-scoped-handlers.sql']],
     [97, ['0102_notification-scope-id-index.sql']],
+    [98, ['0103_share-entry-owner-backfill.sql']],
 ];
 
 export class SqliteDatabaseClient extends AbstractDatabaseClient {

src/backend/clients/database/migrations/mysql/mysql_mig_57.sql

@@ -0,0 +1,25 @@
+-- Copyright (C) 2024-present Puter Technologies Inc.
+--
+-- This file is part of Puter.
+--
+-- Puter is free software: you can redistribute it and/or modify
+-- it under the terms of the GNU Affero General Public License as published
+-- by the Free Software Foundation, either version 3 of the License, or
+-- (at your option) any later version.
+--
+-- This program is distributed in the hope that it will be useful,
+-- but WITHOUT ANY WARRANTY; without even the implied warranty of
+-- MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+-- GNU Affero General Public License for more details.
+--
+-- You should have received a copy of the GNU Affero General Public License
+-- along with this program.  If not, see <https://www.gnu.org/licenses/>.
+
+-- Fills `share`.`entry_owner_user_id` on any row that names an entry but was
+-- written without the owner. Mirrors SQLite migration 0103. No per-file
+-- applied-state tracking; a replay finds nothing to fill.
+
+UPDATE `share` JOIN `fsentries` ON `fsentries`.`id` = `share`.`fsentry_id`
+SET `share`.`entry_owner_user_id` = `fsentries`.`user_id`
+WHERE `share`.`fsentry_id` IS NOT NULL
+  AND `share`.`entry_owner_user_id` IS NULL;

src/backend/clients/database/migrations/postgres/postgres_mig_46.sql

@@ -0,0 +1,27 @@
+-- Copyright (C) 2024-present Puter Technologies Inc.
+--
+-- This file is part of Puter.
+--
+-- Puter is free software: you can redistribute it and/or modify
+-- it under the terms of the GNU Affero General Public License as published
+-- by the Free Software Foundation, either version 3 of the License, or
+-- (at your option) any later version.
+--
+-- This program is distributed in the hope that it will be useful,
+-- but WITHOUT ANY WARRANTY; without even the implied warranty of
+-- MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+-- GNU Affero General Public License for more details.
+--
+-- You should have received a copy of the GNU Affero General Public License
+-- along with this program.  If not, see <https://www.gnu.org/licenses/>.
+
+-- Fills "share".entry_owner_user_id on any row that names an entry but was
+-- written without the owner. Mirrors SQLite migration 0103. No per-file
+-- applied-state tracking; a replay finds nothing to fill.
+
+UPDATE "share"
+SET entry_owner_user_id = f.user_id
+FROM fsentries f
+WHERE f.id = "share".fsentry_id
+  AND "share".fsentry_id IS NOT NULL
+  AND "share".entry_owner_user_id IS NULL;

src/backend/clients/database/migrations/sqlite/0103_share-entry-owner-backfill.sql

@@ -0,0 +1,27 @@
+-- Copyright (C) 2024-present Puter Technologies Inc.
+--
+-- This file is part of Puter.
+--
+-- Puter is free software: you can redistribute it and/or modify
+-- it under the terms of the GNU Affero General Public License as published
+-- by the Free Software Foundation, either version 3 of the License, or
+-- (at your option) any later version.
+--
+-- This program is distributed in the hope that it will be useful,
+-- but WITHOUT ANY WARRANTY; without even the implied warranty of
+-- MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+-- GNU Affero General Public License for more details.
+--
+-- You should have received a copy of the GNU Affero General Public License
+-- along with this program.  If not, see <https://www.gnu.org/licenses/>.
+
+-- Fills `share`.`entry_owner_user_id` on any row that names an entry but was
+-- written without the owner, so reads can rely on the column alone. Rows that
+-- name no entry (invites) keep a NULL owner. A replay finds nothing to fill.
+
+UPDATE `share`
+SET `entry_owner_user_id` = (
+        SELECT `user_id` FROM `fsentries` WHERE `fsentries`.`id` = `share`.`fsentry_id`
+    )
+WHERE `fsentry_id` IS NOT NULL
+  AND `entry_owner_user_id` IS NULL;

src/backend/clients/email/EmailClient.test.ts

@@ -168,6 +168,204 @@ describe('EmailClient — sending', () => {
     });
 });
 
+describe('EmailClient — streams', () => {
+    const STREAMS = {
+        notify: {
+            from: '"Notices" <[email protected]>',
+            headers: { 'X-Example-Stream': 'notify', 'X-Example-Kind': 'n' },
+            tagsHeader: 'X-Example-Tags',
+        },
+        plain: { headers: { 'X-Example-Stream': 'plain' } },
+    };
+    const streamClient = () =>
+        startClient({
+            email: { jsonTransport: true, from: FROM, streams: STREAMS },
+        } as unknown as Partial<IConfig>);
+    const base = { to: '[email protected]', subject: 's', text: 't' };
+
+    it('adds the stream headers and from address to the message', async () => {
+        const info = await streamClient().sendRaw({
+            ...base,
+            stream: 'notify',
+        });
+
+        const message = sentMessage(info);
+        expect(message.headers).toMatchObject({
+            'X-Example-Stream': 'notify',
+            'X-Example-Kind': 'n',
+        });
+        expect(message.from.address).toBe('[email protected]');
+    });
+
+    it('lets caller headers and from win over the stream', async () => {
+        const info = await streamClient().sendRaw({
+            ...base,
+            stream: 'notify',
+            from: '[email protected]',
+            headers: { 'x-example-stream': 'mine' },
+        });
+
+        const message = sentMessage(info);
+        expect(message.from.address).toBe('[email protected]');
+        expect(message.headers?.['x-example-stream']).toBe('mine');
+        expect(message.headers).not.toHaveProperty('X-Example-Stream');
+        expect(message.headers?.['X-Example-Kind']).toBe('n');
+    });
+
+    it('keeps the default from address for a stream without one', async () => {
+        const info = await streamClient().sendRaw({ ...base, stream: 'plain' });
+        expect(sentMessage(info).from.address).toBe('[email protected]');
+    });
+
+    it('leaves the message unchanged for an unknown or missing stream', async () => {
+        const client = streamClient();
+        for (const stream of ['nope', undefined]) {
+            const message = sentMessage(
+                await client.sendRaw({ ...base, stream, tags: { a: 'b' } }),
+            );
+            expect(message.from.address).toBe('[email protected]');
+            expect(message.headers ?? {}).toEqual({});
+        }
+    });
+
+    it('renders valid tags into the stream tags header and drops the rest', async () => {
+        const info = await streamClient().sendRaw({
+            ...base,
+            stream: 'notify',
+            tags: {
+                kind: 'share',
+                'app.id': 'a-1:x',
+                'bad key': 'v',
+                ok: 'bad value',
+                long: 'x'.repeat(129),
+            },
+        });
+        expect(sentMessage(info).headers?.['X-Example-Tags']).toBe(
+            'kind=share, app.id=a-1:x',
+        );
+    });
+
+    it('keeps a tags header the caller set', async () => {
+        const info = await streamClient().sendRaw({
+            ...base,
+            stream: 'notify',
+            headers: { 'X-Example-Tags': 'own=1' },
+            tags: { kind: 'share' },
+        });
+        expect(sentMessage(info).headers?.['X-Example-Tags']).toBe('own=1');
+    });
+
+    it('sends no tags header when the stream names none or no tag survives', async () => {
+        const client = streamClient();
+        const plain = sentMessage(
+            await client.sendRaw({
+                ...base,
+                stream: 'plain',
+                tags: { kind: 'share' },
+            }),
+        );
+        expect(plain.headers).toEqual({ 'X-Example-Stream': 'plain' });
+
+        const dropped = sentMessage(
+            await client.sendRaw({
+                ...base,
+                stream: 'notify',
+                tags: { 'bad key': 'v' },
+            }),
+        );
+        expect(dropped.headers).not.toHaveProperty('X-Example-Tags');
+    });
+
+    it('does not hand stream or tags to the transport', async () => {
+        const info = await streamClient().sendRaw({
+            ...base,
+            stream: 'notify',
+            tags: { kind: 'share' },
+        });
+        const raw = JSON.parse((info as { message: string }).message);
+        expect(raw).not.toHaveProperty('stream');
+        expect(raw).not.toHaveProperty('tags');
+    });
+
+    it('keeps streams out of the transport options', async () => {
+        const nodemailer = (await import('nodemailer')).default;
+        const create = vi.spyOn(nodemailer, 'createTransport');
+        try {
+            streamClient();
+            expect(create).toHaveBeenCalledTimes(1);
+            const [options] = create.mock.calls[0] as [Record<string, unknown>];
+            expect(options).not.toHaveProperty('streams');
+            expect(options).not.toHaveProperty('from');
+            expect(options).toMatchObject({ jsonTransport: true });
+        } finally {
+            create.mockRestore();
+        }
+    });
+
+    it('forwards the template send options to sendRaw', async () => {
+        const client = streamClient();
+        const sendRaw = vi.spyOn(client, 'sendRaw').mockResolvedValue(null);
+
+        await client.send(
+            '[email protected]',
+            'email_verification_code',
+            { code: '1' },
+            { stream: 'notify', replyTo: '[email protected]' },
+        );
+
+        expect(sendRaw).toHaveBeenCalledWith(
+            expect.objectContaining({
+                stream: 'notify',
+                replyTo: '[email protected]',
+            }),
+        );
+    });
+
+    it('applies the stream from address to a template send', async () => {
+        const info = await streamClient().send(
+            '[email protected]',
+            'email_verification_code',
+            { code: '1' },
+            { stream: 'notify' },
+        );
+        expect(sentMessage(info).from.address).toBe('[email protected]');
+    });
+
+    it('reads a stream only from its own config entry', async () => {
+        const inherited = Object.create({
+            base: { from: '[email protected]', headers: { 'X-Example-B': '1' } },
+        });
+        const client = startClient({
+            email: { jsonTransport: true, from: FROM, streams: inherited },
+        } as unknown as Partial<IConfig>);
+        const message = sentMessage(
+            await client.sendRaw({ ...base, stream: 'base' }),
+        );
+        expect(message.from.address).toBe('[email protected]');
+        expect(message.headers ?? {}).toEqual({});
+    });
+
+    it('prints the stream name and no tags when no transport is configured', async () => {
+        const warn = vi.spyOn(console, 'warn').mockImplementation(() => {});
+        try {
+            const client = new EmailClient({
+                port: 0,
+                extensions: [],
+            } as unknown as IConfig);
+            await client.sendRaw({
+                ...base,
+                stream: 'notify',
+                tags: { kind: 'share' },
+            });
+            const printed = warn.mock.calls[0][1] as Record<string, unknown>;
+            expect(printed).not.toHaveProperty('tags');
+            expect(printed.stream).toBe('notify');
+        } finally {
+            warn.mockRestore();
+        }
+    });
+});
+
 describe('EmailClient — template rendering', () => {
     it('renders the code into both subject and body', async () => {
         const client = startClient();

src/backend/clients/email/EmailClient.ts

@@ -69,14 +69,50 @@ export interface SendMailOptions {
     attachments?: EmailAttachment[];
     /** Extra message headers (e.g. List-Unsubscribe), passed to the transport. */
     headers?: Record<string, string>;
+    /** Names the `email.streams` entry whose from address and headers apply. */
+    stream?: string;
+    /** Rendered into the stream's `tagsHeader`; ignored when it has none. */
+    tags?: Record<string, string>;
 }
 
+/** Options a templated {@link EmailClient.send} forwards to `sendRaw`. */
+export type SendTemplateOptions = Pick<SendMailOptions, 'replyTo' | 'stream'>;
+
+const TAG_PART = /^[A-Za-z0-9_.:-]{1,128}$/;
+
 interface CompiledTemplate {
     subject: ReturnType<typeof template>;
     html: ReturnType<typeof template>;
     text?: ReturnType<typeof template>;
 }
 
+/** Pairs whose key or value falls outside `TAG_PART` are dropped. */
+const renderTags = (tags: Record<string, string> | undefined): string =>
+    Object.entries(tags ?? {})
+        .filter(([name, value]) => TAG_PART.test(name) && TAG_PART.test(value))
+        .map(([name, value]) => `${name}=${value}`)
+        .join(', ');
+
+const hasHeader = (
+    headers: Record<string, string> | undefined,
+    name: string,
+): boolean =>
+    Object.keys(headers ?? {}).some(
+        (key) => key.toLowerCase() === name.toLowerCase(),
+    );
+
+// Header names are case-insensitive: `x-a` from `over` replaces `X-A` in `base`.
+const mergeHeaders = (
+    base: Record<string, string> | undefined,
+    over: Record<string, string> | undefined,
+): Record<string, string> => {
+    const merged: Record<string, string> = {};
+    for (const [key, value] of Object.entries(base ?? {})) {
+        if (!hasHeader(over, key)) merged[key] = value;
+    }
+    return { ...merged, ...over };
+};
+
 // -- EmailClient ------------------------------------------------------
 
 /**
@@ -111,7 +147,8 @@ export class EmailClient extends PuterClient {
             return;
         }
 
-        this.transport = nodemailer.createTransport(emailConf);
+        const { streams: _streams, from: _from, ...transportConf } = emailConf;
+        this.transport = nodemailer.createTransport(transportConf);
         console.log('[email] transport configured');
     }
 
@@ -125,7 +162,8 @@ export class EmailClient extends PuterClient {
     /**
      * Render a template and send it to `to`. `options.replyTo` sets the
      * Reply-To header (e.g. so a recipient can respond to the originator of the
-     * message rather than the no-reply From address).
+     * message rather than the no-reply From address); `options.stream` is
+     * passed to {@link sendRaw}.
      *
      * Returns the transport's send result, or `null` when none is configured —
      * {@link sendRaw} drops the message instead of throwing. A caller that
@@ -135,7 +173,7 @@ export class EmailClient extends PuterClient {
         to: string,
         template: T,
         values: Record<string, unknown> = {},
-        options: { replyTo?: string } = {},
+        options: SendTemplateOptions = {},
     ) {
         const compiled = this.compiledTemplates[template];
         if (!compiled) {
@@ -143,12 +181,12 @@ export class EmailClient extends PuterClient {
         }
 
         return await this.sendRaw({
-            from: this.defaultFrom(),
             to,
             subject: compiled.subject(values),
             html: compiled.html(values),
             ...(compiled.text ? { text: compiled.text(values) } : {}),
             ...(options.replyTo ? { replyTo: options.replyTo } : {}),
+            ...(options.stream ? { stream: options.stream } : {}),
         });
     }
 
@@ -159,19 +197,38 @@ export class EmailClient extends PuterClient {
      * Returns the transport's send result, or `null` when no transport is
      * configured (the send is a no-op in that case — callers that must not
      * silently drop mail should check `config.email` before composing, or the
-     * `null` return after).
+     * `null` return after). A configured `stream` supplies the from address
+     * when the caller gives none, and headers the caller's own override.
      */
     async sendRaw(options: SendMailOptions) {
+        const { stream: streamName, tags, ...message } = options;
         if (!this.transport) {
             console.warn(
                 '[email] attempted to send email without transport. If you need to send email, configure an SMTP transport in your config file (see docs for details). Email content:',
-                options,
+                { ...message, ...(streamName ? { stream: streamName } : {}) },
             );
             return null;
         }
+        const streams = this.config.email?.streams;
+        const stream =
+            streamName && streams && Object.hasOwn(streams, streamName)
+                ? streams[streamName]
+                : undefined;
+        let headers = mergeHeaders(stream?.headers, message.headers);
+        const tagsValue = stream?.tagsHeader ? renderTags(tags) : '';
+        if (
+            stream?.tagsHeader &&
+            tagsValue &&
+            !hasHeader(message.headers, stream.tagsHeader)
+        ) {
+            headers = mergeHeaders(headers, {
+                [stream.tagsHeader]: tagsValue,
+            });
+        }
         return await this.transport.sendMail({
-            ...options,
-            from: options.from ?? this.defaultFrom(),
+            ...message,
+            ...(Object.keys(headers).length > 0 ? { headers } : {}),
+            from: message.from ?? stream?.from ?? this.defaultFrom(),
         });
     }
 

src/backend/clients/event/types.ts

@@ -20,6 +20,7 @@ import type {
     Response as ExpressResponse,
 } from 'express';
 import { Actor } from '../../core';
+import type { EmailTemplateName } from '../email/templates';
 import type { UsageInput } from '../../services/metering/types';
 import { FSEntry } from '../../stores/fs/FSEntry';
 
@@ -247,6 +248,12 @@ export type EventMap = {
         requires_phone_verification?: boolean;
         /** Set by the abuse harness — require card verification post-signup. */
         requires_card_verification?: boolean;
+        /**
+         * The email stream the confirmation message is sent on: lowercase
+         * letters, digits, `:`, `_` and `-`, up to 64 characters, starting with
+         * a letter or digit. Any other value is ignored.
+         */
+        email_stream?: string | null;
         [key: string]: unknown;
     };
     'puter.signup.success': {
@@ -298,6 +305,8 @@ export type EventMap = {
         message: string | null;
         [key: string]: unknown;
     };
+    /** Before notification emails; a listener clears `allow` per recipient. */
+    'email.notify.validate': EmailNotifyValidateEvent;
     // Inbound mail to a feedback address (`abuse@`, `fbl@`, ...), emitted via
     // `emitAndWait`. A listener that takes it sets `handled` and it reaches no
     // mailbox; otherwise it is routed like any other message.
@@ -979,6 +988,21 @@ export type EventMap = {
     'outer.pubsub.metering.credits-changed': { userUuid: string };
 } & IExtensionEventMap;
 
+/** A union of `Names`, each of which has to be an email template. */
+type TemplateNames<Names extends EmailTemplateName> = Names;
+
+/** The emails that ask `email.notify.validate`, by template name. */
+export type EmailNotifyKind = TemplateNames<
+    'file_shared_with_you' | 'file_shared_invite' | 'app-user-feedback'
+>;
+
+/** Payload for `email.notify.validate`: one kind of mail, all its recipients. */
+export type EmailNotifyValidateEvent = {
+    kind: EmailNotifyKind;
+    /** `to` is the address as it will be sent; `allow` starts true. */
+    recipients: Array<{ to: string; allow: boolean }>;
+};
+
 /** Payload for `subscription.gate.<surface>` events. */
 export type SubscriptionGateEvent = {
     actor: Actor;

src/backend/controllers/auth/AuthController.http.test.ts

@@ -26,6 +26,7 @@ import { FULL_API_ACCESS } from '../../services/permission/consts.js';
 import { tokenClaimsDigest } from '../../../gui/src/helpers/guiToken.js';
 import {
     createTestUser,
+    lagReadReplica,
     setupPuterTestEnv,
     type PuterTestEnv,
 } from '../../testUtil.js';
@@ -351,6 +352,98 @@ describe('revoke-own-access-token over HTTP', () => {
         expect(await tokenReadStatus(file.uid, readToken)).not.toBe(200);
     });
 
+    const ACCESS_TOKEN_QUERIES =
+        /FROM `access_token_permissions`|`access_token_uid` = \?/;
+    const tokenUidOf = (token: string) =>
+        (
+            env.server.services.token.verify('auth', token) as {
+                token_uid: string;
+            }
+        ).token_uid;
+
+    it('serves a read URL fetched right after minting while the replica lags', async () => {
+        const owner = env.users.user;
+        const file = await makeFile(owner);
+        const replica = await lagReadReplica(env.server, ACCESS_TOKEN_QUERIES);
+        try {
+            const readToken = await mintReadToken(owner.token, file.uid);
+            expect(await tokenReadStatus(file.uid, readToken)).toBe(200);
+            const cached = await env.server.clients.redis.get(
+                `perms:token:${tokenUidOf(readToken)}`,
+            );
+            expect(cached).toBe(JSON.stringify([`fs:${file.uid}:read`]));
+        } finally {
+            replica.catchUp();
+        }
+    });
+
+    it('mints from a just-created personal API token while the replica lags', async () => {
+        const owner = env.users.user;
+        const file = await makeFile(owner);
+        const replica = await lagReadReplica(env.server, ACCESS_TOKEN_QUERIES);
+        try {
+            const pat = await mintPersonalToken(owner);
+            const readToken = await mintReadToken(pat, file.uid);
+            expect(await tokenReadStatus(file.uid, readToken)).toBe(200);
+        } finally {
+            replica.catchUp();
+        }
+    });
+
+    it('revokes a just-created token by its uuid while the replica lags', async () => {
+        const owner = env.users.user;
+        const file = await makeFile(owner);
+        const { actor } = await env.server.services.auth.authenticate(
+            owner.token,
+        );
+        const replica = await lagReadReplica(env.server, ACCESS_TOKEN_QUERIES);
+        let readToken: string;
+        try {
+            readToken = await mintReadToken(owner.token, file.uid);
+            await env.server.services.auth.revokeAccessToken(
+                actor!,
+                tokenUidOf(readToken),
+            );
+            expect(await tokenReadStatus(file.uid, readToken)).not.toBe(200);
+        } finally {
+            replica.catchUp();
+        }
+        expect(await tokenReadStatus(file.uid, readToken)).not.toBe(200);
+        expect(await whoamiStatus(readToken)).toBe(401);
+    });
+
+    it('keeps a revoked token dead while the replica still shows it live', async ({
+        skip,
+    }) => {
+        // The frozen replica is a sqlite copy.
+        skip(process.env.PUTER_TEST_DB_ENGINE?.toLowerCase() === 'postgres');
+        const owner = env.users.user;
+        const file = await makeFile(owner);
+        const { actor } = await env.server.services.auth.authenticate(
+            owner.token,
+        );
+        const readToken = await mintReadToken(owner.token, file.uid);
+        const tokenUid = tokenUidOf(readToken);
+        const replica = await lagReadReplica(env.server, ACCESS_TOKEN_QUERIES, {
+            mode: 'frozen',
+        });
+        try {
+            await env.server.services.auth.revokeAccessToken(actor!, tokenUid);
+            expect(await tokenReadStatus(file.uid, readToken)).not.toBe(200);
+            expect(
+                await env.server.stores.permission.listAccessTokenPerms(
+                    tokenUid,
+                ),
+            ).toEqual([]);
+            expect(
+                await env.server.clients.redis.get(`perms:token:${tokenUid}`),
+            ).toBeNull();
+        } finally {
+            replica.catchUp();
+        }
+        expect(await whoamiStatus(readToken)).toBe(401);
+    });
+
     // These three run last in the file's shared `env.users.user`: each one
     // revokes a session belonging to `owner.token` / `owner.workerToken`, so
     // later tests can't rely on those credentials still being live.
@@ -394,7 +487,10 @@ describe('revoke-own-access-token over HTTP', () => {
 
     it('a revoked GUI session still gets a reauth_token', async () => {
         const owner = env.users.user;
-        const decoded = env.server.services.token.verify('auth', owner.token) as {
+        const decoded = env.server.services.token.verify(
+            'auth',
+            owner.token,
+        ) as {
             session_uid: string;
         };
         await env.server.stores.session.removeByUuid(decoded.session_uid);
@@ -560,7 +656,6 @@ describe('2FA enrollment over HTTP', () => {
         expect(enabled.status).toBe(200);
         expect((await otpState(account.userId)).enabled).toBe(true);
     });
-
 });
 
 /**

src/backend/controllers/auth/AuthController.test.ts

@@ -30,6 +30,7 @@
 
 import { installSeatStub } from '../../testFixtures/seatStub.js';
 import bcrypt from 'bcrypt';
+import { inspect } from 'node:util';
 import jwt from 'jsonwebtoken';
 import { TOTP } from 'otpauth';
 import { v4 as uuidv4, v5 as uuidv5 } from 'uuid';
@@ -4765,14 +4766,24 @@ describe('AuthController.handleSendConfirmEmail', () => {
         ).rejects.toMatchObject({ statusCode: 403 });
     });
 
-    it('rotates the email_confirm_code and returns {} on success', async () => {
+    it('rotates the email_confirm_code and reports the send', async () => {
         const { user, actor } = await makeUserAndActor();
         const before = await server.stores.user.getById(user.id, {
             force: true,
         });
+        const send = vi
+            .spyOn(server.clients.email, 'send')
+            .mockResolvedValue({ messageId: 'm' } as never);
         const res = makeRes();
-        await controller.handleSendConfirmEmail(makeReq({}, { actor }), res);
-        expect(res.body).toEqual({});
+        try {
+            await controller.handleSendConfirmEmail(
+                makeReq({}, { actor }),
+                res,
+            );
+        } finally {
+            send.mockRestore();
+        }
+        expect(res.body).toEqual({ sent: true });
         const after = await server.stores.user.getById(user.id, {
             force: true,
         });
@@ -4782,7 +4793,7 @@ describe('AuthController.handleSendConfirmEmail', () => {
 
     // The resend is the recovery path for a lost code, so it must not fail
     // silently either.
-    it('alarms — and still returns {} — when the resend send throws', async () => {
+    it('alarms, and still answers 200 with sent: false, when the resend send throws', async () => {
         const { actor } = await makeUserAndActor();
         const alarm = vi
             .spyOn(server.clients.alarm, 'create')
@@ -4797,7 +4808,8 @@ describe('AuthController.handleSendConfirmEmail', () => {
                 res,
             );
             // Not the caller's fault; still a 200.
-            expect(res.body).toEqual({});
+            expect(res.statusCode).toBe(200);
+            expect(res.body).toEqual({ sent: false });
 
             const raised = alarm.mock.calls.find(
                 (c) => c[0] === 'auth:confirmation-email-send-failed:resend',
@@ -7518,6 +7530,46 @@ describe('AuthController.handleSaveAccount', () => {
         };
     };
 
+    it('sends the confirmation code on the account confirmation stream', async () => {
+        const { user, actor } = await makeTempActor();
+        await server.stores.user.updateMetadata(user.id, {
+            emailStream: 'review',
+        });
+        const send = vi
+            .spyOn(server.clients.email, 'send')
+            .mockResolvedValue(null);
+        const alarm = vi
+            .spyOn(server.clients.alarm, 'create')
+            .mockImplementation(() => undefined);
+        try {
+            const username = `s_${uniq()}`;
+            await controller.handleSaveAccount(
+                makeReq(
+                    {
+                        username,
+                        email: `${username}@test.local`,
+                        password: 'correct-horse-battery',
+                    },
+                    { actor },
+                ),
+                makeRes(),
+            );
+            expect(send).toHaveBeenCalledWith(
+                `${username}@test.local`,
+                'email_verification_code',
+                expect.anything(),
+                { stream: 'review' },
+            );
+            // The dropped send is reported under its own stage.
+            expect(alarm.mock.calls.map((c) => c[0])).toEqual([
+                'auth:confirmation-email-send-failed:save-account',
+            ]);
+        } finally {
+            send.mockRestore();
+            alarm.mockRestore();
+        }
+    });
+
     it('rejects non-temp accounts with 400', async () => {
         const { actor } = await makeUserAndActor();
         await expect(
@@ -9509,14 +9561,18 @@ describe('AuthController.handleSignup additional branches', () => {
                 },
                 async () => {
                     const username = `cefail_${uniq()}`;
+                    const res = makeRes();
                     await controller.handleSignup(
                         makeReq({
                             username,
                             email: `${username}@test.local`,
                             password: 'correct-horse-battery',
                         }),
-                        makeRes(),
+                        res,
                     );
+                    expect(res.body).toMatchObject({
+                        confirmation_email_sent: false,
+                    });
                 },
             );
 
@@ -9537,6 +9593,93 @@ describe('AuthController.handleSignup additional branches', () => {
     });
 });
 
+describe('AuthController.handleSignup confirmation email outcome', () => {
+    const signupWithSend = async (send: () => Promise<unknown>) => {
+        const spy = vi
+            .spyOn(server.clients.email, 'send')
+            .mockImplementation(send as never);
+        const alarm = vi
+            .spyOn(server.clients.alarm, 'create')
+            .mockImplementation(() => undefined);
+        const res = makeRes();
+        const username = `ceo_${uniq()}`;
+        let alarms: string[] = [];
+        try {
+            await withSignupValidateOverride(
+                (event) => {
+                    event.requires_email_confirmation = true;
+                },
+                () =>
+                    controller.handleSignup(
+                        makeReq({
+                            username,
+                            email: `${username}@test.local`,
+                            password: 'correct-horse-battery',
+                        }),
+                        res,
+                    ),
+            );
+            alarms = alarm.mock.calls.map((c) => String(c[0]));
+        } finally {
+            spy.mockRestore();
+            alarm.mockRestore();
+        }
+        return {
+            body: res.body as {
+                proceed: boolean;
+                confirmation_email_sent?: boolean;
+                user: { requires_email_confirmation: boolean };
+            },
+            alarms,
+        };
+    };
+
+    it('reports a send that throws and still completes the signup', async () => {
+        const { body, alarms } = await signupWithSend(async () => {
+            throw new Error('refused');
+        });
+        expect(body.proceed).toBe(true);
+        expect(body.confirmation_email_sent).toBe(false);
+        expect(body.user.requires_email_confirmation).toBeTruthy();
+        expect(alarms).toContain('auth:confirmation-email-send-failed:signup');
+    });
+
+    it('reports a send the transport accepted', async () => {
+        const { body } = await signupWithSend(async () => ({ messageId: 'm' }));
+        expect(body.confirmation_email_sent).toBe(true);
+    });
+
+    it('keeps the confirmation stream out of the returned user details', async () => {
+        const res = makeRes();
+        const username = `ces_${uniq()}`;
+        await withSignupValidateOverride(
+            (event) => {
+                (event as Record<string, unknown>).email_stream = 'review';
+            },
+            () =>
+                controller.handleSignup(
+                    makeReq({
+                        username,
+                        email: `${username}@test.local`,
+                        password: 'correct-horse-battery',
+                    }),
+                    res,
+                ),
+        );
+        const stored = await server.stores.user.getByUsername(username);
+        expect(stored!.metadata?.emailStream).toBe('review');
+        const details = (res.body as { user: { metadata?: object } }).user;
+        expect(details.metadata ?? {}).not.toHaveProperty('emailStream');
+    });
+
+    it('leaves the field out when no confirmation email is due', async () => {
+        const res = makeRes();
+        await controller.handleSignup(makeReq({ is_temp: true }), res);
+        expect(res.body).toMatchObject({ proceed: true });
+        expect(res.body).not.toHaveProperty('confirmation_email_sent');
+    });
+});
+
 describe('AuthController.handleSendPassRecoveryEmail additional branches', () => {
     it('rejects an invalid email format with 400 (when no username supplied)', async () => {
         await expect(
@@ -10632,10 +10775,10 @@ describe('AuthController.loginWait audience binding', () => {
         // party holding the session id is somewhere else entirely.
         const token = await mintAppToken(actor, OPENER);
 
-        const { res, outcome } = await waitWithRelay(
-            uuidv4(),
-            { origin: 'https://evil.test' },
-            token,
+        const session = uuidv4();
+        const [{ res, outcome }] = await runWaits(
+            [{ session, origin: 'https://evil.test' }],
+            { during: () => setToken(session, token) },
         );
         // Same 408 the empty path returns — a mismatched caller must not be
         // able to tell "nothing arrived" from "something arrived for someone
@@ -10711,10 +10854,10 @@ describe('AuthController.loginWait audience binding', () => {
         );
         const guiToken = (loginRes.body as { token: string }).token;
 
-        const { res, outcome } = await waitWithRelay(
-            uuidv4(),
-            { origin: OPENER },
-            guiToken,
+        const session = uuidv4();
+        const [{ res, outcome }] = await runWaits(
+            [{ session, origin: OPENER }],
+            { during: () => setToken(session, guiToken) },
         );
         expect(outcome).toMatchObject({ statusCode: 408 });
         expect(res.body).toBeUndefined();
@@ -10729,14 +10872,406 @@ describe('AuthController.loginWait audience binding', () => {
             { keyid: 'v2' },
         );
 
-        const { res, outcome } = await waitWithRelay(
-            uuidv4(),
-            { origin: OPENER },
-            forged,
+        const session = uuidv4();
+        const [{ res, outcome }] = await runWaits(
+            [{ session, origin: OPENER }],
+            { during: () => setToken(session, forged) },
         );
         expect(outcome).toMatchObject({ statusCode: 408 });
         expect(res.body).toBeUndefined();
     });
+
+    /** Post a token to `/login/set` with no wait running. */
+    const setToken = (session: string, token: string) =>
+        controller.loginSet(makeReq({ session, auth_token: token }), makeRes());
+
+    /**
+     * Run waits on fake timers so the 10 s window passes without real waiting.
+     * `during` runs once every wait has subscribed; `now` pins the clock.
+     */
+    const runWaits = async (
+        calls: Array<{ session: string; origin: string; clientGone?: boolean }>,
+        opts: { now?: number; during?: () => Promise<unknown> } = {},
+    ) => {
+        const subscribed = vi.spyOn(eventClient, 'on');
+        vi.useFakeTimers({
+            toFake:
+                opts.now === undefined
+                    ? ['setTimeout']
+                    : ['setTimeout', 'Date'],
+        });
+        if (opts.now !== undefined) vi.setSystemTime(opts.now);
+        const tick = () => new Promise((r) => setImmediate(r));
+        try {
+            let pending = calls.length;
+            const runs = calls.map(({ session, origin, clientGone }) => {
+                const res = makeRes();
+                const req = makeReq({ session }, { headers: { origin } });
+                if (clientGone) {
+                    Object.assign(req.socket, { destroyed: true });
+                }
+                const outcome = controller
+                    .loginWait(req, res)
+                    .then(
+                        () => 'ok' as const,
+                        (e: unknown) => e,
+                    )
+                    .finally(() => {
+                        pending--;
+                    });
+                return { res, outcome };
+            });
+            const allSubscribed = () =>
+                calls.every(({ session }) =>
+                    subscribed.mock.calls.some(
+                        ([key]) => key === `pubsub.login.${session}`,
+                    ),
+                );
+            for (let i = 0; i < 200 && pending > 0 && !allSubscribed(); i++) {
+                await tick();
+            }
+            for (let i = 0; i < 20; i++) await tick();
+            await opts.during?.();
+            for (let i = 0; i < 200 && pending > 0; i++) {
+                await tick();
+                await vi.advanceTimersByTimeAsync(1000);
+            }
+            return await Promise.all(
+                runs.map(async ({ res, outcome }) => ({
+                    res,
+                    outcome: await outcome,
+                })),
+            );
+        } finally {
+            vi.useRealTimers();
+            subscribed.mockRestore();
+        }
+    };
+
+    const waitAlone = async (session: string, origin: string, now?: number) =>
+        (await runWaits([{ session, origin }], { now }))[0];
+
+    it('delivers a token set before the wait subscribes', async () => {
+        const { actor } = await makeUserAndActor();
+        const token = await mintAppToken(actor, OPENER);
+        const session = uuidv4();
+
+        await setToken(session, token);
+        const { res, outcome } = await waitAlone(session, OPENER);
+        expect(outcome).toBe('ok');
+        expect((res.body as { auth_token: string }).auth_token).toBe(token);
+    });
+
+    it('delivers a token set between one wait timing out and the next', async () => {
+        const { actor } = await makeUserAndActor();
+        const token = await mintAppToken(actor, OPENER);
+        const session = uuidv4();
+
+        const first = await waitAlone(session, OPENER);
+        expect(first.outcome).toMatchObject({ statusCode: 408 });
+
+        await setToken(session, token);
+        const { res, outcome } = await waitAlone(session, OPENER);
+        expect(outcome).toBe('ok');
+        expect((res.body as { auth_token: string }).auth_token).toBe(token);
+    });
+
+    it('hands a token out only once', async () => {
+        const { actor } = await makeUserAndActor();
+        const token = await mintAppToken(actor, OPENER);
+        const session = uuidv4();
+
+        await setToken(session, token);
+        expect((await waitAlone(session, OPENER)).outcome).toBe('ok');
+
+        const again = await waitAlone(session, OPENER);
+        expect(again.outcome).toMatchObject({ statusCode: 408 });
+        expect(again.res.body).toBeUndefined();
+    });
+
+    it('withholds a stored token from a mismatched Origin and keeps it for the matching one', async () => {
+        const { actor } = await makeUserAndActor();
+        const token = await mintAppToken(actor, OPENER);
+        const session = uuidv4();
+
+        await setToken(session, token);
+        const other = await waitAlone(session, 'https://other.test');
+        expect(other.outcome).toMatchObject({ statusCode: 408 });
+        expect(other.res.body).toBeUndefined();
+
+        const { res, outcome } = await waitAlone(session, OPENER);
+        expect(outcome).toBe('ok');
+        expect((res.body as { auth_token: string }).auth_token).toBe(token);
+    });
+
+    it('drops a stored token after a couple of minutes', async () => {
+        const { actor } = await makeUserAndActor();
+        const token = await mintAppToken(actor, OPENER);
+        const early = uuidv4();
+        const late = uuidv4();
+        await setToken(early, token);
+        await setToken(late, token);
+
+        const start = Date.now();
+        expect((await waitAlone(early, OPENER, start + 110_000)).outcome).toBe(
+            'ok',
+        );
+        const expired = await waitAlone(late, OPENER, start + 121_000);
+        expect(expired.outcome).toMatchObject({ statusCode: 408 });
+    });
+
+    it('keeps waiting past a stored token for another app and delivers the real one', async () => {
+        const { actor } = await makeUserAndActor();
+        const otherToken = await mintAppToken(actor, 'https://other.test');
+        const token = await mintAppToken(actor, OPENER);
+        const session = uuidv4();
+
+        await setToken(session, otherToken);
+        const [{ res, outcome }] = await runWaits(
+            [{ session, origin: OPENER }],
+            {
+                during: () => setToken(session, token),
+            },
+        );
+        expect(outcome).toBe('ok');
+        expect((res.body as { auth_token: string }).auth_token).toBe(token);
+    });
+
+    it('still relays to a subscribed wait when storing the token fails', async () => {
+        const { actor } = await makeUserAndActor();
+        const token = await mintAppToken(actor, OPENER);
+        const session = uuidv4();
+        const failingSet = vi
+            .spyOn(server.clients.redis, 'set')
+            .mockRejectedValueOnce(new Error('unavailable'));
+        const warn = vi.spyOn(console, 'warn').mockImplementation(() => {});
+        try {
+            let setRes: MockRes | undefined;
+            const [{ res, outcome }] = await runWaits(
+                [{ session, origin: OPENER }],
+                {
+                    during: async () => {
+                        setRes = makeRes();
+                        await controller.loginSet(
+                            makeReq({ session, auth_token: token }),
+                            setRes,
+                        );
+                    },
+                },
+            );
+            expect(setRes?.body).toEqual({ success: true });
+            expect(outcome).toBe('ok');
+            expect((res.body as { auth_token: string }).auth_token).toBe(token);
+        } finally {
+            failingSet.mockRestore();
+            warn.mockRestore();
+        }
+    });
+
+    it('removes the stored copy once a subscribed wait takes the token', async () => {
+        const { actor } = await makeUserAndActor();
+        const token = await mintAppToken(actor, OPENER);
+        const session = uuidv4();
+
+        const { outcome } = await waitWithRelay(
+            session,
+            { origin: OPENER },
+            token,
+        );
+        expect(outcome).toBe('ok');
+
+        const later = await waitAlone(session, OPENER);
+        expect(later.outcome).toMatchObject({ statusCode: 408 });
+    });
+
+    it('hands a stored token to only one of two concurrent waits', async () => {
+        const { actor } = await makeUserAndActor();
+        const token = await mintAppToken(actor, OPENER);
+        const session = uuidv4();
+
+        await setToken(session, token);
+        const results = await runWaits([
+            { session, origin: OPENER },
+            { session, origin: OPENER },
+        ]);
+        const outcomes = results.map((r) => r.outcome);
+        expect(outcomes.filter((o) => o === 'ok')).toHaveLength(1);
+        expect(outcomes.filter((o) => o !== 'ok')).toEqual([
+            expect.objectContaining({ statusCode: 408 }),
+        ]);
+    });
+
+    it('relays a token to every wait already subscribed', async () => {
+        const { actor } = await makeUserAndActor();
+        const token = await mintAppToken(actor, OPENER);
+        const session = uuidv4();
+
+        const results = await runWaits(
+            [
+                { session, origin: OPENER },
+                { session, origin: OPENER },
+            ],
+            { during: () => setToken(session, token) },
+        );
+        expect(results.map((r) => r.outcome)).toEqual(['ok', 'ok']);
+        for (const { res } of results) {
+            expect((res.body as { auth_token: string }).auth_token).toBe(token);
+        }
+    });
+
+    it('keeps the stored copy when the subscribed wait has lost its client', async () => {
+        const { actor } = await makeUserAndActor();
+        const token = await mintAppToken(actor, OPENER);
+        const session = uuidv4();
+
+        await runWaits([{ session, origin: OPENER, clientGone: true }], {
+            during: () => setToken(session, token),
+        });
+
+        const { res, outcome } = await waitAlone(session, OPENER);
+        expect(outcome).toBe('ok');
+        expect((res.body as { auth_token: string }).auth_token).toBe(token);
+    });
+
+    it('still relays to a subscribed wait when the stored copy cannot be read or removed', async () => {
+        const { actor } = await makeUserAndActor();
+        const token = await mintAppToken(actor, OPENER);
+        const session = uuidv4();
+        const failingGet = vi
+            .spyOn(server.clients.redis, 'get')
+            .mockRejectedValue(new Error('unavailable'));
+        const failingEval = vi
+            .spyOn(server.clients.redis, 'eval')
+            .mockRejectedValue(new Error('unavailable'));
+        try {
+            const [{ res, outcome }] = await runWaits(
+                [{ session, origin: OPENER }],
+                { during: () => setToken(session, token) },
+            );
+            expect(outcome).toBe('ok');
+            expect((res.body as { auth_token: string }).auth_token).toBe(token);
+        } finally {
+            failingGet.mockRestore();
+            failingEval.mockRestore();
+        }
+    });
+
+    it('answers a subscribed wait when a second token is set right after the first', async () => {
+        const { actor } = await makeUserAndActor();
+        const first = await mintAppToken(actor, OPENER);
+        // A later `iat` makes the second token differ from the first.
+        await new Promise((r) => setTimeout(r, 1100));
+        const second = await mintAppToken(actor, OPENER);
+        expect(second).not.toBe(first);
+        const session = uuidv4();
+
+        const [{ res, outcome }] = await runWaits(
+            [{ session, origin: OPENER }],
+            {
+                during: async () => {
+                    await setToken(session, first);
+                    await setToken(session, second);
+                },
+            },
+        );
+        expect(outcome).toBe('ok');
+        expect((res.body as { auth_token: string }).auth_token).toBe(first);
+    });
+
+    it('keeps a subscribed wait listening past a token for another app', async () => {
+        const { actor } = await makeUserAndActor();
+        const otherToken = await mintAppToken(actor, 'https://other.test');
+        const token = await mintAppToken(actor, OPENER);
+        const session = uuidv4();
+
+        const [{ res, outcome }] = await runWaits(
+            [{ session, origin: OPENER }],
+            {
+                during: async () => {
+                    await setToken(session, otherToken);
+                    await setToken(session, token);
+                },
+            },
+        );
+        expect(outcome).toBe('ok');
+        expect((res.body as { auth_token: string }).auth_token).toBe(token);
+    });
+
+    it("keeps a stored token when a later set carries another app's token or an unsigned one", async () => {
+        const { actor } = await makeUserAndActor();
+        const token = await mintAppToken(actor, OPENER);
+        const otherToken = await mintAppToken(actor, 'https://other.test');
+        const session = uuidv4();
+
+        await setToken(session, token);
+        await setToken(session, otherToken);
+        await setToken(session, 'x'.repeat(100_000));
+
+        const { res, outcome } = await waitAlone(session, OPENER);
+        expect(outcome).toBe('ok');
+        expect((res.body as { auth_token: string }).auth_token).toBe(token);
+    });
+
+    it('stores only a token this server signed for an app', async () => {
+        const { actor } = await makeUserAndActor();
+        const real = await mintAppToken(actor, OPENER);
+        const forged = jwt.sign(
+            jwt.decode(real) as object,
+            'not-the-server-secret',
+            { keyid: 'v2' },
+        );
+        const set = vi.spyOn(server.clients.redis, 'set');
+        try {
+            const session = uuidv4();
+            await setToken(session, forged);
+            await setToken(session, 'x'.repeat(100_000));
+            expect(set).not.toHaveBeenCalled();
+
+            await setToken(session, real);
+            expect(set).toHaveBeenCalledTimes(1);
+        } finally {
+            set.mockRestore();
+        }
+    });
+
+    it('leaves the token out of the warning when storing it fails', async () => {
+        const { actor } = await makeUserAndActor();
+        const token = await mintAppToken(actor, OPENER);
+        const session = uuidv4();
+        const failure = Object.assign(new Error('ERR unavailable'), {
+            command: { name: 'set', args: [session, token, 'EX', '120'] },
+        });
+        const failingSet = vi
+            .spyOn(server.clients.redis, 'set')
+            .mockRejectedValueOnce(failure);
+        const warn = vi.spyOn(console, 'warn').mockImplementation(() => {});
+        try {
+            const res = makeRes();
+            await controller.loginSet(
+                makeReq({ session, auth_token: token }),
+                res,
+            );
+            expect(res.body).toEqual({ success: true });
+            expect(warn).toHaveBeenCalled();
+            const logged = warn.mock.calls
+                .flat()
+                .map((arg) => inspect(arg, { depth: 10 }))
+                .join(' ');
+            expect(logged).not.toContain(token);
+        } finally {
+            failingSet.mockRestore();
+            warn.mockRestore();
+        }
+    });
+
+    it('answers 400 when auth_token is not a string', async () => {
+        await expect(
+            controller.loginSet(
+                makeReq({ session: uuidv4(), auth_token: { nested: true } }),
+                makeRes(),
+            ),
+        ).rejects.toMatchObject({ statusCode: 400, legacyCode: 'bad_request' });
+    });
 });
 
 // -- Batch grant / revoke + cross-app data grants -----------------------
@@ -11093,3 +11628,100 @@ describe('AuthController — a seat address nobody confirmed', () => {
         expect(await emailOf(seat.id)).toBeNull();
     });
 });
+
+describe('AuthController account mail streams', () => {
+    const spySend = () =>
+        vi.spyOn(server.clients.email, 'send').mockResolvedValue(null);
+
+    it('sends password recovery on the auth stream', async () => {
+        const { user } = await makeUserAndActor();
+        const send = spySend();
+        try {
+            await controller.handleSendPassRecoveryEmail(
+                makeReq({ email: user.email! }),
+                makeRes(),
+            );
+            expect(send).toHaveBeenCalledWith(
+                user.email,
+                'email_password_recovery',
+                expect.anything(),
+                { stream: 'auth' },
+            );
+        } finally {
+            send.mockRestore();
+        }
+    });
+
+    it('sends the password change notice on the auth stream', async () => {
+        const { user, actor } = await makeUserAndActor();
+        const req = makeReq({ new_pass: 'a-fresh-password-456' }, { actor });
+        (req as unknown as { userProtected: unknown }).userProtected = { user };
+        const send = spySend();
+        try {
+            await controller.handleChangePassword(req, makeRes());
+            expect(send).toHaveBeenCalledWith(
+                user.email,
+                'password_change_notification',
+                expect.anything(),
+                { stream: 'auth' },
+            );
+        } finally {
+            send.mockRestore();
+        }
+    });
+
+    it('sends both change-email messages on the auth stream', async () => {
+        const { user, actor } = await makeUserAndActor();
+        const newEmail = `cs_${uniq()}@test.local`;
+        const send = spySend();
+        const sendRaw = vi
+            .spyOn(server.clients.email, 'sendRaw')
+            .mockResolvedValue(null);
+        try {
+            await controller.handleChangeEmail(
+                makeReq({ new_email: newEmail }, { actor }),
+                makeRes(),
+            );
+            expect(send).toHaveBeenCalledWith(
+                newEmail,
+                'email_verification_link',
+                expect.anything(),
+                { stream: 'auth' },
+            );
+            expect(sendRaw).toHaveBeenCalledWith(
+                expect.objectContaining({ to: user.email, stream: 'auth' }),
+            );
+        } finally {
+            send.mockRestore();
+            sendRaw.mockRestore();
+        }
+    });
+
+    it('sends the 2FA enable and disable notices on the auth stream', async () => {
+        const { user, actor } = await makeUserAndActor({ email_confirmed: 1 });
+        const send = spySend();
+        try {
+            const { secret } = await setup2fa(actor);
+            await enable2fa(actor, { code: liveTotp(user.username, secret) });
+            expect(send).toHaveBeenCalledWith(
+                user.email,
+                'enabled_2fa',
+                { username: user.username },
+                { stream: 'auth' },
+            );
+
+            await controller.handleDisable2fa(
+                makeReq({ code: liveTotp(user.username, secret) }, { actor }),
+                makeRes(),
+            );
+            expect(send).toHaveBeenCalledWith(
+                user.email,
+                'disabled_2fa',
+                { username: user.username },
+                { stream: 'auth' },
+            );
+        } finally {
+            send.mockRestore();
+        }
+    });
+});

src/backend/controllers/auth/AuthController.ts

@@ -71,6 +71,7 @@ import { sessionCookieFlags } from '../../util/cookieFlags.js';
 import { cleanEmail, isStorableEmail } from '../../util/email.js';
 import { isGodmodeApp } from '../../util/godmodeApps.js';
 import { parsePhone } from '../../util/phone.js';
+import { deleteIfEqual } from '../../util/redisLock.js';
 import {
     bonusCodeInvalidError,
     checkSignupBonus,
@@ -143,6 +144,12 @@ const DISPATCH_ID_MAX_LENGTH = 128;
 // One name for the flag, so the write and the read cannot drift apart.
 const APP_AUTHENTICATED_FLAG = 'flag:app-is-authenticated';
 
+// Long enough to span the gap between one `/login/wait` and the client's next.
+const LOGIN_RELAY_TTL_SECONDS = 120;
+// Keyed by app too, so a token for one app never replaces another app's.
+const loginRelayKey = (session: string, appUid: string) =>
+    `login:relay:${session}:${appUid}`;
+
 // -- Post-login route limits -----------------------------------------
 //
 // The credential legs above (login, signup, recovery, confirmation) each
@@ -345,36 +352,43 @@ export class AuthController extends PuterController {
         const expectedAppUid =
             await this.services.auth.appUidFromOrigin(reqOrigin);
 
-        const { resolve, promise } = Promise.withResolvers<void>();
-
-        let token: string | null = null;
-        const listener = (_key: string, value: { authtoken: string }) => {
-            token = value.authtoken;
-            resolve();
-        };
-        this.clients.event.on(`pubsub.login.${session}`, listener);
-
-        const timeout = new Promise<void>((resolve) =>
-            setTimeout(resolve, 10000),
-        );
-        await Promise.race([promise, timeout]);
-        this.clients.event.off(`pubsub.login.${session}`, listener);
-        if (!token) {
-            throw new HttpError(408, 'Request timeout.', {
-                legacyCode: 'request_timeout',
-            });
-        }
+        const relayKey = loginRelayKey(session, expectedAppUid);
+        const { resolve, promise } = Promise.withResolvers<string>();
 
         // Audience check. The postMessage hand-off this relay stands in for
         // is origin-bound for free — it posts with `targetOrigin`, so a page
         // can only ever receive a token minted for *itself*. Delivering
-        // server-side dropped that binding; this restores it. Without it a
-        // popup talked into minting for app X (see `trustsOpenerOriginParam`
-        // in the GUI) hands X's token to whoever holds the session id.
-        if (!this.#tokenIsForApp(token, expectedAppUid)) {
-            // Deliberately the same 408 the no-token path returns: a caller
-            // learns only that nothing arrived for them, not that a token
-            // for a different app went past.
+        // server-side dropped that binding; this restores it. Any other token
+        // is passed over and the wait runs on, so a caller learns only that
+        // nothing arrived for them.
+        const listener = (_key: string, value: { authtoken: string }) => {
+            if (this.#relayedTokenAppUid(value.authtoken) === expectedAppUid) {
+                resolve(value.authtoken);
+            }
+        };
+        this.clients.event.on(`pubsub.login.${session}`, listener);
+        let token: string | null;
+        try {
+            // Read after subscribing, so a token set before this wait is still delivered.
+            token = await this.#takeStoredLoginToken(relayKey, expectedAppUid);
+            if (!token) {
+                const timeout = new Promise<null>((resolve) =>
+                    setTimeout(resolve, 10000, null),
+                );
+                token = await Promise.race([promise, timeout]);
+                // A wait whose client went away leaves the copy for the next one.
+                if (token && !req.socket?.destroyed) {
+                    await deleteIfEqual(
+                        this.clients.redis,
+                        relayKey,
+                        token,
+                    ).catch(() => false);
+                }
+            }
+        } finally {
+            this.clients.event.off(`pubsub.login.${session}`, listener);
+        }
+        if (!token) {
             throw new HttpError(408, 'Request timeout.', {
                 legacyCode: 'request_timeout',
             });
@@ -386,24 +400,46 @@ export class AuthController extends PuterController {
     }
 
     /**
-     * Whether a relayed token is an app-under-user token minted for
-     * `expectedAppUid`. Verifies the signature — an unverified decode would let
-     * a caller relay a token whose claims it wrote itself.
+     * Take the copy `/login/set` kept for this app, once. Null when there is
+     * none, another wait took it, or Redis fails; the wait then just listens.
      */
-    #tokenIsForApp(token: string, expectedAppUid: string): boolean {
+    async #takeStoredLoginToken(
+        relayKey: string,
+        expectedAppUid: string,
+    ): Promise<string | null> {
+        try {
+            const kept = await this.clients.redis.get(relayKey);
+            if (!kept || this.#relayedTokenAppUid(kept) !== expectedAppUid) {
+                return null;
+            }
+            const took = await deleteIfEqual(
+                this.clients.redis,
+                relayKey,
+                kept,
+            );
+            return took ? kept : null;
+        } catch {
+            return null;
+        }
+    }
+
+    /**
+     * The app a relayed app-under-user token was minted for, or null. Verifies
+     * the signature — an unverified decode would let a caller relay a token
+     * whose claims it wrote itself.
+     */
+    #relayedTokenAppUid(token: string): string | null {
         try {
             const payload = this.services.token.verify<{
                 type?: string;
                 app_uid?: string;
             }>('auth', token);
-            return (
-                payload.type === 'app-under-user' &&
-                !!payload.app_uid &&
-                payload.app_uid === expectedAppUid
-            );
+            return payload.type === 'app-under-user' && payload.app_uid
+                ? payload.app_uid
+                : null;
         } catch {
             // Malformed, expired, or signed with a key we don't hold.
-            return false;
+            return null;
         }
     }
     @Post('/login/set', {
@@ -418,12 +454,34 @@ export class AuthController extends PuterController {
     })
     async loginSet(req: Request, res: Response) {
         const { session, auth_token } = req.body ?? {};
-        if (!session || !auth_token || !validateUuid(session)) {
+        if (
+            !session ||
+            typeof auth_token !== 'string' ||
+            !auth_token ||
+            !validateUuid(session)
+        ) {
             throw new HttpError(400, 'session and auth_token are required.', {
                 legacyCode: 'bad_request',
             });
         }
 
+        // Only a token a wait could deliver is kept: one this server signed for an app.
+        const appUid = this.#relayedTokenAppUid(auth_token);
+        if (appUid) {
+            try {
+                await this.clients.redis.set(
+                    loginRelayKey(session, appUid),
+                    auth_token,
+                    'EX',
+                    LOGIN_RELAY_TTL_SECONDS,
+                );
+            } catch (e) {
+                console.warn(
+                    '[login-set] storing the relayed token failed:',
+                    e instanceof Error ? e.message : String(e),
+                );
+            }
+        }
         this.clients.event.emit(
             `pubsub.login.${session}`,
             {
@@ -882,14 +940,19 @@ export class AuthController extends PuterController {
             if (!bonusCode) throw bonusCodeInvalidError();
         }
 
-        const user = await this.services.signup.signup({
-            req,
-            body,
-            isTemp: is_temp,
-            fingerprint,
-            bonusCode,
+        const { user, confirmationEmailSent } =
+            await this.services.signup.signup({
+                req,
+                body,
+                isTemp: is_temp,
+                fingerprint,
+                bonusCode,
+            });
+        await this.#completeLogin(req, res, user, undefined, {
+            ...(confirmationEmailSent !== undefined
+                ? { confirmation_email_sent: confirmationEmailSent }
+                : {}),
         });
-        await this.#completeLogin(req, res, user);
     }
 
     /**
@@ -1028,10 +1091,12 @@ export class AuthController extends PuterController {
             email_confirm_code: code,
         });
 
-        await this.services.signup.sendConfirmationEmail(user, 'resend', {
-            code,
-        });
-        res.json({});
+        const sent = await this.services.signup.sendConfirmationEmail(
+            user,
+            'resend',
+            { code },
+        );
+        res.json({ sent });
     }
 
     @Post('/confirm-email', {
@@ -2019,6 +2084,7 @@ export class AuthController extends PuterController {
                     user.email,
                     'email_password_recovery',
                     { link },
+                    { stream: 'auth' },
                 );
             } catch (e) {
                 console.warn('[send-pass-recovery-email] send failed:', e);
@@ -2282,6 +2348,7 @@ export class AuthController extends PuterController {
                     {
                         username: user.username,
                     },
+                    { stream: 'auth' },
                 );
             } catch (e) {
                 console.warn('[change-password] notification send failed:', e);
@@ -2507,6 +2574,7 @@ export class AuthController extends PuterController {
                     new_email,
                     'email_verification_link',
                     { link },
+                    { stream: 'auth' },
                 );
             } catch (e) {
                 console.warn('[change-email] new-address email failed:', e);
@@ -2514,15 +2582,8 @@ export class AuthController extends PuterController {
             // Notify the old address too
             if (user.email) {
                 try {
-                    await (
-                        this.clients.email as unknown as {
-                            sendRaw: (opts: {
-                                to: string;
-                                subject: string;
-                                text: string;
-                            }) => Promise<unknown>;
-                        }
-                    ).sendRaw({
+                    await this.clients.email.sendRaw({
+                        stream: 'auth',
                         to: user.email,
                         subject: 'Your Puter email change was requested',
                         text: `A change to ${new_email} was requested on your account. If this wasn't you, please contact support.`,
@@ -2811,18 +2872,11 @@ export class AuthController extends PuterController {
             username,
         });
 
-        // Send confirmation email
-        if (this.clients.email) {
-            try {
-                await this.clients.email.send(
-                    email,
-                    'email_verification_code',
-                    { code: email_confirm_code },
-                );
-            } catch (e) {
-                console.warn('[save-account] confirmation email failed:', e);
-            }
-        }
+        await this.services.signup.sendConfirmationEmail(
+            { ...user, username, email },
+            'save-account',
+            { code: email_confirm_code },
+        );
 
         try {
             this.clients.event?.emit(
@@ -4272,9 +4326,12 @@ export class AuthController extends PuterController {
 
             if (this.clients.email && user.email) {
                 try {
-                    await this.clients.email.send(user.email, 'enabled_2fa', {
-                        username: user.username,
-                    });
+                    await this.clients.email.send(
+                        user.email,
+                        'enabled_2fa',
+                        { username: user.username },
+                        { stream: 'auth' },
+                    );
                 } catch (e) {
                     console.warn('[configure-2fa] email send failed:', e);
                 }
@@ -4348,9 +4405,12 @@ export class AuthController extends PuterController {
 
         if (this.clients.email && user.email) {
             try {
-                await this.clients.email.send(user.email, 'disabled_2fa', {
-                    username: user.username,
-                });
+                await this.clients.email.send(
+                    user.email,
+                    'disabled_2fa',
+                    { username: user.username },
+                    { stream: 'auth' },
+                );
             } catch (e) {
                 console.warn('[disable-2fa] email send failed:', e);
             }
@@ -4766,6 +4826,7 @@ export class AuthController extends PuterController {
         res: Response,
         user: UserRow,
         oidcContinuation?: unknown,
+        extra: { confirmation_email_sent?: boolean } = {},
     ): Promise<void> {
         const redirectUrl =
             oidcContinuation === undefined
@@ -4800,6 +4861,7 @@ export class AuthController extends PuterController {
             token: gui_token,
             user: details,
             ...(redirectUrl ? { redirectUrl } : {}),
+            ...extra,
         });
     }
 }

src/backend/controllers/drivers/DriverController.concurrent.test.ts

@@ -324,7 +324,7 @@ describe('DriverController — concurrent acquire/release', () => {
         const driver = {
             ...makeSyntheticDriver(),
             ping: async () => {
-                Context.get('keepDriverSlot')?.(
+                Context.get('keepConcurrencySlot')?.(
                     new Promise<void>((resolve) => {
                         settleWork = resolve;
                     }),

src/backend/controllers/drivers/DriverController.ts

@@ -51,7 +51,7 @@ import { PermissionUtil } from '../../services/permission/permissionUtil.js';
 import type { WithLifecycle } from '../../types';
 import { withSpan } from '../../util/span.js';
 import { PuterController } from '../types.js';
-import { CallSlot } from './callSlot.js';
+import { CallSlot } from '../../core/http/callSlot.js';
 
 type DriverInstance = WithLifecycle & Record<string, unknown>;
 
@@ -446,7 +446,7 @@ export class DriverController extends PuterController {
                 });
             }
             slot.attach(handle, res);
-            Context.set('keepDriverSlot', (work) => slot.keep(work));
+            Context.set('keepConcurrencySlot', (work) => slot.keep(work));
         }
 
         // Stash the requested driver name in Context so multi-provider

src/backend/controllers/fs/FSController.ts

@@ -1850,7 +1850,9 @@ export class FSController extends PuterController {
     }
 
     async #assertCanDedupeCreate(actor: Actor, targetPath: string) {
-        const existing = await this.stores.fsEntry.getEntryByPath(targetPath);
+        const existing = await this.stores.fsEntry.getEntryByPath(targetPath, {
+            foldedNames: true,
+        });
         if (!existing) return;
         const parent = pathPosix.dirname(targetPath);
         await this.#assertAccess(

src/backend/controllers/fs/LegacyFSController.http.test.ts

@@ -168,6 +168,27 @@ describe('legacy file downloads over HTTP', () => {
         },
     );
 
+    it('GET /token-read types a file by its name, and one with no known extension as a byte stream', async () => {
+        const typed = await requestFor(
+            '/token-read',
+            await writeFile('notes.txt', Buffer.from('hello')),
+        );
+        expect(typed.headers.get('content-type')).toBe(
+            'text/plain; charset=utf-8',
+        );
+
+        for (const name of ['README', 'archive.unknownext']) {
+            const response = await requestFor(
+                '/token-read',
+                await writeFile(name, Buffer.from('hello')),
+            );
+            expect(response.status).toBe(200);
+            expect(response.headers.get('content-type')).toBe(
+                'application/octet-stream',
+            );
+        }
+    });
+
     it('GET /read answers byte_count on an empty file with an empty 200', async () => {
         const file = await writeFile('empty-byte-count.bin', Buffer.alloc(0));
         for (const query of ['byte_count=512', 'offset=0']) {

src/backend/controllers/fs/LegacyFSController.ts

@@ -765,8 +765,10 @@ export class LegacyFSController extends PuterController {
             normalizedTarget,
         );
         if (dedupeName) {
-            const existing =
-                await this.stores.fsEntry.getEntryByPath(normalizedTarget);
+            const existing = await this.stores.fsEntry.getEntryByPath(
+                normalizedTarget,
+                { foldedNames: true },
+            );
             if (existing) {
                 const parent = pathPosix.dirname(normalizedTarget);
                 await assertAccess(
@@ -1320,7 +1322,7 @@ export class LegacyFSController extends PuterController {
         if (options.realMime) {
             res.setHeader(
                 'Content-Type',
-                contentTypeFromMime(entry.name) as string,
+                contentTypeFromMime(entry.name) || 'application/octet-stream',
             );
         } else {
             res.setHeader('Content-Type', 'application/octet-stream');

src/backend/controllers/fs/sharedFolderWrites.http.test.ts

@@ -277,4 +277,124 @@ describe('writes inside a folder shared with write', () => {
             expect(JSON.stringify(res.json)).not.toContain(s.realDir);
         }
     }, 180_000);
+
+    describe('a file the recipient opened with an app', () => {
+        const makeApp = (ownerUserId: number) =>
+            (
+                env.server.stores.app.create as unknown as (
+                    fields: Record<string, unknown>,
+                    opts: { ownerUserId: number },
+                ) => Promise<{ uid: string; id: number }>
+            )(
+                {
+                    name: `sfw-app-${Math.random().toString(36).slice(2, 9)}`,
+                    title: 'Shared folder app',
+                    index_url: `https://sfw-${Math.random().toString(36).slice(2, 9)}.test/`,
+                },
+                { ownerUserId },
+            );
+
+        /** Opens `note.txt` with a new app, as a launch does. */
+        const openWithApp = async (
+            s: Awaited<ReturnType<typeof shareAFolder>>,
+        ) => {
+            const recipientId = (await env.server.stores.user.getByUsername(
+                s.recipient.username,
+            ))!.id;
+            const app = await makeApp(recipientId);
+            const signed = await post('/sign', s.recipient.token, {
+                items: [{ uid: s.noteUid, action: 'write' }],
+                app_uid: app.uid,
+            });
+            expect(signed.status).toBe(200);
+            return { app, appToken: signed.json!.token as string };
+        };
+
+        const read = async (token: string, query: Record<string, string>) => {
+            const res = await fetch(
+                new URL(`/read?${new URLSearchParams(query)}`, env.apiOrigin),
+                { headers: { authorization: `Bearer ${token}` } },
+            );
+            return { status: res.status, text: await res.text() };
+        };
+
+        const write = (token: string, path: string, content: string) =>
+            post('/fs/write', token, {
+                fileMetadata: {
+                    path,
+                    size: content.length,
+                    contentType: 'text/plain',
+                    overwrite: true,
+                },
+                fileContent: content,
+            });
+
+        it('reads and saves it by path and uid', async () => {
+            const s = await shareAFolder();
+            const { appToken } = await openWithApp(s);
+            const masked = `${s.maskedDir}/note.txt`;
+            const real = `${s.realDir}/note.txt`;
+
+            expect((await write(appToken, masked, 'one')).status).toBe(200);
+            expect(await read(appToken, { uid: s.noteUid })).toEqual({
+                status: 200,
+                text: 'one',
+            });
+            expect((await write(appToken, real, 'two')).status).toBe(200);
+            expect(await read(appToken, { file: real })).toEqual({
+                status: 200,
+                text: 'two',
+            });
+            expect(
+                (await post('/stat', appToken, { uid: s.noteUid })).status,
+            ).toBe(200);
+        }, 180_000);
+
+        it('only reads it once the share drops to read', async () => {
+            const s = await shareAFolder();
+            const { appToken } = await openWithApp(s);
+            const dir = await post('/stat', s.owner.token, { path: s.realDir });
+            const reshared = await post('/share', s.owner.token, {
+                recipients: [s.recipient.username],
+                items: [{ uid: dir.json!.uid }],
+                mode: 'read',
+            });
+            expect(reshared.status).toBe(200);
+
+            expect((await read(appToken, { uid: s.noteUid })).status).toBe(200);
+            expect(
+                (await write(appToken, `${s.maskedDir}/note.txt`, 'x')).status,
+            ).toBe(403);
+        }, 180_000);
+
+        it('gives nothing to another app of the recipient', async () => {
+            const s = await shareAFolder();
+            const { appToken } = await openWithApp(s);
+            const recipientId = (await env.server.stores.user.getByUsername(
+                s.recipient.username,
+            ))!.id;
+            const other = await makeApp(recipientId);
+            const minted = await post(
+                '/auth/get-user-app-token',
+                s.recipient.token,
+                { app_uid: other.uid },
+            );
+            expect(minted.status).toBe(200);
+            const otherToken = minted.json!.token as string;
+
+            // The same requests the opened app gets through.
+            const real = `${s.realDir}/note.txt`;
+            expect((await read(appToken, { uid: s.noteUid })).status).toBe(200);
+            expect((await write(appToken, real, 'one')).status).toBe(200);
+
+            expect((await read(otherToken, { uid: s.noteUid })).status).toBe(
+                404,
+            );
+            expect((await write(otherToken, real, 'x')).status).toBe(404);
+            expect(await read(appToken, { uid: s.noteUid })).toEqual({
+                status: 200,
+                text: 'one',
+            });
+        }, 180_000);
+    });
 });

src/backend/controllers/puterai/PuterAIController.shapes.test.ts

@@ -44,7 +44,7 @@ import {
 } from 'vitest';
 
 import type { Actor } from '../../core/actor.js';
-import type { ChatCompletionDriver } from '../../drivers/ai-chat/ChatCompletionDriver.js';
+import type { ChatCompletionDriver } from '../../drivers/ai/interfaces/chat/ChatCompletionDriver.js';
 import { PuterServer } from '../../server.js';
 import { inRequestScope, setupTestServer } from '../../testUtil.js';
 import { PuterAIController } from './PuterAIController.js';

src/backend/controllers/puterai/PuterAIController.test.ts

@@ -49,8 +49,8 @@ import type { RouteOptions } from '../../core/http/index.js';
 import {
     COUNT_TOKENS,
     type ChatCompletionDriver,
-} from '../../drivers/ai-chat/ChatCompletionDriver.js';
-import { AI_CONCURRENT, AI_RATE_LIMIT } from '../../drivers/util/aiLimits.js';
+} from '../../drivers/ai/interfaces/chat/ChatCompletionDriver.js';
+import { AI_CONCURRENT, AI_RATE_LIMIT } from '../../drivers/ai/shared/aiLimits.js';
 import { PuterServer } from '../../server.js';
 import { inRequestScope, setupTestServer } from '../../testUtil.js';
 import { PuterAIController } from './PuterAIController.js';

src/backend/controllers/puterai/PuterAIController.ts

@@ -30,25 +30,28 @@ import type { PuterRouter } from '../../core/http/PuterRouter.js';
 import {
     COUNT_TOKENS,
     type ChatCompletionDriver,
-} from '../../drivers/ai-chat/ChatCompletionDriver.js';
+} from '../../drivers/ai/interfaces/chat/ChatCompletionDriver.js';
 import type {
     IChatCompleteResult,
     IChatMessageResult,
     IChatModel,
     ICompleteArguments,
     UsageDetails,
-} from '../../drivers/ai-chat/types.js';
+} from '../../drivers/ai/interfaces/chat/types.js';
 import {
     outputFormatFromResponseFormat,
     rejectStatefulResponsesFields,
     toolChoiceFromWire,
-} from '../../drivers/ai-chat/utils/openaiParams.js';
+} from '../../drivers/ai/protocols/openaiCompatible/openaiParams.js';
 import {
     promoteStopForToolCalls,
     toFinishReason,
-} from '../../drivers/ai-chat/utils/stopReason.js';
+} from '../../drivers/ai/interfaces/chat/utils/stopReason.js';
 import { isDriverStreamResult } from '../../drivers/meta.js';
-import { AI_CONCURRENT, AI_RATE_LIMIT } from '../../drivers/util/aiLimits.js';
+import {
+    AI_CONCURRENT,
+    AI_RATE_LIMIT,
+} from '../../drivers/ai/shared/aiLimits.js';
 import { PuterController } from '../types.js';
 import { parseAnthropicRequest, toAnthropicMessage } from './anthropicWire.js';
 import { pipeNdjsonStream } from './ndjsonStream.js';
@@ -1301,13 +1304,18 @@ export class PuterAIController extends PuterController {
         return driver;
     }
 
-    /** A completion that stops, and stops billing, when the caller hangs up. */
+    /**
+     * A completion whose caller may hang up. It runs on to its usage report
+     * either way, so it holds the route's concurrency slot until it settles.
+     */
     #complete(
         res: Response,
         args: ICompleteArguments,
     ): Promise<IChatCompleteResult> {
         Context.set('abortSignal', abortOnDisconnect(res));
-        return this.#driver().complete(args);
+        const completion = this.#driver().complete(args);
+        Context.get('keepConcurrencySlot')?.(completion);
+        return completion;
     }
 }
 

src/backend/controllers/puterai/anthropicWire.test.ts

@@ -18,7 +18,7 @@
  */
 
 import { describe, expect, it } from 'vitest';
-import type { IChatMessageResult } from '../../drivers/ai-chat/types.js';
+import type { IChatMessageResult } from '../../drivers/ai/interfaces/chat/types.js';
 import {
     anthropicUsage,
     parseAnthropicRequest,

src/backend/controllers/puterai/anthropicWire.ts

@@ -32,7 +32,7 @@
 
 import type { IncomingHttpHeaders } from 'node:http';
 import { HttpError } from '../../core/http/HttpError.js';
-import { sanitizeCacheControl } from '../../drivers/ai-chat/providers/claude/anthropicPolicy.js';
+import { sanitizeCacheControl } from '../../drivers/ai/providers/claude/chat/anthropicPolicy.js';
 import type {
     ICompleteArguments,
     IChatMessageResult,
@@ -42,9 +42,9 @@ import type {
     ThinkingConfig,
     ToolChoice,
     UsageDetails,
-} from '../../drivers/ai-chat/types.js';
-import { needsOpenAICoercion } from '../../drivers/ai-chat/utils/normalizeToOpenAI.js';
-import { fromFinishReason } from '../../drivers/ai-chat/utils/stopReason.js';
+} from '../../drivers/ai/interfaces/chat/types.js';
+import { needsOpenAICoercion } from '../../drivers/ai/interfaces/chat/utils/normalizeToOpenAI.js';
+import { fromFinishReason } from '../../drivers/ai/interfaces/chat/utils/stopReason.js';
 
 const toStringOrEmpty = (v: unknown): string =>
     typeof v === 'string' ? v : '';

src/backend/controllers/puterai/sse.ts

@@ -20,14 +20,14 @@
 /**
  * SSE transport (`startSse`) plus the Anthropic `/v1/messages` streaming writer
  * (`AnthropicSseWriter`), which turns the driver's NDJSON chunk protocol
- * (`drivers/ai-chat/utils/Streaming.js`) into the exact Anthropic event
- * sequence: `message_start` → `content_block_start/delta/stop`* →
+ * (`drivers/ai/interfaces/chat/utils/Streaming.js`) into the exact Anthropic
+ * event sequence: `message_start` → `content_block_start/delta/stop`* →
  * `message_delta` → `message_stop`.
  */
 
 import type { Response } from 'express';
-import type { UsageDetails } from '../../drivers/ai-chat/types.js';
-import { promoteStopForToolCalls } from '../../drivers/ai-chat/utils/stopReason.js';
+import type { UsageDetails } from '../../drivers/ai/interfaces/chat/types.js';
+import { promoteStopForToolCalls } from '../../drivers/ai/interfaces/chat/utils/stopReason.js';
 import { anthropicUsage } from './anthropicWire.js';
 
 // -- SSE transport ------------------------------------------------------------

src/backend/controllers/system/SystemController.js

@@ -301,6 +301,7 @@ export class SystemController extends PuterController {
                 if (this.clients.email && req.actor.user?.email) {
                     try {
                         await this.clients.email.sendRaw({
+                            stream: 'notify',
                             to: supportEmail,
                             replyTo: req.actor.user.email,
                             subject: `Contact from ${req.actor.user.username}`,

src/backend/controllers/system/SystemController.test.ts

@@ -547,6 +547,7 @@ describe('SystemController POST /contactUs — attachments', () => {
 
             expect(sendRaw).toHaveBeenCalledTimes(1);
             const sent = sendRaw.mock.calls[0][0] as {
+                stream: string;
                 text: string;
                 attachments: Array<{
                     filename: string;
@@ -555,6 +556,7 @@ describe('SystemController POST /contactUs — attachments', () => {
                     contentDisposition: string;
                 }>;
             };
+            expect(sent.stream).toBe('notify');
             expect(sent.attachments).toHaveLength(1);
             expect(sent.attachments[0].filename).toBe('payload.png');
             expect(sent.attachments[0].contentType).toBe('image/png');

src/backend/controllers/webdav/WebDAVController.ts

@@ -813,7 +813,10 @@ export class WebDAVController extends PuterController {
         const userId = actor.user!.id as number;
         await this.#assertCreate(actor, davPath);
 
-        const existing = await this.stores.fsEntry.getEntryByPath(davPath);
+        // A name only the collation matches is taken too.
+        const existing = await this.stores.fsEntry.getEntryByPath(davPath, {
+            foldedNames: true,
+        });
         if (existing)
             throw new HttpError(405, 'Already exists', {
                 legacyCode: 'bad_request',
@@ -937,7 +940,9 @@ export class WebDAVController extends PuterController {
         await this.#assertCreate(actor, destPath);
 
         const overwrite = req.headers.overwrite !== 'F';
-        const destExists = await this.stores.fsEntry.getEntryByPath(destPath);
+        const destExists = await this.stores.fsEntry.getEntryByPath(destPath, {
+            foldedNames: true,
+        });
         if (destExists && !overwrite)
             throw new HttpError(412, 'Destination exists and Overwrite=F', {
                 legacyCode: 'conflict',
@@ -985,7 +990,9 @@ export class WebDAVController extends PuterController {
         await this.#assertCreate(actor, destPath);
 
         const overwrite = req.headers.overwrite !== 'F';
-        const destExists = await this.stores.fsEntry.getEntryByPath(destPath);
+        const destExists = await this.stores.fsEntry.getEntryByPath(destPath, {
+            foldedNames: true,
+        });
         if (destExists && !overwrite)
             throw new HttpError(412, 'Destination exists and Overwrite=F', {
                 legacyCode: 'conflict',

src/backend/core/context.ts

@@ -69,11 +69,11 @@ export interface KnownContextFields {
      */
     abortSignal: AbortSignal;
     /**
-     * Keeps the call's concurrency slot until `work` settles (set by
-     * DriverController when the method is capped), for work that outlives the
-     * response.
+     * Keeps the request's concurrency slot until `work` settles, for work that
+     * outlives the response. Set by DriverController for a capped method and by
+     * the route concurrency gate.
      */
-    keepDriverSlot: (work: Promise<unknown>) => void;
+    keepConcurrencySlot: (work: Promise<unknown>) => void;
     /**
      * Aborts the chat driver's upstream request. A client disconnect doesn't
      * fire it: the upstream bills a request it has accepted either way, so the
@@ -102,7 +102,7 @@ const KNOWN_KEY_FLAGS: Record<keyof KnownContextFields, true> = {
     requestId: true,
     driverName: true,
     abortSignal: true,
-    keepDriverSlot: true,
+    keepConcurrencySlot: true,
     upstreamSignal: true,
     strictUpstreamErrors: true,
     platformWrite: true,

src/backend/core/http/callSlot.ts

@@ -28,9 +28,9 @@ interface SlotHandle {
 }
 
 /**
- * A driver call's concurrency slot, held until the response is done and the
- * call's work has settled, including work a driver carries on after the caller
- * hung up or was answered.
+ * A request's concurrency slot, held until the response is done and the work
+ * registered with `keep` has settled, including work that carries on after the
+ * caller hung up or was answered.
  */
 export class CallSlot {
     #handle?: SlotHandle;

src/backend/core/http/middleware/rateLimit.js

@@ -20,6 +20,8 @@
 
 import crypto from 'node:crypto';
 import { withSpan } from '../../../util/span.js';
+import { Context } from '../../context.js';
+import { CallSlot } from '../callSlot.js';
 import { HttpError } from '../HttpError.js';
 import { subscriptionOverride } from '../../../services/metering/consts.js';
 
@@ -412,8 +414,8 @@ async function peekKv(kv, key, limit) {
 //
 // Lifecycle is the wedge between rate and concurrent limits: rate just
 // records a tick, concurrent has to track "still in flight" → "done"
-// across a request boundary. The route middleware hooks `res.finish` /
-// `res.close`; the driver helper wraps the invocation in `try/finally`.
+// across a request boundary. The route middleware and the driver controller
+// both hold the slot in a `CallSlot`.
 
 // Orphan TTL safety nets — used when the process dies between acquire
 // and release. Memory backend doesn't need one (the process is also
@@ -1137,8 +1139,9 @@ async function resolveSubscriptionLimit(req, opts) {
  * bySubscription: { user_free: 2, unlimited: 50 } } } { concurrent: { limit:
  * 10, backend: 'redis', scope: 'expensive-op' } }
  *
- * On accept, schedules release on `res.finish` / `res.close` so even aborted
- * requests give their slot back. On reject, 429 with the same
+ * On accept, holds the slot until the response is done and any work the handler
+ * registered through `keepConcurrencySlot` has settled, so work that outlives a
+ * caller who hung up still counts. On reject, 429 with the same
  * `too_many_requests` legacyCode as the rate gate (clients already handle that
  * branch). Fails open on backend error.
  */
@@ -1164,13 +1167,11 @@ export function concurrencyGate(opts) {
             return;
         }
 
-        // `finish` (response sent) and `close` (connection closed, possibly
-        // aborted before finish) can both fire; the guard releases once.
-        const { release } = guardSlot(slot, '[concurrent]');
-        const onDone = () => void release();
-        res.once('finish', onDone);
-        res.once('close', onDone);
-        if (res.destroyed || res.writableFinished) onDone();
+        const held = new CallSlot();
+        held.attach(guardSlot(slot, '[concurrent]'), res);
+        if (Context.current()) {
+            Context.set('keepConcurrencySlot', (work) => held.keep(work));
+        }
         next();
     };
 }

src/backend/core/http/middleware/rateLimit.test.js

@@ -29,6 +29,7 @@ import {
     vi,
 } from 'vitest';
 import { EventEmitter } from 'node:events';
+import { Context, runWithContext } from '../../context.js';
 import { isHttpError } from '../HttpError.js';
 import { setupTestServer } from '../../../testUtil.ts';
 import {
@@ -977,6 +978,27 @@ describe('concurrencyGate — memory backend', () => {
         expect(isHttpError(third.err)).toBe(true);
     });
 
+    it('holds the slot past the response for work the handler keeps', async () => {
+        const opts = { limit: 1, key: 'ip', scope: 'cg-kept-work' };
+        let finishWork;
+        const work = new Promise((resolve) => {
+            finishWork = resolve;
+        });
+        const res = makeRes();
+        await runWithContext({}, async () => {
+            await concurrencyGate(opts)(baseReq(), res, () => {
+                Context.get('keepConcurrencySlot')(work);
+            });
+        });
+        res.emit('close');
+        await new Promise((r) => setImmediate(r));
+        expect((await runGate(opts, baseReq())).err?.statusCode).toBe(429);
+
+        finishWork();
+        await new Promise((r) => setImmediate(r));
+        expect((await runGate(opts, baseReq())).err).toBeUndefined();
+    });
+
     it('different keys do not share slots', async () => {
         const opts = { limit: 1, key: 'ip', scope: 'cg-keyed' };
         const a = await runGate(opts, baseReq({ ip: '1.1.1.1' }));

src/backend/core/http/types.ts

@@ -263,10 +263,10 @@ export interface RouteOptions {
     rateLimit?: RouteRateLimit | RouteRateLimit[];
 
     /**
-     * Cap simultaneous in-flight requests per key; slots are released on
-     * response finish or close. `bySubscription` overrides `limit` per
-     * `SubscriptionPolicy.id` when metering is wired in. `key`, `scope`,
-     * `backend` as in `rateLimit`.
+     * Cap simultaneous in-flight requests per key; a slot is released once the
+     * response is done and any work the handler kept it for has settled.
+     * `bySubscription` overrides `limit` per `SubscriptionPolicy.id` when
+     * metering is wired in. `key`, `scope`, `backend` as in `rateLimit`.
      */
     concurrent?: {
         limit: number;

src/backend/drivers/ai-chat/utils/compaction.test.ts

@@ -1,132 +0,0 @@
-/*
- * Copyright (C) 2024-present Puter Technologies Inc.
- *
- * This file is part of Puter.
- *
- * Puter is free software: you can redistribute it and/or modify
- * it under the terms of the GNU Affero General Public License as published
- * by the Free Software Foundation, either version 3 of the License, or
- * (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU Affero General Public License for more details.
- *
- * You should have received a copy of the GNU Affero General Public License
- * along with this program.  If not, see <https://www.gnu.org/licenses/>.
- */
-
-import { describe, expect, it } from 'vitest';
-import {
-    messagesHaveCompaction,
-    toAnthropicContextManagement,
-    toOpenAiContextManagement,
-    wantsCompaction,
-} from './compaction.js';
-
-describe('toOpenAiContextManagement', () => {
-    it('returns undefined when compaction is off', () => {
-        expect(toOpenAiContextManagement({})).toBeUndefined();
-        expect(
-            toOpenAiContextManagement({ compaction: false }),
-        ).toBeUndefined();
-    });
-
-    it('builds a compaction entry from `true`', () => {
-        expect(toOpenAiContextManagement({ compaction: true })).toEqual([
-            { type: 'compaction' },
-        ]);
-    });
-
-    it('maps trigger_tokens to compact_threshold', () => {
-        expect(
-            toOpenAiContextManagement({ compaction: { trigger_tokens: 1000 } }),
-        ).toEqual([{ type: 'compaction', compact_threshold: 1000 }]);
-    });
-
-    it('passes a raw context_management payload through verbatim', () => {
-        const raw = [{ type: 'compaction', compact_threshold: 5 }];
-        expect(
-            toOpenAiContextManagement({
-                compaction: true,
-                context_management: raw,
-            }),
-        ).toBe(raw);
-    });
-});
-
-describe('toAnthropicContextManagement', () => {
-    it('returns undefined when compaction is off', () => {
-        expect(toAnthropicContextManagement({})).toBeUndefined();
-    });
-
-    it('builds a compact_20260112 edit from `true`', () => {
-        expect(toAnthropicContextManagement({ compaction: true })).toEqual({
-            edits: [{ type: 'compact_20260112' }],
-        });
-    });
-
-    it('maps trigger_tokens to an input_tokens trigger', () => {
-        expect(
-            toAnthropicContextManagement({
-                compaction: { trigger_tokens: 2000 },
-            }),
-        ).toEqual({
-            edits: [
-                {
-                    type: 'compact_20260112',
-                    trigger: { type: 'input_tokens', value: 2000 },
-                },
-            ],
-        });
-    });
-
-    it('passes a raw context_management payload through verbatim', () => {
-        const raw = { edits: [{ type: 'compact_20260112' }] };
-        expect(
-            toAnthropicContextManagement({ context_management: raw }),
-        ).toBe(raw);
-    });
-});
-
-describe('wantsCompaction', () => {
-    it('is false without opt-in', () => {
-        expect(wantsCompaction({})).toBe(false);
-        expect(wantsCompaction({ compaction: false })).toBe(false);
-    });
-
-    it('is true for the neutral opt-in or a raw passthrough', () => {
-        expect(wantsCompaction({ compaction: true })).toBe(true);
-        expect(wantsCompaction({ compaction: { trigger_tokens: 1 } })).toBe(
-            true,
-        );
-        expect(wantsCompaction({ context_management: [] })).toBe(true);
-    });
-});
-
-describe('messagesHaveCompaction', () => {
-    it('detects a round-tripped compaction content block', () => {
-        expect(
-            messagesHaveCompaction([
-                { role: 'user', content: [{ type: 'text', text: 'hi' }] },
-                {
-                    role: 'assistant',
-                    content: [
-                        { type: 'compaction', encrypted_content: 'ENC' },
-                    ],
-                },
-            ]),
-        ).toBe(true);
-    });
-
-    it('is false for ordinary messages or non-arrays', () => {
-        expect(
-            messagesHaveCompaction([
-                { role: 'user', content: [{ type: 'text', text: 'hi' }] },
-            ]),
-        ).toBe(false);
-        expect(messagesHaveCompaction(undefined)).toBe(false);
-        expect(messagesHaveCompaction('nope')).toBe(false);
-    });
-});

src/backend/drivers/ai-ocr/OCRDriver.ts

@@ -1,718 +0,0 @@
-/*
- * Copyright (C) 2024-present Puter Technologies Inc.
- *
- * This file is part of Puter.
- *
- * Puter is free software: you can redistribute it and/or modify
- * it under the terms of the GNU Affero General Public License as published
- * by the Free Software Foundation, either version 3 of the License, or
- * (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU Affero General Public License for more details.
- *
- * You should have received a copy of the GNU Affero General Public License
- * along with this program.  If not, see <https://www.gnu.org/licenses/>.
- */
-
-import {
-    DetectDocumentTextCommand,
-    InvalidS3ObjectException,
-    TextractClient,
-    UnsupportedDocumentException,
-} from '@aws-sdk/client-textract';
-import { Mistral } from '@mistralai/mistralai';
-import { Actor } from '../../core/actor.js';
-import { Context } from '../../core/context.js';
-import { HttpError } from '../../core/http/HttpError.js';
-import {
-    awsCredentialsFrom,
-    type AwsCredentials,
-} from '../../util/awsCredentials.js';
-import { mimeFromName } from '../../util/fileSigning.js';
-import {
-    assertActorHasCredits,
-    insufficientCreditsError,
-} from '../../services/metering/enforcement.js';
-import type { CreditHold } from '../../services/metering/types.js';
-import { PuterDriver } from '../types.js';
-import {
-    type AiMeteringService,
-    withAiCostFactor,
-} from '../util/aiCostFactor.js';
-import { AI_CONCURRENT, AI_RATE_LIMIT } from '../util/aiLimits.js';
-import {
-    type LoadedFile,
-    type ResolvedFileInput,
-    resolveFileInput,
-} from '../util/fileInput.js';
-import {
-    type ProviderCatalog,
-    ProviderRegistry,
-    readProviderKey,
-} from '../util/providerRegistry.js';
-import { OCR_COSTS } from './costs.js';
-import {
-    DEFAULT_OCR_MODEL,
-    findOcrModel,
-    OCR_MAX_INPUT_BYTES,
-    OCR_MAX_PAGES,
-    RETIRED_OCR_MODELS,
-    type OcrModel,
-    type OcrProviderId,
-} from './models.js';
-import { countPdfPages } from './pdfPages.js';
-import { textractRates } from './textractPricing.js';
-
-/**
- * Driver implementing `puter-ocr` — document OCR. Two providers: •
- * `aws-textract` — AWS Textract (region-aware clients; direct S3 source when
- * available) • `mistral` — Mistral OCR (URL/data-URL based)
- */
-interface RecognizeArgs {
-    source?: unknown;
-    file?: unknown;
-    provider?: string;
-    model?: string;
-    // Mistral-specific options — ignored by Textract.
-    pages?: number[];
-    includeImageBase64?: boolean;
-    imageLimit?: number;
-    imageMinSize?: number;
-    bboxAnnotationFormat?: unknown;
-    documentAnnotationFormat?: unknown;
-    documentAnnotationPrompt?: string;
-    tableFormat?: string;
-    extractHeader?: boolean;
-    extractFooter?: boolean;
-    test_mode?: boolean;
-}
-
-/** One recognized line, in the same shape for every provider. */
-interface OcrBlock {
-    type: string;
-    text: string;
-    confidence?: number;
-    page: number;
-}
-
-interface TextractBlock {
-    BlockType?: string;
-    Confidence?: number;
-    Text?: string;
-}
-
-interface MistralOcrResponse {
-    model?: string;
-    pages?: Array<{
-        index?: number;
-        markdown?: string;
-        images?: unknown[];
-        dimensions?: unknown;
-    }>;
-    documentAnnotation?: string | null;
-    usageInfo?: { pagesProcessed?: number };
-}
-
-interface MistralOcrClient {
-    ocr: {
-        process: (
-            payload: Record<string, unknown>,
-        ) => Promise<MistralOcrResponse>;
-    };
-}
-
-// Aliases callers may use in place of a canonical provider id. Resolved here
-// rather than in the SDK so a new alias reaches every caller at once.
-const OCR_CATALOG: ProviderCatalog = {
-    label: 'OCR',
-    ids: ['aws-textract', 'mistral'],
-    defaultId: 'aws-textract',
-    aliases: {
-        aws: 'aws-textract',
-        'aws-textract': 'aws-textract',
-        textract: 'aws-textract',
-        mistral: 'mistral',
-        'mistral-ocr': 'mistral',
-    },
-};
-
-/** Recognizes one input with one provider's model. */
-type OcrRecognizer = (
-    input: ResolvedFileInput,
-    args: RecognizeArgs,
-    model: OcrModel,
-    actor: Actor,
-) => Promise<unknown>;
-
-const NOT_CONFIGURED: Record<OcrProviderId, string> = {
-    'aws-textract': 'AWS credentials not configured',
-    mistral: 'Mistral OCR not configured',
-};
-
-const TABLE_FORMATS = new Set(['markdown', 'html']);
-
-const DEFAULT_TEXTRACT_REGION = 'us-west-2';
-const TEXTRACT_PAGE_USAGE_TYPE = 'aws-textract:detect-document-text:page';
-
-const badRequest = (message: string) =>
-    new HttpError(400, message, { legacyCode: 'bad_request' });
-
-/**
- * Accept a Mistral annotation format in the REST spelling
- * (`json_schema.schema`) or the SDK spelling (`jsonSchema.schemaDefinition`)
- * and return the SDK shape.
- */
-const toMistralResponseFormat = (
-    name: string,
-    value: unknown,
-): Record<string, unknown> => {
-    const format = value as Record<string, unknown> | null;
-    const jsonSchema = (format?.jsonSchema ?? format?.json_schema) as
-        Record<string, unknown> | undefined;
-    const schema = jsonSchema?.schemaDefinition ?? jsonSchema?.schema;
-    if (
-        !format ||
-        typeof format !== 'object' ||
-        (format.type !== undefined && format.type !== 'json_schema') ||
-        !schema ||
-        typeof schema !== 'object'
-    ) {
-        throw badRequest(
-            `\`${name}\` must be { type: 'json_schema', json_schema: { name, schema } }`,
-        );
-    }
-    return {
-        type: 'json_schema',
-        jsonSchema: {
-            name:
-                typeof jsonSchema?.name === 'string'
-                    ? jsonSchema.name
-                    : 'annotation',
-            schemaDefinition: schema,
-            ...(typeof jsonSchema?.description === 'string' && {
-                description: jsonSchema.description,
-            }),
-            ...(typeof jsonSchema?.strict === 'boolean' && {
-                strict: jsonSchema.strict,
-            }),
-        },
-    };
-};
-
-const inputMimeType = (loaded: LoadedFile): string =>
-    loaded.mimeType ??
-    mimeFromName(loaded.filename) ??
-    'application/octet-stream';
-
-/**
- * Declared documents (PDF, DOCX, PPTX, ...) and PDF bytes are documents; images
- * and untyped bytes are read as a single image.
- */
-const isDocumentInput = (loaded: LoadedFile): boolean => {
-    const mime = inputMimeType(loaded);
-    return (
-        loaded.buffer.subarray(0, 4).toString('latin1') === '%PDF' ||
-        loaded.filename.toLowerCase().endsWith('.pdf') ||
-        (!mime.startsWith('image/') && mime !== 'application/octet-stream')
-    );
-};
-
-/**
- * The most pages a call can bill, known before the provider runs: a PDF's page
- * count, or a size-based guess for other documents, capped by a `pages`
- * selection and by what the provider reads in one call. Reads the input only
- * for a provider that takes more than one page.
- */
-const estimateOcrPages = async (
-    input: ResolvedFileInput,
-    provider: OcrProviderId,
-    selection?: unknown,
-): Promise<number> => {
-    const maxPages = OCR_MAX_PAGES[provider];
-    if (maxPages <= 1) return 1;
-    const loaded = await input.load();
-    if (!isDocumentInput(loaded)) return 1;
-    // A document we can't count is billed in proportion to its size, reaching
-    // the provider's page limit at its size limit (20 pages per MB for
-    // Mistral). Small files stay cheap; a large one can't pass as one page.
-    const documentPages =
-        (await countPdfPages(loaded.buffer, maxPages)) ??
-        Math.ceil(
-            (loaded.buffer.length * maxPages) / OCR_MAX_INPUT_BYTES[provider],
-        );
-    const selected = Array.isArray(selection)
-        ? new Set(
-              selection.filter(
-                  (page) => Number.isInteger(page) && (page as number) >= 0,
-              ),
-          ).size
-        : 0;
-    return Math.max(1, Math.min(documentPages, maxPages, selected || Infinity));
-};
-
-export class OCRDriver extends PuterDriver {
-    readonly driverInterface = 'puter-ocr';
-    readonly driverName = 'ai-ocr';
-
-    // Shared AI policy — see `drivers/util/aiLimits.ts` for the tier table.
-    readonly rateLimit = AI_RATE_LIMIT;
-    readonly concurrent = AI_CONCURRENT;
-
-    /** Metering scoped to this driver. Lazy: services wire up after drivers. */
-    get #aiMetering(): AiMeteringService {
-        return withAiCostFactor(
-            this.services.metering,
-            this.clients.event,
-            this.driverName,
-        );
-    }
-
-    /**
-     * Textract is reported at the configured region's first-tier rate. A call
-     * that reads its file from a bucket in another region is billed at that
-     * region's rate instead, which this per-usage-type report can't show.
-     */
-    override getReportedCosts() {
-        const textractRegion =
-            this.#awsConfig?.region ?? DEFAULT_TEXTRACT_REGION;
-        return Object.entries(OCR_COSTS).map(([usageType, ucentsPerUnit]) => ({
-            usageType,
-            ucentsPerUnit:
-                usageType === TEXTRACT_PAGE_USAGE_TYPE
-                    ? this.#textractRates.peek(textractRegion)
-                    : ucentsPerUnit,
-            unit: 'page',
-            source: 'driver:aiOcr',
-        }));
-    }
-
-    // Older SDK bundles name the provider in the driver slot instead of
-    // passing `{ provider }`; `#resolveModel` reads the requested alias
-    // back off the Context.
-    readonly driverAliases = [...OCR_CATALOG.ids];
-    readonly isDefault = true;
-
-    // Textract state — one client per region.
-    #textractClients: Record<string, TextractClient> = {};
-    #awsConfig: { credentials: AwsCredentials; region: string } | null = null;
-    /** DetectDocumentText rates per region, from AWS's public price list. */
-    #textractRates = textractRates(OCR_COSTS[TEXTRACT_PAGE_USAGE_TYPE]);
-
-    // Mistral state.
-    #mistral: MistralOcrClient | null = null;
-
-    /** Configured providers, each a recognizer bound to its state above. */
-    #providers = new ProviderRegistry<OcrRecognizer>(OCR_CATALOG);
-
-    override onServerStart() {
-        const providers = this.config.providers ?? {};
-
-        const textract = providers['aws-textract'] as
-            Record<string, unknown> | undefined;
-        const textractAws = (textract?.aws ?? textract) as
-            Record<string, unknown> | undefined;
-        const textractCredentials = awsCredentialsFrom(textractAws);
-        const textractRegion =
-            (textractAws?.region as string | undefined) ??
-            (textract?.region as string | undefined) ??
-            DEFAULT_TEXTRACT_REGION;
-        if (textractCredentials) {
-            this.#awsConfig = {
-                credentials: textractCredentials,
-                region: textractRegion,
-            };
-            // Warm the configured region so the cost report has its rate.
-            void this.#textractRates.rate(textractRegion);
-            this.#providers.register(
-                'aws-textract',
-                (input, _args, model, actor) =>
-                    this.#textractRecognize(input, model, actor),
-            );
-        }
-
-        const mistralKey = readProviderKey(providers['mistral-ocr']);
-        if (mistralKey) {
-            try {
-                this.#mistral = new Mistral({
-                    apiKey: mistralKey,
-                }) as unknown as MistralOcrClient;
-                this.#providers.register(
-                    'mistral',
-                    (input, args, model, actor) =>
-                        this.#mistralRecognize(input, args, model, actor),
-                );
-            } catch (e) {
-                console.warn(
-                    '[OCRDriver] Failed to init Mistral:',
-                    (e as Error).message,
-                );
-            }
-        }
-    }
-
-    async recognize(args: RecognizeArgs) {
-        if (args.test_mode) return sampleResponse();
-
-        const model = this.#resolveModel(args);
-
-        const actor = Context.get('actor');
-        if (!actor)
-            throw new HttpError(401, 'Authentication required', {
-                legacyCode: 'unauthorized',
-            });
-
-        const input = args.source ?? args.file;
-        if (!input) throw badRequest('`source` is required');
-
-        const recognize = this.#providers.get(model.provider);
-        if (!recognize)
-            throw new HttpError(500, NOT_CONFIGURED[model.provider], {
-                legacyCode: 'internal_error',
-            });
-
-        // Cheap, cached check: reject a zero-balance actor before paying for
-        // the file load and page estimate, which a real credit check would
-        // reject anyway once it runs.
-        await assertActorHasCredits(this.services.metering, actor, this.config);
-
-        // A Puter file is resolved and access-checked here but read only if
-        // the provider needs its bytes; Textract reads it straight from S3.
-        const resolved = await resolveFileInput(
-            this.stores,
-            this.services.fs,
-            actor,
-            input,
-            {
-                acceptWebInput: true,
-                maxBytes: OCR_MAX_INPUT_BYTES[model.provider],
-            },
-        );
-
-        return recognize(resolved, args, model, actor);
-    }
-
-    /**
-     * Decide which model handles a call. A `model` picks its own provider; an
-     * explicit `provider`, then the legacy driver alias the caller dispatched
-     * through, then whichever provider is configured pick that provider's
-     * default model.
-     */
-    #resolveModel(args: RecognizeArgs): OcrModel {
-        const provider = args.provider
-            ? (this.#providers.resolve(args.provider) as OcrProviderId)
-            : undefined;
-
-        if (args.model !== undefined) {
-            if (typeof args.model !== 'string' || !args.model.trim())
-                throw badRequest('`model` must be a non-empty string');
-            const retired = RETIRED_OCR_MODELS[args.model.trim().toLowerCase()];
-            if (retired)
-                throw badRequest(
-                    `${args.model} is no longer available: ${retired}`,
-                );
-            const model = findOcrModel(args.model);
-            if (!model) throw badRequest(`Unknown OCR model: ${args.model}`);
-            if (provider && model.provider !== provider)
-                throw badRequest(
-                    `OCR model ${args.model} is not served by provider ${args.provider}`,
-                );
-            return model;
-        }
-
-        const hinted =
-            provider ?? this.#providers.normalize(Context.get('driverName'));
-        if (!hinted && this.#providers.names().length === 0)
-            throw new HttpError(500, 'No OCR provider configured', {
-                legacyCode: 'internal_error',
-            });
-        const chosen = (hinted ?? this.#providers.defaultId()) as OcrProviderId;
-        return findOcrModel(DEFAULT_OCR_MODEL[chosen])!;
-    }
-
-    /**
-     * Refuse a call the balance can't cover, and hold its cost while the
-     * provider runs so the account's concurrent calls see it. Usage is still
-     * metered from the pages the provider reports.
-     */
-    async #holdCredits(
-        actor: Actor,
-        usageType: string,
-        cost: number,
-    ): Promise<CreditHold> {
-        // Priced at the cost factor usage is recorded at.
-        const hold = await this.#aiMetering.reserveAiCredits(
-            actor,
-            usageType,
-            cost,
-        );
-        if (!hold) throw insufficientCreditsError();
-        return hold;
-    }
-
-    // -- AWS Textract -------------------------------------------------
-
-    #textractClientFor(region: string): TextractClient {
-        const cached = this.#textractClients[region];
-        if (cached) return cached;
-        const client = new TextractClient({
-            credentials: this.#awsConfig!.credentials,
-            region,
-        });
-        this.#textractClients[region] = client;
-        return client;
-    }
-
-    async #textractRecognize(
-        input: ResolvedFileInput,
-        model: OcrModel,
-        actor: Actor,
-    ) {
-        // Prefer S3 direct source if the file is FS-backed; fall back to raw bytes.
-        const { fsEntry } = input;
-        const s3Info =
-            fsEntry && fsEntry.bucket && fsEntry.bucketRegion
-                ? {
-                      bucket: fsEntry.bucket,
-                      bucketRegion: fsEntry.bucketRegion,
-                      key: fsEntry.uuid,
-                  }
-                : null;
-
-        const configuredRegion =
-            this.#awsConfig!.region ?? DEFAULT_TEXTRACT_REGION;
-
-        // Both regions the call may run in are priced up front, so the hold
-        // covers either and a refresh mid-call can't change the charge.
-        const [configuredRate, s3Rate] = await Promise.all([
-            this.#textractRates.rate(configuredRegion),
-            s3Info ? this.#textractRates.rate(s3Info.bucketRegion) : undefined,
-        ]);
-
-        const tryRun = async (useS3: boolean) => {
-            const region =
-                s3Info && useS3 ? s3Info.bucketRegion : configuredRegion;
-            const client = this.#textractClientFor(region);
-            const document =
-                s3Info && useS3
-                    ? { S3Object: { Bucket: s3Info.bucket, Name: s3Info.key } }
-                    : { Bytes: (await input.load()).buffer };
-            return client.send(
-                new DetectDocumentTextCommand({ Document: document }),
-            );
-        };
-
-        const hold = await this.#holdCredits(
-            actor,
-            model.pageUsageType,
-            Math.max(configuredRate, s3Rate ?? 0) *
-                (await estimateOcrPages(input, model.provider)),
-        );
-        try {
-            let response;
-            let costPerPage: number;
-            try {
-                try {
-                    response = await tryRun(Boolean(s3Info));
-                    costPerPage = s3Rate ?? configuredRate;
-                } catch (err) {
-                    if (!(s3Info && err instanceof InvalidS3ObjectException))
-                        throw err;
-                    response = await tryRun(false);
-                    costPerPage = configuredRate;
-                }
-            } catch (err) {
-                if (err instanceof UnsupportedDocumentException)
-                    throw badRequest(
-                        'AWS Textract reads JPEG, PNG, TIFF and single-page PDF documents; use a Mistral OCR model for multi-page PDFs and other formats',
-                    );
-                throw err;
-            }
-
-            const blocks: OcrBlock[] = [];
-            let pageCount = 0;
-            for (const block of (response.Blocks ?? []) as TextractBlock[]) {
-                if (block.BlockType === 'PAGE') {
-                    pageCount += 1;
-                    continue;
-                }
-                if (block.BlockType !== 'LINE' || !block.Text) continue;
-                blocks.push({
-                    type: 'text/textract:LINE',
-                    text: block.Text,
-                    confidence: Number(block.Confidence ?? 0),
-                    page: Math.max(pageCount - 1, 0),
-                });
-            }
-
-            const pages = pageCount || 1;
-            this.#aiMetering.incrementUsage(
-                actor,
-                model.pageUsageType,
-                pages,
-                costPerPage * pages,
-            );
-            return {
-                model: model.id,
-                blocks,
-                text: blocks.map((b) => b.text).join('\n'),
-            };
-        } finally {
-            await hold.release();
-        }
-    }
-
-    // -- Mistral OCR --------------------------------------------------
-
-    async #mistralRecognize(
-        input: ResolvedFileInput,
-        args: RecognizeArgs,
-        model: OcrModel,
-        actor: Actor,
-    ) {
-        const loaded = await input.load();
-        const payload: Record<string, unknown> = {
-            model: model.id,
-            document: this.#mistralBuildChunk(loaded),
-        };
-        if (args.pages) payload.pages = args.pages;
-        if (args.includeImageBase64 !== undefined)
-            payload.includeImageBase64 = args.includeImageBase64;
-        if (typeof args.imageLimit === 'number')
-            payload.imageLimit = args.imageLimit;
-        if (typeof args.imageMinSize === 'number')
-            payload.imageMinSize = args.imageMinSize;
-        if (args.bboxAnnotationFormat !== undefined)
-            payload.bboxAnnotationFormat = toMistralResponseFormat(
-                'bboxAnnotationFormat',
-                args.bboxAnnotationFormat,
-            );
-        if (args.documentAnnotationFormat !== undefined)
-            payload.documentAnnotationFormat = toMistralResponseFormat(
-                'documentAnnotationFormat',
-                args.documentAnnotationFormat,
-            );
-        if (typeof args.documentAnnotationPrompt === 'string')
-            payload.documentAnnotationPrompt = args.documentAnnotationPrompt;
-        if (args.tableFormat !== undefined) {
-            if (!TABLE_FORMATS.has(args.tableFormat))
-                throw badRequest("`tableFormat` must be 'markdown' or 'html'");
-            payload.tableFormat = args.tableFormat;
-        }
-        if (typeof args.extractHeader === 'boolean')
-            payload.extractHeader = args.extractHeader;
-        if (typeof args.extractFooter === 'boolean')
-            payload.extractFooter = args.extractFooter;
-
-        const annotations =
-            payload.documentAnnotationFormat !== undefined ||
-            payload.bboxAnnotationFormat !== undefined;
-        const costPerPage =
-            OCR_COSTS[model.pageUsageType] +
-            (annotations && model.annotationUsageType
-                ? OCR_COSTS[model.annotationUsageType]
-                : 0);
-        const hold = await this.#holdCredits(
-            actor,
-            model.pageUsageType,
-            costPerPage *
-                (await estimateOcrPages(input, model.provider, args.pages)),
-        );
-
-        try {
-            const response = await this.#mistral!.ocr.process(payload);
-            this.#recordMistralUsage(response, model, actor, annotations);
-            return this.#normalizeMistralResponse(response, model);
-        } finally {
-            await hold.release();
-        }
-    }
-
-    #mistralBuildChunk(loaded: LoadedFile): Record<string, unknown> {
-        const mime = inputMimeType(loaded);
-        const dataUrl = `data:${mime};base64,${loaded.buffer.toString('base64')}`;
-        if (isDocumentInput(loaded)) {
-            return {
-                type: 'document_url',
-                documentUrl: dataUrl,
-                documentName: loaded.filename,
-            };
-        }
-        return { type: 'image_url', imageUrl: { url: dataUrl } };
-    }
-
-    #normalizeMistralResponse(response: MistralOcrResponse, model: OcrModel) {
-        const pages = response?.pages ?? [];
-        const blocks: OcrBlock[] = [];
-        for (const [position, page] of pages.entries()) {
-            if (typeof page?.markdown !== 'string') continue;
-            const lines = page.markdown
-                .split('\n')
-                .map((l) => l.trim())
-                .filter(Boolean);
-            for (const line of lines) {
-                blocks.push({
-                    type: 'text/mistral:LINE',
-                    text: line,
-                    page: page.index ?? position,
-                });
-            }
-        }
-        return {
-            model: response?.model ?? model.id,
-            pages,
-            usage_info: response?.usageInfo,
-            ...(typeof response?.documentAnnotation === 'string' && {
-                document_annotation: response.documentAnnotation,
-            }),
-            blocks,
-            text: blocks.map((b) => b.text).join('\n'),
-        };
-    }
-
-    #recordMistralUsage(
-        response: MistralOcrResponse,
-        model: OcrModel,
-        actor: Actor,
-        annotations: boolean,
-    ) {
-        try {
-            const pagesProcessed =
-                response?.usageInfo?.pagesProcessed ??
-                (Array.isArray(response?.pages) ? response.pages.length : 1);
-            this.#aiMetering.incrementUsage(
-                actor,
-                model.pageUsageType,
-                pagesProcessed,
-                OCR_COSTS[model.pageUsageType] * pagesProcessed,
-            );
-            if (annotations && model.annotationUsageType) {
-                this.#aiMetering.incrementUsage(
-                    actor,
-                    model.annotationUsageType,
-                    pagesProcessed,
-                    OCR_COSTS[model.annotationUsageType] * pagesProcessed,
-                );
-            }
-        } catch {
-            // Non-critical.
-        }
-    }
-}
-
-function sampleResponse() {
-    return {
-        model: 'test-mode',
-        blocks: [
-            {
-                type: 'text/puter:sample-output',
-                confidence: 1,
-                text: 'test_mode is enabled; this is a sample OCR response.',
-                page: 0,
-            },
-        ],
-        text: 'test_mode is enabled; this is a sample OCR response.',
-    };
-}

src/backend/drivers/ai-speech2speech/VoiceChangerDriver.ts

@@ -1,511 +0,0 @@
-/*
- * Copyright (C) 2024-present Puter Technologies Inc.
- *
- * This file is part of Puter.
- *
- * Puter is free software: you can redistribute it and/or modify
- * it under the terms of the GNU Affero General Public License as published
- * by the Free Software Foundation, either version 3 of the License, or
- * (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU Affero General Public License for more details.
- *
- * You should have received a copy of the GNU Affero General Public License
- * along with this program.  If not, see <https://www.gnu.org/licenses/>.
- */
-
-import { pipeline, Readable, Transform } from 'node:stream';
-import { Context } from '../../core/context.js';
-import { HttpError } from '../../core/http/HttpError.js';
-import type { DriverStreamResult } from '../meta.js';
-import { OUTPUT_FORMATS } from '../ai-tts/providers/elevenlabs/ElevenLabsTTSProvider.js';
-import { PuterDriver } from '../types.js';
-import {
-    type AiMeteringService,
-    withAiCostFactor,
-    withStreamedAiCharge,
-} from '../util/aiCostFactor.js';
-import { AI_CONCURRENT, AI_RATE_LIMIT } from '../util/aiLimits.js';
-import { loadFileInput } from '../util/fileInput.js';
-import {
-    type ProviderCatalog,
-    ProviderRegistry,
-    readProviderKey,
-} from '../util/providerRegistry.js';
-import { SAMPLE_AUDIO_URL } from '../util/testMode.js';
-import { upstreamBodyStream, upstreamFetch } from '../util/upstreamErrors.js';
-import { VOICE_CHANGER_COSTS } from './costs.js';
-
-/**
- * Driver implementing `puter-speech2speech` — voice changer. Currently a single
- * provider (ElevenLabs).
- */
-
-const DEFAULT_MODEL = 'eleven_multilingual_sts_v2';
-const DEFAULT_VOICE_ID = '21m00Tcm4TlvDq8ikWAM';
-const DEFAULT_OUTPUT_FORMAT = 'mp3_44100_128';
-const MAX_AUDIO_FILE_SIZE = 25 * 1024 * 1024;
-// Covers the upload as well as the conversion.
-const CONVERT_TIMEOUT_MS = 10 * 60 * 1000;
-
-const SUPPORTED_MODELS = Object.keys(VOICE_CHANGER_COSTS).map(
-    (key) => key.split(':')[1]!,
-);
-
-const VOICE_CHANGER_CATALOG: ProviderCatalog = {
-    label: 'Speech-to-speech',
-    ids: ['elevenlabs'],
-    defaultId: 'elevenlabs',
-    aliases: { elevenlabs: 'elevenlabs' },
-};
-
-interface ElevenLabsConfig {
-    apiKey: string;
-    baseUrl: string;
-    defaultVoiceId: string;
-    defaultModelId: string;
-}
-
-interface ConvertArgs {
-    audio: unknown;
-    provider?: string;
-    voice?: string;
-    voice_id?: string;
-    voiceId?: string;
-    model?: string;
-    model_id?: string;
-    voice_settings?: unknown;
-    voiceSettings?: unknown;
-    seed?: number;
-    remove_background_noise?: boolean;
-    output_format?: string;
-    file_format?: string;
-    optimize_streaming_latency?: number;
-    enable_logging?: boolean;
-    test_mode?: boolean;
-}
-
-export class VoiceChangerDriver extends PuterDriver {
-    readonly driverInterface = 'puter-speech2speech';
-    readonly driverName = 'ai-speech2speech';
-    // Older SDK bundles name the provider in the driver slot.
-    readonly driverAliases = ['elevenlabs-voice-changer'];
-    readonly isDefault = true;
-
-    // Shared AI policy — see `drivers/util/aiLimits.ts` for the tier table.
-    readonly rateLimit = AI_RATE_LIMIT;
-    readonly concurrent = AI_CONCURRENT;
-
-    /** Metering scoped to this driver. Lazy: services wire up after drivers. */
-    get #aiMetering(): AiMeteringService {
-        return withAiCostFactor(
-            this.services.metering,
-            this.clients.event,
-            this.driverName,
-        );
-    }
-
-    override getReportedCosts(): Record<string, unknown>[] {
-        return Object.entries(VOICE_CHANGER_COSTS).map(
-            ([usageType, ucentsPerUnit]) => ({
-                usageType,
-                ucentsPerUnit,
-                unit: 'second',
-                source: 'driver:aiSpeech2Speech',
-            }),
-        );
-    }
-
-    #providers = new ProviderRegistry<ElevenLabsConfig>(VOICE_CHANGER_CATALOG);
-
-    override onServerStart() {
-        const elevenlabs = this.config.providers?.elevenlabs;
-        const apiKey = readProviderKey(elevenlabs);
-        if (!apiKey) return;
-        this.#providers.register('elevenlabs', {
-            apiKey,
-            baseUrl:
-                (elevenlabs?.apiBaseUrl as string | undefined) ??
-                'https://api.elevenlabs.io',
-            defaultVoiceId:
-                (elevenlabs?.defaultVoiceId as string | undefined) ??
-                DEFAULT_VOICE_ID,
-            defaultModelId:
-                (elevenlabs?.speechToSpeechModelId as string | undefined) ??
-                DEFAULT_MODEL,
-        });
-    }
-
-    async convert(
-        args: ConvertArgs,
-    ): Promise<DriverStreamResult | { url: string; content_type: string }> {
-        // Only one provider exists today, but naming a different one should
-        // fail loudly rather than quietly convert with this one.
-        const providerName = this.#providers.resolve(args.provider);
-
-        if (args.test_mode) {
-            return { url: SAMPLE_AUDIO_URL, content_type: 'audio/mpeg' };
-        }
-
-        const elevenlabs = this.#providers.get(providerName);
-        if (!elevenlabs) {
-            throw new HttpError(500, 'ElevenLabs API key not configured', {
-                legacyCode: 'internal_error',
-            });
-        }
-
-        const actor = Context.get('actor');
-        if (!actor)
-            throw new HttpError(401, 'Authentication required', {
-                legacyCode: 'unauthorized',
-            });
-
-        if (!args.audio) {
-            throw new HttpError(400, '`audio` is required', {
-                legacyCode: 'bad_request',
-            });
-        }
-
-        const modelId =
-            args.model_id || args.model || elevenlabs.defaultModelId;
-        const voiceId =
-            args.voice_id ||
-            args.voiceId ||
-            args.voice ||
-            elevenlabs.defaultVoiceId;
-        if (!voiceId)
-            throw new HttpError(400, '`voice` is required', {
-                legacyCode: 'bad_request',
-            });
-        // `voiceId` lands in the request URL path, which carries our API key,
-        // so anything outside ElevenLabs' `[A-Za-z0-9_-]+` id shape could
-        // steer the request at a different endpoint.
-        if (!/^[A-Za-z0-9_-]+$/.test(voiceId))
-            throw new HttpError(400, '`voice` must be alphanumeric', {
-                legacyCode: 'bad_request',
-            });
-
-        // Gate on the cost table: an id we can't price is one we can't bill
-        // for, and ElevenLabs bills us for it either way. This also keeps
-        // anything but a known id out of the multipart `model_id` field.
-        const usageKey = `elevenlabs:${modelId}:second`;
-        if (!Object.hasOwn(VOICE_CHANGER_COSTS, usageKey)) {
-            throw new HttpError(
-                400,
-                `Invalid model: ${modelId}. Expected: ${SUPPORTED_MODELS.join(', ')}`,
-                {
-                    legacyCode: 'field_invalid',
-                    fields: {
-                        key: 'model',
-                        expected: SUPPORTED_MODELS,
-                        got: modelId,
-                    },
-                },
-            );
-        }
-        const ucentsPerSecond = VOICE_CHANGER_COSTS[usageKey]!;
-
-        const loaded = await loadFileInput(
-            this.stores,
-            this.services.fs,
-            actor,
-            args.audio,
-            { maxBytes: MAX_AUDIO_FILE_SIZE, acceptWebInput: true },
-        );
-
-        // The hold estimates seconds from the input at 128 kbps: compact audio
-        // is under-held rather than refused. Usage is metered from the length
-        // of the audio that comes back.
-        const estimatedSeconds = Math.max(
-            1,
-            Math.ceil(loaded.buffer.byteLength / 16000),
-        );
-        const estimatedCost = ucentsPerSecond * estimatedSeconds;
-
-        const formData = new FormData();
-        const blob = new Blob([loaded.buffer as BlobPart], {
-            type: loaded.mimeType ?? 'application/octet-stream',
-        });
-        formData.append('audio', blob, loaded.filename);
-        formData.append('model_id', modelId);
-
-        const settings = args.voice_settings ?? args.voiceSettings;
-        if (settings !== undefined && settings !== null) {
-            formData.append(
-                'voice_settings',
-                typeof settings === 'string'
-                    ? settings
-                    : JSON.stringify(settings),
-            );
-        }
-        if (args.seed !== undefined && args.seed !== null) {
-            formData.append('seed', String(args.seed));
-        }
-        if (typeof args.remove_background_noise === 'boolean') {
-            formData.append(
-                'remove_background_noise',
-                String(args.remove_background_noise),
-            );
-        }
-        if (args.file_format) {
-            formData.append('file_format', args.file_format);
-        }
-
-        const searchParams = new URLSearchParams();
-        const outputFormat = args.output_format || DEFAULT_OUTPUT_FORMAT;
-        if (outputFormat) searchParams.set('output_format', outputFormat);
-        if (
-            args.optimize_streaming_latency !== undefined &&
-            args.optimize_streaming_latency !== null
-        ) {
-            searchParams.set(
-                'optimize_streaming_latency',
-                String(args.optimize_streaming_latency),
-            );
-        }
-        if (args.enable_logging !== undefined && args.enable_logging !== null) {
-            searchParams.set('enable_logging', String(args.enable_logging));
-        }
-
-        const url = new URL(
-            `/v1/speech-to-speech/${voiceId}`,
-            elevenlabs.baseUrl,
-        );
-        const search = searchParams.toString();
-        if (search) url.search = search;
-
-        const metering = this.#aiMetering;
-        const output = measuredOutput(
-            outputBytesPerSecond(outputFormat),
-            outputFormat,
-        );
-        return withStreamedAiCharge(
-            metering,
-            actor,
-            usageKey,
-            estimatedCost,
-            async (): Promise<DriverStreamResult> => {
-                const response = await upstreamFetch(
-                    'elevenlabs',
-                    url,
-                    {
-                        method: 'POST',
-                        headers: { 'xi-api-key': elevenlabs.apiKey },
-                        body: formData,
-                    },
-                    {
-                        providerLabel: 'ElevenLabs',
-                        timeoutMs: CONVERT_TIMEOUT_MS,
-                        stream: true,
-                    },
-                );
-                return {
-                    dataType: 'stream',
-                    content_type:
-                        response.headers.get('content-type') ?? 'audio/mpeg',
-                    stream: output.measure(upstreamBodyStream(response)),
-                };
-            },
-            async () => {
-                const measured = await output.seconds;
-                // A stream cut short was still converted in full upstream.
-                const seconds =
-                    measured.complete && measured.seconds
-                        ? measured.seconds
-                        : Math.max(measured.seconds ?? 0, estimatedSeconds);
-                return metering.incrementUsage(
-                    actor,
-                    usageKey,
-                    seconds,
-                    ucentsPerSecond * seconds,
-                );
-            },
-        );
-    }
-}
-
-/**
- * Bytes per second of an ElevenLabs `output_format`. A format outside the
- * documented set is sized as the default, so a made-up bitrate can't shrink the
- * bill.
- */
-export function outputBytesPerSecond(format: string): number {
-    const known = OUTPUT_FORMATS.has(format) ? format : DEFAULT_OUTPUT_FORMAT;
-    const [codec, rate, kbps] = known.split('_');
-    if (codec === 'mp3' || codec === 'opus') return Number(kbps) * 125;
-    if (codec === 'ulaw' || codec === 'alaw') return Number(rate);
-    // pcm and wav: 16-bit mono.
-    return Number(rate) * 2;
-}
-
-// Past this, a WAV whose data chunk hasn't started is billed by raw length.
-const WAV_HEADER_MAX_BYTES = 64 * 1024;
-
-/**
- * Where the samples of a RIFF/WAVE stream start, once `head` reaches its `data`
- * chunk; undefined until then, or if `head` isn't a WAV.
- */
-export function wavDataOffset(head: Buffer): number | undefined {
-    if (head.length < 12) return undefined;
-    if (
-        head.toString('ascii', 0, 4) !== 'RIFF' ||
-        head.toString('ascii', 8, 12) !== 'WAVE'
-    )
-        return undefined;
-    let offset = 12;
-    while (offset + 8 <= head.length) {
-        if (head.toString('ascii', offset, offset + 4) === 'data')
-            return offset + 8;
-        const size = head.readUInt32LE(offset + 4);
-        offset += 8 + size + (size & 1);
-    }
-    return undefined;
-}
-
-const OGG_HEADER_BYTES = 27;
-const NO_GRANULE = 2n ** 64n - 1n;
-
-/**
- * Walks an Ogg Opus stream page by page as it arrives. Opus is variable
- * bitrate, so its length comes from the last page's granule position (48 kHz
- * samples, less the stream's pre-skip) rather than its byte count.
- */
-export class OggOpusClock {
-    #header = Buffer.alloc(0);
-    #skip = 0;
-    #firstBody: Buffer | undefined = Buffer.alloc(0);
-    #firstBodyBytes = 0;
-    #granule: bigint | undefined;
-    #preSkip = 0;
-    #broken = false;
-
-    push(chunk: Buffer): void {
-        let offset = 0;
-        while (!this.#broken && offset < chunk.length) {
-            if (this.#skip > 0) {
-                const n = Math.min(this.#skip, chunk.length - offset);
-                if (this.#firstBody && this.#firstBody.length < 19) {
-                    this.#firstBody = Buffer.concat([
-                        this.#firstBody,
-                        chunk.subarray(offset, offset + n),
-                    ]);
-                }
-                this.#skip -= n;
-                offset += n;
-                if (this.#skip === 0 && this.#firstBody) this.#readOpusHead();
-                continue;
-            }
-            const want =
-                this.#header.length < OGG_HEADER_BYTES
-                    ? OGG_HEADER_BYTES
-                    : OGG_HEADER_BYTES + this.#header[26]!;
-            const n = Math.min(
-                want - this.#header.length,
-                chunk.length - offset,
-            );
-            this.#header = Buffer.concat([
-                this.#header,
-                chunk.subarray(offset, offset + n),
-            ]);
-            offset += n;
-            if (this.#header.length < want) continue;
-            if (this.#header.toString('ascii', 0, 4) !== 'OggS') {
-                this.#broken = true;
-                return;
-            }
-            if (want === OGG_HEADER_BYTES && this.#header[26]! > 0) continue;
-            const granule = this.#header.readBigUInt64LE(6);
-            if (granule !== NO_GRANULE) this.#granule = granule;
-            let body = 0;
-            for (const lacing of this.#header.subarray(OGG_HEADER_BYTES)) {
-                body += lacing;
-            }
-            this.#header = Buffer.alloc(0);
-            this.#skip = body;
-            if (this.#firstBody) this.#firstBodyBytes = body;
-        }
-    }
-
-    /** Whole seconds so far, once the stream has proven to be Ogg Opus. */
-    get seconds(): number | undefined {
-        if (this.#broken || this.#granule === undefined) return undefined;
-        const samples = Number(this.#granule) - this.#preSkip;
-        return samples > 0
-            ? Math.max(1, Math.ceil(samples / 48_000))
-            : undefined;
-    }
-
-    #readOpusHead(): void {
-        const head = this.#firstBody!;
-        this.#firstBody = undefined;
-        if (
-            this.#firstBodyBytes < 19 ||
-            head.toString('ascii', 0, 8) !== 'OpusHead'
-        ) {
-            this.#broken = true;
-            return;
-        }
-        this.#preSkip = head.readUInt16LE(10);
-    }
-}
-
-/**
- * Counts the bytes of a converted stream. `seconds` settles when the stream
- * ends or closes: its length in whole seconds (undefined when nothing came
- * back), and whether the upstream sent all of it. A WAV's header isn't audio,
- * so it isn't counted; Opus is timed by its pages.
- */
-function measuredOutput(bytesPerSecond: number, format: string) {
-    let bytes = 0;
-    let head: Buffer | undefined = format.startsWith('wav_')
-        ? Buffer.alloc(0)
-        : undefined;
-    const opus = format.startsWith('opus_') ? new OggOpusClock() : undefined;
-    let headerBytes = 0;
-    let settle!: (measured: { seconds?: number; complete: boolean }) => void;
-    const seconds = new Promise<{ seconds?: number; complete: boolean }>(
-        (resolve) => {
-            settle = resolve;
-        },
-    );
-    const lengthOf = () => {
-        const timed = opus?.seconds;
-        if (timed !== undefined) return timed;
-        const audio = bytes - headerBytes;
-        return audio > 0
-            ? Math.max(1, Math.ceil(audio / bytesPerSecond))
-            : undefined;
-    };
-    const measure = (source: Readable): Readable => {
-        const counter = new Transform({
-            transform(chunk: Buffer, _encoding, callback) {
-                bytes += chunk.length;
-                opus?.push(chunk);
-                if (head) {
-                    head = Buffer.concat([head, chunk]);
-                    const offset = wavDataOffset(head);
-                    if (offset !== undefined) headerBytes = offset;
-                    if (
-                        offset !== undefined ||
-                        head.length >= WAV_HEADER_MAX_BYTES
-                    )
-                        head = undefined;
-                }
-                callback(null, chunk);
-            },
-            flush(callback) {
-                settle({ seconds: lengthOf(), complete: true });
-                callback();
-            },
-        });
-        counter.once('close', () =>
-            settle({ seconds: lengthOf(), complete: false }),
-        );
-        pipeline(source, counter, () => {});
-        return counter;
-    };
-    return { measure, seconds };
-}

src/backend/drivers/ai/interfaces/chat/ChatCompletionDriver.availability.http.test.ts

@@ -19,9 +19,9 @@
 
 import { createServer, type Server } from 'node:http';
 import { afterAll, beforeAll, beforeEach, describe, expect, it } from 'vitest';
-import { setupPuterTestEnv, type PuterTestEnv } from '../../testUtil.js';
+import { setupPuterTestEnv, type PuterTestEnv } from '../../../../testUtil.js';
 import { clearUnhealthyRoutes } from './utils/providerHealth.js';
-import { makeActor } from '../../core/actor.js';
+import { makeActor } from '../../../../core/actor.js';
 
 const policyMessage =
     'Policy Violation: this user has been blocked for a previous policy violation. Learn more: https://vendor.test/private';
@@ -129,6 +129,17 @@ describe('model availability through real HTTP', () => {
             meteringEnforcement: { subscriptions: false },
         } as never);
     }, 120000);
+    it('serves qualified chat model names through HTTP', async () => {
+        const response = await fetch(
+            new URL('/puterai/chat/models', env.apiOrigin),
+        );
+        expect(response.status).toBe(200);
+        const { models } = (await response.json()) as { models: string[] };
+        expect(models).toContain('openrouter:vendor/availability-test');
+        expect(models.every((id) => /^[^:/]+:[^/]+\/.+/.test(id))).toBe(true);
+        expect(models).not.toContain('vendor/availability-test');
+    });
+
     afterAll(async () => {
         await env?.shutdown();
         upstream?.closeAllConnections();

src/backend/drivers/ai/interfaces/chat/ChatCompletionDriver.cancellation.http.test.ts

@@ -19,8 +19,8 @@
 
 import { createServer, type Server, type ServerResponse } from 'node:http';
 import { afterAll, beforeAll, describe, expect, it, vi } from 'vitest';
-import { makeActor, type Actor } from '../../core/actor.js';
-import { setupPuterTestEnv, type PuterTestEnv } from '../../testUtil.js';
+import { makeActor, type Actor } from '../../../../core/actor.js';
+import { setupPuterTestEnv, type PuterTestEnv } from '../../../../testUtil.js';
 
 const routes = [
     '/drivers/call',

src/backend/drivers/ai/interfaces/chat/ChatCompletionDriver.concurrency.http.test.ts

@@ -0,0 +1,225 @@
+/*
+ * Copyright (C) 2024-present Puter Technologies Inc.
+ *
+ * This file is part of Puter.
+ *
+ * Puter is free software: you can redistribute it and/or modify
+ * it under the terms of the GNU Affero General Public License as published
+ * by the Free Software Foundation, either version 3 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU Affero General Public License for more details.
+ *
+ * You should have received a copy of the GNU Affero General Public License
+ * along with this program.  If not, see <https://www.gnu.org/licenses/>.
+ */
+
+import { createServer, type Server, type ServerResponse } from 'node:http';
+import { afterAll, beforeAll, describe, expect, it, vi } from 'vitest';
+import { setupPuterTestEnv, type PuterTestEnv } from '../../../../testUtil.js';
+
+/**
+ * A completion runs on to its usage report after the caller hangs up, so it
+ * keeps counting against the caller's concurrency cap until it settles.
+ */
+describe('chat concurrency over HTTP after the caller hangs up', () => {
+    let upstream: Server;
+    let env: PuterTestEnv;
+    let onRequest: (res: ServerResponse, body: string) => void;
+
+    beforeAll(async () => {
+        upstream = createServer((req, res) => {
+            if (req.url === '/api/tags') {
+                res.setHeader('Content-Type', 'application/json');
+                res.end(JSON.stringify({ models: [{ name: 'slot-test' }] }));
+                return;
+            }
+            let body = '';
+            req.setEncoding('utf8');
+            req.on('data', (chunk: string) => {
+                body += chunk;
+            });
+            req.once('end', () => onRequest(res, body));
+        });
+        await new Promise<void>((resolve) =>
+            upstream.listen(0, '127.0.0.1', resolve),
+        );
+        const port = (upstream.address() as { port: number }).port;
+        env = await setupPuterTestEnv({
+            providers: {
+                ollama: { apiBaseUrl: `http://127.0.0.1:${port}` },
+            },
+            meteringEnforcement: { subscriptions: false },
+        } as never);
+        await vi.waitFor(async () => {
+            expect(
+                (await env.server.drivers.aiChat.models()).some(
+                    (model) => model.id === 'ollama:ollama/slot-test',
+                ),
+            ).toBe(true);
+        });
+    }, 120_000);
+
+    afterAll(async () => {
+        await env?.shutdown();
+        upstream?.closeAllConnections();
+        if (upstream)
+            await new Promise<void>((resolve) =>
+                upstream.close(() => resolve()),
+            );
+    });
+
+    const call = (route: string, stream: boolean, signal?: AbortSignal) => {
+        const args = {
+            model: 'ollama:ollama/slot-test',
+            stream,
+            messages: [{ role: 'user', content: 'hi' }],
+            max_tokens: 16,
+        };
+        return fetch(new URL(route, env.apiOrigin), {
+            method: 'POST',
+            headers: {
+                'Content-Type': 'application/json',
+                Authorization: `Bearer ${env.users.user.apiToken}`,
+                Origin: env.apiOrigin,
+            },
+            body: JSON.stringify(
+                route === '/drivers/call'
+                    ? {
+                          interface: 'puter-chat-completion',
+                          method: 'complete',
+                          args,
+                      }
+                    : args,
+            ),
+            signal,
+        });
+    };
+
+    const usage = { prompt_tokens: 3, completion_tokens: 5, total_tokens: 8 };
+    const chunk = (delta: object, finish: string | null, extra = {}) =>
+        `data: ${JSON.stringify({
+            id: 'chatcmpl_1',
+            object: 'chat.completion.chunk',
+            choices: [{ index: 0, delta, finish_reason: finish }],
+            ...extra,
+        })}\n\n`;
+
+    const finishAnswer = (res: ServerResponse, body: string) => {
+        if (!(JSON.parse(body) as { stream?: boolean }).stream) {
+            res.setHeader('Content-Type', 'application/json');
+            res.end(
+                JSON.stringify({
+                    id: 'chatcmpl_1',
+                    object: 'chat.completion',
+                    created: 0,
+                    model: 'slot-test',
+                    choices: [
+                        {
+                            index: 0,
+                            message: { role: 'assistant', content: 'done' },
+                            finish_reason: 'stop',
+                        },
+                    ],
+                    usage,
+                }),
+            );
+            return;
+        }
+        if (!res.headersSent)
+            res.setHeader('Content-Type', 'text/event-stream');
+        res.end(
+            `${chunk({ content: 'done' }, 'stop')}data: ${JSON.stringify({
+                id: 'chatcmpl_1',
+                object: 'chat.completion.chunk',
+                choices: [],
+                usage,
+            })}\n\ndata: [DONE]\n\n`,
+        );
+    };
+
+    /** Starts a completion, waits until it is generating, then hangs up. */
+    const abandon = async (route: string, stream: boolean) => {
+        let received!: () => void;
+        const reached = new Promise<void>((resolve) => {
+            received = resolve;
+        });
+        const pending: { res: ServerResponse; body: string }[] = [];
+        onRequest = (res, body) => {
+            pending.push({ res, body });
+            if (stream) {
+                res.setHeader('Content-Type', 'text/event-stream');
+                res.write(chunk({ role: 'assistant', content: 'partial' }, null));
+            }
+            received();
+        };
+        const abort = new AbortController();
+        const request = call(route, stream, abort.signal);
+        const outcome = await Promise.race([
+            reached.then(() => 'generating' as const),
+            request.then((response) => response),
+        ]);
+        if (outcome !== 'generating') {
+            return { refused: outcome, pending };
+        }
+        if (stream) {
+            const response = await request;
+            const reader = response.body!.getReader();
+            let text = '';
+            while (!text.includes('partial')) {
+                const { value, done } = await reader.read();
+                if (done) break;
+                text += new TextDecoder().decode(value);
+            }
+        }
+        abort.abort();
+        await request.catch(() => undefined);
+        return { refused: undefined, pending };
+    };
+
+    it.each([
+        { route: '/drivers/call', stream: true },
+        { route: '/drivers/call', stream: false },
+        { route: '/puterai/openai/v1/chat/completions', stream: true },
+        { route: '/puterai/openai/v1/chat/completions', stream: false },
+        { route: '/puterai/anthropic/v1/messages', stream: true },
+    ])(
+        'counts an abandoned completion until it settles: $route (stream=$stream)',
+        async ({ route, stream }) => {
+            const running: { res: ServerResponse; body: string }[] = [];
+            let refused: Response | undefined;
+            try {
+                for (let i = 0; i < 25 && !refused; i++) {
+                    const attempt = await abandon(route, stream);
+                    running.push(...attempt.pending);
+                    refused = attempt.refused;
+                    // Let the server see the hang-up before the next call.
+                    await new Promise((resolve) => setTimeout(resolve, 50));
+                }
+                expect(refused?.status).toBe(429);
+                expect(await refused!.text()).toContain(
+                    'Too many concurrent requests',
+                );
+                expect(running.length).toBeGreaterThan(0);
+
+                for (const { res, body } of running.splice(0))
+                    finishAnswer(res, body);
+                onRequest = finishAnswer;
+                await expect
+                    .poll(async () => (await call(route, false)).status, {
+                        timeout: 15_000,
+                    })
+                    .toBe(200);
+            } finally {
+                for (const { res, body } of running) finishAnswer(res, body);
+                upstream.closeAllConnections();
+                // The next case starts with a fresh rate-limit window.
+                await new Promise((resolve) => setTimeout(resolve, 10_100));
+            }
+        },
+        60_000,
+    );
+});

src/backend/drivers/ai/interfaces/chat/ChatCompletionDriver.edges.test.ts

@@ -42,22 +42,22 @@ import {
     vi,
 } from 'vitest';
 
-import { Context } from '../../core/context.js';
-import { HttpError } from '../../core/http/HttpError.js';
-import { PuterServer } from '../../server.js';
-import { setupTestServer } from '../../testUtil.js';
-import { withTestActor } from '../integrationTestUtil.js';
+import { Context } from '../../../../core/context.js';
+import { HttpError } from '../../../../core/http/HttpError.js';
+import { PuterServer } from '../../../../server.js';
+import { setupTestServer } from '../../../../testUtil.js';
+import { withTestActor } from '../../shared/integrationTestUtil.js';
 import { ChatCompletionDriver } from './ChatCompletionDriver.js';
-import { AzureChatProvider } from './providers/azure/AzureChatProvider.js';
-import { FakeChatProvider } from './providers/FakeChatProvider.js';
-import { InfronProvider } from './providers/infron/InfronProvider.js';
-import { NeuralwattProvider } from './providers/neuralwatt/NeuralwattProvider.js';
-import { OpenAiChatProvider } from './providers/openai/OpenAiChatCompletionsProvider.js';
-import { OpenRouterProvider } from './providers/openrouter/OpenRouterProvider.js';
-import { TogetherAIProvider } from './providers/together/TogetherAIProvider.js';
-import { XAI_CHAT_MODELS } from './providers/xai/catalog.js';
-import { XAIProvider } from './providers/xai/XAIProvider.js';
-import { handle_completion_output } from './utils/OpenAIUtil.js';
+import { AzureChatProvider } from '../../providers/azure/chat/AzureChatProvider.js';
+import { FakeChatProvider } from '../../providers/fake/chat/FakeChatProvider.js';
+import { InfronProvider } from '../../providers/infron/chat/InfronProvider.js';
+import { NeuralwattProvider } from '../../providers/neuralwatt/chat/NeuralwattProvider.js';
+import { OpenAiChatProvider } from '../../providers/openai/chat/OpenAiChatCompletionsProvider.js';
+import { OpenRouterProvider } from '../../providers/openrouter/chat/OpenRouterProvider.js';
+import { TogetherAIProvider } from '../../providers/together/chat/TogetherAIProvider.js';
+import { XAI_CHAT_MODELS } from '../../providers/xai/chat/catalog.js';
+import { XAIProvider } from '../../providers/xai/chat/XAIProvider.js';
+import { handle_completion_output } from '../../protocols/openaiCompatible/OpenAIUtil.js';
 import { clearUnhealthyRoutes, isRouteUnhealthy } from './utils/providerHealth.js';
 
 let server: PuterServer;
@@ -1231,4 +1231,41 @@ describe('ChatCompletionDriver streaming failure handling', () => {
         expect(events).toContainEqual({ type: 'text', text: 'hello' });
         expect(cleanup).toHaveBeenCalledTimes(1);
     });
+
+    it('frees the concurrency slot before the provider cleanup hook finishes', async () => {
+        let finishCleanup!: () => void;
+        const cleanup = vi.fn(
+            () =>
+                new Promise<void>((resolve) => {
+                    finishCleanup = resolve;
+                }),
+        );
+        vi.spyOn(FakeChatProvider.prototype, 'complete').mockResolvedValue({
+            stream: true,
+            init_chat_stream: async ({
+                chatStream,
+            }: {
+                chatStream: { end: (usage?: Record<string, number>) => void };
+            }) => {
+                chatStream.end({ input_tokens: 1, output_tokens: 1 });
+            },
+            finally_fn: cleanup,
+        } as never);
+
+        const kept: Promise<unknown>[] = [];
+        const result = (await withTestActor(() => {
+            Context.set('keepConcurrencySlot', (work) => kept.push(work));
+            return fakeOnlyDriver.complete({
+                model: 'fake',
+                messages: [{ role: 'user', content: 'hi' }],
+                stream: true,
+            } as never);
+        })) as unknown as { stream: Readable };
+        await collect(result.stream);
+
+        expect(kept).toHaveLength(1);
+        await kept[0];
+        await vi.waitFor(() => expect(cleanup).toHaveBeenCalledTimes(1));
+        finishCleanup();
+    });
 });

src/backend/drivers/ai/interfaces/chat/ChatCompletionDriver.fuzz.test.ts

@@ -0,0 +1,726 @@
+/*
+ * Copyright (C) 2024-present Puter Technologies Inc.
+ *
+ * This file is part of Puter.
+ *
+ * Puter is free software: you can redistribute it and/or modify
+ * it under the terms of the GNU Affero General Public License as published
+ * by the Free Software Foundation, either version 3 of the License, or
+ * (at your option) any later version.
+ *
+ * Puter is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU Affero General Public License for more details.
+ *
+ * You should have received a copy of the GNU Affero General Public License
+ * along with Puter. If not, see <https://www.gnu.org/licenses/>.
+ */
+
+/**
+ * Seeded fuzzing of `ChatCompletionDriver.complete` through every registered
+ * provider. The vendors are played at the HTTP boundary, so the real SDKs and
+ * the providers' own request and response code run.
+ */
+
+import { afterAll, beforeAll, describe, expect, it, vi } from 'vitest';
+
+import { isHttpError } from '../../../../core/http/HttpError.js';
+import type { PuterServer } from '../../../../server.js';
+import { setupTestServer } from '../../../../testUtil.js';
+import { kv } from '../../../../util/kvSingleton.js';
+import { isDriverStreamResult } from '../../../meta.js';
+import {
+    caseRandom,
+    corruptReply,
+    Findings,
+    fuzzCases,
+    hostileValue,
+    mutate,
+    pick,
+    pickStable,
+    type Random,
+    unclassifiedFailure,
+    upstream,
+    type UpstreamReply,
+    type UpstreamRequest,
+} from '../../shared/fuzzTestUtil.js';
+import {
+    readStreamResult,
+    withTestActor,
+} from '../../shared/integrationTestUtil.js';
+import { ChatCompletionDriver } from './ChatCompletionDriver.js';
+import type { ICompleteArguments } from './types.js';
+import { clearUnhealthyRoutes } from './utils/providerHealth.js';
+
+vi.mock('undici', async (importOriginal) => ({
+    ...(await importOriginal<typeof import('undici')>()),
+    fetch: (input: unknown, init?: RequestInit) => upstream.fetch(input, init),
+}));
+
+// groq-sdk brings its own HTTP client. Groq's API is OpenAI-compatible, so the
+// OpenAI SDK stands in for it and the requests reach the stub like the rest.
+vi.mock('groq-sdk', async () => ({ default: (await import('openai')).OpenAI }));
+
+vi.mock('axios', () => {
+    const request = (config: Parameters<typeof upstream.axios>[0]) =>
+        upstream.axios(config);
+    const get = (url: string, config?: object) =>
+        upstream.axios({ ...config, url, method: 'GET' });
+    return { default: { request, get }, request, get };
+});
+
+// -- The vendors, played at the HTTP boundary --
+
+const TEXT = 'pong';
+const chatUsage = { prompt_tokens: 3, completion_tokens: 5, total_tokens: 8 };
+const chatChunk = (delta: object, finish: string | null) => ({
+    id: 'chatcmpl-1',
+    object: 'chat.completion.chunk',
+    created: 1,
+    model: 'm',
+    choices: [{ index: 0, delta, finish_reason: finish }],
+});
+const responsesMessage = {
+    type: 'message',
+    id: 'msg_1',
+    role: 'assistant',
+    status: 'completed',
+    content: [{ type: 'output_text', text: TEXT, annotations: [] }],
+};
+const responsesBody = {
+    id: 'resp_1',
+    object: 'response',
+    status: 'completed',
+    model: 'm',
+    output: [responsesMessage],
+    usage: {
+        input_tokens: 3,
+        output_tokens: 5,
+        total_tokens: 8,
+        input_tokens_details: { cached_tokens: 0 },
+        output_tokens_details: { reasoning_tokens: 0 },
+    },
+};
+const anthropicUsage = { input_tokens: 3, output_tokens: 5 };
+const geminiBody = {
+    candidates: [
+        {
+            index: 0,
+            content: { role: 'model', parts: [{ text: TEXT }] },
+            finishReason: 'STOP',
+        },
+    ],
+    usageMetadata: {
+        promptTokenCount: 3,
+        candidatesTokenCount: 5,
+        totalTokenCount: 8,
+    },
+};
+
+const anthropicEvents = [
+    {
+        type: 'message_start',
+        message: {
+            id: 'msg_1',
+            type: 'message',
+            role: 'assistant',
+            model: 'm',
+            content: [],
+            stop_reason: null,
+            stop_sequence: null,
+            usage: { input_tokens: 3, output_tokens: 1 },
+        },
+    },
+    {
+        type: 'content_block_start',
+        index: 0,
+        content_block: { type: 'text', text: '' },
+    },
+    {
+        type: 'content_block_delta',
+        index: 0,
+        delta: { type: 'text_delta', text: TEXT },
+    },
+    { type: 'content_block_stop', index: 0 },
+    {
+        type: 'message_delta',
+        delta: { stop_reason: 'end_turn', stop_sequence: null },
+        usage: { output_tokens: 5 },
+    },
+    { type: 'message_stop' },
+];
+
+const responsesEvents = [
+    {
+        type: 'response.created',
+        response: { ...responsesBody, status: 'in_progress', output: [] },
+    },
+    {
+        type: 'response.output_item.added',
+        output_index: 0,
+        item: { ...responsesMessage, status: 'in_progress', content: [] },
+    },
+    {
+        type: 'response.output_text.delta',
+        item_id: 'msg_1',
+        output_index: 0,
+        content_index: 0,
+        delta: TEXT,
+    },
+    {
+        type: 'response.output_item.done',
+        output_index: 0,
+        item: responsesMessage,
+    },
+    { type: 'response.completed', response: responsesBody },
+];
+
+/** A well-formed answer from whichever vendor API the request went to. */
+const healthyUpstream = ({
+    url,
+    json,
+}: UpstreamRequest): UpstreamReply | undefined => {
+    const path = url.pathname;
+    // A caller-supplied media link that leads nowhere.
+    if (url.hostname === 'upstream.test') return { status: 404, body: '' };
+    const streaming = (json as { stream?: unknown } | undefined)?.stream;
+    if (path.endsWith('/chat/completions')) {
+        if (!streaming) {
+            return {
+                body: {
+                    id: 'chatcmpl-1',
+                    object: 'chat.completion',
+                    created: 1,
+                    model: 'm',
+                    choices: [
+                        {
+                            index: 0,
+                            message: { role: 'assistant', content: TEXT },
+                            finish_reason: 'stop',
+                        },
+                    ],
+                    usage: chatUsage,
+                },
+            };
+        }
+        return {
+            sse: [
+                { data: chatChunk({ role: 'assistant', content: TEXT }, null) },
+                { data: chatChunk({}, 'stop') },
+                {
+                    data: {
+                        ...chatChunk({}, null),
+                        choices: [],
+                        usage: chatUsage,
+                    },
+                },
+                { data: '[DONE]' },
+            ],
+        };
+    }
+    if (path.endsWith('/responses')) {
+        return streaming
+            ? {
+                  sse: responsesEvents.map((data) => ({
+                      event: data.type,
+                      data,
+                  })),
+              }
+            : { body: responsesBody };
+    }
+    if (path.endsWith('/messages/count_tokens')) {
+        return { body: { input_tokens: 3 } };
+    }
+    if (path.endsWith('/messages')) {
+        return streaming
+            ? {
+                  sse: anthropicEvents.map((data) => ({
+                      event: data.type,
+                      data,
+                  })),
+              }
+            : {
+                  body: {
+                      id: 'msg_1',
+                      type: 'message',
+                      role: 'assistant',
+                      model: 'm',
+                      content: [{ type: 'text', text: TEXT }],
+                      stop_reason: 'end_turn',
+                      stop_sequence: null,
+                      usage: anthropicUsage,
+                  },
+              };
+    }
+    if (path.endsWith(':generateContent')) return { body: geminiBody };
+    if (path.endsWith(':streamGenerateContent')) {
+        return { sse: [{ data: geminiBody }] };
+    }
+    if (path.endsWith(':countTokens')) return { body: { totalTokens: 3 } };
+    if (path.endsWith('/moderations')) {
+        return {
+            body: {
+                id: 'modr_1',
+                model: 'm',
+                results: [
+                    { flagged: false, categories: {}, category_scores: {} },
+                ],
+            },
+        };
+    }
+    return undefined;
+};
+
+// -- Requests to mutate --
+
+const PNG =
+    'data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAAEAAAABCAYAAAAfFcSJAAAADUlEQVR42mP8z8BQDwAEhQGAhKmMIQAAAABJRU5ErkJggg==';
+
+const weatherTool = {
+    type: 'function',
+    function: {
+        name: 'get_weather',
+        description: 'Get the weather for a city',
+        parameters: {
+            type: 'object',
+            properties: { city: { type: 'string' } },
+            required: ['city'],
+        },
+    },
+};
+
+const CORPUS: Record<string, unknown>[] = [
+    { messages: [{ role: 'user', content: 'hi' }] },
+    {
+        messages: [
+            { role: 'system', content: 'Be brief.' },
+            {
+                role: 'user',
+                content: [
+                    { type: 'text', text: 'What is this?' },
+                    { type: 'image_url', image_url: { url: PNG } },
+                ],
+            },
+        ],
+        max_tokens: 64,
+        temperature: 0.5,
+        top_p: 0.9,
+        stream: true,
+    },
+    {
+        messages: [
+            { role: 'user', content: 'Weather in Paris?' },
+            {
+                role: 'assistant',
+                content: null,
+                tool_calls: [
+                    {
+                        id: 'call_1',
+                        type: 'function',
+                        function: {
+                            name: 'get_weather',
+                            arguments: '{"city":"Paris"}',
+                        },
+                    },
+                ],
+            },
+            { role: 'tool', tool_call_id: 'call_1', content: 'Sunny' },
+        ],
+        tools: [weatherTool],
+        tool_choice: 'auto',
+        parallel_tool_calls: false,
+    },
+    {
+        messages: [
+            {
+                role: 'user',
+                content: [
+                    {
+                        type: 'text',
+                        text: 'Weather in Paris?',
+                        cache_control: { type: 'ephemeral' },
+                    },
+                ],
+            },
+            {
+                role: 'assistant',
+                content: [
+                    { type: 'text', text: 'Checking.' },
+                    {
+                        type: 'tool_use',
+                        id: 'toolu_1',
+                        name: 'get_weather',
+                        input: { city: 'Paris' },
+                    },
+                ],
+            },
+            {
+                role: 'user',
+                content: [
+                    {
+                        type: 'tool_result',
+                        tool_use_id: 'toolu_1',
+                        content: 'Sunny',
+                    },
+                ],
+            },
+        ],
+        tools: [weatherTool, { type: 'web_search' }],
+        tool_choice: { type: 'function', function: { name: 'get_weather' } },
+        stream: true,
+        streamToolInput: true,
+    },
+    {
+        messages: [{ role: 'user', content: 'Reply in JSON.' }],
+        outputFormat: {
+            type: 'json_schema',
+            schema: { type: 'object', properties: { a: { type: 'string' } } },
+        },
+        reasoning: { effort: 'low' },
+        reasoning_effort: 'low',
+        thinking: { type: 'enabled', budget_tokens: 1024 },
+        text: { verbosity: 'low' },
+        verbosity: 'low',
+        stopSequences: ['END'],
+        topK: 5,
+        normalize: true,
+    },
+    {
+        messages: [{ role: 'user', content: 'hi' }],
+        instructions: 'Be brief.',
+        compaction: { trigger_tokens: 150000 },
+        context_management: { edits: [{ type: 'clear_tool_uses_20250919' }] },
+        cacheControl: { type: 'ephemeral', ttl: '1h' },
+        prompt_cache_key: 'k',
+        prompt_cache_retention: '24h',
+        serviceSpeed: 'fast',
+        service_tier: 'flex',
+        speed: 'fast',
+        metadata: { trace: 't' },
+        include: ['reasoning.encrypted_content'],
+        store: false,
+        truncation: 'auto',
+        taskBudget: { total: 1000, remaining: 500 },
+        safeguards: [{ type: 'prompt_injection' }],
+        anthropicBetas: ['context-management-2025-06-27'],
+        moderation: true,
+        response: { normalize: true },
+        fallback: false,
+    },
+];
+
+CORPUS.push(
+    {
+        messages: [
+            {
+                role: 'user',
+                content: [
+                    { type: 'text', text: 'Describe these.' },
+                    { type: 'image_url', image_url: PNG },
+                    {
+                        type: 'image',
+                        source: {
+                            type: 'base64',
+                            media_type: 'image/png',
+                            data: PNG.split(',')[1],
+                        },
+                    },
+                    {
+                        type: 'video_url',
+                        video_url: { url: 'data:video/mp4;base64,AAAA' },
+                    },
+                    {
+                        type: 'file',
+                        file: {
+                            filename: 'a.pdf',
+                            file_data: 'data:application/pdf;base64,JVBERi0=',
+                        },
+                    },
+                    {
+                        type: 'document',
+                        source: {
+                            type: 'base64',
+                            media_type: 'application/pdf',
+                            data: 'JVBERi0=',
+                        },
+                    },
+                ],
+            },
+        ],
+    },
+    {
+        messages: [
+            {
+                role: 'user',
+                content: [
+                    { type: 'text', text: 'Read it.' },
+                    { puter_path: '~/Documents/a.png' },
+                ],
+            },
+        ],
+    },
+    // Model output sent back, in each vendor's shape.
+    {
+        messages: [
+            { role: 'user', content: 'Think, then search.' },
+            {
+                role: 'assistant',
+                content: [
+                    { type: 'thinking', thinking: 'Hm.', signature: 'sig' },
+                    { type: 'redacted_thinking', data: 'x' },
+                    {
+                        type: 'reasoning',
+                        id: 'rs_1',
+                        summary: [{ type: 'summary_text', text: 'Hm.' }],
+                        encrypted_content: 'enc',
+                    },
+                    { type: 'text', text: 'Searching.' },
+                    {
+                        type: 'server_tool_use',
+                        id: 'srvtoolu_1',
+                        name: 'web_search',
+                        input: { query: 'x' },
+                    },
+                    {
+                        type: 'web_search_tool_result',
+                        tool_use_id: 'srvtoolu_1',
+                        content: [],
+                    },
+                    {
+                        type: 'compaction',
+                        id: 'cmp_1',
+                        encrypted_content: 'enc',
+                    },
+                ],
+                reasoning: 'Hm.',
+                refusal: null,
+            },
+            { type: 'compaction', id: 'cmp_2', encrypted_content: 'enc' },
+            { role: 'user', content: 'Go on.' },
+        ],
+        tools: [
+            { type: 'web_search_20250305', name: 'web_search', max_uses: 3 },
+            {
+                type: 'function',
+                function: {
+                    name: 'strict_tool',
+                    strict: true,
+                    parameters: {
+                        type: 'object',
+                        properties: {},
+                        additionalProperties: false,
+                    },
+                },
+            },
+            {
+                name: 'anthropic_style',
+                description: 'x',
+                input_schema: { type: 'object', properties: {} },
+            },
+        ],
+        tool_choice: 'required',
+        thinking: { type: 'adaptive' },
+        prompt_cache_options: { ttl: '30m' },
+        instructions: [{ role: 'system', content: 'Be brief.' }],
+    },
+);
+
+const OPTION_NAMES = [
+    ...new Set(CORPUS.flatMap((request) => Object.keys(request))),
+    'previous_response_id',
+    'conversation',
+    'prompt',
+    'prompt_cache_options',
+    'background',
+    'custom',
+    'customLimitMessage',
+    'test_mode',
+];
+
+// -- Harness --
+
+const key = { apiKey: 'fuzz-key' };
+const providers = {
+    claude: key,
+    'azure-openai': { ...key, apiURL: 'https://azure.upstream.test/openai' },
+    'openai-completion': key,
+    gemini: key,
+    meta: key,
+    groq: key,
+    deepseek: key,
+    mistral: key,
+    xai: key,
+    moonshot: key,
+    minimax: key,
+    zai: key,
+    alibaba: key,
+    byteplus: key,
+    hoonify: key,
+    ollama: { enabled: false },
+};
+
+let server: PuterServer;
+let driver: ChatCompletionDriver;
+// Every provider gets the same share of cases, whatever its catalog size.
+let routes: Map<string, { provider: string; id: string }[]>;
+
+beforeAll(async () => {
+    upstream.install();
+    server = await setupTestServer();
+    driver = new ChatCompletionDriver(
+        { providers } as never,
+        server.clients,
+        server.stores,
+        server.services,
+    );
+    await driver.onServerStart();
+    routes = new Map();
+    for (const model of await driver.models()) {
+        if (!model.provider || model.provider === 'fake-chat') continue;
+        const route = { provider: model.provider, id: model.id };
+        routes.set(route.provider, [
+            ...(routes.get(route.provider) ?? []),
+            route,
+        ]);
+    }
+}, 120_000);
+
+afterAll(async () => {
+    await server?.shutdown();
+    upstream.uninstall();
+});
+
+const pickRoute = (random: Random) =>
+    pickStable(
+        random,
+        routes.get(pickStable(random, [...routes.keys()], (name) => name))!,
+        (route) => route.id,
+    );
+
+/** Runs one completion to its end, stream included, and returns its failure. */
+const complete = async (args: Record<string, unknown>): Promise<unknown> => {
+    try {
+        const result = await withTestActor(() =>
+            driver.complete(
+                structuredClone(args) as unknown as ICompleteArguments,
+            ),
+        );
+        if (isDriverStreamResult(result)) await readStreamResult(result);
+        return undefined;
+    } catch (error) {
+        return error;
+    }
+};
+
+describe('ChatCompletionDriver seeded fuzzing', () => {
+    it('covers every configured provider', () => {
+        expect([...routes.keys()].sort()).toEqual([
+            'alibaba',
+            'azure-openai',
+            'azure-openai-responses',
+            'byteplus',
+            'claude',
+            'deepseek',
+            'gemini',
+            'groq',
+            'hoonify',
+            'meta',
+            'minimax',
+            'mistral',
+            'moonshotai',
+            'openai-completion',
+            'openai-responses',
+            'xai',
+            'zai',
+        ]);
+    });
+
+    it('answers or rejects a malformed request without failing a healthy route', async () => {
+        upstream.respond = healthyUpstream;
+        upstream.unanswered.clear();
+        clearUnhealthyRoutes();
+        const findings = new Findings();
+        let answered = 0;
+
+        for (let index = 0; index < fuzzCases(3000); index++) {
+            const random = caseRandom(0xc4a7, index);
+            const route = pickRoute(random);
+            const args: Record<string, unknown> = {
+                ...mutate(pick(random, CORPUS), random, OPTION_NAMES),
+                provider: route.provider,
+                model: route.id,
+            };
+            // Now and then the route itself is the malformed part.
+            if (random() < 0.05) {
+                args[pick(random, ['provider', 'model'])] =
+                    hostileValue(random);
+            }
+            const label = `${route.provider}:${route.id}`;
+            const error = await complete(args);
+            if (!error) answered++;
+            const unclassified = error && unclassifiedFailure(error);
+            if (unclassified) findings.add(unclassified, index, label, args);
+            else if (isHttpError(error) && error.statusCode >= 500) {
+                const attempts = (error.fields?.attempts ?? []) as {
+                    status?: number;
+                    error: string;
+                }[];
+                findings.add(
+                    `${error.statusCode} ${error.legacyCode}: ${error.message} [${attempts.map((a) => `${a.status ?? 'no status'} ${a.error}`).join(' | ')}]`,
+                    index,
+                    label,
+                    args,
+                );
+            }
+            // The vendors answered every request, so no route failed.
+            for (const marked of kv.keys('aiChat:unhealthyRoute:*')) {
+                findings.add(`marked unhealthy ${marked}`, index, label, args);
+            }
+            clearUnhealthyRoutes();
+        }
+
+        for (const request of upstream.unanswered) {
+            findings.add(`no upstream fixture for ${request}`, -1, '', {});
+        }
+        findings.assertNone();
+        // A run where nothing is answered has stopped reaching the providers.
+        expect(answered).toBeGreaterThan(0);
+    }, 600_000);
+
+    it('ends every request with an answer or a classified error when the upstream misbehaves', async () => {
+        const findings = new Findings();
+        const askedBefore = upstream.asked;
+
+        for (let index = 0; index < fuzzCases(2000); index++) {
+            const random = caseRandom(0x0b5e, index);
+            const route = pickRoute(random);
+            const replies: unknown[] = [];
+            upstream.respond = (request) => {
+                const healthy = healthyUpstream(request);
+                const reply = healthy && corruptReply(healthy, random);
+                replies.push(reply);
+                return reply;
+            };
+            const error = await complete({
+                messages: [{ role: 'user', content: 'hi' }],
+                provider: route.provider,
+                model: route.id,
+                stream: random() < 0.5,
+                fallback: random() < 0.5,
+            });
+            const unclassified = error && unclassifiedFailure(error);
+            if (unclassified) {
+                findings.add(
+                    unclassified,
+                    index,
+                    `${route.provider}:${route.id}`,
+                    replies,
+                );
+            }
+            clearUnhealthyRoutes();
+        }
+        findings.assertNone();
+        expect(upstream.asked).toBeGreaterThan(askedBefore);
+    }, 600_000);
+});

src/backend/drivers/ai/interfaces/chat/ChatCompletionDriver.media.test.ts

@@ -38,11 +38,11 @@ import {
     vi,
 } from 'vitest';
 
-import { PuterServer } from '../../server.js';
-import { setupTestServer } from '../../testUtil.js';
-import { withTestActor } from '../integrationTestUtil.js';
+import { PuterServer } from '../../../../server.js';
+import { setupTestServer } from '../../../../testUtil.js';
+import { withTestActor } from '../../shared/integrationTestUtil.js';
 import { ChatCompletionDriver } from './ChatCompletionDriver.js';
-import { FakeChatProvider } from './providers/FakeChatProvider.js';
+import { FakeChatProvider } from '../../providers/fake/chat/FakeChatProvider.js';
 import type { IChatModel, ICompleteArguments } from './types.js';
 
 // The puter_path resolver reads the user's filesystem; stub it and assert on
@@ -51,7 +51,7 @@ const { processPuterPathUploadsMock } = vi.hoisted(() => ({
     processPuterPathUploadsMock: vi.fn(async (_messages: unknown) => {}),
 }));
 
-vi.mock('./providers/openai/fileUpload.js', () => ({
+vi.mock('../../providers/openai/chat/fileUpload.js', () => ({
     processPuterPathUploads: processPuterPathUploadsMock,
     MAX_FILE_SIZE: 5 * 1_000_000,
 }));

src/backend/drivers/ai/interfaces/chat/ChatCompletionDriver.metering.test.ts

@@ -38,14 +38,14 @@ import {
     vi,
 } from 'vitest';
 
-import { Context } from '../../core/context.js';
-import type { UsageInput } from '../../services/metering/types.js';
-import { PuterServer } from '../../server.js';
-import { setupTestServer } from '../../testUtil.js';
-import { withTestActor } from '../integrationTestUtil.js';
+import { Context } from '../../../../core/context.js';
+import type { UsageInput } from '../../../../services/metering/types.js';
+import { PuterServer } from '../../../../server.js';
+import { setupTestServer } from '../../../../testUtil.js';
+import { withTestActor } from '../../shared/integrationTestUtil.js';
 import { ChatCompletionDriver } from './ChatCompletionDriver.js';
 import { clearUnhealthyRoutes, isRouteUnhealthy } from './utils/providerHealth.js';
-import { FakeChatProvider } from './providers/FakeChatProvider.js';
+import { FakeChatProvider } from '../../providers/fake/chat/FakeChatProvider.js';
 import type { IChatCompleteResult } from './types.js';
 import { SDK_TIMEOUT_MS } from './utils/sdkClient.js';
 import type { AIChatStream } from './utils/Streaming.js';

src/backend/drivers/ai/interfaces/chat/ChatCompletionDriver.routing.test.ts

@@ -44,21 +44,21 @@ import type { Request } from 'express';
 import {
     renderAnthropicError,
     renderOpenAIError,
-} from '../../controllers/puterai/wireErrors.js';
-import { Context } from '../../core/context.js';
-import { HttpError } from '../../core/http/HttpError.js';
-import { PuterServer } from '../../server.js';
-import { setupTestServer } from '../../testUtil.js';
-import { withTestActor } from '../integrationTestUtil.js';
+} from '../../../../controllers/puterai/wireErrors.js';
+import { Context } from '../../../../core/context.js';
+import { HttpError } from '../../../../core/http/HttpError.js';
+import { PuterServer } from '../../../../server.js';
+import { setupTestServer } from '../../../../testUtil.js';
+import { withTestActor } from '../../shared/integrationTestUtil.js';
 import { ChatCompletionDriver } from './ChatCompletionDriver.js';
-import { OPEN_AI_MODELS } from './providers/openai/models.js';
+import { OPEN_AI_MODELS } from '../../providers/openai/chat/models.js';
 import {
     clearUnhealthyRoutes,
     isRouteUnhealthy,
     markRouteUnhealthy,
 } from './utils/providerHealth.js';
-import { InfronProvider } from './providers/infron/InfronProvider.js';
-import { UpstreamDeadlineError } from '../util/upstreamErrors.js';
+import { InfronProvider } from '../../providers/infron/chat/InfronProvider.js';
+import { UpstreamDeadlineError } from '../../../util/upstreamErrors.js';
 
 // -- OpenAI SDK mock ------------------------------------------------
 // Gemini reaches Google through `new openai.OpenAI()` (default export) and

src/backend/drivers/ai/interfaces/chat/ChatCompletionDriver.test.ts

@@ -44,17 +44,17 @@ import {
     vi,
 } from 'vitest';
 
-import { Context } from '../../core/context.js';
-import { HttpError } from '../../core/http/HttpError.js';
-import { PuterServer } from '../../server.js';
-import { setupTestServer } from '../../testUtil.js';
-import { withTestActor } from '../integrationTestUtil.js';
+import { Context } from '../../../../core/context.js';
+import { HttpError } from '../../../../core/http/HttpError.js';
+import { PuterServer } from '../../../../server.js';
+import { setupTestServer } from '../../../../testUtil.js';
+import { withTestActor } from '../../shared/integrationTestUtil.js';
 import { COUNT_TOKENS, ChatCompletionDriver } from './ChatCompletionDriver.js';
-import { ClaudeProvider } from './providers/claude/ClaudeProvider.js';
-import { FakeChatProvider } from './providers/FakeChatProvider.js';
-import { OllamaChatProvider } from './providers/ollama/OllamaProvider.js';
-import { XAI_CHAT_MODELS } from './providers/xai/catalog.js';
-import { XAIProvider } from './providers/xai/XAIProvider.js';
+import { ClaudeProvider } from '../../providers/claude/chat/ClaudeProvider.js';
+import { FakeChatProvider } from '../../providers/fake/chat/FakeChatProvider.js';
+import { OllamaChatProvider } from '../../providers/ollama/chat/OllamaProvider.js';
+import { XAI_CHAT_MODELS } from '../../providers/xai/chat/catalog.js';
+import { XAIProvider } from '../../providers/xai/chat/XAIProvider.js';
 import type {
     IChatCompleteResult,
     IChatProvider,
@@ -207,6 +207,50 @@ describe('ChatCompletionDriver model map', () => {
         d.onServerShutdown();
     });
 
+    it('lists qualified model ids without publishing aliases as models', async () => {
+        const ids = [
+            'kimi/kimi-3',
+            'ollama:plain-model',
+            'ollama:vendor/qualified',
+            'vendor/tagged:free',
+        ];
+        vi.spyOn(OllamaChatProvider.prototype, 'models').mockResolvedValue(
+            ids.map((id) => ({
+                id,
+                aliases: ['legacy-' + id],
+                costs_currency: 'usd-cents',
+                costs: {},
+                max_tokens: 8192,
+            })),
+        );
+        const d = newDriver({ ollama: {} });
+        await d.onServerStart();
+        try {
+            expect(
+                (await d.list()).filter(
+                    (id) => !['abuse', 'costly', 'fake'].includes(id),
+                ),
+            ).toEqual([
+                'ollama:kimi/kimi-3',
+                'ollama:ollama/plain-model',
+                'ollama:vendor/qualified',
+                'ollama:vendor/tagged:free',
+            ]);
+            const models = (await d.models()).filter(
+                (model) => model.provider === 'ollama',
+            );
+            expect(models.map((model) => model.id).sort()).toEqual(
+                [...ids].sort(),
+            );
+            for (const model of models) {
+                expect(model.aliases).toContain(model.puterId);
+                expect(model.aliases).toContain('legacy-' + model.id);
+            }
+        } finally {
+            d.onServerShutdown();
+        }
+    });
+
     it('lists the catalog to a caller that asks while it is still loading', async () => {
         const d = newDriver({ ollama: { enabled: false } });
         d.onServerStart();
@@ -2396,3 +2440,97 @@ describe('ChatCompletionDriver service speed', () => {
         },
     );
 });
+
+describe('ChatCompletionDriver.complete option shapes', () => {
+    const hi = [{ role: 'user', content: 'hi' }];
+
+    it.each(['model', 'provider', 'service_tier'])(
+        'rejects a value that cannot be text as `%s`',
+        async (name) => {
+            const args = { model: 'fake', messages: hi, [name]: { toString: null } };
+            await expect(
+                withTestActor(() => driver.complete(args as never)),
+            ).rejects.toMatchObject({
+                statusCode: 400,
+                legacyCode: 'bad_request',
+                message: `\`${name}\` is not a usable value`,
+            });
+            await expect(
+                withTestActor(() => driver[COUNT_TOKENS](args as never)),
+            ).rejects.toMatchObject({ statusCode: 400 });
+        },
+    );
+
+    it('routes by the model when `provider` is an object, as it did before', async () => {
+        const completeSpy = vi.spyOn(FakeChatProvider.prototype, 'complete');
+        await withTestActor(() =>
+            driver.complete({
+                model: 'fake',
+                messages: hi,
+                provider: { order: ['Anthropic'] },
+            } as never),
+        );
+        expect(completeSpy).toHaveBeenCalledTimes(1);
+    });
+
+    it.each([false, 0, '', null])(
+        'treats `tools: %j` as no tools when counting tokens',
+        async (tools) => {
+            const countTokens = vi.fn(async (_args: object) => 1);
+            const fake = FakeChatProvider.prototype as {
+                countTokens?: typeof countTokens;
+            };
+            fake.countTokens = countTokens;
+            try {
+                await withTestActor(() =>
+                    driver[COUNT_TOKENS]({
+                        model: 'fake',
+                        messages: hi,
+                        tools,
+                    } as never),
+                );
+            } finally {
+                delete fake.countTokens;
+            }
+            expect(countTokens.mock.calls[0]![0]).not.toHaveProperty('tools');
+        },
+    );
+
+    it.each([false, 0, '', null])(
+        'treats `tools: %j` as no tools',
+        async (tools) => {
+            const completeSpy = vi.spyOn(FakeChatProvider.prototype, 'complete');
+            await withTestActor(() =>
+                driver.complete({ model: 'fake', messages: hi, tools } as never),
+            );
+            expect(completeSpy.mock.calls[0]![0]).not.toHaveProperty('tools');
+        },
+    );
+
+    it('reports zero tokens in the cost event for a usage count that is not a number', async () => {
+        vi.spyOn(FakeChatProvider.prototype, 'models').mockResolvedValueOnce([
+            {
+                id: 'priced',
+                aliases: [],
+                costs_currency: 'usd-cents',
+                costs: { input_tokens: 1000, output_tokens: 2000 },
+                max_tokens: 8192,
+            },
+        ]);
+        const d = await makeDriver();
+        const costEvents = captureEvent('ai.prompt.cost-calculated');
+        vi.spyOn(FakeChatProvider.prototype, 'complete').mockResolvedValueOnce({
+            message: { role: 'assistant', content: [{ type: 'text', text: 'ok' }] },
+            usage: { input_tokens: 10, output_tokens: { toString: null } },
+            finish_reason: 'stop',
+        } as never);
+
+        await withTestActor(() => d.complete({ model: 'priced', messages: hi }));
+
+        expect(costEvents[0]![1]).toMatchObject({
+            input_tokens: 10,
+            output_tokens: 0,
+            total_ucents: 10 * 1000,
+        });
+    });
+});

src/backend/drivers/ai/interfaces/chat/ChatCompletionDriver.ts

@@ -19,56 +19,56 @@
 
 import crypto from 'node:crypto';
 import { PassThrough } from 'node:stream';
-import { EventMap } from '../../clients/event/types.js';
-import type { Actor } from '../../core/actor.js';
-import { Context } from '../../core/context.js';
-import { HttpError, isHttpError } from '../../core/http/HttpError.js';
-import { insufficientCreditsError } from '../../services/metering/enforcement.js';
-import { isFreeSubscription } from '../../services/metering/consts.js';
-import type { MeteringService } from '../../services/metering/MeteringService.js';
-import type { CreditHold } from '../../services/metering/types.js';
-import { NO_CREDIT_HOLD } from '../../services/metering/types.js';
-import type { DriverStreamResult } from '../meta.js';
-import { PuterDriver } from '../types.js';
+import { EventMap } from '../../../../clients/event/types.js';
+import type { Actor } from '../../../../core/actor.js';
+import { Context } from '../../../../core/context.js';
+import { HttpError, isHttpError } from '../../../../core/http/HttpError.js';
+import { insufficientCreditsError } from '../../../../services/metering/enforcement.js';
+import { isFreeSubscription } from '../../../../services/metering/consts.js';
+import type { MeteringService } from '../../../../services/metering/MeteringService.js';
+import type { CreditHold } from '../../../../services/metering/types.js';
+import { NO_CREDIT_HOLD } from '../../../../services/metering/types.js';
+import type { DriverStreamResult } from '../../../meta.js';
+import { PuterDriver } from '../../../types.js';
 import {
     type AiMeteringService,
     factoredTotal,
     requestAiCosts,
     withAiCostFactor,
-} from '../util/aiCostFactor.js';
-import { AI_CONCURRENT, AI_RATE_LIMIT } from '../util/aiLimits.js';
+} from '../../../../util/aiCostFactor.js';
+import { AI_CONCURRENT, AI_RATE_LIMIT } from '../../shared/aiLimits.js';
 import {
     isCreditExhaustion as isUpstreamCreditExhaustion,
     isUpstreamConnectionError,
     isUpstreamTimeoutError,
     sanitizeUpstreamMessage,
     UpstreamDeadlineError,
-} from '../util/upstreamErrors.js';
-import { AlibabaProvider } from './providers/alibaba/AlibabaProvider.js';
-import { AzureChatProvider } from './providers/azure/AzureChatProvider.js';
-import { AzureResponsesProvider } from './providers/azure/AzureResponsesProvider.js';
-import { BytePlusProvider } from './providers/byteplus/BytePlusProvider.js';
-import { ClaudeProvider } from './providers/claude/ClaudeProvider.js';
-import { DeepSeekProvider } from './providers/deepseek/DeepSeekProvider.js';
-import { FakeChatProvider } from './providers/FakeChatProvider.js';
-import { GeminiChatProvider } from './providers/gemini/GeminiChatProvider.js';
-import { GroqAIProvider } from './providers/groq/GroqAIProvider.js';
-import { HoonifyProvider } from './providers/hoonify/HoonifyProvider.js';
-import { InfronProvider } from './providers/infron/InfronProvider.js';
-import { MetaProvider } from './providers/meta/MetaProvider.js';
-import { MiniMaxProvider } from './providers/minimax/MiniMaxProvider.js';
-import { MistralAIProvider } from './providers/mistral/MistralAiProvider.js';
-import { MoonshotProvider } from './providers/moonshot/MoonshotProvider.js';
-import { NeuralwattProvider } from './providers/neuralwatt/NeuralwattProvider.js';
-import { OllamaChatProvider } from './providers/ollama/OllamaProvider.js';
-import type { ChatProviderConfig } from './providers/OpenAICompatProvider.js';
-import { processPuterPathUploads } from './providers/openai/fileUpload.js';
-import { OpenAiChatProvider } from './providers/openai/OpenAiChatCompletionsProvider.js';
-import { OpenAiResponsesChatProvider } from './providers/openai/OpenAiChatResponsesProvider.js';
-import { OpenRouterProvider } from './providers/openrouter/OpenRouterProvider.js';
-import { TogetherAIProvider } from './providers/together/TogetherAIProvider.js';
-import { XAIProvider } from './providers/xai/XAIProvider.js';
-import { ZAIProvider } from './providers/zai/ZAIProvider.js';
+} from '../../../util/upstreamErrors.js';
+import { AlibabaProvider } from '../../providers/alibaba/chat/AlibabaProvider.js';
+import { AzureChatProvider } from '../../providers/azure/chat/AzureChatProvider.js';
+import { AzureResponsesProvider } from '../../providers/azure/chat/AzureResponsesProvider.js';
+import { BytePlusProvider } from '../../providers/byteplus/chat/BytePlusProvider.js';
+import { ClaudeProvider } from '../../providers/claude/chat/ClaudeProvider.js';
+import { DeepSeekProvider } from '../../providers/deepseek/chat/DeepSeekProvider.js';
+import { FakeChatProvider } from '../../providers/fake/chat/FakeChatProvider.js';
+import { GeminiChatProvider } from '../../providers/gemini/chat/GeminiChatProvider.js';
+import { GroqAIProvider } from '../../providers/groq/chat/GroqAIProvider.js';
+import { HoonifyProvider } from '../../providers/hoonify/chat/HoonifyProvider.js';
+import { InfronProvider } from '../../providers/infron/chat/InfronProvider.js';
+import { MetaProvider } from '../../providers/meta/chat/MetaProvider.js';
+import { MiniMaxProvider } from '../../providers/minimax/chat/MiniMaxProvider.js';
+import { MistralAIProvider } from '../../providers/mistral/chat/MistralAiProvider.js';
+import { MoonshotProvider } from '../../providers/moonshot/chat/MoonshotProvider.js';
+import { NeuralwattProvider } from '../../providers/neuralwatt/chat/NeuralwattProvider.js';
+import { OllamaChatProvider } from '../../providers/ollama/chat/OllamaProvider.js';
+import type { ChatProviderConfig } from '../../protocols/openaiCompatible/OpenAICompatProvider.js';
+import { processPuterPathUploads } from '../../providers/openai/chat/fileUpload.js';
+import { OpenAiChatProvider } from '../../providers/openai/chat/OpenAiChatCompletionsProvider.js';
+import { OpenAiResponsesChatProvider } from '../../providers/openai/chat/OpenAiChatResponsesProvider.js';
+import { OpenRouterProvider } from '../../providers/openrouter/chat/OpenRouterProvider.js';
+import { TogetherAIProvider } from '../../providers/together/chat/TogetherAIProvider.js';
+import { XAIProvider } from '../../providers/xai/chat/XAIProvider.js';
+import { ZAIProvider } from '../../providers/zai/chat/ZAIProvider.js';
 import type {
     IChatCompleteResult,
     IChatMessageResult,
@@ -103,9 +103,13 @@ import {
     normalizeResultToOpenAI,
     shouldPresentAsOpenAI,
 } from './utils/normalizeToOpenAI.js';
-import { isToolChoice, toolChoiceFromWire } from './utils/openaiParams.js';
 import {
-    catalogPrice,
+    isToolChoice,
+    toolChoiceFromWire,
+} from '../../protocols/openaiCompatible/openaiParams.js';
+import { assertScalarOptions } from '../../shared/scalarOptions.js';
+import { catalogPrice } from '../../shared/catalogPrice.js';
+import {
     costKeys,
     costsForRequest,
     isFreeModel,
@@ -121,7 +125,7 @@ import {
     TRANSIENT_UNHEALTHY_TTL_SEC,
     UNHEALTHY_TTL_SEC,
 } from './utils/providerHealth.js';
-import { CATALOG_TTL_MS } from './utils/cachedRemoteCatalog.js';
+import { CATALOG_TTL_MS } from '../../shared/cachedRemoteCatalog.js';
 import { SDK_TIMEOUT_MS } from './utils/sdkClient.js';
 import { fromFinishReason } from './utils/stopReason.js';
 import { AIChatStream } from './utils/Streaming.js';
@@ -178,6 +182,9 @@ export const COUNT_TOKENS = Symbol('aiChat.countTokens');
  */
 const HOLD_RENEW_INTERVAL_MS = 5 * 60 * 1000;
 
+// Options that reach error messages and request headers as text.
+const SCALAR_OPTIONS = ['model', 'provider', 'service_tier'];
+
 /**
  * A moderation refusal is a completion that was produced and charged, then
  * withheld — not a route failure. Retrying it on a fallback provider would bill
@@ -585,7 +592,7 @@ export class ChatCompletionDriver extends PuterDriver {
     readonly driverName = 'ai-chat';
     readonly isDefault = true;
 
-    // Shared AI policy — see `drivers/util/aiLimits.ts` for the tier table.
+    // Shared AI policy — see `drivers/ai/shared/aiLimits.ts` for the tier table.
     readonly rateLimit = AI_RATE_LIMIT;
     readonly concurrent = AI_CONCURRENT;
 
@@ -690,6 +697,7 @@ export class ChatCompletionDriver extends PuterDriver {
                 { legacyCode: 'invalid_service_speed' },
             );
         }
+        assertScalarOptions(args, SCALAR_OPTIONS);
         const abortSignal = Context.get('abortSignal');
         abortSignal?.throwIfAborted();
         const actor = Context.get('actor');
@@ -744,6 +752,9 @@ export class ChatCompletionDriver extends PuterDriver {
         args.messages = normalizeMediaParts(normalize_messages(args.messages));
         if (args.tools) {
             normalize_tools_object(args.tools);
+        } else {
+            // `tools: enabled && list` leaves `false` here; it means no tools.
+            delete args.tools;
         }
         // A raw `/drivers/call` caller still sends the OpenAI wire form
         // ('auto'/'none'/'required', {type:'function', function:{name}}) —
@@ -1297,8 +1308,17 @@ export class ChatCompletionDriver extends PuterDriver {
             }, HOLD_RENEW_INTERVAL_MS);
             renewHold.unref?.();
 
-            // Fire-and-forget — the stream writes happen async while the
-            // response is being piped to the client.
+            // The upstream runs on after a caller hangs up, so the request
+            // keeps its concurrency slot until the upstream is done, not until
+            // the cleanup after it.
+            let upstreamDone!: () => void;
+            const upstreamRunning = new Promise<void>((resolve) => {
+                upstreamDone = resolve;
+            });
+            Context.get('keepConcurrencySlot')?.(upstreamRunning);
+
+            // The stream writes happen async while the response is piped to
+            // the client.
             (async () => {
                 try {
                     await init({ chatStream });
@@ -1323,6 +1343,7 @@ export class ChatCompletionDriver extends PuterDriver {
                     }
                     passthrough.end();
                 } finally {
+                    upstreamDone();
                     clearInterval(renewHold);
                     clearTimeout(detachedLimit);
                     abortSignal?.removeEventListener('abort', detachStream);
@@ -1490,6 +1511,7 @@ export class ChatCompletionDriver extends PuterDriver {
     async [COUNT_TOKENS](
         args: ICompleteArguments,
     ): Promise<{ input_tokens: number }> {
+        assertScalarOptions(args, SCALAR_OPTIONS);
         let intendedProvider = args.provider || '';
         if (!args.model && !intendedProvider) {
             intendedProvider = 'azure-openai';
@@ -1515,6 +1537,9 @@ export class ChatCompletionDriver extends PuterDriver {
         args.messages = normalizeMediaParts(normalize_messages(args.messages));
         if (args.tools) {
             normalize_tools_object(args.tools);
+        } else {
+            // `tools: enabled && list` leaves `false` here; it means no tools.
+            delete args.tools;
         }
 
         const provider = this.#providers[model.provider!];
@@ -1848,20 +1873,20 @@ export class ChatCompletionDriver extends PuterDriver {
 
         const cost = usageCost(usage, model, usageCosts, pricingTime);
         const { inputKey, outputKey } = costKeys(model);
+        // The vendor reports usage, and pricing skips a count that is not a
+        // number; so does this.
+        const count = (value: unknown) =>
+            typeof value === 'number' && Number.isFinite(value) ? value : 0;
         const inputTokens = cost
-            ? Number(
-                  usage[inputKey] ??
-                      usage.prompt_tokens ??
-                      usage.input_tokens ??
-                      0,
+            ? count(
+                  usage[inputKey] ?? usage.prompt_tokens ?? usage.input_tokens,
               )
             : 0;
         const outputTokens = cost
-            ? Number(
+            ? count(
                   usage[outputKey] ??
                       usage.completion_tokens ??
-                      usage.output_tokens ??
-                      0,
+                      usage.output_tokens,
               )
             : 0;
         const inputMicroCents = cost?.inputMicroCents ?? 0;
@@ -2061,14 +2086,39 @@ export class ChatCompletionDriver extends PuterDriver {
                 // instance, so they are read and never written: normalizing
                 // the id or appending puterId in place would accumulate across
                 // instantiations. The bucket gets its own copy instead.
-                const aliases =
-                    entry.puterId &&
-                    !(entry.aliases ?? []).includes(entry.puterId)
-                        ? [...(entry.aliases ?? []), entry.puterId]
-                        : entry.aliases;
+                // Keep upstream ids for provider calls and publish a qualified
+                // routing name even when a catalog omits its vendor namespace.
+                const publicId = entry.puterId || entry.id;
+                // A colon after the first slash belongs to the model name, as
+                // in `vendor/model:free`, and names no service.
+                const serviceSeparator = publicId
+                    .split('/', 1)[0]!
+                    .indexOf(':');
+                const service =
+                    serviceSeparator < 0
+                        ? providerName
+                        : publicId.slice(0, serviceSeparator);
+                const modelPath =
+                    serviceSeparator < 0
+                        ? publicId
+                        : publicId.slice(serviceSeparator + 1);
+                const puterId =
+                    providerName === 'fake-chat'
+                        ? entry.puterId
+                        : `${service}:${modelPath.includes('/') ? modelPath : `${service}/${modelPath}`}`;
+                const aliases = puterId
+                    ? [
+                          ...new Set([
+                              ...(entry.aliases ?? []),
+                              ...(entry.puterId ? [entry.puterId] : []),
+                              puterId,
+                          ]),
+                      ]
+                    : entry.aliases;
                 const model = {
                     ...entry,
                     id: normalizeModelKey(entry.id),
+                    ...(puterId ? { puterId } : {}),
                 };
                 // Assigned only when the entry has names to carry: models()
                 // is serialized to the API, and an entry that declared no

src/backend/drivers/ai/interfaces/chat/modelCatalogs.test.ts

@@ -47,29 +47,29 @@
  * on that test.)
  */
 
-import { readdirSync } from 'node:fs';
+import { existsSync, readdirSync } from 'node:fs';
 import { dirname, join } from 'node:path';
 import { fileURLToPath, pathToFileURL } from 'node:url';
 
 import { describe, expect, it } from 'vitest';
 
-import type { IChatModel } from '../types.js';
-import { ALIBABA_MODELS } from './alibaba/models.js';
-import { AZURE_MODELS } from './azure/models.js';
-import { BYTEPLUS_MODELS } from './byteplus/models.js';
-import { CLAUDE_MODELS } from './claude/models.js';
-import { DEEPSEEK_MODELS } from './deepseek/models.js';
-import { GEMINI_MODELS } from './gemini/models.js';
-import { GROQ_MODELS } from './groq/models.js';
-import { HOONIFY_MODELS } from './hoonify/models.js';
-import { META_MODELS } from './meta/models.js';
-import { MINIMAX_MODELS } from './minimax/models.js';
-import { MISTRAL_MODELS } from './mistral/models.js';
-import { MOONSHOT_MODELS } from './moonshot/models.js';
-import { OPEN_AI_MODELS } from './openai/models.js';
-import { OPEN_ROUTER_MODEL_OVERRIDES } from './openrouter/modelOverrides.js';
-import { XAI_MODELS } from './xai/models.js';
-import { ZAI_MODELS } from './zai/models.js';
+import type { IChatModel } from './types.js';
+import { ALIBABA_MODELS } from '../../providers/alibaba/chat/models.js';
+import { AZURE_MODELS } from '../../providers/azure/chat/models.js';
+import { BYTEPLUS_MODELS } from '../../providers/byteplus/chat/models.js';
+import { CLAUDE_MODELS } from '../../providers/claude/chat/models.js';
+import { DEEPSEEK_MODELS } from '../../providers/deepseek/chat/models.js';
+import { GEMINI_MODELS } from '../../providers/gemini/chat/models.js';
+import { GROQ_MODELS } from '../../providers/groq/chat/models.js';
+import { HOONIFY_MODELS } from '../../providers/hoonify/chat/models.js';
+import { META_MODELS } from '../../providers/meta/chat/models.js';
+import { MINIMAX_MODELS } from '../../providers/minimax/chat/models.js';
+import { MISTRAL_MODELS } from '../../providers/mistral/chat/models.js';
+import { MOONSHOT_MODELS } from '../../providers/moonshot/chat/models.js';
+import { OPEN_AI_MODELS } from '../../providers/openai/chat/models.js';
+import { OPEN_ROUTER_MODEL_OVERRIDES } from '../../providers/openrouter/chat/modelOverrides.js';
+import { XAI_MODELS } from '../../providers/xai/chat/models.js';
+import { ZAI_MODELS } from '../../providers/zai/chat/models.js';
 
 // Providers whose catalog is fetched at runtime (OpenRouter, Ollama, Together,
 // Infron, Neuralwatt) have nothing static to check and are absent by design;
@@ -201,28 +201,34 @@ describe('CATALOGS', () => {
     // silent gap these tests are about, so the list is checked against what
     // is actually on disk.
     //
-    // The scan covers every non-test source file under providers/*/ with
-    // "model" in its name — models.ts, but also siblings like openrouter's
-    // modelOverrides.ts. Importing every provider file regardless of name
-    // would drag in SDK modules for a filename sweep, so that naming
-    // convention is the one assumption left unenforced here: a catalog in a
-    // file named without "model" would escape this net.
-    it('lists every static catalog under providers/', async () => {
-        const here = dirname(fileURLToPath(import.meta.url));
+    // The scan covers every non-test source file under providers/*/chat/
+    // with "model" in its name — models.ts, but also siblings like
+    // openrouter's modelOverrides.ts. Importing every provider file
+    // regardless of name would drag in SDK modules for a filename sweep, so
+    // that naming convention is the one assumption left unenforced here: a
+    // catalog in a file named without "model" would escape this net.
+    it('lists every static catalog under providers/*/chat/', async () => {
+        const providersDir = join(
+            dirname(fileURLToPath(import.meta.url)),
+            '../../providers',
+        );
         const registered = new Map(CATALOGS);
+        const found = new Set<string>();
         const problems: string[] = [];
 
-        for (const dir of readdirSync(here, { withFileTypes: true })) {
+        for (const dir of readdirSync(providersDir, { withFileTypes: true })) {
             if (!dir.isDirectory()) continue;
+            const chatDir = join(providersDir, dir.name, 'chat');
+            if (!existsSync(chatDir)) continue;
 
-            for (const file of readdirSync(join(here, dir.name))) {
+            for (const file of readdirSync(chatDir)) {
                 if (!/model/i.test(file)) continue;
                 if (!file.endsWith('.ts') || file.endsWith('.test.ts')) {
                     continue;
                 }
 
                 const module = await import(
-                    pathToFileURL(join(here, dir.name, file)).href
+                    pathToFileURL(join(chatDir, file)).href
                 );
                 for (const [name, value] of Object.entries(module)) {
                     // A catalog is a non-empty array of entries carrying an
@@ -233,16 +239,19 @@ describe('CATALOGS', () => {
                         value.length > 0 &&
                         typeof value[0]?.id === 'string';
                     if (!isCatalog) continue;
+                    found.add(name);
 
                     if (!registered.has(name)) {
-                        problems.push(`${dir.name}/${file} exports ${name}`);
+                        problems.push(
+                            `${dir.name}/chat/${file} exports ${name}`,
+                        );
                     } else if (registered.get(name) !== value) {
                         // The row's label names this export but its value is
                         // a different array — the wrong catalog would be the
                         // one getting checked.
                         problems.push(
                             `the CATALOGS row named ${name} does not hold ` +
-                                `the ${name} that ${dir.name}/${file} exports`,
+                                `the ${name} that ${dir.name}/chat/${file} exports`,
                         );
                     }
                 }
@@ -250,5 +259,7 @@ describe('CATALOGS', () => {
         }
 
         expect(problems, problems.join('\n')).toEqual([]);
+        // A scan pointed at the wrong directory finds nothing and passes.
+        expect([...found].sort()).toEqual([...registered.keys()].sort());
     });
 });

src/backend/drivers/ai/interfaces/chat/providerConsistency.test.ts

@@ -39,41 +39,41 @@
 
 import { describe, expect, it, vi } from 'vitest';
 
-import type { MeteringService } from '../../../services/metering/MeteringService.js';
-import { withTestActor } from '../../integrationTestUtil.js';
+import type { MeteringService } from '../../../../services/metering/MeteringService.js';
+import { withTestActor } from '../../shared/integrationTestUtil.js';
 import type {
     IChatMessageResult,
     IChatModel,
     IChatProvider,
-} from '../types.js';
+} from './types.js';
 import {
     needsOpenAICoercion,
     normalizeResultToOpenAI,
-} from '../utils/normalizeToOpenAI.js';
+} from './utils/normalizeToOpenAI.js';
 
-import { AlibabaProvider } from './alibaba/AlibabaProvider.js';
-import { AzureChatProvider } from './azure/AzureChatProvider.js';
-import { AzureResponsesProvider } from './azure/AzureResponsesProvider.js';
-import { BytePlusProvider } from './byteplus/BytePlusProvider.js';
-import { ClaudeProvider } from './claude/ClaudeProvider.js';
-import { DeepSeekProvider } from './deepseek/DeepSeekProvider.js';
-import { FakeChatProvider } from './FakeChatProvider.js';
-import { GeminiChatProvider } from './gemini/GeminiChatProvider.js';
-import { GroqAIProvider } from './groq/GroqAIProvider.js';
-import { HoonifyProvider } from './hoonify/HoonifyProvider.js';
-import { InfronProvider } from './infron/InfronProvider.js';
-import { MetaProvider } from './meta/MetaProvider.js';
-import { MiniMaxProvider } from './minimax/MiniMaxProvider.js';
-import { MistralAIProvider } from './mistral/MistralAiProvider.js';
-import { MoonshotProvider } from './moonshot/MoonshotProvider.js';
-import { NeuralwattProvider } from './neuralwatt/NeuralwattProvider.js';
-import { OllamaChatProvider } from './ollama/OllamaProvider.js';
-import { OpenAiChatProvider } from './openai/OpenAiChatCompletionsProvider.js';
-import { OpenAiResponsesChatProvider } from './openai/OpenAiChatResponsesProvider.js';
-import { OpenRouterProvider } from './openrouter/OpenRouterProvider.js';
-import { TogetherAIProvider } from './together/TogetherAIProvider.js';
-import { XAIProvider } from './xai/XAIProvider.js';
-import { ZAIProvider } from './zai/ZAIProvider.js';
+import { AlibabaProvider } from '../../providers/alibaba/chat/AlibabaProvider.js';
+import { AzureChatProvider } from '../../providers/azure/chat/AzureChatProvider.js';
+import { AzureResponsesProvider } from '../../providers/azure/chat/AzureResponsesProvider.js';
+import { BytePlusProvider } from '../../providers/byteplus/chat/BytePlusProvider.js';
+import { ClaudeProvider } from '../../providers/claude/chat/ClaudeProvider.js';
+import { DeepSeekProvider } from '../../providers/deepseek/chat/DeepSeekProvider.js';
+import { FakeChatProvider } from '../../providers/fake/chat/FakeChatProvider.js';
+import { GeminiChatProvider } from '../../providers/gemini/chat/GeminiChatProvider.js';
+import { GroqAIProvider } from '../../providers/groq/chat/GroqAIProvider.js';
+import { HoonifyProvider } from '../../providers/hoonify/chat/HoonifyProvider.js';
+import { InfronProvider } from '../../providers/infron/chat/InfronProvider.js';
+import { MetaProvider } from '../../providers/meta/chat/MetaProvider.js';
+import { MiniMaxProvider } from '../../providers/minimax/chat/MiniMaxProvider.js';
+import { MistralAIProvider } from '../../providers/mistral/chat/MistralAiProvider.js';
+import { MoonshotProvider } from '../../providers/moonshot/chat/MoonshotProvider.js';
+import { NeuralwattProvider } from '../../providers/neuralwatt/chat/NeuralwattProvider.js';
+import { OllamaChatProvider } from '../../providers/ollama/chat/OllamaProvider.js';
+import { OpenAiChatProvider } from '../../providers/openai/chat/OpenAiChatCompletionsProvider.js';
+import { OpenAiResponsesChatProvider } from '../../providers/openai/chat/OpenAiChatResponsesProvider.js';
+import { OpenRouterProvider } from '../../providers/openrouter/chat/OpenRouterProvider.js';
+import { TogetherAIProvider } from '../../providers/together/chat/TogetherAIProvider.js';
+import { XAIProvider } from '../../providers/xai/chat/XAIProvider.js';
+import { ZAIProvider } from '../../providers/zai/chat/ZAIProvider.js';
 
 // ── Upstream SDK mocks ──────────────────────────────────────────────
 // One create-mock per wire dialect; every provider speaking that dialect

src/backend/drivers/ai/interfaces/chat/utils/FunctionCalling.js

@@ -18,7 +18,6 @@
  */
 
 import { HttpError } from '@heyputer/backend/src/core/http';
-import { claudeToolPolicy } from '../providers/claude/anthropicPolicy.js';
 
 // Anthropic server/typed tool ids (`web_search_20250305`,
 // `advisor_20260301`, …) and the OpenAI Responses `web_search` tool pass
@@ -124,7 +123,7 @@ export const normalize_tools_object = (tools) => {
         };
 
         // Claude-only extras, carried on the `{type:'function', ...}`
-        // wrapper so `make_claude_tools` can forward them; a top-level
+        // wrapper so `claudeToolPolicy` can forward them; a top-level
         // `strict` (Claude's own convention) moves onto `function.strict`.
         const extras = {};
         if (tool.cache_control !== undefined)
@@ -169,76 +168,3 @@ export const normalize_tools_object = (tools) => {
     }
     return tools;
 };
-
-// OpenAI's own tool conventions pass through untouched.
-const OPENAI_NATIVE_WEB_SEARCH = new Set(['web_search', 'web_search_preview']);
-const ANTHROPIC_WEB_SEARCH_TYPE = (type) =>
-    type === 'web_search_20250305' || /^web_search_2026/.test(type ?? '');
-
-/**
- * Converts a normalized tools object to the format expected by an OpenAI-family
- * dialect: function tools drop their Anthropic-only extras (`cache_control`,
- * `defer_loading`, `eager_input_streaming`, `input_examples`); every other
- * Anthropic typed/server tool (`web_search_20250305`, `advisor_20260301`,
- * `bash_*`, …) is dropped, since none of it is a wire shape OpenAI recognizes.
- * The one exception: an Anthropic web-search tool is translated to OpenAI's own
- * `web_search` tool for the Responses dialect, which supports it natively.
- *
- * @param {any} tools
- * @param {{ dialect?: 'chat' | 'responses' }} [opts]
- * @returns {any[] | undefined}
- */
-export const make_openai_tools = (tools, opts = {}) => {
-    if (!tools) return tools;
-    const dialect = opts.dialect ?? 'chat';
-    const out = [];
-    for (const tool of tools) {
-        if (!tool || typeof tool !== 'object') continue;
-        if (tool.type === 'function') {
-            const stripped = { ...tool };
-            delete stripped.cache_control;
-            delete stripped.defer_loading;
-            delete stripped.eager_input_streaming;
-            delete stripped.input_examples;
-            out.push(stripped);
-            continue;
-        }
-        if (OPENAI_NATIVE_WEB_SEARCH.has(tool.type)) {
-            out.push(tool);
-            continue;
-        }
-        if (dialect === 'responses' && ANTHROPIC_WEB_SEARCH_TYPE(tool.type)) {
-            out.push({
-                type: 'web_search',
-                ...(tool.allowed_domains
-                    ? { filters: { allowed_domains: tool.allowed_domains } }
-                    : {}),
-                ...(tool.user_location
-                    ? { user_location: tool.user_location }
-                    : {}),
-            });
-            continue;
-        }
-        // Any other Anthropic typed/server tool (web_search_* on the chat
-        // dialect, advisor, bash, memory, web_fetch, tool_search, …) has no
-        // OpenAI equivalent — drop it rather than forward an unrecognized type.
-    }
-    return out;
-};
-
-/**
- * This function will convert a normalized tools object to the format expected
- * by Claude: function tools become `{name, description, input_schema, ...}`,
- * and typed/server tools (`web_search`, `web_search_20250305`,
- * `advisor_20260301`, …) go through the allowlist/clamp/reject policy in
- * `claudeToolPolicy` instead of being treated as malformed function
- * definitions.
- *
- * @param {any} tools
- * @param {{ models?: import('../types.js').IChatModel[] }} [opts]
- * @returns {any[] | undefined}
- */
-export const make_claude_tools = (tools, opts = {}) => {
-    if (!tools) return undefined;
-    return claudeToolPolicy(tools, opts.models ?? []).tools;
-};

src/backend/drivers/ai/interfaces/chat/utils/FunctionCalling.test.ts

@@ -20,13 +20,11 @@
 import { describe, expect, it } from 'vitest';
 // @ts-expect-error — sibling JS module without an adjacent .d.ts
 import {
-    make_claude_tools,
-    make_openai_tools,
     normalize_json_schema,
     normalize_tools_object,
 } from './FunctionCalling.js';
 
-// All four exports are pure data transforms — these tests just feed
+// Both exports are pure data transforms — these tests just feed
 // inputs and check the normalized output, no service mocks involved.
 
 // ── normalize_json_schema ───────────────────────────────────────────
@@ -242,159 +240,3 @@ describe('normalize_tools_object', () => {
         expect(out[0].function.parameters.properties).toBe('x');
     });
 });
-
-// ── make_openai_tools ───────────────────────────────────────────────
-
-describe('make_openai_tools', () => {
-    it('keeps a function tool, dropping its Anthropic-only extras', () => {
-        const tools = [
-            {
-                type: 'function',
-                function: { name: 'lookup', parameters: { type: 'object' } },
-                cache_control: { type: 'ephemeral' },
-                defer_loading: true,
-                eager_input_streaming: true,
-                input_examples: [{}],
-            },
-        ];
-        expect(make_openai_tools(tools)).toEqual([
-            {
-                type: 'function',
-                function: { name: 'lookup', parameters: { type: 'object' } },
-            },
-        ]);
-    });
-
-    it('drops an Anthropic web_search tool on the chat dialect', () => {
-        const tools = [{ type: 'web_search_20250305', name: 'web_search' }];
-        expect(make_openai_tools(tools, { dialect: 'chat' })).toEqual([]);
-    });
-
-    it('converts an Anthropic web_search tool to OpenAI web_search on the responses dialect', () => {
-        const tools = [
-            {
-                type: 'web_search_20250305',
-                name: 'web_search',
-                max_uses: 5,
-                allowed_domains: ['example.com'],
-                user_location: { type: 'approximate' },
-            },
-        ];
-        expect(
-            make_openai_tools(tools, { dialect: 'responses' }),
-        ).toEqual([
-            {
-                type: 'web_search',
-                filters: { allowed_domains: ['example.com'] },
-                user_location: { type: 'approximate' },
-            },
-        ]);
-    });
-
-    it('keeps OpenAI web_search/web_search_preview tools verbatim', () => {
-        const tools = [{ type: 'web_search' }, { type: 'web_search_preview' }];
-        expect(make_openai_tools(tools, { dialect: 'responses' })).toEqual(
-            tools,
-        );
-    });
-
-    it('drops other Anthropic typed/server tools (advisor, bash, …)', () => {
-        const tools = [
-            { type: 'advisor_20260301', model: 'claude-haiku-4-5' },
-            { type: 'bash_20250124', name: 'bash' },
-        ];
-        expect(make_openai_tools(tools, { dialect: 'responses' })).toEqual([]);
-    });
-
-    it('passes a falsy tools value through unchanged', () => {
-        expect(make_openai_tools(undefined)).toBeUndefined();
-        expect(make_openai_tools(null)).toBeNull();
-    });
-});
-
-describe('make_claude_tools with a malformed tool', () => {
-    it.each([
-        ['type:function with no function property', { type: 'function' }],
-        ['a null entry', null],
-        ['a bare string entry', 'lookup'],
-    ])('answers 400 for a tool with %s', (_label, tool) => {
-        // A TypeError here has no status, so the retry loop reads it as a
-        // provider failure and marks the route unhealthy for every caller.
-        expect(() => make_claude_tools([tool] as never)).toThrowError(
-            expect.objectContaining({
-                statusCode: 400,
-                legacyCode: 'bad_request',
-            }),
-        );
-    });
-
-    it('answers 400 for an unresolvable advisor model', () => {
-        expect(() =>
-            make_claude_tools([
-                { type: 'advisor_20260301', model: 'not-a-real-model' },
-            ] as never),
-        ).toThrowError(
-            expect.objectContaining({ statusCode: 400, legacyCode: 'bad_request' }),
-        );
-    });
-
-    it('answers 400 for an mcp_toolset tool', () => {
-        expect(() =>
-            make_claude_tools([{ type: 'mcp_toolset' }] as never),
-        ).toThrowError(
-            expect.objectContaining({ statusCode: 400, legacyCode: 'bad_request' }),
-        );
-    });
-});
-
-// ── make_claude_tools ───────────────────────────────────────────────
-
-describe('make_claude_tools', () => {
-    it('returns undefined when tools is undefined', () => {
-        expect(make_claude_tools(undefined)).toBeUndefined();
-    });
-
-    it('returns [] when tools is an empty array', () => {
-        expect(make_claude_tools([])).toEqual([]);
-    });
-
-    it('flattens the OpenAI {function:{...}} wrapper into Claude shape', () => {
-        const out = make_claude_tools([
-            {
-                type: 'function',
-                function: {
-                    name: 'lookup',
-                    description: 'Search the docs',
-                    parameters: {
-                        type: 'object',
-                        properties: { q: { type: 'string' } },
-                    },
-                },
-            },
-        ]);
-        expect(out).toEqual([
-            {
-                name: 'lookup',
-                description: 'Search the docs',
-                input_schema: {
-                    type: 'object',
-                    properties: { q: { type: 'string' } },
-                },
-            },
-        ]);
-    });
-
-    it('maps the OpenAI {type:"web_search"} form to web_search_20250305', () => {
-        const out = make_claude_tools([{ type: 'web_search' }] as never);
-        expect(out).toEqual([
-            { type: 'web_search_20250305', name: 'web_search', max_uses: 10 },
-        ]);
-    });
-
-    it('passes a typed server tool through by its own regexp-matched type', () => {
-        const out = make_claude_tools([
-            { type: 'bash_20250124', name: 'bash' },
-        ] as never);
-        expect(out).toEqual([{ type: 'bash_20250124', name: 'bash' }]);
-    });
-});

src/backend/drivers/ai/interfaces/chat/utils/Messages.js

@@ -18,6 +18,7 @@
  */
 
 import { HttpError } from '@heyputer/backend/src/core/http';
+import { convertsToText } from '../../../shared/scalarOptions.js';
 
 /**
  * Normalizes a single message into a standardized format with role and content
@@ -154,6 +155,39 @@ export const normalize_single_message = (message, params = {}) => {
         }
     }
 
+    // Providers write a block's type and a tool call's id into text, which
+    // throws on a value that can't be converted.
+    for (const block of message.content) {
+        if (!convertsToText(block.type)) {
+            throw new HttpError(
+                400,
+                'each message content item type must be a string',
+                { legacyCode: 'bad_request' },
+            );
+        }
+        const callId =
+            block.type === 'tool_use'
+                ? block.id
+                : block.type === 'tool_result'
+                  ? block.tool_use_id
+                  : undefined;
+        if (!convertsToText(callId)) {
+            throw new HttpError(400, 'a tool call id must be a string', {
+                legacyCode: 'bad_request',
+            });
+        }
+        // A tool's result is text or content blocks; any other object is sent
+        // as its JSON, like the content of a `tool` message above.
+        if (
+            block.type === 'tool_result' &&
+            block.content &&
+            typeof block.content === 'object' &&
+            !Array.isArray(block.content)
+        ) {
+            block.content = JSON.stringify(block.content);
+        }
+    }
+
     // Remove "text" properties from content blocks with type=tool_use
     for (let i = 0; i < message.content.length; i++) {
         if (message.content[i].type !== 'tool_use') {

src/backend/drivers/ai/interfaces/chat/utils/Messages.test.ts

@@ -449,3 +449,106 @@ describe('extract_text', () => {
         ).toThrow(expect.objectContaining({ statusCode: 400 }));
     });
 });
+
+describe('normalize_single_message block validation', () => {
+    it.each([
+        [
+            'an assistant tool call',
+            {
+                role: 'assistant',
+                tool_calls: [
+                    { id: { toString: null }, function: { name: 'f', arguments: '{}' } },
+                ],
+            },
+        ],
+        [
+            'a tool_use block',
+            {
+                role: 'assistant',
+                content: [
+                    {
+                        type: 'tool_use',
+                        id: { toString: null },
+                        name: 'f',
+                        input: {},
+                    },
+                ],
+            },
+        ],
+        [
+            'a tool message',
+            { role: 'tool', tool_call_id: [{ toString: null }], content: 'ok' },
+        ],
+        [
+            'a tool_result block',
+            {
+                role: 'user',
+                content: [
+                    {
+                        type: 'tool_result',
+                        tool_use_id: { toString: null },
+                        content: 'ok',
+                    },
+                ],
+            },
+        ],
+    ])('rejects a tool call id that cannot be text on %s', (_label, message) => {
+        expect(() => normalize_single_message(message)).toThrow(
+            expect.objectContaining({
+                statusCode: 400,
+                message: 'a tool call id must be a string',
+            }),
+        );
+    });
+
+    it('keeps a numeric tool call id as the caller sent it', () => {
+        const message = normalize_single_message({
+            role: 'assistant',
+            content: [{ type: 'tool_use', id: 7, name: 'f', input: {} }],
+        });
+        expect(message.content[0].id).toBe(7);
+    });
+
+    it('keeps a tool call that has no id', () => {
+        const message = normalize_single_message({
+            role: 'assistant',
+            tool_calls: [{ function: { name: 'f', arguments: '{}' } }],
+        });
+        expect(message.content).toEqual([
+            { type: 'tool_use', id: undefined, name: 'f', input: '{}' },
+        ]);
+    });
+
+    it('rejects a content item whose type cannot be text', () => {
+        expect(() =>
+            normalize_single_message({
+                role: 'user',
+                content: [{ type: { toString: null }, text: 'hi' }],
+            }),
+        ).toThrow(
+            expect.objectContaining({
+                statusCode: 400,
+                message: 'each message content item type must be a string',
+            }),
+        );
+    });
+
+    it('sends an object tool result as its JSON', () => {
+        const message = normalize_single_message({
+            role: 'user',
+            content: [
+                { type: 'tool_result', tool_use_id: 't1', content: { temp: 21 } },
+            ],
+        });
+        expect(message.content[0].content).toBe('{"temp":21}');
+    });
+
+    it('keeps a tool result made of content blocks', () => {
+        const blocks = [{ type: 'text', text: 'Sunny' }];
+        const message = normalize_single_message({
+            role: 'user',
+            content: [{ type: 'tool_result', tool_use_id: 't1', content: blocks }],
+        });
+        expect(message.content[0].content).toEqual(blocks);
+    });
+});

src/backend/drivers/ai/interfaces/chat/utils/compaction.js

@@ -18,20 +18,21 @@
  */
 
 /**
- * Inline-compaction translation helpers.
+ * Inline-compaction opt-in helpers.
  *
  * The driver-facing surface exposes a single provider-neutral opt-in
  * (`compaction: boolean | { trigger_tokens }` on `ICompleteArguments`), plus a
  * raw `context_management` escape hatch for callers hitting `/responses` with
- * the OpenAI-native shape. These helpers map that neutral opt-in to each
- * provider's SDK shape so the providers stay free of opt-in-parsing logic.
+ * the OpenAI-native shape. This module reads the opt-in; each dialect maps it
+ * to its own SDK shape (`toOpenAiContextManagement` in the OpenAI protocol,
+ * `toAnthropicContextManagement` in the Claude provider).
  */
 
 /**
  * @param {boolean | { trigger_tokens?: number } | undefined} compaction
  * @returns {{ enabled: boolean; trigger_tokens?: number }}
  */
-const readCompaction = (compaction) => {
+export const readCompaction = (compaction) => {
     if (compaction === true) return { enabled: true };
     if (compaction && typeof compaction === 'object') {
         return {
@@ -44,65 +45,6 @@ const readCompaction = (compaction) => {
     return { enabled: false };
 };
 
-/**
- * Build OpenAI Responses `context_management` from the neutral opt-in. A raw
- * `context_management` passthrough (already in OpenAI shape) wins.
- *
- * @param {{
- *     compaction?: boolean | { trigger_tokens?: number };
- *     context_management?: unknown;
- * }} args
- * @returns {{ type: 'compaction'; compact_threshold?: number }[] | undefined}
- */
-export const toOpenAiContextManagement = (args) => {
-    if (args.context_management !== undefined) {
-        return /** @type {any} */ (args.context_management);
-    }
-    const { enabled, trigger_tokens } = readCompaction(args.compaction);
-    if (!enabled) return undefined;
-    return [
-        {
-            type: 'compaction',
-            ...(trigger_tokens !== undefined
-                ? { compact_threshold: trigger_tokens }
-                : {}),
-        },
-    ];
-};
-
-/**
- * Build Anthropic `context_management` (beta `compact-2026-01-12`) from the
- * neutral opt-in. A raw `context_management` passthrough wins.
- *
- * @param {{
- *     compaction?: boolean | { trigger_tokens?: number };
- *     context_management?: unknown;
- * }} args
- * @returns {{ edits: Record<string, unknown>[] } | undefined}
- */
-export const toAnthropicContextManagement = (args) => {
-    if (args.context_management !== undefined) {
-        return /** @type {any} */ (args.context_management);
-    }
-    const { enabled, trigger_tokens } = readCompaction(args.compaction);
-    if (!enabled) return undefined;
-    return {
-        edits: [
-            {
-                type: 'compact_20260112',
-                ...(trigger_tokens !== undefined
-                    ? {
-                          trigger: {
-                              type: 'input_tokens',
-                              value: trigger_tokens,
-                          },
-                      }
-                    : {}),
-            },
-        ],
-    };
-};
-
 /**
  * Whether the request opted into inline compaction by any route.
  *

src/backend/drivers/ai/interfaces/chat/utils/compaction.test.ts

@@ -0,0 +1,62 @@
+/*
+ * Copyright (C) 2024-present Puter Technologies Inc.
+ *
+ * This file is part of Puter.
+ *
+ * Puter is free software: you can redistribute it and/or modify
+ * it under the terms of the GNU Affero General Public License as published
+ * by the Free Software Foundation, either version 3 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU Affero General Public License for more details.
+ *
+ * You should have received a copy of the GNU Affero General Public License
+ * along with this program.  If not, see <https://www.gnu.org/licenses/>.
+ */
+
+import { describe, expect, it } from 'vitest';
+import { messagesHaveCompaction, wantsCompaction } from './compaction.js';
+
+describe('wantsCompaction', () => {
+    it('is false without opt-in', () => {
+        expect(wantsCompaction({})).toBe(false);
+        expect(wantsCompaction({ compaction: false })).toBe(false);
+    });
+
+    it('is true for the neutral opt-in or a raw passthrough', () => {
+        expect(wantsCompaction({ compaction: true })).toBe(true);
+        expect(wantsCompaction({ compaction: { trigger_tokens: 1 } })).toBe(
+            true,
+        );
+        expect(wantsCompaction({ context_management: [] })).toBe(true);
+    });
+});
+
+describe('messagesHaveCompaction', () => {
+    it('detects a round-tripped compaction content block', () => {
+        expect(
+            messagesHaveCompaction([
+                { role: 'user', content: [{ type: 'text', text: 'hi' }] },
+                {
+                    role: 'assistant',
+                    content: [
+                        { type: 'compaction', encrypted_content: 'ENC' },
+                    ],
+                },
+            ]),
+        ).toBe(true);
+    });
+
+    it('is false for ordinary messages or non-arrays', () => {
+        expect(
+            messagesHaveCompaction([
+                { role: 'user', content: [{ type: 'text', text: 'hi' }] },
+            ]),
+        ).toBe(false);
+        expect(messagesHaveCompaction(undefined)).toBe(false);
+        expect(messagesHaveCompaction('nope')).toBe(false);
+    });
+});

src/backend/drivers/ai/interfaces/chat/utils/mediaParts.ts

@@ -40,7 +40,7 @@ type Part = Record<string, unknown>;
 const isObject = (value: unknown): value is Part =>
     !!value && typeof value === 'object' && !Array.isArray(value);
 
-export { parseDataUri } from '../../util/dataUri.js';
+export { parseDataUri } from '../../../../util/dataUri.js';
 
 /** The URL out of a bare string or an OpenAI-style `{ url }` object. */
 export const mediaUrlOf = (value: unknown): string | undefined => {

src/backend/drivers/ai/interfaces/chat/utils/meterChatUsage.test.ts

@@ -18,19 +18,19 @@
  */
 
 import { describe, expect, it } from 'vitest';
-import type { Actor } from '../../../core/actor.js';
-import { ALIBABA_MODELS } from '../providers/alibaba/models.js';
-import { BYTEPLUS_MODELS } from '../providers/byteplus/models.js';
-import { DEEPSEEK_MODELS } from '../providers/deepseek/models.js';
-import { GROQ_MODELS } from '../providers/groq/models.js';
-import { HOONIFY_MODELS } from '../providers/hoonify/models.js';
-import { MINIMAX_MODELS } from '../providers/minimax/models.js';
-import { MISTRAL_MODELS } from '../providers/mistral/models.js';
-import { MOONSHOT_MODELS } from '../providers/moonshot/models.js';
-import { ZAI_MODELS } from '../providers/zai/models.js';
+import type { Actor } from '../../../../../core/actor.js';
+import { ALIBABA_MODELS } from '../../../providers/alibaba/chat/models.js';
+import { BYTEPLUS_MODELS } from '../../../providers/byteplus/chat/models.js';
+import { DEEPSEEK_MODELS } from '../../../providers/deepseek/chat/models.js';
+import { GROQ_MODELS } from '../../../providers/groq/chat/models.js';
+import { HOONIFY_MODELS } from '../../../providers/hoonify/chat/models.js';
+import { MINIMAX_MODELS } from '../../../providers/minimax/chat/models.js';
+import { MISTRAL_MODELS } from '../../../providers/mistral/chat/models.js';
+import { MOONSHOT_MODELS } from '../../../providers/moonshot/chat/models.js';
+import { ZAI_MODELS } from '../../../providers/zai/chat/models.js';
 import type { IChatModel } from '../types.js';
 import { meterChatUsage } from './meterChatUsage.js';
-import { splitCachedPrompt } from './OpenAIUtil.js';
+import { splitCachedPrompt } from '../../../protocols/openaiCompatible/OpenAIUtil.js';
 import { usageCost } from './pricing.js';
 
 type Recorded = [Record<string, number>, string, Record<string, number>];

src/backend/drivers/ai/interfaces/chat/utils/meterChatUsage.ts

@@ -17,8 +17,8 @@
  * along with this program.  If not, see <https://www.gnu.org/licenses/>.
  */
 
-import type { Actor } from '../../../core/actor.js';
-import type { MeteringService } from '../../../services/metering/MeteringService.js';
+import type { Actor } from '../../../../../core/actor.js';
+import type { MeteringService } from '../../../../../services/metering/MeteringService.js';
 import type { IChatModel, ServiceSpeed } from '../types.js';
 import { serviceSpeedBillingModel } from './serviceSpeed.js';
 import { buildCostsOverride } from './pricing.js';

src/backend/drivers/ai/interfaces/chat/utils/modelRouting.test.ts

@@ -19,7 +19,7 @@
  */
 
 import { describe, expect, it } from 'vitest';
-import { GEMINI_MODELS } from '../providers/gemini/models.js';
+import { GEMINI_MODELS } from '../../../providers/gemini/chat/models.js';
 import type { IChatModel } from '../types.js';
 import {
     compareModelPreference,

src/backend/drivers/ai/interfaces/chat/utils/pricing.test.ts

@@ -21,7 +21,6 @@ import { describe, expect, it } from 'vitest';
 import type { IChatModel } from '../types.js';
 import {
     buildCostsOverride,
-    catalogPrice,
     costsForRequest,
     isFreeModel,
     isOutputCostKey,
@@ -480,12 +479,6 @@ it('preserves free classification for legacy hyphenated token keys', () => {
     expect(isFreeModel(model({ 'input-tokens': 0, 'output-tokens': 0 }))).toBe(true);
 });
 
-it('leaves overflowing catalog unit conversions unknown', () => {
-    expect(catalogPrice(1e308, 100)).toBeUndefined();
-    expect(catalogPrice(0, 100)).toBe(0);
-    expect(catalogPrice('0.0000000014', 100_000_000)).toBeCloseTo(0.14);
-});
-
 describe('costsForRequest prompt-size overrides', () => {
     const model = (minPromptTokensInclusive?: boolean): IChatModel => ({
         id: 'tiered',

src/backend/drivers/ai/interfaces/chat/utils/pricing.ts

@@ -23,29 +23,7 @@ import type {
     ModelPricingOverride,
     UsageDetails,
 } from '../types.js';
-
-/**
- * Absent, negative and placeholder prices remain unpriced, including empty
- * strings.
- */
-export const catalogPrice = (
-    value: unknown,
-    multiplier = 1,
-): number | undefined => {
-    if (typeof value !== 'number' && typeof value !== 'string')
-        return undefined;
-    if (
-        typeof value === 'string' &&
-        !/^(?:\d+(?:\.\d*)?|\.\d+)(?:e[+-]?\d+)?$/i.test(value.trim())
-    )
-        return undefined;
-    const price = Number(value);
-    if (!Number.isFinite(price) || price < 0) return undefined;
-    const converted = price * multiplier;
-    return Number.isFinite(converted) && !(price > 0 && converted === 0)
-        ? converted
-        : undefined;
-};
+import { catalogPrice } from '../../../shared/catalogPrice.js';
 
 const CENTS_PER_USD = 100;
 const MTOK = 1_000_000;
@@ -360,7 +338,8 @@ export const buildCostsOverride = (
  * What a usage object costs in µ¢, split into its input and output sides.
  * `recordedCosts` are the per-key costs a provider already metered with and win
  * over the model's rates, so the figure matches the ledger. Null when nothing
- * in the usage could be priced. `now` is the instant the request was priced at.
+ * in the usage could be priced. `now` is the instant the request was priced
+ * at.
  */
 export const usageCost = (
     usage: Record<string, unknown>,

src/backend/drivers/ai/interfaces/chat/utils/providerHealth.test.ts

@@ -19,7 +19,7 @@
  */
 
 import { afterEach, describe, expect, it } from 'vitest';
-import { kv } from '../../../util/kvSingleton.js';
+import { kv } from '../../../../../util/kvSingleton.js';
 import {
     clearUnhealthyRoutes,
     isRouteUnhealthy,

src/backend/drivers/ai/interfaces/chat/utils/providerHealth.ts

@@ -30,7 +30,7 @@
  * blip doesn't hand the model's traffic to a reseller for long.
  */
 
-import { kv } from '../../../util/kvSingleton.js';
+import { kv } from '../../../../../util/kvSingleton.js';
 
 /**
  * How long a route stays marked after a failure that won't heal on its own,

src/backend/drivers/ai/interfaces/chat/utils/serviceSpeed.fuzz.test.ts

@@ -19,21 +19,21 @@
 
 import { describe, expect, it } from 'vitest';
 import type { IChatModel, ServiceSpeed } from '../types.js';
-import { ALIBABA_MODELS } from '../providers/alibaba/models.js';
-import { AZURE_MODELS } from '../providers/azure/models.js';
-import { BYTEPLUS_MODELS } from '../providers/byteplus/models.js';
-import { CLAUDE_MODELS } from '../providers/claude/models.js';
-import { DEEPSEEK_MODELS } from '../providers/deepseek/models.js';
-import { GEMINI_MODELS } from '../providers/gemini/models.js';
-import { GROQ_MODELS } from '../providers/groq/models.js';
-import { HOONIFY_MODELS } from '../providers/hoonify/models.js';
-import { META_MODELS } from '../providers/meta/models.js';
-import { MINIMAX_MODELS } from '../providers/minimax/models.js';
-import { MISTRAL_MODELS } from '../providers/mistral/models.js';
-import { MOONSHOT_MODELS } from '../providers/moonshot/models.js';
-import { OPEN_AI_MODELS } from '../providers/openai/models.js';
-import { XAI_MODELS } from '../providers/xai/models.js';
-import { ZAI_MODELS } from '../providers/zai/models.js';
+import { ALIBABA_MODELS } from '../../../providers/alibaba/chat/models.js';
+import { AZURE_MODELS } from '../../../providers/azure/chat/models.js';
+import { BYTEPLUS_MODELS } from '../../../providers/byteplus/chat/models.js';
+import { CLAUDE_MODELS } from '../../../providers/claude/chat/models.js';
+import { DEEPSEEK_MODELS } from '../../../providers/deepseek/chat/models.js';
+import { GEMINI_MODELS } from '../../../providers/gemini/chat/models.js';
+import { GROQ_MODELS } from '../../../providers/groq/chat/models.js';
+import { HOONIFY_MODELS } from '../../../providers/hoonify/chat/models.js';
+import { META_MODELS } from '../../../providers/meta/chat/models.js';
+import { MINIMAX_MODELS } from '../../../providers/minimax/chat/models.js';
+import { MISTRAL_MODELS } from '../../../providers/mistral/chat/models.js';
+import { MOONSHOT_MODELS } from '../../../providers/moonshot/chat/models.js';
+import { OPEN_AI_MODELS } from '../../../providers/openai/chat/models.js';
+import { XAI_MODELS } from '../../../providers/xai/chat/models.js';
+import { ZAI_MODELS } from '../../../providers/zai/chat/models.js';
 import { shouldPresentAsOpenAI } from './normalizeToOpenAI.js';
 import {
     isServiceSpeedUnavailable,

src/backend/drivers/ai/interfaces/chat/utils/serviceSpeed.integration.test.ts

@@ -20,19 +20,19 @@
 import { describe, expect, it } from 'vitest';
 import {
     makeMeteringStub,
-    optionalEnv,
     withTestActor,
-} from '../../integrationTestUtil.js';
+} from '../../../shared/integrationTestUtil.js';
+import { optionalEnv } from '../../../../../testEnv.js';
 import type {
     IChatMessageResult,
     IChatProvider,
     ICompleteArguments,
 } from '../types.js';
-import { OpenAiResponsesChatProvider } from '../providers/openai/OpenAiChatResponsesProvider.js';
-import { GeminiChatProvider } from '../providers/gemini/GeminiChatProvider.js';
-import { MiniMaxProvider } from '../providers/minimax/MiniMaxProvider.js';
-import { MoonshotProvider } from '../providers/moonshot/MoonshotProvider.js';
-import { MistralAIProvider } from '../providers/mistral/MistralAiProvider.js';
+import { OpenAiResponsesChatProvider } from '../../../providers/openai/chat/OpenAiChatResponsesProvider.js';
+import { GeminiChatProvider } from '../../../providers/gemini/chat/GeminiChatProvider.js';
+import { MiniMaxProvider } from '../../../providers/minimax/chat/MiniMaxProvider.js';
+import { MoonshotProvider } from '../../../providers/moonshot/chat/MoonshotProvider.js';
+import { MistralAIProvider } from '../../../providers/mistral/chat/MistralAiProvider.js';
 import { selectServiceSpeed } from './serviceSpeed.js';
 
 type Case = {

src/backend/drivers/ai/interfaces/chat/utils/serviceSpeed.test.ts

@@ -23,7 +23,7 @@ import { AIChatStream } from './Streaming.js';
 import {
     handle_completion_output,
     handle_completion_output_responses_api,
-} from './OpenAIUtil.js';
+} from '../../../protocols/openaiCompatible/OpenAIUtil.js';
 import type { IChatModel, ServiceSpeed } from '../types.js';
 import {
     requestedServiceSpeed,
@@ -33,10 +33,10 @@ import {
     isServiceSpeedUnavailable,
 } from './serviceSpeed.js';
 import { meterChatUsage } from './meterChatUsage.js';
-import { OPEN_AI_MODELS } from '../providers/openai/models.js';
-import { XAI_MODELS } from '../providers/xai/models.js';
-import { GEMINI_MODELS } from '../providers/gemini/models.js';
-import { CLAUDE_MODELS } from '../providers/claude/models.js';
+import { OPEN_AI_MODELS } from '../../../providers/openai/chat/models.js';
+import { XAI_MODELS } from '../../../providers/xai/chat/models.js';
+import { GEMINI_MODELS } from '../../../providers/gemini/chat/models.js';
+import { CLAUDE_MODELS } from '../../../providers/claude/chat/models.js';
 
 const model = (provider: string, id: string): IChatModel => ({
     provider,

src/backend/drivers/ai/interfaces/chat/utils/usageEstimate.test.ts

@@ -216,6 +216,24 @@ describe('estimatePromptTokens', () => {
     });
 });
 
+describe('estimatePromptTokens compaction blocks', () => {
+    const withCompaction = (encrypted_content: unknown) => [
+        { role: 'assistant', content: [{ type: 'compaction', encrypted_content }] },
+    ];
+
+    it('counts the encrypted content as text', () => {
+        expect(estimatePromptTokens(withCompaction('a'.repeat(400)))).toBe(
+            estimateTextTokens('a'.repeat(400)),
+        );
+    });
+
+    it('counts content that is not a string by its JSON', () => {
+        expect(
+            estimatePromptTokens(withCompaction({ toString: null, blob: 'abcdefgh' })),
+        ).toBe(estimateTextTokens('{"toString":null,"blob":"abcdefgh"}'));
+    });
+});
+
 describe('estimateToolTokens', () => {
     it('is zero for no tools', () => {
         expect(estimateToolTokens(undefined)).toBe(0);

src/backend/drivers/ai/interfaces/chat/utils/usageEstimate.ts

@@ -33,10 +33,10 @@ import {
     createWordScanBudget,
     estimateTextTokens,
     type WordScanBudget,
-} from '../../util/tokenEstimate.js';
+} from '../../../shared/tokenEstimate.js';
 
 // Re-exported so existing consumers keep one import site for all estimators.
-export { estimateTextTokens } from '../../util/tokenEstimate.js';
+export { estimateTextTokens } from '../../../shared/tokenEstimate.js';
 
 /** Tokens per byte of an inline (base64) attachment; see `attachmentTokens`. */
 const ATTACHMENT_BYTES_PER_TOKEN = 150;
@@ -154,7 +154,12 @@ const partTokens = (part: unknown, budget: WordScanBudget): number => {
         );
     }
     if (p.type === 'compaction') {
-        return estimateTextTokens(String(p.encrypted_content ?? ''), budget);
+        return estimateTextTokens(
+            typeof p.encrypted_content === 'string'
+                ? p.encrypted_content
+                : JSON.stringify(p.encrypted_content ?? ''),
+            budget,
+        );
     }
 
     return UNMEASURED_ATTACHMENT_TOKENS;

src/backend/drivers/ai/interfaces/image/ImageGenerationDriver.test.ts

@@ -41,23 +41,22 @@ import {
 } from 'vitest';
 
 import { v4 as uuidv4 } from 'uuid';
-import { runWithContext } from '../../core/context.js';
-import { type Actor, SYSTEM_ACTOR } from '../../core/actor.js';
-import { PuterServer } from '../../server.js';
-import { setupTestServer } from '../../testUtil.js';
-import { withAiCostFactorHook } from '../integrationTestUtil.js';
-import { generateDefaultFsentries } from '../../util/userProvisioning.js';
-import { CLOUDFLARE_IMAGE_GENERATION_MODELS } from './providers/cloudflare/models.js';
-import cloudflareModelSearchFixture from './providers/cloudflare/fixtures/model-search.json';
-import { GEMINI_IMAGE_GENERATION_MODELS } from './providers/gemini/models.js';
-import { OPEN_AI_IMAGE_GENERATION_MODELS } from './providers/openai/models.js';
-import { REPLICATE_IMAGE_GENERATION_MODELS } from './providers/replicate/models.js';
-import { TOGETHER_IMAGE_GENERATION_MODELS } from './providers/together/models.js';
-import { XAI_IMAGE_GENERATION_MODELS } from './providers/xai/models.js';
-import xaiLiveCatalog from './providers/xai/fixtures/image-generation-models.json';
+import { runWithContext } from '../../../../core/context.js';
+import { type Actor, SYSTEM_ACTOR } from '../../../../core/actor.js';
+import { PuterServer } from '../../../../server.js';
+import { setupTestServer, withAiCostFactorHook } from '../../../../testUtil.js';
+import { generateDefaultFsentries } from '../../../../util/userProvisioning.js';
+import { CLOUDFLARE_IMAGE_GENERATION_MODELS } from '../../providers/cloudflare/image/models.js';
+import cloudflareModelSearchFixture from '../../providers/cloudflare/image/fixtures/model-search.json';
+import { GEMINI_IMAGE_GENERATION_MODELS } from '../../providers/gemini/image/models.js';
+import { OPEN_AI_IMAGE_GENERATION_MODELS } from '../../providers/openai/image/models.js';
+import { REPLICATE_IMAGE_GENERATION_MODELS } from '../../providers/replicate/image/models.js';
+import { TOGETHER_IMAGE_GENERATION_MODELS } from '../../providers/together/image/models.js';
+import { XAI_IMAGE_GENERATION_MODELS } from '../../providers/xai/image/models.js';
+import xaiLiveCatalog from '../../providers/xai/image/fixtures/image-generation-models.json';
 import { ImageGenerationDriver } from './ImageGenerationDriver.js';
-import { CATALOG_TTL_MS } from '../ai-chat/utils/cachedRemoteCatalog.js';
-import { ReplicateImageGenerationProvider } from './providers/replicate/ReplicateImageGenerationProvider.js';
+import { CATALOG_TTL_MS } from '../../shared/cachedRemoteCatalog.js';
+import { ReplicateImageGenerationProvider } from '../../providers/replicate/image/ReplicateImageGenerationProvider.js';
 
 // ── SDK mocks ──────────────────────────────────────────────────────
 //
@@ -141,8 +140,8 @@ vi.mock('replicate', () => {
 
 const { secureFetchMock } = vi.hoisted(() => ({ secureFetchMock: vi.fn() }));
 
-vi.mock('../../util/secureHttp.js', async (importOriginal) => ({
-    ...(await importOriginal<typeof import('../../util/secureHttp.js')>()),
+vi.mock('../../../../util/secureHttp.js', async (importOriginal) => ({
+    ...(await importOriginal<typeof import('../../../../util/secureHttp.js')>()),
     secureFetch: secureFetchMock,
 }));
 
@@ -483,6 +482,33 @@ describe('ImageGenerationDriver.generate provider routing', () => {
         },
     );
 
+    it('rejects an input image type that is not a string before any provider runs', async () => {
+        await expect(withActor(() =>
+            driver.generate({
+                model: 'gpt-image-2',
+                prompt: 'make it blue',
+                input_image: 'data:image/png;base64,aGVsbG8=',
+                input_image_mime_type: 5,
+            } as never),
+        )).rejects.toMatchObject({
+            statusCode: 400,
+            message: 'input_image_mime_type must be a string',
+        });
+    });
+
+    it('ignores an input image type that is not a string when there is no input image', async () => {
+        openaiImagesGenerateMock.mockResolvedValueOnce({
+            data: [{ url: 'https://oai/image.png' }],
+        });
+        await expect(withDriverName('ai-image', () =>
+            driver.generate({
+                model: 'gpt-image-2',
+                prompt: 'a landscape',
+                input_image_mime_type: 5,
+            } as never),
+        )).resolves.toBe('https://oai/image.png');
+    });
+
     it('rejects an excluded model regardless of caller casing', async () => {
         await expect(withActor(() =>
             driver.generate({
@@ -1273,7 +1299,7 @@ describe('ImageGenerationDriver.generate audit log', () => {
 // ── puter_output_path ─────────────────────────────────────────────
 
 describe('ImageGenerationDriver.generate puter_output_path', () => {
-    const TEST_ACTOR: import('../../core/actor.js').Actor = {
+    const TEST_ACTOR: import('../../../../core/actor.js').Actor = {
         user: { uuid: 'a1b2c3d4-e5f6-4a7b-8c9d-0e1f2a3b4c5d', id: 42, username: 'testuser' },
     };
 
@@ -1462,7 +1488,7 @@ describe('ImageGenerationDriver.generate puter_output_path', () => {
     });
 
     it('throws 400 when actor has no user ID but puter_output_path is set', async () => {
-        const noIdActor: import('../../core/actor.js').Actor = {
+        const noIdActor: import('../../../../core/actor.js').Actor = {
             user: { uuid: 'f0e1d2c3-b4a5-4968-8777-0a1b2c3d4e5f', username: 'noone' },
         };
         await expect(