v0.8.17: ci improvements, outdated docs i18n removal, desktop improvements

.agents/skills/add-column-type/SKILL.md

@@ -149,7 +149,7 @@ Registering the *type* is compiler-enforced. Registering its *metadata* is not,
 - [ ] `migrateCellsTo` / `migrateCellsFrom` added if the stored bytes change
 - [ ] New metadata keys added to `TYPE_SPECIFIC_COLUMN_KEYS` + `FOREIGN_METADATA_VERB`
 - [ ] Unit tests for `coerce` / `isCompatibleWith` round-trips, verified to fail without the code
-- [ ] Docs row added to `apps/docs/content/docs/en/tables/index.mdx`
+- [ ] Docs row added to `apps/docs/content/docs/tables/index.mdx`
 
 ## Final Validation (Required)
 

.agents/skills/add-integration/SKILL.md

@@ -576,7 +576,7 @@ bun run deployment-config:check
 bun run docs:check
 ```
 
-This creates `apps/docs/content/docs/en/integrations/{service}.mdx` — one page per service carrying the block's Actions and, if it has one, its Triggers section. Never hand-edit generated pages; the only editable region is the `{/* MANUAL-CONTENT */}` block (see `scripts/README.md`).
+This creates `apps/docs/content/docs/integrations/{service}.mdx` — one page per service carrying the block's Actions and, if it has one, its Triggers section. Never hand-edit generated pages; the only editable region is the `{/* MANUAL-CONTENT */}` block (see `scripts/README.md`).
 
 The docs generator refreshes `packages/deployment-config/src/integrations.json`, and the deployment
 config generator projects service-account provider IDs from that catalog plus the canonical OAuth

.agents/skills/add-model/SKILL.md

@@ -153,7 +153,7 @@ If the entry has `capabilities.thinking` or `capabilities.reasoningEffort`, it a
 
 - **Anthropic-family (`anthropic`, `azure-anthropic`) thinking models MUST declare `capabilities.thinking.streamed`** (`'full' | 'summary' | 'none'`). Verify against Anthropic's current thinking-display and streaming docs: visible thinking returned by the API is summarized, including when Sim opts models whose default display is `omitted` into `display: 'summarized'` on agent-events runs, so current Claude thinking models use `'summary'`. Use `'full'` only if future official API docs explicitly guarantee raw thinking deltas. `bun run agent-stream-docs:check` (CI) fails if the field is missing.
 - Other families usually omit the field and inherit the provider default in `getThinkingStreamVisibility` (Gemini/OpenAI → summaries; Bedrock/Meta → none; OpenAI-compatible vendors with documented reasoning fields → full deltas). Set it explicitly only when the model deviates from its family.
-- After inserting the entry, run `bun run agent-stream-docs:generate` and commit the regenerated `apps/docs/content/docs/en/workflows/blocks/agent.mdx` — CI diffs it.
+- After inserting the entry, run `bun run agent-stream-docs:generate` and commit the regenerated `apps/docs/content/docs/workflows/blocks/agent.mdx` — CI diffs it.
 - Include the `streamed` value (with its source URL) in the verification report when set.
 
 ### Wrong family entirely?

.github/actions/docker-build/action.yml

@@ -21,10 +21,13 @@ inputs:
     required: true
   max-cache-size-mb:
     description: >-
-      Layer cache to retain after the post-job prune, in MB. Must stay above one
+      Layer cache to retain after this action prunes, in MB. Must stay above one
       build's working set (base + dependency layers + RUN --mount=type=cache
       dirs) or every build evicts what the next one needs. Falls back to the
-      small-image default below when empty.
+      small-image default in the prune step when empty — the fallback lives there
+      rather than here because callers pass this from a matrix field, and an unset
+      matrix key arrives as the empty string, which counts as "provided" and would
+      bypass an input `default:` entirely.
     required: false
 
 # Registry logins must precede this action. provenance/sbom stay off: attestation
@@ -49,24 +52,16 @@ runs:
         PLATFORMS: ${{ inputs.platforms }}
       run: echo "value=${GITHUB_REPOSITORY##*/}/${FILE#./}/${PLATFORMS//\//-}" >> "$GITHUB_OUTPUT"
 
-    # max-cache-size-mb is what bounds the disk: BuildKit's default GC is
-    # time-based only (layers unused for 8 days), and setup-docker-builder skips
-    # pruning altogether when the value is empty. On a repo that builds this
-    # often nothing ever ages out, so the disks grew without limit —
-    # app.Dockerfile/linux-amd64 reached 351 GB inside a day, and realtime, whose
-    # image is under 300 MB, sat at 249 GB. Sticky disks bill at ~$0.51/GB-month,
-    # so that was real money for layers no build would ever read again.
-    #
-    # The fallback is here rather than an input `default:` because callers pass
-    # this from a matrix field, and an unset matrix key arrives as the empty
-    # string — which counts as "provided", so a `default:` would never apply and
-    # a row that forgot the field would silently go back to unbounded growth.
+    # This action does NOT bound the disk — see the prune step below. BuildKit's
+    # own GC is time-based only (layers unused for 8 days), and these disks are
+    # mounted many times a day, so nothing ever ages out: app.Dockerfile/linux-amd64
+    # reached 351 GB inside a day of being created, and realtime, whose image is
+    # under 300 MB, sat at 249 GB. Sticky disks bill at ~$0.51/GB-month.
     - name: Set up Blacksmith builder
       if: inputs.provider == '' || inputs.provider == 'blacksmith'
       uses: useblacksmith/setup-docker-builder@a5256a73e30f09e37e3eceb8ca36043d17621d24 # v2
       with:
         cache-key: ${{ steps.cache-key.outputs.value }}
-        max-cache-size-mb: ${{ inputs.max-cache-size-mb || '25600' }}
 
     - name: Build and push (Blacksmith)
       if: inputs.provider == '' || inputs.provider == 'blacksmith'
@@ -80,6 +75,94 @@ runs:
         provenance: false
         sbom: false
 
+    # Bound the layer cache ourselves. setup-docker-builder v1 took a
+    # max-cache-size-mb input and pruned in its own post step, but the v2 rewrite
+    # dropped it — and GitHub only WARNS on an unknown composite input, so passing
+    # it to v2 silently did nothing for a day while the app disk sat at 200+ GB.
+    #
+    # This is v1's command verbatim (its dist/index.js pruneBuildkitCache), against
+    # the fixed address v2 itself uses for `buildctl du` and `debug workers`:
+    #   sudo buildctl --addr tcp://127.0.0.1:1234 prune --all --keep-storage <MB>
+    #
+    # Note buildctl's --all is NOT `docker buildx prune --all`. Here it means
+    # "include internal/frontend references" (cache/manager.go: without it, records
+    # typed internal or frontend, and any ref shared with an external source, are
+    # skipped). It does not wipe the cache, and --keep-storage still caps what is
+    # retained -- it maps straight onto the modern MaxUsedSpace field, so it is the
+    # buildctl spelling of --max-used-space rather than a deprecated alias.
+    # `RUN --mount=type=cache` dirs are typed exec.cachemount and are reclaimed
+    # either way; --all is here because it is what v1 used and it prunes strictly
+    # more. Runs before the builder's post step, which is what commits the disk.
+    #
+    # Warn rather than fail: a cache that is too large is not worth failing a
+    # deploy over. The du either side is what makes a silent no-op visible — the
+    # failure mode that hid the v2 input regression in the first place.
+    - name: Prune the layer cache
+      if: (inputs.provider == '' || inputs.provider == 'blacksmith') && !cancelled()
+      shell: bash
+      env:
+        KEEP_MB: ${{ inputs.max-cache-size-mb || '25600' }}
+      run: |
+        addr='tcp://127.0.0.1:1234'
+
+        # A zero or non-numeric value is NOT a no-op. buildctl parses
+        # --keep-storage as a float, and BuildKit's cache manager treats
+        # keepBytes==0 as "no cap" (`gcMode := opt.keepBytes != 0`), pruning
+        # everything eligible rather than trimming to a limit. A typo such as
+        # '40GB' — valid in turbo.json, but this flag is a bare MB number — would
+        # silently empty the cache and make every later build cold, costing far
+        # more than the storage it saves. Refuse instead.
+        if ! [[ "$KEEP_MB" =~ ^[1-9][0-9]*$ ]]; then
+          echo "::warning::max-cache-size-mb must be a positive whole number of MB, got '${KEEP_MB}' — skipping prune rather than risk wiping the cache"
+          exit 0
+        fi
+
+        # Print the whole Total line rather than picking a column: buildctl's du
+        # table is whitespace-aligned and its layout is not a stable contract.
+        #
+        # The trailing `|| true` is load-bearing. Composite steps run under
+        # `bash -e -o pipefail`, where `cur="$(total)"` takes the substitution's
+        # exit status, so a failing du would abort the step and fail the build --
+        # `echo "$(total)"` survives but the assignment in the settle loop does
+        # not. buildctl exiting non-zero here is entirely plausible: deleting a
+        # sticky disk out from under a running job makes buildkitd panic inside
+        # DiskUsage, and grep also exits 1 whenever the table has no Total line.
+        # Cache hygiene must never be able to fail a deploy.
+        total() { sudo buildctl --addr "$addr" du 2>/dev/null | grep -iE '^total:' | tr -s ' \t' ' ' || true; }
+        echo "before prune -> $(total)"
+
+        if sudo buildctl --addr "$addr" prune --all --keep-storage "$KEEP_MB"; then
+          # buildctl prune returns BEFORE buildkitd has finished deleting
+          # (moby/buildkit#1198). The builder's post step then SIGTERMs buildkitd
+          # and SIGKILLs it after 30s (shutdownBuildkitd: `const a=3e4`); on
+          # SIGKILL it sets sigkillUsed and SKIPS the sticky disk commit, throwing
+          # away this run's cache and risking a corrupt bbolt metadata DB. So wait
+          # for du to stop moving before handing back. Bounded — this is hygiene,
+          # not correctness, and the steady-state trim settles almost at once.
+          prev=''; stable=0
+          for _ in $(seq 1 60); do
+            cur="$(total)"
+            # An empty reading means du FAILED, never that the cache is empty:
+            # buildctl prints its `Total:` line unconditionally (cmd/buildctl
+            # diskusage.go), so an empty cache still reports `Total: 0B`. Without
+            # the -n guard the initial prev='' matched two empty readings and the
+            # loop exited after ~2s -- precisely when du is failing and the prune
+            # is most likely still deleting. Treat it as unstable and wait out the
+            # bound instead.
+            if [ -n "$cur" ] && [ "$cur" = "$prev" ]; then
+              stable=$((stable + 1))
+              [ "$stable" -ge 2 ] && break
+            else
+              stable=0
+            fi
+            prev="$cur"
+            sleep 2
+          done
+          echo "after prune  -> $(total)  (keep-storage ${KEEP_MB} MB)"
+        else
+          echo "::warning::Layer cache prune failed; this sticky disk is unbounded for this run"
+        fi
+
     - name: Set up Docker Buildx
       if: inputs.provider != '' && inputs.provider != 'blacksmith'
       uses: docker/setup-buildx-action@bb05f3f5519dd87d3ba754cc423b652a5edd6d2c # v4

.github/workflows/ci.yml

@@ -630,7 +630,7 @@ jobs:
         with:
           filters: |
             docs:
-              - 'apps/docs/content/docs/en/**'
+              - 'apps/docs/content/docs/**'
               - 'apps/sim/scripts/process-docs.ts'
               - 'apps/sim/lib/chunkers/**'
 

.gitignore

@@ -86,7 +86,6 @@ start-collector.sh
 
 ## Helm Chart Tests
 helm/sim/test
-i18n.cache
 
 ## Claude Code
 .claude/launch.json

apps/desktop/src/main/browser-agent/cdp.test.ts

@@ -548,6 +548,8 @@ describe('browser-agent screenshot capture', () => {
     expect(shot).toEqual({
       dataUrl: `data:image/jpeg;base64,${Buffer.from('resized').toString('base64')}`,
       scale: 0.5,
+      viewport: { width: 2048, height: 1024 },
+      imageSize: { width: 1024, height: 512 },
     })
   })
 
@@ -558,14 +560,115 @@ describe('browser-agent screenshot capture', () => {
 
     const image = vi.mocked(nativeImage.createFromBuffer).mock.results[0].value
     expect(image.resize).not.toHaveBeenCalled()
-    expect(shot).toEqual({ dataUrl: 'data:image/jpeg;base64,c2lt', scale: 0.5 })
+    expect(shot).toEqual({
+      dataUrl: 'data:image/jpeg;base64,c2lt',
+      scale: 0.5,
+      viewport: { width: 2048, height: 1024 },
+      imageSize: { width: 1024, height: 512 },
+    })
   })
 
   it('returns the raw capture when the image cannot be decoded', async () => {
     const { contents } = captureFixture(null)
 
     const shot = await captureScreenshot(contents)
 
-    expect(shot).toEqual({ dataUrl: 'data:image/jpeg;base64,c2lt', scale: 0.5 })
+    expect(shot).toEqual({
+      dataUrl: 'data:image/jpeg;base64,c2lt',
+      scale: 0.5,
+      viewport: { width: 2048, height: 1024 },
+      imageSize: null,
+    })
   })
+
+  it('does not expose deprecated device-pixel metrics as a CSS viewport', async () => {
+    const { contents } = captureFixture({ width: 1024, height: 512 })
+    vi.mocked(contents.debugger.sendCommand).mockImplementation((method: string) => {
+      if (method === 'Page.getLayoutMetrics') {
+        return Promise.resolve({ layoutViewport: { clientWidth: 2048, clientHeight: 1024 } })
+      }
+      if (method === 'Page.captureScreenshot') return Promise.resolve({ data: 'c2lt' })
+      return Promise.resolve(undefined)
+    })
+
+    const shot = await captureScreenshot(contents)
+
+    expect(shot.viewport).toBeNull()
+    expect(shot.imageSize).toEqual({ width: 1024, height: 512 })
+  })
+
+  it('accepts stable finite scroll offsets around the capture', async () => {
+    const { contents } = captureFixture({ width: 1024, height: 512 })
+    vi.mocked(contents.debugger.sendCommand).mockImplementation((method: string) => {
+      if (method === 'Page.getLayoutMetrics') {
+        return Promise.resolve({
+          cssLayoutViewport: {
+            clientWidth: 2048,
+            clientHeight: 1024,
+            pageX: 12,
+            pageY: 34,
+          },
+        })
+      }
+      if (method === 'Page.captureScreenshot') return Promise.resolve({ data: 'c2lt' })
+      return Promise.resolve(undefined)
+    })
+
+    await expect(captureScreenshot(contents)).resolves.toMatchObject({
+      viewport: { width: 2048, height: 1024 },
+      imageSize: { width: 1024, height: 512 },
+    })
+  })
+
+  it.each([
+    [
+      'dimensions',
+      { cssLayoutViewport: { clientWidth: 2048, clientHeight: 1024 } },
+      { cssLayoutViewport: { clientWidth: 1024, clientHeight: 512 } },
+    ],
+    [
+      'metric units',
+      { cssLayoutViewport: { clientWidth: 2048, clientHeight: 1024 } },
+      { layoutViewport: { clientWidth: 2048, clientHeight: 1024 } },
+    ],
+    [
+      'horizontal scroll offset',
+      { cssLayoutViewport: { clientWidth: 2048, clientHeight: 1024, pageX: 0, pageY: 20 } },
+      { cssLayoutViewport: { clientWidth: 2048, clientHeight: 1024, pageX: 10, pageY: 20 } },
+    ],
+    [
+      'vertical scroll offset',
+      { cssLayoutViewport: { clientWidth: 2048, clientHeight: 1024, pageX: 10, pageY: 20 } },
+      { cssLayoutViewport: { clientWidth: 2048, clientHeight: 1024, pageX: 10, pageY: 30 } },
+    ],
+    [
+      'offset validity',
+      { cssLayoutViewport: { clientWidth: 2048, clientHeight: 1024, pageX: 0, pageY: 0 } },
+      {
+        cssLayoutViewport: {
+          clientWidth: 2048,
+          clientHeight: 1024,
+          pageX: 0,
+          pageY: Number.NaN,
+        },
+      },
+    ],
+    ['availability', {}, {}],
+  ])(
+    'rejects a capture when viewport %s change during CDP capture',
+    async (_label, before, after) => {
+      const { contents } = captureFixture({ width: 1024, height: 512 })
+      let metricsRead = 0
+      vi.mocked(contents.debugger.sendCommand).mockImplementation((method: string) => {
+        if (method === 'Page.getLayoutMetrics') {
+          metricsRead++
+          return Promise.resolve(metricsRead === 1 ? before : after)
+        }
+        if (method === 'Page.captureScreenshot') return Promise.resolve({ data: 'c2lt' })
+        return Promise.resolve(undefined)
+      })
+
+      await expect(captureScreenshot(contents)).rejects.toThrow(/viewport changed/)
+    }
+  )
 })