Skip to content

Commit 7de0ad1

Browse files
fix(queue): reconcile edit holds with current queue UI
2 parents d8e9db9 + 7f2dcd8 commit 7de0ad1

1,599 files changed

Lines changed: 87652 additions & 29394 deletions

File tree

Some content is hidden

Large Commits have some content hidden by default. Use the searchbox below for content that may be hidden.

‎.coderabbit.config.ts‎

Lines changed: 6 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -26,13 +26,19 @@ export default defineConfig((ctx) => ({
2626
path: "apps/web/src/**/*.{tsx,css}",
2727
instructions: "Hold changed code to the rules in docs/internals/web-ui.md.",
2828
},
29+
{
30+
path: "**/*.test.*",
31+
instructions:
32+
"Hold changed tests to the rules in docs/internals/testing.md. Request tests only as those rules allow.",
33+
},
2934
],
3035
},
3136
knowledge_base: {
3237
code_guidelines: {
3338
filePatterns: [
3439
{ files: "docs/internals/effect-services.md", applyTo: "{apps,packages,infra}/**/*.ts" },
3540
{ files: "docs/internals/web-ui.md", applyTo: "apps/web/src/**/*.{tsx,css}" },
41+
{ files: "docs/internals/testing.md", applyTo: "{apps,packages,infra}/**/*.{ts,tsx}" },
3642
],
3743
},
3844
},

‎.github/scripts/ci-changes.cjs‎

Lines changed: 2 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -32,6 +32,8 @@ const RUST = /^native\/(resource-monitor|kde-snap-shot|hyprland-snap-shot)\//;
3232

3333
// These tests read other packages without declaring dependencies.
3434
const TEST_ONLY_DEPS = {
35+
// Evals import the server's source to test its real model-facing text.
36+
"@t3tools/evals": ["t3"],
3537
"@t3tools/provider-pi": ["@t3tools/client-runtime"],
3638
"@t3tools/scripts": [
3739
"@t3tools/desktop",

‎.github/triage/PLAYBOOK.md‎

Lines changed: 2 additions & 2 deletions
Original file line numberDiff line numberDiff line change
@@ -11,8 +11,8 @@ provided alongside this playbook. Everything machine-specific lives there, not h
1111

1212
## 1. Ask what went wrong
1313

14-
Your first message to the user: ask them to describe what went wrong, in their own
15-
words. Ask them to paste screenshots directly into this session if they have any.
14+
Unless the user already described it, your first message asks what went wrong, in
15+
their own words. Ask them to paste screenshots directly into this session if they have any.
1616
Ask follow-up questions when the description is vague. Good repro steps are the most
1717
valuable thing you can extract from this conversation.
1818

Lines changed: 55 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,55 @@
1+
name: Agent Context Budget
2+
3+
# Fails when a PR raises a value in agentContextBudget.json above main's. AgentContextBudget.test.ts
4+
# keeps that file equal to the measured context, so the context cannot grow by editing the file.
5+
# To accept growth on purpose, a maintainer adds the agent-context-increase label.
6+
on:
7+
pull_request:
8+
types: [opened, synchronize, reopened, labeled, unlabeled]
9+
10+
permissions:
11+
contents: read
12+
13+
concurrency:
14+
group: agent-context-budget-${{ github.event.pull_request.number }}
15+
cancel-in-progress: true
16+
17+
jobs:
18+
budget:
19+
name: Agent context budget
20+
runs-on: ubuntu-24.04
21+
timeout-minutes: 5
22+
env:
23+
BUDGET: apps/server/src/provider/agentContextBudget.json
24+
ALLOW_INCREASE: ${{ contains(github.event.pull_request.labels.*.name, 'agent-context-increase') }}
25+
steps:
26+
- name: Checkout
27+
uses: actions/checkout@v6
28+
with:
29+
sparse-checkout: apps/server/src/provider/agentContextBudget.json
30+
sparse-checkout-cone-mode: false
31+
32+
- name: Compare with main
33+
run: |
34+
git fetch --quiet --depth=1 origin main
35+
if ! git cat-file -e "FETCH_HEAD:$BUDGET" 2>/dev/null; then
36+
echo "main has no agent context budget yet."
37+
exit 0
38+
fi
39+
git show "FETCH_HEAD:$BUDGET" > "$RUNNER_TEMP/main.json"
40+
grown=$(jq -r --slurpfile main "$RUNNER_TEMP/main.json" '
41+
to_entries[]
42+
| select($main[0][.key] != null and .value > $main[0][.key])
43+
| "\(.key): \($main[0][.key]) -> \(.value) (+\(.value - $main[0][.key]))"
44+
' "$BUDGET")
45+
if [ -z "$grown" ]; then
46+
echo "Agent context is not larger than main."
47+
exit 0
48+
fi
49+
printf 'Agent context grew compared to main:\n%s\n' "$grown"
50+
if [ "$ALLOW_INCREASE" = "true" ]; then
51+
echo "Accepted by the agent-context-increase label."
52+
exit 0
53+
fi
54+
echo "::error file=$BUDGET::Agent context grew compared to main. Cut the added text, or ask a maintainer to add the agent-context-increase label."
55+
exit 1

‎.github/workflows/ci.yml‎

Lines changed: 6 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -344,6 +344,12 @@ jobs:
344344
- name: Test
345345
run: vp run --filter @t3tools/web test
346346

347+
# Browser tests run source modules; this boots the production chunk graph.
348+
- name: Boot the built web client
349+
run: |
350+
vp run --filter @t3tools/web build
351+
node apps/web/scripts/verify-built-boot.ts
352+
347353
# apps/server sets `fileParallelism: false`, so its test files run strictly
348354
# one at a time. Sharding spreads them over separate runners instead of
349355
# separate workers, so no two server test files ever share a machine and the

‎.github/workflows/deploy-relay.yml‎

Lines changed: 2 additions & 3 deletions
Original file line numberDiff line numberDiff line change
@@ -5,12 +5,11 @@ on:
55
branches:
66
- main
77
# Redeploys main after a variable or secret change. Alchemy redeploys the
8-
# Worker when a value it reads changes, so force is rarely needed, and it
9-
# replaces the Postgres runtime role (alchemy-run/alchemy#1832).
8+
# Worker when a value it reads changes, so force is rarely needed.
109
workflow_dispatch:
1110
inputs:
1211
force:
13-
description: Redeploy every resource, including ones with no detected changes. Replaces the Postgres runtime role.
12+
description: Redeploy every resource, including ones with no detected changes.
1413
type: boolean
1514
default: false
1615

‎.github/workflows/mobile-eas-production.yml‎

Lines changed: 19 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -275,6 +275,7 @@ jobs:
275275
--environment production \
276276
--platform ${{ inputs.platform }} \
277277
--message "$OTA_MESSAGE" \
278+
--emit-metadata \
278279
--non-interactive
279280
280281
# Reconcile each version separately because the major is in the fingerprint.
@@ -313,8 +314,11 @@ jobs:
313314
--environment production \
314315
--platform "$platform" \
315316
--message "$message" \
317+
--emit-metadata \
316318
--non-interactive; then
317319
echo ":white_check_mark: $platform/$profile: OTA published to production (fingerprint \`$hash\`)" >> "$GITHUB_STEP_SUMMARY"
320+
# The next target's export replaces dist; keep this one for the map upload.
321+
rm -rf "dist-$platform-$profile" && mv dist "dist-$platform-$profile"
318322
else
319323
failed=1
320324
echo ":x: $platform/$profile: OTA publish failed (fingerprint \`$hash\`)" >> "$GITHUB_STEP_SUMMARY"
@@ -354,3 +358,18 @@ jobs:
354358
fi
355359
done
356360
exit "$failed"
361+
362+
# Lets the relay symbolicate crash stacks from the updates published
363+
# above. A step of its own so the R2 credentials reach only this script,
364+
# not `eas update` and the dependencies it runs. Never fails the job.
365+
- name: Upload OTA source maps
366+
if: ${{ !cancelled() && steps.expo-token.outputs.present == 'true' }}
367+
working-directory: apps/mobile
368+
env:
369+
MOBILE_SOURCEMAPS_R2: ${{ secrets.MOBILE_SOURCEMAPS_R2 }}
370+
run: |
371+
for dir in dist dist-*; do
372+
if [ -f "$dir/eas-update-metadata.json" ]; then
373+
node scripts/upload-sourcemaps.mts ota "$dir"
374+
fi
375+
done

‎.github/workflows/release-desktop.yml‎

Lines changed: 38 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -64,6 +64,12 @@ on:
6464
required: false
6565
default: false
6666
type: boolean
67+
# Whether the job opens the packaged app against a seeded database and
68+
# opens a thread before uploading it. Linux AppImage or macOS DMG.
69+
launch_check:
70+
required: false
71+
default: false
72+
type: boolean
6773
# A runner of the target's own platform and architecture, for a `runner`
6874
# that cannot execute the target. The build job skips everything that
6975
# runs the packaged binaries, and a second job runs it there.
@@ -517,6 +523,38 @@ jobs:
517523
518524
vp run dist:desktop:artifact "${args[@]}"
519525
526+
# A build can package fine and still not open (a missing module in the
527+
# backend or the bundle). This launches the app from the shipped
528+
# AppImage or DMG.
529+
- name: Launch check
530+
if: inputs.launch_check
531+
shell: bash
532+
run: |
533+
set -euo pipefail
534+
check=(node scripts/smoke-desktop-app.ts --artifacts-dir "$RUNNER_TEMP/desktop-launch-check")
535+
if [[ "${{ inputs.platform }}" == "mac" ]]; then
536+
mount="$RUNNER_TEMP/desktop-launch-dmg"
537+
hdiutil attach -nobrowse -readonly -mountpoint "$mount" "$(ls "$GITHUB_WORKSPACE"/release/*.dmg)"
538+
trap 'hdiutil detach "$mount" -force >/dev/null || true' EXIT
539+
app=$(ls -d "$mount"/*.app)
540+
executable=$(/usr/libexec/PlistBuddy -c "Print :CFBundleExecutable" "$app/Contents/Info.plist")
541+
"${check[@]}" --executable "$app/Contents/MacOS/$executable"
542+
else
543+
sudo apt-get install -y xvfb
544+
appimage=$(ls "$GITHUB_WORKSPACE"/release/*.AppImage)
545+
chmod +x "$appimage"
546+
(cd "$RUNNER_TEMP" && "$appimage" --appimage-extract >/dev/null)
547+
xvfb-run -a "${check[@]}" --executable "$RUNNER_TEMP/squashfs-root/t3code"
548+
fi
549+
550+
- name: Upload launch check output
551+
if: failure() && inputs.launch_check
552+
uses: actions/upload-artifact@043fb46d1a93c77aae656e7c1c64a875d1fc6a0a # v7
553+
with:
554+
name: desktop-launch-check-${{ inputs.platform }}-${{ inputs.arch }}
555+
path: ${{ runner.temp }}/desktop-launch-check
556+
if-no-files-found: ignore
557+
520558
# The verify job runs what this host could not: the packaged natives and
521559
# the CLI. Its scripts are bundled so that job needs no install.
522560
- name: Stage verification inputs

‎.github/workflows/release.yml‎

Lines changed: 8 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -344,6 +344,12 @@ jobs:
344344
- name: Test
345345
run: vp run --filter @t3tools/web test
346346

347+
# Browser tests run source modules; this boots the production chunk graph.
348+
- name: Boot the built web client
349+
run: |
350+
vp run --filter @t3tools/web build
351+
node apps/web/scripts/verify-built-boot.ts
352+
347353
# Server test files run one at a time, so more small runners beat fewer big ones.
348354
test_server:
349355
name: Release server tests ${{ matrix.shard }}
@@ -613,6 +619,7 @@ jobs:
613619
rust_target: aarch64-apple-darwin
614620
resource_key: darwin-arm64
615621
cli_archive: true
622+
launch_check: true
616623

617624
desktop_mac_x64:
618625
name: Desktop macOS x64
@@ -662,6 +669,7 @@ jobs:
662669
rust_target: x86_64-unknown-linux-gnu
663670
resource_key: linux-x64
664671
cli_archive: true
672+
launch_check: true
665673

666674
# node-pty has no Linux prebuild and compiles from source, so the arm64 app
667675
# and archive are built on arm64 hardware rather than cross-built.
Lines changed: 27 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,27 @@
1+
---
2+
title: Test Signal
3+
model: gpt-6-1-terra
4+
reasoning: low
5+
input: incremental
6+
tools:
7+
- browse_code
8+
- modify_pr
9+
# An explicit include overrides ignore.md, which skips test files for every other check.
10+
include:
11+
- "**/*.test.*"
12+
exclude:
13+
- ".repos/**"
14+
requires:
15+
- Check
16+
maxBudgetPerRun: 1
17+
maxBudgetPerPR: 5
18+
conclusion: neutral
19+
---
20+
21+
# Test signal review
22+
23+
Review only the tests this pull request adds or grows. Tests it moves, renames, or deletes are not findings. The rules are in `docs/internals/testing.md` under `## What to test`; read that section first and hold new tests to it.
24+
25+
Post each finding as a brief inline comment on the new test with one fix. Ask only for fewer or smaller tests, never for more coverage.
26+
27+
When there are no findings, make the entire final response exactly `All clear` on one line with nothing else.

0 commit comments

Comments
 (0)