0303af17f3
test: remove low-value implementation assertions ( #121085 )
...
* test: remove low-value implementation assertions
* test: refresh native i18n inventory
2026-08-09 08:48:48 -07:00
faaeebe208
refactor: deduplicate Codex prompt snapshot fixtures ( #117476 )
2026-08-01 09:02:43 -07:00
669db2968f
refactor(agents): retire TOOLS.md into an AGENTS.md section with a doctor migration ( #113966 )
...
* fix(agents): stop retired attestation hashes from faking a vanished workspace
* feat(agents): migrate TOOLS.md content into the AGENTS.md tools section
* refactor(agents): drop TOOLS.md from the workspace bootstrap set
* refactor(policy): read tool policy entries from AGENTS.md
* docs: describe local tool notes as an AGENTS.md section
* test(codex): drop TOOLS.md developer-instruction coverage with the removed path
* test(agents): cover the TOOLS.md doctor migration behaviors
* refactor(doctor): satisfy TOOLS.md migration lint
* test(agents): split workspace attestation survival coverage
* refactor(codex): simplify workspace context basenames
* refactor(doctor): keep TOOLS.md migration helpers module-local
* docs: regenerate docs map
* fix(doctor): keep migration claims fresh
* fix(doctor): preserve nested tool notes
* refactor(doctor): split tools migration helpers
* refactor(doctor): limit TOOLS.md migration to workspace root
* style(doctor): keep migration under line limit
* fix(doctor): recover interrupted AGENTS publish
* docs(hooks): describe root-only TOOLS.md migration accurately
* fix(doctor): preserve migrated tool guidance visibility
* test(agents): regenerate prompt snapshots after rebase
* fix(policy): block evaluation while TOOLS.md is unmigrated
* fix(doctor): check merged bootstrap budget per agent
* fix(doctor): keep budget helper internal
* refactor(doctor): keep migration budget helpers to their consumers
2026-07-27 03:56:30 -04:00
3e2b3ea4d5
feat(cron): database-backed heartbeat monitor scratch replaces HEARTBEAT.md ( #112967 )
...
* feat(cron): move heartbeat context into database-backed per-job cron scratch
- new additive cron_job_scratch SQLite table (revision tombstones keep
compare-and-swap monotonic across unset/recreate; 256KiB cap)
- heartbeat runner reads monitor scratch instead of workspace HEARTBEAT.md;
heartbeat_respond gains a private scratch replacement parameter
- openclaw doctor --fix migrates HEARTBEAT.md into scratch (hash-verified,
archived under state backups, idempotent, symlink-contained)
- gateway cron.scratch.get/set admin RPCs + openclaw cron scratch CLI
- workspace bootstrap no longer seeds HEARTBEAT.md; Codex heartbeat file
guidance removed; docs and prompt snapshots updated
* fix(cron): review round 2 — shared-workspace heartbeat migration and non-default agent monitors
- doctor migration groups agents by heartbeat source file and imports into
every monitor before archiving/removing the shared file once
- exempt heartbeat payloads from the main-session default-agent restriction:
monitors only poke the wake bus, so non-default agents converge again
- document why disabled monitors retain their last cadence (config default
already resolves before the fallback)
* fix(cron): honor configured cron store, legacy heartbeat fallback, and safer doctor claim
* fix(cron): claim HEARTBEAT.md before committing scratch and restore without clobbering
* fix(cron): pin migration CAS to precondition revision, re-verify claim on release, archive first, report scratch as pending
* docs(heartbeat): remove retired config options
* fix(cron): crash-recoverable migration claims, partial-import rollback, latest-response scratch pairing
* test(heartbeat): keep latest scratch proposal paired
* fix(cron): roll back committed scratch on changed-claim release and restore no-row state
* fix(cron): revision-guarded rollback delete and recreated-file detection on claim release
* fix(cron): treat every failed claim re-verification as a migration conflict
* test(heartbeat): rename ack test after ackMaxChars retirement
* fix(heartbeat): keep monitor scratch out of bypass-scope runs
* fix(cron): resolve claimed symlinks on release and gate legacy fallback on proven scratch state
* fix(cron): strict claim-name recovery and per-entry migration grouping
* fix(ci): heartbeat scratch gate repairs — lint causes, dead exports, since-train, inventory path, prompt snapshot, regenerated docs map, SDK baseline, protocol bindings
* fix(cron): live-owner claim guard and canonical entry-key migration grouping
* fix(cron): archive claimed inode on release and flag orphan claims beside recreated files
* docs(cron): document process-global state-db invariant for scratch service ops
* chore(i18n): refresh native inventory line numbers after protocol binding regen
2026-07-23 11:10:49 -07:00
78e11ca2c0
perf(ci): keep prompt snapshot generation off the jiti loader (5.1min lane -> ~1.5min) ( #109757 )
...
Measured breakdown of check-prompt-snapshots in run 29557851276 (5m03s):
- 37s checkout + Node env setup
- 4m25s inside one `pnpm prompt:snapshots:check` process:
- ~35s tsx import of the generator graph
- ~3min first createOpenClawCodingTools call: the message-tool schema
build resolves the scenario channel plugin, the empty loaded registry
falls back to the bundled-channel jiti loader
(extensions/telegram/index.ts), and jiti re-transpiles the core source
graph (136.6s jiti self time in --cpu-prof; second generation call in
the same process takes 0.3s)
- ~1min more for the cold provider-plugin lookup in
normalizeAgentRuntimeTools; no provider plugin owns tool-schema hooks
for the `codex` harness provider, so the jiti load only rediscovers a
no-op
- <2s actual rendering + oxfmt + drift compare
Split axis decision: the planned 2-3 way scenario shard matrix cannot
lower the pole because the cost is a one-time per-process transpile;
every shard would pay the full ~4min again (jiti fsCache does not help:
a warm-cache rerun still took 200s). Fix the generator instead:
- Preload each scenario's channel plugin surface (channel-plugin-api.js,
resolved via the bundled-plugin public-surface resolver) through the
ambient tsx/vitest ESM graph, and pin exactly that channel in a scoped
loaded registry while the scenario's tools are built. Snapshot bytes
are unchanged: the loaded plugin object is the same export the bundled
jiti fallback materializes, and cross-channel action discovery still
sees no other loaded channels.
- Pass allowProviderRuntimePluginLoad=false to normalizeAgentRuntimeTools;
registry-only resolution returns the same undefined plugin instantly.
Coverage guard: test/scripts/prompt-snapshots.test.ts now generates the
snapshot files and asserts zero jiti plugin-loader calls (with the
offending transform targets in the failure message), so a future scenario
or channel that misses the preload fails the suite instead of silently
restoring the 4-minute lane.
Proof: `pnpm prompt:snapshots:check` passes byte-identical against the
committed fixtures in 54s wall / 35s CPU locally (was 354s wall / 306s
CPU); focused vitest suites (32 tests incl. new guard), tsgo core-test +
extensions-test lanes, scoped oxlint/oxfmt, and `git diff --check` are
green. Expected CI pole when the lane fires: ~5.1min -> ~1.5-2min.
2026-07-17 00:27:23 -07:00
204d2b176a
refactor(agents): compress model prompts and tool instructions ( #105095 )
...
* refactor(agents): compress model prompt instructions
* test(agents): align compact prompt assertions
* test(gateway): align compact message prompt assertion
* chore(plugin-sdk): refresh prompt overlay API baseline
* docs(changelog): note prompt instruction compaction
* test(agents): align compact prompt contracts
* test(agents): align CLI prompt contracts
* style(agents): format CLI prompt tests
* fix(qa): prioritize shadow trial workflow
* test(agents): refresh rebased prompt snapshots
2026-07-12 09:45:30 +01:00
fa77fe10d5
chore: migrate active GPT-5.5 references to GPT-5.6 ( #104452 )
...
* chore(models): migrate active GPT-5.5 references
* test(workboard): expect GPT-5.6 Sol default
* chore: keep release notes in PR body
* test(models): align picker fixtures with Sol default
* test: update PDF default model expectation
* test(qa): migrate thinking smoke to Luna
* test(gateway): align mock catalog with Sol default
* ci: retrigger exact-head PR checks
* test(gateway): document default catalog invariant
2026-07-11 06:30:57 -07:00
0004cfd59e
test(scripts): route prompt snapshot helper changes
2026-06-21 08:16:47 +02:00
58c663920d
docs: document script tests
2026-06-04 20:49:50 -04:00
7b3be04582
fix(codex): ensure codex subagent bootstrap parity with pi subagents - only inject AGENTS.md and TOOLS.md ( #85811 )
...
* fix: limit Codex native subagent bootstrap context
* fix: preserve Codex turn instructions accounting
* fix: split Codex workspace instruction renderers
* fix(codex): keep persona files turn-scoped
---------
Co-authored-by: Beru <beru@lastguru.lv >
Co-authored-by: Peter Steinberger <steipete@gmail.com >
2026-05-24 02:48:03 +01:00
e0d1a2a9b9
Move Codex soul context to developer instructions ( #84331 )
...
* Move Codex soul context to developer instructions
* Route Codex workspace context by lifetime
* Refresh Codex prompt snapshots
* Update prompt snapshot expectations
* Fix Codex workspace context diagnostics
2026-05-19 16:47:32 -07:00
2a0350b5b4
Separate prompt surfaces by selected harness ( #83454 )
...
* fix: scope agent prompt surfaces
* fix(codex): preserve lightweight project doc suppression
* fix(codex): demote openclaw context for native turns
* fix(codex): report demoted prompt context
* fix(codex): align demoted prompt observability
* docs: format codex runtime table
* docs: align codex prompt overlay docs
* test: align codex prompt snapshots
* test: update prompt snapshot contract
---------
Co-authored-by: Eva (agent) <eva+agent-78055@100yen.org >
Co-authored-by: Peter Steinberger <steipete@gmail.com >
2026-05-18 13:00:53 +01:00
2d2c420ed2
test: speed up prompt snapshot checks
2026-05-18 01:37:31 +01:00
b5b193076e
test: share repo file helpers
2026-05-17 02:29:55 +08:00
cb313d5378
test: share fs scan assertions
2026-05-17 01:35:39 +08:00
41b4eb97f0
fix(test): avoid scanning prompt snapshots
2026-05-16 14:20:17 +08:00
1bcc071385
ci(release): harden beta validation gates
2026-05-15 18:28:52 +01:00
d273ae73c0
refactor: trim OpenClaw prompt guidance
2026-05-10 14:59:48 +01:00
6f7862bc71
test: reuse prompt snapshot generation
2026-05-09 16:04:16 +01:00
805b959c6f
test: tighten prompt snapshot catalog assertions
2026-05-09 09:42:03 +01:00
330ba1fa31
refactor: move canvas to plugin surfaces
2026-05-07 09:07:18 +01:00
25343f3242
ci: scope prompt snapshot support tests
2026-05-07 01:39:13 +01:00
5bcc321343
Scope Codex heartbeat guidance to heartbeat turns ( #76788 )
...
* fix(codex): scope heartbeat guidance to collaboration mode
* fix heartbeat tool direct context
* test prompt heartbeat collaboration snapshots
* fix heartbeat changelog credit
2026-05-04 01:58:39 +09:00
ad0e1a0d5d
test: show bootstrap context in prompt snapshots ( #76302 )
2026-05-03 08:29:34 +09:00
bcb2476ae7
Rename Codex runtime prompt snapshot directory ( #76274 )
...
* test: rename Codex runtime prompt snapshots
* test: refresh prompt snapshots with node24
* test: format prompt snapshot markdown in generator
2026-05-03 07:34:59 +09:00
9e57b98bb9
Improve Codex happy path prompt snapshots ( #76229 )
...
* test: add Codex model prompt layers to snapshots
* test: keep rendered prompt snapshots raw
* test: check prompt snapshot drift in ci
* test: prefer codex model cache for prompt fixtures
* fix: exclude publishable plugin dist from core package
2026-05-03 06:40:20 +09:00
563dca82f4
Add Codex happy path prompt snapshots ( #75807 )
...
* Add Codex prompt snapshots
* Fix prompt snapshot scenario catalogs
* Harden prompt snapshot drift check
* Fix CLI compat build export
* fix: keep codex snapshots out of core plugin surface
* fix: harden prompt snapshot ci checks
* fix: accept readonly web search onboarding scopes
* fix: repair plugin sdk package boundary types
* fix: clear prompt snapshot ci regressions
* fix: clear latest main ci checks
* fix: resolve latest main discord helper overlap
* fix: refresh codex dynamic tool snapshots
* fix: align prompt snapshot branch with latest ci
* fix: isolate plugin auto enable tests
* test: refresh prompt dynamic tool snapshots
* fix: stabilize bundled channel auto enable
* fix: clean stale prompt snapshots
2026-05-03 00:59:55 +09:00
Peter Steinberger