Summary:
- Adds an OpenCode provider-policy public artifact that delegates Claude thinking profiles, plus regression tests and a changelog entry for preserving `xhigh` on `opencode/claude-opus-4-7`.
- Reproducibility: yes. Source inspection on current main shows the model-switch path remaps unsupported store ... vider-policy-api` artifact for the fallback resolver; the proposed test exercises that stored-`xhigh` path.
Automerge notes:
- No ClawSweeper repair was needed after automerge opt-in.
Validation:
- ClawSweeper review passed for head efa152cca5.
- Required merge gates passed before the squash merge.
Prepared head SHA: efa152cca5
Review: https://github.com/openclaw/openclaw/pull/76760#issuecomment-4366483080
Co-authored-by: mkdev11 <MkDev11@users.noreply.github.com>
Summary:
- Adds a Vitest regression case in `src/agents/session-file-repair.test.ts` for `repairSessionFileIfNeeded` preserving a final stop assistant message after a tool-call/tool-result pair.
- Reproducibility: yes. The added JSONL sequence can be traced through current `repairSessionFileIfNeeded`: no ... ry, so the function returns `repaired: false`; I did not execute the test because this review is read-only.
Automerge notes:
- No ClawSweeper repair was needed after automerge opt-in.
Validation:
- ClawSweeper review passed for head ee3aa0e036.
- Required merge gates passed before the squash merge.
Prepared head SHA: ee3aa0e036
Review: https://github.com/openclaw/openclaw/pull/76538#issuecomment-4365670008
Co-authored-by: Vinh Nguyen <vinhnt36@fpt.com>
Co-authored-by: Claude Sonnet 4.6 <noreply@anthropic.com>
Fixes#76176.
OpenAI live verification showed `gpt-5.4-mini` supports reasoning effort generally, but rejects `/v1/chat/completions` payloads that combine function tools with `reasoning_effort`. This keeps reasoning effort for tool-free Chat Completions and Responses, and omits it only for the rejected Chat Completions + function tools combination.
Validation:
- Live OpenAI API matrix on 2026-05-03
- pnpm test src/agents/openai-reasoning-effort.test.ts src/agents/openai-transport-stream.test.ts -- --reporter=verbose
- GitHub PR CI green on ea3915308c
Thanks @ThisIsAdilah and @chinar-amrutkar.
Fixes the session-list plugin metadata hot path by reusing the active workspace-scoped plugin metadata snapshot for manifest model-id normalization and setup CLI backend fallback. Also keeps model-pricing collection on its provided manifest registry and fixes the CI-only hoisted test mock failure.
Validated with targeted plugin/gateway/model-selection tests, CI-shaped gateway startup shard, Testbox `pnpm check:changed`, and green PR CI.
Thanks @rolandrscheel.
Summary:
- The PR adds `sensitive` support to wizard text prompts, routes sensitive Clack prompts through `password()`, ... preserves existing gateway secrets through masked-preview confirms, and adds tests plus a changelog entry.
- Reproducibility: yes. Source inspection shows current main routes onboarding credential entry through visibl ... y provides a concrete Windows PowerShell `openclaw onboard --install-daemon` reproduction with screenshots.
Automerge notes:
- No ClawSweeper repair was needed after automerge opt-in.
Validation:
- ClawSweeper review passed for head a3db64c265.
- Required merge gates passed before the squash merge.
Prepared head SHA: a3db64c265
Review: https://github.com/openclaw/openclaw/pull/76693#issuecomment-4366253531
Co-authored-by: anurag-bg-neu <bheemappagnanamurt.a@northeastern.edu>
- gate the compaction continuation retry on existing replay side-effect metadata
- type the bundled compaction notifier hook without explicit any
- add an Unreleased changelog entry
When an automatic compaction happens mid-turn, chat users currently see a long stall and the run can finish without a final visible answer.
This adds an optional bundled compaction notifier hook and a one-shot compacted-transcript continuation retry when a compaction produced no user-visible final payload.
Summary:
- The branch marks runtime `toolsAllow` sources as enforceable during disabled-tool runs, filters inherited allowlist sources in the guard, adds focused guard coverage, and updates the changelog.
- Reproducibility: yes. The linked report gives concrete config and invocation steps, and source inspection on ... sables tools while the guard still treats inherited allowlist sources plus zero callable tools as an error.
Automerge notes:
- No ClawSweeper repair was needed after automerge opt-in.
Validation:
- ClawSweeper review passed for head 9c3e5f773e.
- Required merge gates passed before the squash merge.
Prepared head SHA: 9c3e5f773e
Review: https://github.com/openclaw/openclaw/pull/76686#issuecomment-4366216196
Co-authored-by: Alex Knight <15041791+amknight@users.noreply.github.com>
Summary:
- The PR changes the agent web_search wrapper to keep runtime provider discovery enabled when runtime metadata is absent, adds focused regression coverage, and records an unreleased changelog fix.
- Reproducibility: yes. at source level: current main passes preferRuntimeProviders: false when runtime web-se ... d issue supplies live Brave CLI-vs-agent evidence; this read-only review did not rerun a live Gateway call.
Automerge notes:
- No ClawSweeper repair was needed after automerge opt-in.
Validation:
- ClawSweeper review passed for head e7f379c68d.
- Required merge gates passed before the squash merge.
Prepared head SHA: e7f379c68d
Review: https://github.com/openclaw/openclaw/pull/76685#issuecomment-4366216450
Co-authored-by: Alex Knight <15041791+amknight@users.noreply.github.com>
The sandbox registry stores one JSON document per scope (containers
and browsers), with every writer serialized through
`acquireSessionWriteLock` against that single file. In a host running
several sessions in parallel — multiple pairings, subagent spawns, or
just an `ensureSandboxContainer` landing at the same moment as a
`removeRegistryEntry` — each writer waits up to 60s for the lock, and
a crashed process can leave the lock file behind long enough to
wedge every subsequent sandbox operation until the stale-lock
threshold elapses. The lock's only job is to keep entries from
trampling each other inside one JSON blob, so it is a whole-file
mutex gating reads/writes that touch disjoint entries.
Each container already has a unique name (enforced at creation), so
each entry's storage can be disjoint too. This change turns the
`~/.openclaw/sandbox/containers.json` and `browsers.json`
monolithic files into per-entry JSON files under
`~/.openclaw/sandbox/containers/` and `~/.openclaw/sandbox/browsers/`
directories. `writeJsonAtomic` (tmp-file + rename) keeps each
per-entry write crash-safe, and because concurrent writers only
touch their own files there is nothing left to serialize across.
Changes:
- `src/agents/sandbox/constants.ts`: add `SANDBOX_CONTAINERS_DIR`
and `SANDBOX_BROWSERS_DIR` sibling to the existing monolithic
paths. The old paths stay exported because the one-shot migration
still needs to locate the legacy file.
- `src/agents/sandbox/registry.ts`: replace the
`withRegistryLock` / `readRegistryFromFile("strict")` /
`writeRegistryFile` loop with per-entry read/write/remove
primitives against the sharded directories, and drop the
`acquireSessionWriteLock` import. The existing upstream additions
are preserved: the zod `RegistryEntrySchema`, the
`backendId`/`runtimeLabel`/`configLabelKind` fields on
`SandboxRegistryEntry`, and `normalizeSandboxRegistryEntry` still
decorate reads. Upsert merge semantics (preserve `createdAtMs` and
`image` from the prior entry, prefer the newer `configHash`) are
kept bit-for-bit.
- `src/agents/sandbox/registry.ts`: add `readRegistryEntry(name)`
for O(1) single-container lookup. The previous hot path in
`ensureSandboxContainer` had to read the whole registry and
`Array.find` the one entry it wanted; the new API avoids both the
full directory scan and the JSON round-trip on every other entry.
- `src/agents/sandbox/registry.ts`: add a one-shot
`migrateMonolithicIfNeeded` helper invoked at the top of every
public read/write. If a legacy `containers.json` / `browsers.json`
exists, its entries are fanned out into per-entry files, the old
file and its `.lock` are removed, and subsequent calls skip the
migration branch entirely. Malformed legacy files are dropped
rather than throwing forever, because a corrupt single-file
registry that has already been superseded by the new storage
would otherwise block every sandbox ensure/remove on every boot.
Live per-entry files still go through the same schema validation
the upstream strict path used — a corrupt per-entry file is
simply skipped during enumeration so that one bad file cannot
hide every other running container from the operator.
- `src/agents/sandbox/docker.ts`: swap the `readRegistry()` +
`Array.find` lookup in `ensureSandboxContainer` for the new
`readRegistryEntry(containerName)`. This is the only in-tree
caller that needed the full scan just to pick one entry.
- `src/agents/sandbox/registry.test.ts`: rewrite around the new
per-file semantics. The old tests covered two properties that no
longer exist — "the lock serializes concurrent update/remove so
the later write cannot resurrect a removed entry" and "a
malformed monolithic file makes every `update` throw" — both of
which were artifacts of the single-file design. The rewrite keeps
the normalizeSandboxRegistryEntry contract, the
concurrent-updates-succeed contract (now without any lock in
play), the malformed-legacy-migration contract, and adds coverage
for `readRegistryEntry`, the stale-`.lock` cleanup, and the
"corrupt per-entry file does not hide its siblings" guarantee.
- `src/agents/sandbox/docker.config-hash-recreate.test.ts`: update
the mock module to expose `readRegistryEntry` instead of
`readRegistry`, and return single-entry objects or `null` rather
than `{ entries: [...] }`.
Other in-tree consumers (`manage.ts`, `prune.ts`, `browser.ts`,
`context.ts`) only call the public `readRegistry` / `updateRegistry`
/ `remove*` surface, whose return shapes and observable behavior
are unchanged; their existing tests (`manage.test.ts`,
`browser.create.test.ts`, `sandbox.resolveSandboxContext.test.ts`)
all pass unmodified.
Default behavior is unchanged from the operator's point of view:
the first boot on the new code sees the legacy files, migrates them
in place, and deletes them. Subsequent boots never touch the
migration path. No config surface, no types, and no public exports
are removed.
External context-engine plugins (e.g. lossless-claw) register via
api.registerContextEngine at load time but ship without
activation.onStartup in their manifest. The gateway startup planner
only considered memory plugins and explicit sidecar plugins, so a
selected non-legacy context engine was omitted from the startup load
plan and never loaded before agent turns resolved the active engine,
producing the "Context engine X is not registered; falling back to
default engine legacy" warning.
Fix: add resolveContextEngineSlotStartupPluginId mirroring the memory
slot pattern; pass contextEngineSlotStartupPluginId into
shouldConsiderForGatewayStartup so the selected context-engine plugin
is included in pluginIds regardless of its manifest activation shape.
Tests: added four regression cases covering include, exclude, legacy
bypass, and id normalization. 82 tests pass.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Peter Steinberger