Add a bounded `chat.message.get` gateway method so Control UI can fetch one display-normalized transcript message by id when an assistant history preview was truncated. Keep `chat.history` lightweight, reject oversized/hidden/missing rows with explicit unavailable reasons, and wire the WebChat side reader to request full content only for visible truncated assistant messages.
Also refresh the generated Swift gateway protocol models and document the new assistant-message side-reader behavior.
Closes#84651.
Related #53242.
Co-authored-by: NianJiuZst <3235467914@qq.com>
Add MCP server add/configure/login/reload flows plus config/runtime support for enablement, filters, timeouts, OAuth, TLS, and parallel execution hints. Update docs and tests for the expanded MCP operator surface.
Fixes#63558.
Adds a Dreaming-tab agent selector and propagates the selected agent through Dreaming status, diary, and diary actions while preserving default-agent fallback when agentId is omitted. Also keeps report Memory Palace cards in the Control UI wiki-preview flow and documents the optional Dreaming agentId gateway parameters.
Verification:
- GitHub CI run 26693682975 passed on 43a2b17243.
- CodeQL Critical Quality run 26693682971 passed.
- CodeQL / Security High run 26693682957 passed.
- Workflow Sanity run 26693682949 passed.
- OpenGrep PR Diff run 26693682947 passed.
- Dependency Guard run 26693682003 passed.
- Real behavior proof run 26693860539 passed.
- git diff --check origin/main...refs/remotes/origin/pr/78748 passed.
- git merge-tree --write-tree origin/main refs/remotes/origin/pr/78748 passed.
Thanks @stevenepalmer.
Co-authored-by: Steven Palmer <6134396+stevenepalmer@users.noreply.github.com>
Forward OpenAI-compatible stop sequences from gateway chat completions through the agent runner into provider transports.
The gateway now normalizes stop into sampling extras, agent transports pass it into the shared stream options, and OpenAI, Anthropic, Mistral, Google, and Vertex-backed simple providers map it to their native request fields. Provider/gateway/agent coverage plus Crabbox live gateway proof verify valid stop dispatch and invalid stop rejection.
Refs #87920
Fixes#88198.
Ignore top-level helper scripts in auto-discovered global/workspace extension roots so they do not become manifestless plugin candidates during config validation. Standalone plugin files remain supported when explicitly configured through `plugins.load.paths`, and docs now call out the supported path.
Verification:
- `node scripts/run-vitest.mjs src/plugins/discovery.test.ts src/config/config.plugin-validation.test.ts`
- `node scripts/run-oxlint.mjs src/plugins/discovery.ts src/plugins/discovery.test.ts src/config/config.plugin-validation.test.ts`
- `git diff --check`
- GitHub CI green at `93073bfa85ee294e644c623881ba59ba71d90975`
- `.agents/skills/autoreview/scripts/autoreview --mode branch --base origin/main`
Thanks @mushuiyu886 for the fix and @mmhzlrj for the report.
Refactor OpenAI provider identity so OpenAI remains the canonical provider for API-key and OAuth-backed flows while legacy openai-codex state is doctor/migration-only.
Keeps OpenAI Codex Responses as an API/transport class rather than a provider identity, moves auth aliases through providerAuthAliases, updates doctor repair sequencing for old auth/profile state, and refreshes tests/docs around the canonical OpenAI behavior.
Fixes#87438.
Bound unset heartbeat run timeouts so background heartbeat turns no longer inherit the built-in 48-hour interactive agent default. Timeout precedence is explicit heartbeat timeout, explicit global agent timeout, then heartbeat cadence capped at 600 seconds.
Verification:
- git diff --check
- Testbox tbx_01kstna69zvznn4fq7zrqr04a1: corepack pnpm test src/infra/heartbeat-runner.model-override.test.ts -- --reporter=verbose passed 13 tests
- Direct node --import tsx runtime probe verified 300s, 600s, 60s, and 45s timeout precedence cases
- Autoreview clean
Known CI state:
- PR CI run 26661465248 has failures matching latest main CI run 26661386468 at a7820b2f54; failures are outside this six-file heartbeat/docs diff.
Keep session lock cleanup from removing live OpenClaw-owned locks solely because they are old. Cleanup now reports age-only stale locks without deleting them, while still removing dead, orphaned, recycled, malformed-old, and non-OpenClaw-owned locks.
Update doctor docs and regression coverage for the cleanup/repair contract.
Refs #87779
Forward initial image/file attachments when spawning ACP subagents through the existing sessions_spawn attachment opt-in. Remove the PR-only acpEnabled config split so ACP uses the same attachment gate as other runtimes.
Also fix the PR branch CI fallout: type the browser element CLI request mock and use Vitest env stubs in the Azure speech test to satisfy the changed-path security scan.
Verification:
- GitHub CI passed on f6ca26b160.
- Autoreview clean.
- Crabbox AWS live OpenAI proof passed: cbx_a576d49493fe / run_081dcc6c6a1b.
Thanks @zhangguiping-xydt.
* feat: add Claude Opus 4.8 support
* fix: omit Vertex Opus sampling overrides
* fix: preserve Opus adaptive thinking levels
* fix: clamp Anthropic max effort support
* fix: use sha256 for QA mock call ids
* fix: type Anthropic transport test model metadata
* test: update PDF model default for Opus 4.8
Fixes#87132.
Default Usage now requests all configured agents with `agentScope: "all"`, while selecting a specific agent sends `agentId` consistently to both session usage and cost usage calls. The gateway now supports explicit all-agent session usage, aggregates all-agent cost summaries across configured agents, and keeps scoped cache entries separate. Legacy gateway fallbacks remain for older `agentId` / `agentScope` support, with protocol docs/schema and Swift generated models updated.
Verification:
- `node scripts/run-vitest.mjs ui/src/ui/controllers/usage.node.test.ts ui/src/ui/app-render-usage-tab.test.ts ui/src/ui/views/usage.test.ts --reporter=dot`
- `node scripts/run-vitest.mjs run --config test/vitest/vitest.gateway-methods.config.ts src/gateway/server-methods/usage.test.ts src/gateway/server-methods/usage.cost-usage-cache.test.ts src/gateway/server-methods/usage.sessions-usage.test.ts --reporter=dot`
- `pnpm check:test-types`
- `pnpm protocol:check`
- targeted `node scripts/run-oxlint.mjs ...`
- `git diff --check`
- autoreview clean after Swift compatibility fix
- PR CI green at head `d67156a3c552c4f9c8b6edf8516b6242bf5cdd26`
Co-authored-by: Alix-007 <267018309+Alix-007@users.noreply.github.com>
Add read-only MCP visibility to `tools.effective` by projecting MCP tools only after a session catalog has already been warmed by an agent turn. Keep the gateway additive: no `tools.effective.refresh`, no forced MCP startup, and no behavior change for MCP loading.
Verification:
- `git diff --check origin/main..HEAD`
- `node scripts/run-vitest.mjs run --config test/vitest/vitest.agents.config.ts --reporter=verbose src/agents/tools-effective-inventory.test.ts`
- GitHub checks green on `a8a7f8442adb216f60da24d50118374a15c62e06`, including `Real behavior proof`, `check-guards`, `check-prod-types`, `check-test-types`, `build-artifacts`, `Critical Quality (gateway-runtime-boundary)`, and `Critical Quality (network-runtime-boundary)`.
Co-authored-by: David Huang <nxmxbbd@gmail.com>
Move vLLM Qwen thinking control onto configured model compat metadata and carry it through catalog/model-selection/runtime thinking contexts.
Also migrate legacy provider/default request params in doctor and keep Pi/runtime model rows buildable with explicit reasoning defaults.
Thanks @rendrag-git.
Co-authored-by: rendrag-git <253747599+rendrag-git@users.noreply.github.com>
Fix Claude CLI skill prompt handling so native skill plugin materialization is prepared before prompt suppression, with the prompt fallback preserved when plugin args are unavailable. Also keeps direct prepared-run callers covered by an execute-time fallback.
Fixes#87063.
Co-authored-by: uday <udaymanish.thumma@gmail.com>
Recover idle queued sessions whose diagnostic activity retained stale ownerless model or tool calls by classifying them as recoverable session.stuck after the usual recovery gates. Yield the event loop before stale session-lock process inspection so sync process lookup cannot monopolize lock contention paths.
Docs now describe the widened session.stuck telemetry contract for recoverable stale bookkeeping, including ownerless activity. Thanks @samuelsoaress.
Refs #84903.
Co-authored-by: samuelsoaress <samuelsoares177778@gmail.com>
Remove the proposed public `maxReseedHistoryChars` config surface and scale Claude CLI reseed history automatically from the resolved context tier instead.
Claude CLI 200K-context runs now keep a 64K-character reseed slice, 1M Opus/Sonnet runs use the bounded 256KiB cap, and non-Claude CLI backends keep the existing 12KiB default. This preserves the intended long-context behavior without adding another config option.
Verification:
- `node scripts/run-vitest.mjs src/agents/cli-runner/session-history.test.ts src/agents/cli-runner/prepare.test.ts`
- `node scripts/run-vitest.mjs src/agents/cli-runner/prepare.test.ts -t "automatic Claude CLI cap"`
- `node scripts/run-oxlint.mjs src/agents/cli-runner/prepare.ts src/agents/cli-runner/prepare.test.ts src/agents/cli-runner/session-history.ts src/agents/cli-runner/session-history.test.ts src/config/types.agent-defaults.ts src/config/zod-schema.core.ts`
- `pnpm check:changed` via Testbox `tbx_01kska2twjxb925xft9dj82hvb`
- GitHub PR checks green
Closes#83985
Co-authored-by: Abdel Gomez-Perez <nabdel07@icloud.com>
Forward OpenAI-compatible frequency_penalty, presence_penalty, and seed params through the gateway/chat-completions path while keeping Responses untouched.
Verification:
- pnpm test src/gateway/openai-http.test.ts src/agents/pi-embedded-runner/extra-params.sampling.test.ts src/agents/openai-transport-stream.test.ts
- CI passed on head 9abb9466d9 after rerunning cancelled jobs: preflight, critical quality network-runtime-boundary, security high, checks, docs, Real behavior proof.
Co-authored-by: lellansin <lellansin@gmail.com>
Behavior addressed: Native Codex app-server threads now disable Codex's built-in personality on thread/start, thread/resume, turn/start, bound conversation turns, and /btw side-thread forks so OpenClaw agent workspace identity stays authoritative.
Real environment tested: Local OpenClaw source checkout plus GitHub CI on PR #85891.
Exact steps or command run after this patch: pnpm test extensions/codex/src/app-server/thread-lifecycle.test.ts extensions/codex/src/app-server/side-question.test.ts extensions/codex/src/conversation-binding.test.ts extensions/codex/src/app-server/schema-normalization-runtime-contract.test.ts; pnpm check:docs; pnpm prompt:snapshots:check; OPENCLAW_ADDITIONAL_BOUNDARY_SHARD=1/4 OPENCLAW_ADDITIONAL_BOUNDARY_CONCURRENCY=4 node scripts/run-additional-boundary-checks.mjs.
Evidence after fix: Focused Codex test shard passed 4 files / 79 tests; docs check passed; prompt snapshots are current; CI passed all code/quality checks, with only Real behavior proof failing as unrelated proof-bot gating for this non-channel change.
Observed result after fix: App-server request snapshots and unit tests include personality: "none" on native Codex start/resume/turn/fork paths.
What was not tested: A live Codex app-server model run was not executed.
Co-authored-by: Beru <beru@lastguru.lv>
Normalize Google Gemini 3.1 Flash Lite routing to the GA model id and keep the retired preview spelling as a compatibility alias. Align default alias docs, FAQ guidance, and deprecated-model manifest recommendations with the GA id.
Fixes#86151.
Co-authored-by: Sebastien Tardif <sebtardif@ncf.ca>
* fix(agents): answer Claude live control_request can_use_tool via exec policy
Claude CLI emits stream-json control_request frames with subtype
can_use_tool when it wants to use a native tool. The Claude live-session
bridge previously dropped these frames, leaving Claude waiting for a
control_response until the 180/600s no-output timeout fired (see #80819).
Resolve the effective OpenClaw exec policy (per-agent tools.exec -> global
tools.exec -> allowlist/on-miss defaults) once at session-start time and
thread it through fingerprinting and the session record. When a
can_use_tool request arrives:
- Allow native Bash when the resolved policy is security=full, ask=off
(matching the bypassPermissions semantics OpenClaw already documents).
- Otherwise deny with a message that names the resolved policy and
points the agent at OpenClaw MCP tools.
Unsupported control_request subtypes get a structured error response
instead of a silent no-op, and stray control_response frames are
silently dropped. Adds spawn-test coverage for both allow and deny paths.
Fixes#80819
* fix(agents): align Claude live control_request policy with backend defaults
Resolve the effective exec policy through the same defaults that
extensions/anthropic/cli-shared.ts:isOpenClawRequestedYolo and
src/agents/exec-defaults.ts:resolveExecDefaults already use (security
?? "full", ask ?? "off") instead of falling back to a hand-rolled
allowlist/on-miss default that disagreed with the rest of the codebase.
Without this, a default-config OpenClaw deployment launches Claude with
--permission-mode bypassPermissions but the bridge would still deny
Bash control_requests, re-creating the #80819 stall for the very
default-config case the issue reports.
Also thread the effective Claude permission mode into the policy
decision. Prefer the operator's explicit --permission-mode in argv,
falling back to what normalizeClaudePermissionArgs would have inserted
for an un-overridden launch. Native Bash is auto-allowed only when the
effective mode is bypassPermissions AND tools.exec resolves to
full/no-ask, so explicit raw-arg overrides like --permission-mode
default or acceptEdits broaden Claude's native prompting and are
honored by routing through deny.
Adds a no-config regression test (default deployment allows Bash, no
stall) and a permission-mode-override test (tools.exec full/off plus
explicit --permission-mode default in raw args denies). Existing
allow/deny tests continue to pass via the synthesized-mode fallback.
* fix(agents): honor effective exec policy for Claude live Bash
---------
Co-authored-by: Guillaume Thirry <g.thirry@gmail.com>
