Gateway startup now includes plugin owners for explicit memorySearch.provider and memorySearch.fallback values, including custom models.providers API owners and generic embedding provider contracts.
Sentinel and disabled paths keep existing startup behavior for auto, local, none, disabled memory search, and disabled memory slots.
Adds post-runtime-load diagnostics for configured memory embedding providers that remain unregistered.
Closes#89651
Co-authored-by: Joseph Krug <5925937+joeykrug@users.noreply.github.com>
Narrow cron server_error retry classification so incidental 500-599 numbers in failure text no longer trigger retryable server_error. Genuine HTTP/status 5xx strings, canonical 5xx phrases, 5xx, and standalone terse codes still retry.
Maintainer proof: focused cron retry tests, formatter/lint/diff checks, clean autoreview, Testbox-through-Crabbox check:changed tbx_01kteteqqrppbzgh560sybe0nk / Actions run 27066938422, and green PR CI on 6124f14850.
Fixes#90947.
Ensure selected-agent auth profiles are tried before inherited main-agent profiles for the same provider while preserving explicit agent auth order as a hard filter.
Fixes#64274
Allow ordinary spaces in Docker setup host persistence paths while preserving control-character and comma mount guards. Quote generated and base Compose volume scalars so OPENCLAW_CONFIG_DIR, OPENCLAW_WORKSPACE_DIR, and auth-profile secret paths can be parsed when host directories contain spaces.
Add the small-model selector to the gateway live-model profile harness and document the OPENCLAW_LIVE_GATEWAY_MODELS=small recipe.\n\nVerification: node scripts/run-vitest.mjs run --config test/vitest/vitest.live.config.ts src/gateway/gateway-models.profiles.live.test.ts; GitHub Actions CI run 27064309683; CodeQL run 27064309687; OpenGrep PR Diff run 27064309689.
Count streamed text/thinking/tool-call deltas incrementally in model diagnostics instead of repeatedly estimating full event payloads. Updates diagnostics docs and OTEL wording for the new response byte baseline.\n\nVerification: node scripts/run-vitest.mjs run src/agents/embedded-agent-runner/run/attempt.model-diagnostic-events.test.ts; GitHub Actions CI run 27064304709; CodeQL run 27064304710; OpenGrep PR Diff run 27064304716.
Stream same-item phased final-answer deltas incrementally without rereading full partial assistant text on every token. Preserves sanitizer context for split hidden tool-call payloads and keeps full partial reads for item boundaries and text_end finalization.\n\nRefs https://github.com/openclaw/openclaw/issues/86599.
Fixes#89691.
Memory search now treats explicitly configured non-local embedding providers as required. When that provider is unavailable, search and sync surface an unavailable memory-search result instead of silently returning FTS-only recall.
Unset/default/local/none-style paths keep FTS fallback so existing workflows do not lose keyword recall entirely. The fallback state is now surfaced in diagnostics/status instead of being hidden.
Maintainer merge note: current CI still has unrelated baseline boundary failures in extensions/google/google.live.test.ts and extensions/minimax/minimax.live.test.ts. This PR does not touch those files; the PR-specific memory, docs, lint, type, security, and ClawSweeper checks were reviewed before merge.
Carry terminal abort state into embedded agent lifecycle events before agent_end emits, and include terminal stopReason from the last assistant message when runner metadata is not available yet.
Fixes#66534
* fix(uninstall): refuse to remove current working directory during cleanup
* fix(uninstall): guard cleanup ancestors of cwd
---------
Co-authored-by: sallyom <somalley@redhat.com>
Surface Codex-specific completion-timeout outcomes and structural diagnostics while preserving the existing replay-safe retry behavior.\n\nVerified with focused Vitest coverage, live forced-timeout Showboat proof, and green PR CI.
Summary:
- The branch moves Anthropic `start` emission into `message_start` handling for the provider and transport stream paths and adds focused ordering/error tests.
- PR surface: Source +5, Tests +149. Total +154 across 4 files.
- Reproducibility: Do we have a high-confidence way to reproduce the issue? Yes from source: current main emit ... ecovery intentionally refuses to retry after any non-error output; no live expired-cache run was performed.
Automerge notes:
- PR branch already contained follow-up commit before automerge: fix(agents): defer Anthropic transport stream start event until after…
Validation:
- ClawSweeper review passed for head 399a243c64.
- Required merge gates passed before the squash merge.
Prepared head SHA: 399a243c64
Review: https://github.com/openclaw/openclaw/pull/90697#issuecomment-4632866448
Co-authored-by: openperf <16864032@qq.com>
Co-authored-by: clawsweeper[bot] <274271284+clawsweeper[bot]@users.noreply.github.com>
Approved-by: takhoffman
Co-authored-by: takhoffman <781889+takhoffman@users.noreply.github.com>
Summary:
- The PR converts wider MCP CallToolResult content blocks into text/image AgentToolResult blocks at the bundle-MCP materialization boundary and adds regression tests.
- PR surface: Source +36, Tests +66. Total +102 across 2 files.
- Reproducibility: yes. Source inspection shows current main lets MCP resource/audio blocks cross into a text/ ... a spawned stdio MCP server; I did not run a live hosted Anthropic API round trip in this read-only review.
Automerge notes:
- No ClawSweeper repair was needed after automerge opt-in.
Validation:
- ClawSweeper review passed for head f70dccf33e.
- Required merge gates passed before the squash merge.
Prepared head SHA: f70dccf33e
Review: https://github.com/openclaw/openclaw/pull/90728#issuecomment-4634126025
Co-authored-by: 宇宙熊Yzx <53250620+849261680@users.noreply.github.com>
Co-authored-by: clawsweeper[bot] <274271284+clawsweeper[bot]@users.noreply.github.com>
Approved-by: takhoffman
Co-authored-by: takhoffman <781889+takhoffman@users.noreply.github.com>
Fix embedded attempts falsely reporting session takeover after OpenClaw-owned auto-compaction writes a compaction entry while the prompt fence is released.
The compaction append path now publishes an owned session-file fence only when the guarded SessionManager append produced the expected compaction entry. External or interleaved session-file edits remain takeover errors.
Closes#90729
Fixes#90702.
Allow a single-provider primary to periodically probe through the existing cooldown throttle even when no fallback chain is configured. This lets WHAM/subscription-limit cooldown state recover without waiting for a far-future provider reset timestamp.
Verified:
- node scripts/run-vitest.mjs src/agents/model-fallback.probe.test.ts
- git diff --check
- cherry-pick onto current origin/main and rerun focused regression
- New extensions/parallel package modeled on extensions/exa
- Wires Parallel's POST /v1/search through the generic web_search contract,
exposing Parallel's recommended {objective, search_queries} shape (plus
optional count, session_id, client_model) so the model can supply both the
natural-language goal and 2-3 short keyword queries as Parallel docs advise
- client_model lets the model report its own slug so Parallel can tailor
optimizations for the consuming model's capabilities; partitions the cache
by client_model so different models do not silently share ranked excerpts
- Honors top-level tools.web.search.{maxResults,timeoutSeconds,cacheTtlMinutes}
via the shared SDK helpers (mergeScopedSearchConfig, withTrustedWebSearchEndpoint,
buildSearchCacheKey, read/writeCachedSearchPayload)
- Auto-detect order 75; auth via PARALLEL_API_KEY or
plugins.entries.parallel.config.webSearch.apiKey
- Optional baseUrl override for proxies (e.g. Cloudflare AI Gateway)
- Threads caller-supplied session_id through follow-up calls; strips
auto-generated session_id from the shared cache to avoid cross-task leaks
- Always sends advanced_settings.max_results so result volume matches the
OpenClaw web_search default (5) instead of Parallel's default (10)
- Identifies the plugin via User-Agent header built from package version
- Runtime accepts the generic `query` arg as a fallback so the operator
CLI (openclaw capability web.search) keeps working when Parallel is the
active provider: it is promoted into the lone `search_queries` entry.
`objective` stays optional and is never synthesized from a keyword
query (Parallel documents it as natural-language intent). Agent callers
using the native objective+search_queries shape take precedence; the
schema still advertises only the native keys
- Updates the agent tool-display extractor (src/agents/tool-display-common.ts)
to recognize Parallel's objective+search_queries shape so calls render with
query context in CLI progress and Codex activity metadata
- Adds /tools/parallel-search docs page, web.md provider listing, docs nav,
labeler entry, per-plugin registration contract test, and minimal core
touch-points (legacy migrate, registration cases, providers contract list,
runtime bundled list, vitest extension paths)
