1311 Commits

Author SHA1 Message Date
Kesku
adec8b28bb
alphabetize web search providers (#40259)
Merged via squash.

Prepared head SHA: be6350e5ae1c0610f813483dca0a5c98813a7f8e
Co-authored-by: kesku <62210496+kesku@users.noreply.github.com>
Co-authored-by: obviyus <22031114+obviyus@users.noreply.github.com>
Reviewed-by: @obviyus
2026-03-09 08:54:54 +05:30
bbblending
4ff4ed7ec9
fix(config): refresh runtime snapshot from disk after write. Fixes #37175 (#37313)
Merged via squash.

Prepared head SHA: 69e1861abf97d20c787a790d37e68c9e3ae2cb1d
Co-authored-by: bbblending <122739024+bbblending@users.noreply.github.com>
Co-authored-by: gumadeiras <5599352+gumadeiras@users.noreply.github.com>
Reviewed-by: @gumadeiras
2026-03-08 19:49:15 -04:00
Peter Steinberger
d3111fbbcb fix: make browser relay bind address configurable (#39364) (thanks @mvanhorn) 2026-03-08 19:15:21 +00:00
Matt Van Horn
e883d0b556 fix(browser): add IP validation, fix upgrade handler for non-loopback bind
- Zod schema: validate relayBindHost with ipv4/ipv6 instead of bare string
- Upgrade handler: allow non-loopback connections when bindHost is explicitly
  non-loopback (e.g. 0.0.0.0 for WSL2), keeping loopback-only default
- Test: verify actual bind address via relay.bindHost instead of just checking
  reachability on 127.0.0.1 which passes regardless
- Expose bindHost on ChromeExtensionRelayServer type for inspection

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
2026-03-08 19:15:21 +00:00
Matt Van Horn
436ae8a07c fix(infra): make browser relay bind address configurable
Add browser.relayBindHost config option so the Chrome extension relay
server can bind to a non-loopback address (e.g. 0.0.0.0 for WSL2).
Defaults to 127.0.0.1 when unset, preserving current behavior.

Closes #39214

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
2026-03-08 19:15:21 +00:00
Mariano
404b1527e6
fix(acp): persist spawned child session history (#40137)
Merged via squash.

Prepared head SHA: 62de5d56691e1fd185cc617bb5e7283a14ce90b0
Co-authored-by: mbelinky <132747814+mbelinky@users.noreply.github.com>
Co-authored-by: mbelinky <132747814+mbelinky@users.noreply.github.com>
Reviewed-by: @mbelinky
2026-03-08 19:37:00 +01:00
Peter Steinberger
749eb4efea refactor: thread config runtime env through models config 2026-03-08 18:26:35 +00:00
Peter Steinberger
e5c06dd64a refactor: use model compat for anthropic tool payload normalization 2026-03-08 18:26:35 +00:00
GitBuck
caf1b84822
feat: allow compaction model override via config (#38753)
Merged via squash.

Prepared head SHA: a3d6d6c845c9ef492370c4cc12ea790ca92123f0
Co-authored-by: starbuck100 <25417736+starbuck100@users.noreply.github.com>
Co-authored-by: jalehman <550978+jalehman@users.noreply.github.com>
Reviewed-by: @jalehman
2026-03-08 10:47:34 -07:00
Peter Steinberger
b7ad8fd661 fix: fail closed talk provider selection 2026-03-08 16:22:48 +00:00
Ayaan Zaidi
28e46d04e5
fix(web-search): restore OpenRouter compatibility for Perplexity (#39937) (#39937) 2026-03-08 20:37:54 +05:30
Tak Hoffman
d9e8e8ac15
fix: resolve live config paths in status and gateway metadata (#39952)
* fix: resolve live config paths in status and gateway metadata

* fix: resolve remaining runtime config path references

* test: cover gateway config.set config path response
2026-03-08 09:59:32 -05:00
Peter Steinberger
e8ad80afc7 test: cover invalid talk config inputs 2026-03-08 14:58:29 +00:00
Peter Steinberger
b4c8950417 refactor: centralize talk silence timeout defaults 2026-03-08 14:58:29 +00:00
Peter Steinberger
4e2290b841 refactor: add canonical talk config payload 2026-03-08 14:58:29 +00:00
dano does design
6ff7e8f42e talk: add configurable silence timeout 2026-03-08 14:30:25 +00:00
Peter Steinberger
acac7e3132 fix: land Brave llm-context gaps (#33383) (thanks @thirumaleshp) 2026-03-08 13:57:12 +00:00
Thirumalesh
8a1015f1aa feat: add Brave Search LLM Context API mode for web_search
Add support for Brave's LLM Context API endpoint (/res/v1/llm/context)
as an optional mode for the web_search tool. When configured with
tools.web.search.brave.mode set to llm-context, the tool returns
pre-extracted page content optimized for LLM grounding instead of
standard URL/snippet results.

The llm-context cache key excludes count and ui_lang parameters that
the LLM Context API does not accept, preventing unnecessary cache
misses.

Closes #14992

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
2026-03-08 13:57:12 +00:00
gambletan
e5fdfec9dc
fix(config): accept "openclaw" as browser profile driver in Zod schema (#39374)
Merged via squash.

Prepared head SHA: 0eba5ab939e8074e44fe45dcb76e1a021d74156b
Co-authored-by: gambletan <266203672+gambletan@users.noreply.github.com>
Co-authored-by: altaywtf <9790196+altaywtf@users.noreply.github.com>
Reviewed-by: @altaywtf
2026-03-08 12:04:49 +03:00
Peter Steinberger
59102a1ff7 fix: add gemini 3.1 flash-lite support 2026-03-08 05:12:48 +00:00
Shadow
d902bae554
fix(discord): validate agentComponents config 2026-03-07 21:08:36 -06:00
Peter Steinberger
2646739d23 refactor: centralize strict numeric parsing 2026-03-08 03:02:25 +00:00
Peter Steinberger
100da9f45c fix: correct gemini flash model id 2026-03-08 02:32:58 +00:00
Peter Steinberger
9d7d961db8 fix: restore Telegram webhook-mode health after restarts
Landed from contributor PR #39313 by @fellanH.

Co-authored-by: Felix Hellström <30758862+fellanH@users.noreply.github.com>
2026-03-08 02:27:18 +00:00
Vincent Koc
2c7fb54956
Config: fail closed invalid config loads (#39071)
* Config: fail closed invalid config loads

* CLI: keep diagnostics on explicit best-effort config

* Tests: cover invalid config best-effort diagnostics

* Changelog: note invalid config fail-closed fix

* Status: pass best-effort config through status-all gateway RPCs

* CLI: pass config through gateway secret RPC

* CLI: skip plugin loading from invalid config

* Tests: align daemon token drift env precedence
2026-03-07 17:48:13 -08:00
Peter Steinberger
8cc477b873 refactor(sessions): simplify provider normalizer matching 2026-03-08 01:27:05 +00:00
Peter Steinberger
ad7399b6e6 refactor(sessions): add provider key normalizers 2026-03-08 01:17:06 +00:00
Peter Steinberger
74e3c071b2 refactor(discord): extract session key normalization 2026-03-08 01:15:29 +00:00
Peter Steinberger
cf1c2cc208 fix(discord): normalize DM session keys 2026-03-08 01:06:09 +00:00
Peter Steinberger
f53e10e3fd fix(config): fail closed on invalid config load (#9040, thanks @joetomasone)
Land #9040 by @joetomasone. Add fail-closed config loading, compat coverage, and changelog entry for #5052.

Co-authored-by: Joe Tomasone <joe@tomasone.com>
2026-03-07 22:39:26 +00:00
Peter Steinberger
7649712356 fix(config): degrade gracefully on missing env vars (#39050, thanks @akz142857)
Co-authored-by: ziy <ziyang.liu@wahool.com>
2026-03-07 21:12:26 +00:00
Peter Steinberger
92f5a2e252 fix(models): refresh gpt/gemini alias defaults (#38638, thanks @ademczuk)
Co-authored-by: ademczuk <andrew.demczuk@gmail.com>
2026-03-07 21:10:58 +00:00
Peter Steinberger
cf290e31bd fix(voice-call): align plugin manifest schema with runtime config fields (#38892)
Co-authored-by: giumex <giuliano.messina@gmail.com>
2026-03-07 19:49:58 +00:00
Peter Steinberger
4c2cb73055 fix(config): sanitize validation log output to prevent control character injection (#39116)
Co-authored-by: Bill <gsamzn@gmail.com>
2026-03-07 19:41:59 +00:00
Peter Steinberger
143eca8e86 refactor: dedupe runtime snapshot test fixtures 2026-03-07 19:02:01 +00:00
Vincent Koc
e4d80ed556
CI: restore main detect-secrets scan (#38438)
* Tests: stabilize detect-secrets fixtures

* Tests: fix rebased detect-secrets false positives

* Docs: keep snippets valid under detect-secrets

* Tests: finalize detect-secrets false-positive fixes

* Tests: reduce detect-secrets false positives

* Tests: keep detect-secrets pragmas inline

* Tests: remediate next detect-secrets batch

* Tests: tighten detect-secrets allowlists

* Tests: stabilize detect-secrets formatter drift
2026-03-07 10:06:35 -08:00
Josh Avant
8e20dd22d8
Secrets: harden SecretRef-safe models.json persistence (#38955) 2026-03-07 11:28:39 -06:00
Rodrigo Uroz
4c0b873a4d
Config/Compaction: expose safeguard preserve and quality settings (#25557)
Merged via squash.

Prepared head SHA: ea9904039a35d8d9ced55cd6d1c459a46666954d
Co-authored-by: rodrigouroz <384037+rodrigouroz@users.noreply.github.com>
Co-authored-by: jalehman <550978+jalehman@users.noreply.github.com>
Reviewed-by: @jalehman
2026-03-07 07:13:13 -08:00
Ayaan Zaidi
9e1de97a69
fix(telegram): route native topic commands to the active session (#38871)
* fix(telegram): resolve session entry for /stop in forum topics

Fixes #38675

- Export normalizeStoreSessionKey from store.ts for reuse
- Use it in resolveSessionEntryForKey so topic session keys (lowercase
  in store) are found when handling /stop
- Add test for forum topic session key lookup

* fix(telegram): share native topic routing with inbound messages

* fix: land telegram topic routing follow-up (#38871)

---------

Co-authored-by: xialonglee <li.xialong@xydigit.com>
2026-03-07 19:01:16 +05:30
Peter Steinberger
3c71e2bd48 refactor(core): extract shared dedup helpers 2026-03-07 10:41:05 +00:00
Vincent Koc
ba9eaf2ee2
fix(media): retain inbound media with recursive cleanup TTL (#38292)
* Config: add media retention TTL setting

* Media: recurse persisted media cleanup

* Gateway: add persisted media cleanup timer

* Media: harden retention cleanup sweep

* Media: make recursive retention cleanup opt-in

* Media: retry writes after empty-dir cleanup race
2026-03-06 22:06:09 -05:00
Vincent Koc
42e3d8d693
Secrets: add inline allowlist review set (#38314)
* Secrets: add inline allowlist review set

* Secrets: narrow detect-secrets file exclusions

* Secrets: exclude Docker fingerprint false positive

* Secrets: allowlist test and docs false positives

* Secrets: refresh baseline after allowlist updates

* Secrets: fix gateway chat fixture pragma

* Secrets: format pre-commit config

* Android: keep talk mode fixture JSON valid

* Feishu: rely on client timeout injection

* Secrets: allowlist provider auth test fixtures

* Secrets: allowlist onboard search fixtures

* Secrets: allowlist onboard mode fixture

* Secrets: allowlist gateway auth mode fixture

* Secrets: allowlist APNS wake test key

* Secrets: allowlist gateway reload fixtures

* Secrets: allowlist moonshot video fixture

* Secrets: allowlist auto audio fixture

* Secrets: allowlist tiny audio fixture

* Secrets: allowlist embeddings fixtures

* Secrets: allowlist resolve fixtures

* Secrets: allowlist target registry pattern fixtures

* Secrets: allowlist gateway chat env fixture

* Secrets: refresh baseline after fixture allowlists

* Secrets: reapply gateway chat env allowlist

* Secrets: reapply gateway chat env allowlist

* Secrets: stabilize gateway chat env allowlist

* Secrets: allowlist runtime snapshot save fixture

* Secrets: allowlist oauth profile fixtures

* Secrets: allowlist compaction identifier fixture

* Secrets: allowlist model auth fixture

* Secrets: allowlist model status fixtures

* Secrets: allowlist custom onboarding fixture

* Secrets: allowlist mattermost token summary fixtures

* Secrets: allowlist gateway auth suite fixtures

* Secrets: allowlist channel summary fixture

* Secrets: allowlist provider usage auth fixtures

* Secrets: allowlist media proxy fixture

* Secrets: allowlist secrets audit fixtures

* Secrets: refresh baseline after final fixture allowlists

* Feishu: prefer explicit client timeout

* Feishu: test direct timeout precedence
2026-03-06 19:35:26 -05:00
Vincent Koc
5320ee7731
fix(venice): harden discovery limits and tool support (#38306)
* Config: add supportsTools compat flag

* Agents: add model tool support helper

* Venice: sync discovery and fallback metadata

* Agents: skip tools for unsupported models

* Changelog: note Venice provider hardening

* Update CHANGELOG.md

* Venice: cap degraded discovery metadata

* Apply suggestion from @greptile-apps[bot]

Co-authored-by: greptile-apps[bot] <165735046+greptile-apps[bot]@users.noreply.github.com>

* Venice: tolerate partial discovery capabilities

* Venice: tolerate missing discovery specs

---------

Co-authored-by: greptile-apps[bot] <165735046+greptile-apps[bot]@users.noreply.github.com>
2026-03-06 19:07:11 -05:00
Efe Büken
03b9abab84
feat(compaction): make post-compaction context sections configurable (#34556)
Merged via squash.

Prepared head SHA: 491bb28544b2e0d3563dd1c78593ed2d829d65f6
Co-authored-by: efe-arv <259833796+efe-arv@users.noreply.github.com>
Co-authored-by: jalehman <550978+jalehman@users.noreply.github.com>
Reviewed-by: @jalehman
2026-03-06 14:57:15 -08:00
Vincent Koc
455430a6f8
Dead code: remove unused helper modules (#38318)
* Dead code: remove unused provider runtime policy helper

* Dead code: remove unused shared env writer

* Dead code: remove unused auth store path collector
2026-03-06 17:53:02 -05:00
Altay
6e962d8b9e
fix(agents): handle overloaded failover separately (#38301)
* fix(agents): skip auth-profile failure on overload

* fix(agents): note overload auth-profile fallback fix

* fix(agents): classify overloaded failures separately

* fix(agents): back off before overload failover

* fix(agents): tighten overload probe and backoff state

* fix(agents): persist overloaded cooldown across runs

* fix(agents): tighten overloaded status handling

* test(agents): add overload regression coverage

* fix(agents): restore runner imports after rebase

* test(agents): add overload fallback integration coverage

* fix(agents): harden overloaded failover abort handling

* test(agents): tighten overload classifier coverage

* test(agents): cover all-overloaded fallback exhaustion

* fix(cron): retry overloaded fallback summaries

* fix(cron): treat HTTP 529 as overloaded retry
2026-03-07 01:42:11 +03:00
Kesku
3d7bc5958d
feat(onboarding): add web search to onboarding flow (#34009)
* add web search to onboarding flow

* remove post onboarding step (now redundant)

* post-onboarding nudge if no web search set up

* address comments

* fix test mocking

* add enabled: false assertion to the no-key test

* --skip-search cli flag

* use provider that a user has a key for

* add assertions, replace the duplicated switch blocks

* test for quickstart fast-path with existing config key

* address comments

* cover quickstart falls through to key test

* bring back key source

* normalize secret inputs instead of direct string trimming

* preserve enabled: false if it's already set

* handle missing API keys in flow

* doc updates

* hasExistingKey to detect both plaintext strings and SecretRef objects

* preserve enabled state only on the "keep current" paths

* add test for preserving

* better gate flows

* guard against invalid provider values in config

* Update src/commands/configure.wizard.ts

Co-authored-by: greptile-apps[bot] <165735046+greptile-apps[bot]@users.noreply.github.com>

* format fix

* only mentions env var when it's actually available

* search apiKey fields now typed as SecretInput

* if no provider check if any search provider key is detectable

* handle both kimi keys

* remove .filter(Boolean)

* do not disable web_search after user enables it

* update resolveSearchProvider

* fix(onboarding): skip search key prompt in ref mode

* fix: add onboarding web search step (#34009) (thanks @kesku)

---------

Co-authored-by: greptile-apps[bot] <165735046+greptile-apps[bot]@users.noreply.github.com>
Co-authored-by: Shadow <hi@shadowing.dev>
2026-03-06 13:09:00 -06:00
Josh Lehman
fee91fefce
feature(context): extend plugin system to support custom context management (#22201)
* feat(context-engine): add ContextEngine interface and registry

Introduce the pluggable ContextEngine abstraction that allows external
plugins to register custom context management strategies.

- ContextEngine interface with lifecycle methods: bootstrap, ingest,
  ingestBatch, afterTurn, assemble, compact, prepareSubagentSpawn,
  onSubagentEnded, dispose
- Module-level singleton registry with registerContextEngine() and
  resolveContextEngine() (config-driven slot selection)
- LegacyContextEngine: pass-through implementation wrapping existing
  compaction behavior for 100% backward compatibility
- ensureContextEnginesInitialized() guard for safe one-time registration
- 19 tests covering contract, registry, resolution, and legacy parity

* feat(plugins): add context-engine slot and registerContextEngine API

Wire the ContextEngine abstraction into the plugin system so external
plugins can register context engines via the standard plugin API.

- Add 'context-engine' to PluginKind union type
- Add 'contextEngine' slot to PluginSlotsConfig (default: 'legacy')
- Wire registerContextEngine() through OpenClawPluginApi
- Export ContextEngine types from plugin-sdk for external consumers
- Restore proper slot-based resolution in registry

* feat(context-engine): wire ContextEngine into agent run lifecycle

Integrate the ContextEngine abstraction into the core agent run path:

- Resolve context engine once per run (reused across retries)
- Bootstrap: hydrate canonical store from session file on first run
- Assemble: route context assembly through pluggable engine
- Auto-compaction guard: disable built-in auto-compaction when
  the engine declares ownsCompaction (prevents double-compaction)
- AfterTurn: post-turn lifecycle hook for ingest + background
  compaction decisions
- Overflow compaction: route through contextEngine.compact()
- Dispose: clean up engine resources in finally block
- Notify context engine on subagent lifecycle events

Legacy engine: all lifecycle methods are pass-through/no-op, preserving
100% backward compatibility for users without a context engine plugin.

* feat(plugins): add scoped subagent methods and gateway request scope

Expose runtime.subagent.{run, waitForRun, getSession, deleteSession}
so external plugins can spawn sub-agent sessions without raw gateway
dispatch access.

Uses AsyncLocalStorage request-scope bridge to dispatch internally via
handleGatewayRequest with a synthetic operator client. Methods are only
available during gateway request handling.

- Symbol.for-backed global singleton for cross-module-reload safety
- Fallback gateway context for non-WS dispatch paths (Telegram/WhatsApp)
- Set gateway request scope for all handlers, not just plugin handlers
- 3 staleness tests for fallback context hardening

* feat(context-engine): route /compact and sessions.get through context engine

Wire the /compact command and sessions.get handler through the pluggable
ContextEngine interface.

- Thread tokenBudget and force parameters to context engine compact
- Route /compact through contextEngine.compact() when registered
- Wire sessions.get as runtime alias for plugin subagent dispatch
- Add .pebbles/ to .gitignore

* style: format with oxfmt 0.33.0

Fix duplicate import (ControlUiRootState in server.impl.ts) and
import ordering across all changed files.

* fix: update extension test mocks for context-engine types

Add missing subagent property to bluebubbles PluginRuntime mock.
Add missing registerContextEngine to lobster OpenClawPluginApi mock.

* fix(subagents): keep deferred delete cleanup retryable

* style: format run attempt for CI

* fix(rebase): remove duplicate embedded-run imports

* test: add missing gateway context mock export

* fix: pass resolved auth profile into afterTurn compaction

Ensure the embedded runner forwards resolved auth profile context into
legacy context-engine compaction params on the normal afterTurn path,
matching overflow compaction behavior. This allows downstream LCM
summarization to use the intended provider auth/profile consistently.

Also fix strict TS typing in external-link token dedupe and align an
attempt unit test reasoningLevel value with the current ReasoningLevel
enum.

Regeneration-Prompt: |
  We were debugging context-engine compaction where downstream summary
  calls were missing the right auth/profile context in normal afterTurn
  flow, while overflow compaction already propagated it. Preserve current
  behavior and keep changes additive: thread the resolved authProfileId
  through run -> attempt -> legacy compaction param builder without
  broad refactors.

  Add tests that prove the auth profile is included in afterTurn legacy
  params and that overflow compaction still passes it through run
  attempts. Keep existing APIs stable, and only adjust small type issues
  needed for strict compilation.

* fix: remove duplicate imports from rebase

* feat: add context-engine system prompt additions

* fix(rebase): dedupe attempt import declarations

* test: fix fetch mock typing in ollama autodiscovery

* fix(test): add registerContextEngine to diffs extension mock APIs

* test(windows): use path.delimiter in ios-team-id fixture PATH

* test(cron): add model formatting and precedence edge case tests

Covers:
- Provider/model string splitting (whitespace, nested paths, empty segments)
- Provider normalization (casing, aliases like bedrock→amazon-bedrock)
- Anthropic model alias normalization (opus-4.5→claude-opus-4-5)
- Precedence: job payload > session override > config default
- Sequential runs with different providers (CI flake regression pattern)
- forceNew session preserving stored model overrides
- Whitespace/empty model string edge cases
- Config model as string vs object format

* test(cron): fix model formatting test config types

* test(phone-control): add registerContextEngine to mock API

* fix: re-export ChannelKind from config-reload-plan

* fix: add subagent mock to plugin-runtime-mock test util

* docs: add changelog fragment for context engine PR #22201
2026-03-06 05:31:59 -08:00
Gustavo Madeira Santana
fa6c0e1b40 Gateway: allow slash-delimited schema lookup paths 2026-03-06 06:57:19 -05:00
Altay
ee6f7b1bf0
fix(ci): restore protocol and schema checks (#37470) 2026-03-06 11:46:17 +03:00