Commit Graph

4865 Commits

Author SHA1 Message Date
Vincent Koc
8e821a061c fix(telegram): scope polling offsets per bot and await shared runner stop (#24549)
* Telegram: scope polling offsets and await shared runner stop

* Changelog: remove unrelated session-fix entries from PR

* Update CHANGELOG.md
2026-02-23 09:43:47 -05:00
AkosCz
3a3c2da916 [Feature]: Add Gemini (Google Search grounding) as web_search provider (#13075)
* feat: add Gemini (Google Search grounding) as web_search provider

Add Gemini as a fourth web search provider alongside Brave, Perplexity,
and Grok. Uses Gemini's built-in Google Search grounding tool to return
search results with citations.

- Add runGeminiSearch() with Google Search grounding via tools API
- Resolve Gemini's grounding redirect URLs to direct URLs via parallel
  HEAD requests (5s timeout, graceful fallback)
- Add Gemini config block (apiKey, model) with env var fallback
- Default model: gemini-2.5-flash (fast, cheap, grounding-capable)
- Strip API key from error messages for security
- Add config validation tests for Gemini provider
- Update docs/tools/web.md with Gemini provider documentation

Closes #13074

* feat: auto-detect search provider from available API keys

When no explicit provider is configured, resolveSearchProvider now
checks for available API keys in priority order (Brave → Gemini →
Perplexity → Grok) and selects the first provider with a valid key.

- Add auto-detection logic using existing resolve*ApiKey functions
- Export resolveSearchProvider via __testing_provider for tests
- Add 8 tests covering auto-detection, priority order, and explicit override
- Update docs/tools/web.md with auto-detection documentation

* fix: merge __testing exports, downgrade auto-detect log to debug

* fix: use defaultRuntime.log instead of .debug (not in RuntimeEnv type)

* fix: mark gemini apiKey as sensitive in zod schema

* fix: address Greptile review — add externalContent to Gemini payload, add Gemini/Grok entries to schema labels/help, remove dead schema-fields.ts

* fix(web-search): add JSON parse guard for Gemini API responses

Addresses Greptile review comment: add try/catch to handle non-JSON
responses from Gemini API gracefully, preventing runtime errors on
malformed responses.

Note: FIELD_HELP entries for gemini.apiKey and gemini.model were
already present in schema.help.ts, and gemini.apiKey was already
marked as sensitive in zod-schema.agent-runtime.ts (both fixed in
earlier commits).

* fix: use structured readResponseText result in Gemini error path

readResponseText returns { text, truncated, bytesRead }, not a string.
The Gemini error handler was using the result object directly, which
would always be truthy and never fall through to res.statusText.
Align with Perplexity/xAI/Brave error patterns.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

* style: fix import order and formatting after rebase onto main

* Web search: send Gemini API key via header

---------

Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
Co-authored-by: Vincent Koc <vincentkoc@ieee.org>
2026-02-23 09:30:51 -05:00
Nimrod Gutman
9d37654a90 fix(agents): gate auto reasoning by effective thinking level (openclaw#24335) thanks @Kay-051 2026-02-23 15:38:08 +02:00
Peter Steinberger
9757d2bb64 fix(agents): normalize strict openai-compatible turn ordering
Co-authored-by: liuwenyong1985 <48443240+liuwenyong1985@users.noreply.github.com>
2026-02-23 12:44:23 +00:00
Peter Steinberger
15e32c7341 fix(models): refresh Moonshot Kimi vision capabilities
Co-authored-by: manikv12 <mac1317@live.missouristate.edu>
2026-02-23 12:44:23 +00:00
Peter Steinberger
9bd04849ed fix(agents): detect Kimi model-token-limit overflows
Co-authored-by: Danilo Falcão <danilo@falcao.org>
2026-02-23 12:44:23 +00:00
Peter Steinberger
3640484e28 fix(agents): map Moonshot developer role compatibility
Co-authored-by: Sheng-Fu Chuang <sedernet@gmail.com>

# Conflicts:
#	CHANGELOG.md
2026-02-23 12:44:23 +00:00
Ayaan Zaidi
2247b81219 fix(auto-reply): hide direct-chat metadata without sender-id sentinel (openclaw#24373) thanks @jd316
Co-authored-by: jd316 <138361777+jd316@users.noreply.github.com>
Co-authored-by: obviyus <22031114+obviyus@users.noreply.github.com>
2026-02-23 15:25:31 +05:30
边黎安
a4c373935f fix(agents): fall back to agents.defaults.model when agent has no model config (#24210)
Merged via /review-pr -> /prepare-pr -> /merge-pr.

Prepared head SHA: 0f272b1027
Co-authored-by: bianbiandashen <16240681+bianbiandashen@users.noreply.github.com>
Co-authored-by: gumadeiras <5599352+gumadeiras@users.noreply.github.com>
Reviewed-by: @gumadeiras
2026-02-23 03:18:55 -05:00
Vincent Koc
db32677f1d Update CHANGELOG.md 2026-02-23 03:03:06 -05:00
taw0002
3c57bf4c85 fix: treat HTTP 502/503/504 as failover-eligible (timeout reason) (#21017)
* fix: treat HTTP 502/503/504 as failover-eligible (timeout reason)

When a model API returns 502 Bad Gateway, 503 Service Unavailable, or
504 Gateway Timeout, the error object carries the status code directly.
resolveFailoverReasonFromError() only checked 402/429/401/403/408/400,
so 5xx server errors fell through to message-based classification which
requires the status code to appear at the start of the error message.

Many API SDKs (Google, Anthropic) set err.status = 503 without prefixing
the message with '503', so the message classifier never matched and
failover never triggered — the run retried the same broken model.

Add 502/503/504 to the status-code branch, returning 'timeout' (matching
the existing behavior of isTransientHttpError in the message classifier).

Fixes #20999

* Changelog: add failover 502/503/504 note with credits

* Failover: classify HTTP 504 as transient in message parser

* Changelog: credit taw0002 and vincentkoc for failover fix

---------

Co-authored-by: Vincent Koc <vincentkoc@ieee.org>
2026-02-23 03:01:57 -05:00
Frank Yang
f208518cb9 fix(config): keep write inputs immutable when using unsetPaths (#24134)
Merged via /review-pr -> /prepare-pr -> /merge-pr.

Prepared head SHA: 951f8480c3
Co-authored-by: frankekn <4488090+frankekn@users.noreply.github.com>
Co-authored-by: gumadeiras <5599352+gumadeiras@users.noreply.github.com>
Reviewed-by: @gumadeiras
2026-02-23 02:51:13 -05:00
Vincent Koc
0e28e50b45 fix(security): detect obfuscated commands that bypass allowlist filters (#24287)
* security(exec): add obfuscated command detector

* test(exec): cover obfuscation detector patterns

* security(exec): enforce obfuscation approval on gateway host

* security(exec): enforce obfuscation approval on node host

* test(exec): prevent obfuscation timeout bypass

* chore(changelog): credit obfuscation security fix
2026-02-23 02:50:06 -05:00
Vincent Koc
c8a62e1cea Skills/Python: harden script edge cases and add regression tests (#24277)
* Skill creator: skip self-including .skill output

* Skill creator tests: cover output-dir-inside-skill case

* Skill validator: parse frontmatter robustly across newlines

* Skill validator tests: add CRLF and malformed frontmatter coverage

* Model usage: require positive --days value

* Model usage tests: cover --days validation and filtering

* Nano banana: close input image handles after loading

* Skill validator: keep type hints compatible with older python

* Changelog: credit @vincentkoc for Python skills hardening
2026-02-23 02:34:23 -05:00
Glucksberg
36400df086 fix: pass agentDir to /compact command for agent-specific auth (#24133)
Merged via /review-pr -> /prepare-pr -> /merge-pr.

Prepared head SHA: 4bb10ca78c
Co-authored-by: Glucksberg <80581902+Glucksberg@users.noreply.github.com>
Co-authored-by: gumadeiras <5599352+gumadeiras@users.noreply.github.com>
Reviewed-by: @gumadeiras
2026-02-23 02:33:35 -05:00
Vignesh Natarajan
9ea740afb6 Sessions: canonicalize mixed-case session keys 2026-02-22 23:27:08 -08:00
Vincent Koc
1be8897339 Security: enforce pre-commit security checks in hooks and CI (#24265)
* chore(pre-commit): add security audit hooks

* ci(security): enforce security hooks in ci

* docs(changelog): add security hooks and ci attribution
2026-02-23 02:20:00 -05:00
Vincent Koc
4ab4754bdf chore(changelog): credit skill packager hardening follow-up 2026-02-23 02:09:05 -05:00
Vincent Koc
76dabd5214 CI/Skills: add Python lint and test harness for skills scripts (#24246)
* CI: add skills Python checks job

* Chore: add Python lint and test pre-commit hooks

* Tests: fix skill-creator package test import path

* Chore: add Python tooling config for skills scripts

* CI: run all skills Python tests

* Chore: run all skills Python tests in pre-commit

* Chore: enable pytest discovery for all skills tests

* Changelog: note skills Python quality harness
2026-02-23 01:52:00 -05:00
Vignesh Natarajan
de96f5fed2 CLI/Sessions: honor default agent for implicit store path 2026-02-22 22:47:10 -08:00
Vincent Koc
af4330ef75 Update CHANGELOG.md 2026-02-23 01:44:53 -05:00
Misha Kolesnik
ec1bc41cf2 fix(openrouter): remove conflicting reasoning_effort from payload (#24120)
Merged via /review-pr -> /prepare-pr -> /merge-pr.

Prepared head SHA: cc8ef4bb05
Co-authored-by: tenequm <22403766+tenequm@users.noreply.github.com>
Co-authored-by: gumadeiras <5599352+gumadeiras@users.noreply.github.com>
Reviewed-by: @gumadeiras
2026-02-23 01:41:29 -05:00
CornBrother0x
f3adf142c1 fix(security): escape user input in HTML gallery to prevent stored XSS (#16958)
* Security/openai-image-gen: escape HTML gallery user input

* Tests/openai-image-gen: add gallery XSS regression coverage

* Changelog: add openai-image-gen XSS hardening note

---------

Co-authored-by: Vincent Koc <vincentkoc@ieee.org>
2026-02-23 01:39:58 -05:00
Vignesh Natarajan
5ad5ea53cd Agent: resolve resumed session agent scope before run 2026-02-22 22:38:05 -08:00
brandonwise
7fab4d128a fix(security): redact sensitive data in OTEL log exports (CWE-532) (#18182)
* fix(security): redact sensitive data in OTEL log exports (CWE-532)

The diagnostics-otel plugin exports ALL application logs to external
OTLP collectors without filtering. This leaks API keys, tokens, and
other sensitive data to third-party observability platforms.

Changes:
- Export redactSensitiveText from plugin-sdk for extension use
- Apply redaction to log messages before OTEL export
- Apply redaction to string attribute values
- Add tests for API key and token redaction

The existing redactSensitiveText function handles common patterns:
- API keys (sk-*, ghp_*, gsk_*, AIza*, etc.)
- Bearer tokens
- PEM private keys
- ENV-style assignments (KEY=value)
- JSON credential fields

Fixes #12542

* fix: also redact error/reason in trace spans

Address Greptile feedback:
- Redact evt.error in webhook.error span attributes and status
- Redact evt.reason in message.processed span attributes
- Redact evt.error in message.processed span status

* fix: handle undefined evt.error in type guard

* fix: redact session.state reason in OTEL metrics

Addresses Greptile feedback - session.state reason field now goes
through redactSensitiveText() like message.processed reason.

* test(diagnostics-otel): update service context for stateDir API change

* OTEL diagnostics: redact sensitive values before export

* OTEL diagnostics tests: cover message, attribute, and session reason redaction

* Changelog: note OTEL sensitive-data redaction fix

* Changelog: move OTEL redaction entry to current unreleased

---------

Co-authored-by: Vincent Koc <vincentkoc@ieee.org>
2026-02-23 01:35:32 -05:00
Ayaan Zaidi
fda98f5605 docs(changelog): add telegram topic target fix 2026-02-23 11:45:18 +05:30
Tak Hoffman
9e1a13bf4c Gateway/UI: data-driven agents tools catalog with provenance (openclaw#24199) thanks @Takhoffman
Verified:
- pnpm install --frozen-lockfile
- pnpm build
- gh pr checks 24199 --watch --fail-fast

Co-authored-by: Takhoffman <781889+Takhoffman@users.noreply.github.com>
Co-authored-by: Tak Hoffman <781889+Takhoffman@users.noreply.github.com>
2026-02-22 23:55:59 -06:00
Evgeny Zislis
78f801e243 Validate Telegram delivery targets to reject invalid formats (#21930)
Merged via /review-pr -> /prepare-pr -> /merge-pr.

Prepared head SHA: 02c9b1c3dd
Co-authored-by: kesor <7056+kesor@users.noreply.github.com>
Co-authored-by: obviyus <22031114+obviyus@users.noreply.github.com>
Reviewed-by: @obviyus
2026-02-23 10:44:46 +05:30
Tak Hoffman
77c3b142a9 Web UI: add full cron edit parity, all-jobs run history, and compact filters (openclaw#24155) thanks @Takhoffman
Verified:
- pnpm install --frozen-lockfile
- pnpm build
- pnpm check
- pnpm test:macmini

Co-authored-by: Takhoffman <781889+Takhoffman@users.noreply.github.com>
Co-authored-by: Tak Hoffman <781889+Takhoffman@users.noreply.github.com>
2026-02-22 23:05:42 -06:00
Peter Steinberger
382fe8009a refactor!: remove google-antigravity provider support 2026-02-23 05:20:14 +01:00
Peter Steinberger
558a0137bb chore(release): bump versions to 2026.2.23 2026-02-23 05:13:46 +01:00
Tak Hoffman
a54dc7fe80 Cron: suppress fallback main summary for delivery-target errors (openclaw#24074) thanks @Takhoffman
Verified:
- pnpm build
- pnpm check
- pnpm test:macmini

Co-authored-by: Takhoffman <781889+Takhoffman@users.noreply.github.com>
Co-authored-by: Tak Hoffman <781889+Takhoffman@users.noreply.github.com>
2026-02-22 20:24:08 -06:00
Tak Hoffman
457835b104 Compaction: count only completed auto-compactions (#24056)
* Compaction: count only completed auto-compactions

* Compaction: count only non-retry completions

* Changelog: note completed-only compaction counting

* Agents/Compaction: guard optional compaction increment
2026-02-22 20:16:45 -06:00
Tak Hoffman
259d863353 Gateway: harden cron.runs jobId path handling (openclaw#24038) thanks @Takhoffman
Verified:
- pnpm install --frozen-lockfile
- pnpm build
- pnpm check
- pnpm test:macmini

Co-authored-by: Takhoffman <781889+Takhoffman@users.noreply.github.com>
Co-authored-by: Tak Hoffman <781889+Takhoffman@users.noreply.github.com>
2026-02-22 19:35:26 -06:00
Vignesh Natarajan
a10ec2607f Gateway/Chat UI: sanitize untrusted wrapper markup in final payloads 2026-02-22 16:53:54 -08:00
Peter Steinberger
278331c49c fix(exec): restore sandbox as implicit host default 2026-02-23 01:48:24 +01:00
Tak Hoffman
211ab9e4f6 Cron: persist manual run marker before unlock (#23993)
* Cron: persist manual run marker before unlock

* Cron tests: relax wakeMode now microtask wait after run lock persist
2026-02-22 18:39:37 -06:00
SleuthCo.AI
9c87b53c8e security(cli): redact sensitive values in config get output (#23654)
* security(cli): redact sensitive values in config get output

`runConfigGet()` reads raw config values but never applies redaction
before printing. When a user runs `openclaw config get gateway.token`
the real credential is printed to the terminal, leaking it into shell
history, scrollback buffers, and screenshots.

Use the existing `redactConfigObject()` (from redact-snapshot.ts,
already used by the Web UI path) to scrub sensitive fields before
`getAtPath()` resolves the requested key.

Fixes #13683

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

* CLI/Config: add redaction regression test and changelog

---------

Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
Co-authored-by: Vincent Koc <vincentkoc@ieee.org>
2026-02-22 19:37:33 -05:00
Vignesh Natarajan
f0542df9f0 Docker: precreate identity dir in docker setup 2026-02-22 16:33:53 -08:00
Peter Steinberger
b19a6ee62d docs(changelog): move mistral to top and add synology chat 2026-02-23 01:25:22 +01:00
Phineas1500
8a8faf066e doctor: clean up legacy Linux gateway services (#21188)
* Doctor: clean up legacy Linux gateway services

* doctor: refactor legacy service cleanup flow

* doctor: fix legacy systemd cleanup map key typing

* doctor: add changelog entry for legacy Linux service cleanup

---------

Co-authored-by: Vincent Koc <vincentkoc@ieee.org>
2026-02-22 19:18:59 -05:00
Peter Steinberger
1c2c7843a8 docs: add synology channel docs and fix unreleased changelog 2026-02-23 01:16:05 +01:00
Phineas1500
320b62265d fix(models): synthesize antigravity Gemini 3.1 pro high/low models (#22899)
* Models: add antigravity Gemini 3.1 forward-compat

* models: propagate availability to Gemini 3.1 dot IDs

* test(models): format Gemini 3.1 forward-compat test

* test(models): type Gemini 3.1 forward-compat fixtures

* models: add changelog note for antigravity gemini 3.1 forward-compat

---------

Co-authored-by: Vincent Koc <vincentkoc@ieee.org>
2026-02-22 19:11:39 -05:00
Vignesh Natarajan
5c7c37a02a Agents: infer auth-profile unavailable failover reason 2026-02-22 16:10:32 -08:00
Phineas1500
331b728b8d fix(tui): add OSC 8 hyperlinks for wrapped URLs (#17814)
* feat(tui): add OSC 8 hyperlinks to make wrapped URLs clickable

Long URLs that exceed terminal width get broken across lines by pi-tui's
word wrapping, making them unclickable. Post-process rendered markdown
output to add OSC 8 terminal hyperlink sequences around URL fragments,
so each line fragment links to the full URL. Gracefully degrades on
terminals without OSC 8 support.

* tui: harden OSC8 URL extraction and prefix resolution

* tui: add changelog entry for OSC 8 markdown hyperlinks

---------

Co-authored-by: Vincent Koc <vincentkoc@ieee.org>
2026-02-22 19:09:07 -05:00
Vincent Koc
d92ba4f8aa feat: Provider/Mistral full support for Mistral on OpenClaw 🇫🇷 (#23845)
* Onboard: add Mistral auth choice and CLI flags

* Onboard/Auth: add Mistral provider config defaults

* Auth choice: wire Mistral API-key flow

* Onboard non-interactive: support --mistral-api-key

* Media understanding: add Mistral Voxtral audio provider

* Changelog: note Mistral onboarding and media support

* Docs: add Mistral provider and onboarding/media references

* Tests: cover Mistral media registry/defaults and auth mapping

* Memory: add Mistral embeddings provider support

* Onboarding: refresh Mistral model metadata

* Docs: document Mistral embeddings and endpoints

* Memory: persist Mistral embedding client state in managers

* Memory: add regressions for mistral provider wiring

* Gateway: add live tool probe retry helper

* Gateway: cover live tool probe retry helper

* Gateway: retry malformed live tool-read probe responses

* Memory: support plain-text batch error bodies

* Tests: add Mistral Voxtral live transcription smoke

* Docs: add Mistral live audio test command

* Revert: remove Mistral live voice test and docs entry

* Onboard: re-export Mistral default model ref from models

* Changelog: credit joeVenner for Mistral work

* fix: include Mistral in auto audio key fallback

* Update CHANGELOG.md

* Update CHANGELOG.md

---------

Co-authored-by: Shakker <shakkerdroid@gmail.com>
2026-02-23 00:03:56 +00:00
yinghaosang
a66b98a9da fix(plugins): hook systemPrompt gets collected then thrown away (#14583) (#14602)
* fix(plugins): apply before_agent_start hook systemPrompt to session (#14583)

* fix(plugins): apply legacy systemPrompt override and add changelog credit

---------

Co-authored-by: yinghaosang <yinghaosang@users.noreply.github.com>
Co-authored-by: Vincent Koc <vincentkoc@ieee.org>
2026-02-22 18:58:21 -05:00
Vignesh Natarajan
1000ff04ea fix(memory): hard-cap embedding inputs before batch 2026-02-22 15:40:18 -08:00
Aether AI
d306fc8ef1 fix(security): OC-07 redact session history credentials and enforce webhook secret (#16928)
* Security: refresh sessions history redaction patch

* tests: align sessions_history redaction-only truncation expectation

* Changelog: credit sessions history security hardening

---------

Co-authored-by: Vincent Koc <vincentkoc@ieee.org>
2026-02-22 18:29:40 -05:00
Tak Hoffman
3efe63d1ad Cron: respect aborts in main wake-now retries (#23967)
* Cron: respect aborts in main wake-now retries

* Changelog: add main-session cron abort retry fix note

* Cron tests: format post-rebase conflict resolution
2026-02-22 17:19:27 -06:00