Vincent Koc
9c86a9fd23
fix(gateway): support image_url in OpenAI chat completions ( #34068 )
...
* fix(gateway): parse image_url in openai chat completions
* test(gateway): cover openai chat completions image_url flows
* docs(changelog): note openai image_url chat completions fix (#17685 )
* fix(gateway): harden openai image_url parsing and limits
* test(gateway): add openai image_url regression coverage
* docs(changelog): expand #17685 openai chat completions note
* Gateway: make OpenAI image_url URL fetch opt-in and configurable
* Diagnostics: redact image base64 payload data in trace logs
* Changelog: note OpenAI image_url hardening follow-ups
* Gateway: enforce OpenAI image_url total budget incrementally
* Gateway: scope OpenAI image_url extraction to the active turn
* Update CHANGELOG.md
2026-03-06 00:35:50 -05:00
Harold Hunt
d58dafae88
feat(telegram/acp): Topic Binding, Pin Binding Message, Fix Spawn Param Parsing ( #36683 )
...
* fix(acp): normalize unicode flags and Telegram topic binding
* feat(telegram/acp): restore topic-bound ACP and session bindings
* fix(acpx): clarify permission-denied guidance
* feat(telegram/acp): pin spawn bind notice in topics
* docs(telegram): document ACP topic thread binding behavior
* refactor(reply): share Telegram conversation-id resolver
* fix(telegram/acp): preserve bound session routing semantics
* fix(telegram): respect binding persistence and expiry reporting
* refactor(telegram): simplify binding lifecycle persistence
* fix(telegram): bind acp spawns in direct messages
* fix: document telegram ACP topic binding changelog (#36683 ) (thanks @huntharo)
---------
Co-authored-by: Onur <2453968+osolmaz@users.noreply.github.com>
2026-03-06 02:17:50 +01:00
Gustavo Madeira Santana
688b72e158
plugins: enforce prompt hook policy with runtime validation ( #36567 )
...
Merged via squash.
Prepared head SHA: 6b9d883b6ae33628235fb02ce39c0d0f46a065bb
Co-authored-by: gumadeiras <5599352+gumadeiras@users.noreply.github.com>
Co-authored-by: gumadeiras <5599352+gumadeiras@users.noreply.github.com>
Reviewed-by: @gumadeiras
2026-03-05 18:15:54 -05:00
Bob
063e493d3d
fix: decouple Discord inbound worker timeout from listener timeout ( #36602 ) (thanks @dutifulbob) ( #36602 )
...
Co-authored-by: Onur Solmaz <2453968+osolmaz@users.noreply.github.com>
2026-03-06 00:09:14 +01:00
Rodrigo Uroz
036c329716
Compaction/Safeguard: add summary quality audit retries ( #25556 )
...
Merged via squash.
Prepared head SHA: be473efd1635616ebbae6e649d542ed50b4a827f
Co-authored-by: rodrigouroz <384037+rodrigouroz@users.noreply.github.com>
Co-authored-by: jalehman <550978+jalehman@users.noreply.github.com>
Reviewed-by: @jalehman
2026-03-05 13:39:25 -08:00
Bob
6a705a37f2
ACP: add persistent Discord channel and Telegram topic bindings ( #34873 )
...
* docs: add ACP persistent binding experiment plan
* docs: align ACP persistent binding spec to channel-local config
* docs: scope Telegram ACP bindings to forum topics only
* docs: lock bound /new and /reset behavior to in-place ACP reset
* ACP: add persistent discord/telegram conversation bindings
* ACP: fix persistent binding reuse and discord thread parent context
* docs: document channel-specific persistent ACP bindings
* ACP: split persistent bindings and share conversation id helpers
* ACP: defer configured binding init until preflight passes
* ACP: fix discord thread parent fallback and explicit disable inheritance
* ACP: keep bound /new and /reset in-place
* ACP: honor configured bindings in native command flows
* ACP: avoid configured fallback after runtime bind failure
* docs: refine ACP bindings experiment config examples
* acp: cut over to typed top-level persistent bindings
* ACP bindings: harden reset recovery and native command auth
* Docs: add ACP bound command auth proposal
* Tests: normalize i18n registry zh-CN assertion encoding
* ACP bindings: address review findings for reset and fallback routing
* ACP reset: gate hooks on success and preserve /new arguments
* ACP bindings: fix auth and binding-priority review findings
* Telegram ACP: gate ensure on auth and accepted messages
* ACP bindings: fix session-key precedence and unavailable handling
* ACP reset/native commands: honor fallback targets and abort on bootstrap failure
* Config schema: validate ACP binding channel and Telegram topic IDs
* Discord ACP: apply configured DM bindings to native commands
* ACP reset tails: dispatch through ACP after command handling
* ACP tails/native reset auth: fix target dispatch and restore full auth
* ACP reset detection: fallback to active ACP keys for DM contexts
* Tests: type runTurn mock input in ACP dispatch test
* ACP: dedup binding route bootstrap and reset target resolution
* reply: align ACP reset hooks with bound session key
* docs: replace personal discord ids with placeholders
* fix: add changelog entry for ACP persistent bindings (#34873 ) (thanks @dutifulbob)
---------
Co-authored-by: Onur <2453968+osolmaz@users.noreply.github.com>
2026-03-05 09:38:12 +01:00
Gustavo Madeira Santana
e4b4486a96
Agent: unify bootstrap truncation warning handling ( #32769 )
...
Merged via squash.
Prepared head SHA: 5d6d4ddfa620011e267d892b402751847d5ac0c3
Co-authored-by: gumadeiras <5599352+gumadeiras@users.noreply.github.com>
Co-authored-by: gumadeiras <5599352+gumadeiras@users.noreply.github.com>
Reviewed-by: @gumadeiras
2026-03-03 16:28:38 -05:00
Shadow
65816657c2
feat(discord): add allowBots mention gating
2026-03-03 12:47:25 -06:00
Shadow
e28ff1215c
fix: discord auto presence health signal ( #33277 ) (thanks @thewilloftheshadow) ( #33277 )
2026-03-03 11:20:59 -06:00
nico-hoff
3eec79bd6c
feat(memory): add Ollama embedding provider ( #26349 )
...
Merged via /review-pr -> /prepare-pr -> /merge-pr.
Prepared head SHA: ac413865431614c352c3b29f2dfccc5593f0605a
Co-authored-by: nico-hoff <43175972+nico-hoff@users.noreply.github.com>
Co-authored-by: gumadeiras <5599352+gumadeiras@users.noreply.github.com>
Reviewed-by: @gumadeiras
2026-03-02 20:56:40 -05:00
Peter Steinberger
36dfd462a8
feat(acp): enable dispatch by default
2026-03-03 00:47:35 +00:00
Peter Steinberger
1b5ac8b0b1
feat(cli): add configurable banner tagline mode
2026-03-03 00:31:51 +00:00
Peter Steinberger
fc1787fd4b
feat(telegram): default streaming preview to partial
2026-03-02 23:04:12 +00:00
Peter Steinberger
6545317a2c
refactor(media): split audio helpers and attachment cache
2026-03-02 22:01:24 +00:00
AytuncYildizli
1b61269eec
feat(audio): auto-echo transcription to chat before agent processing
...
When echoTranscript is enabled in tools.media.audio config, the
transcription text is sent back to the originating chat immediately
after successful audio transcription — before the agent processes it.
This lets users verify what was heard from their voice note.
Changes:
- config/types.tools.ts: add echoTranscript (bool) and echoFormat
(string template) to MediaUnderstandingConfig
- media-understanding/apply.ts: sendTranscriptEcho() helper that
resolves channel/to from ctx, guards on isDeliverableMessageChannel,
and calls deliverOutboundPayloads best-effort
- config/schema.help.ts: help text for both new fields
- config/schema.labels.ts: labels for both new fields
- media-understanding/apply.echo-transcript.test.ts: 10 vitest cases
covering disabled/enabled/custom-format/no-audio/failed-transcription/
non-deliverable-channel/missing-from/OriginatingTo/delivery-failure
Default echoFormat: '📝 "{transcript}"'
Closes #32102
2026-03-02 21:47:09 +00:00
Vincent Koc
5d53b61d9e
fix(browser): honor profile attachOnly for loopback CDP ( #31429 )
...
* config(browser): allow profile attachOnly field
* config(schema): accept profile attachOnly
* browser(config): resolve per-profile attachOnly
* browser(runtime): honor profile attachOnly checks
* browser(routes): expose profile attachOnly in status
* config(labels): add browser profile attachOnly label
* config(help): document browser profile attachOnly
* test(config): cover profile attachOnly resolution
* test(browser): cover profile attachOnly runtime path
* test(config): include profile attachOnly help target
* changelog: note profile attachOnly override
* browser(runtime): prioritize attachOnly over loopback ownership error
* test(browser): cover attachOnly ws-failure ownership path
2026-03-02 00:49:57 -08:00
Vincent Koc
22be0c5801
fix(browser): support configurable CDP auto-port range start ( #31352 )
...
* config(browser): add cdpPortRangeStart type
* config(schema): validate browser.cdpPortRangeStart
* config(labels): add browser.cdpPortRangeStart label
* config(help): document browser.cdpPortRangeStart
* browser(config): resolve custom cdp port range start
* browser(profiles): allocate ports from resolved CDP range
* test(browser): cover cdpPortRangeStart config behavior
* test(browser): cover cdpPortRangeStart profile allocation
* test(browser): include CDP range fields in remote tab harness
* test(browser): include CDP range fields in ensure-tab harness
* test(browser): include CDP range fields in bridge auth config
* build(browser): add resolved CDP range metadata
* fix(browser): fallback CDP port allocation to derived range
* test(browser): cover missing resolved CDP range fallback
* fix(browser): remove duplicate resolved CDP range fields
* fix(agents): provide resolved CDP range in sandbox browser config
* chore(browser): format sandbox bridge resolved config
* chore(browser): reformat sandbox imports to satisfy oxfmt
2026-03-01 23:50:50 -08:00
Tyler Yust
d0ac1b0195
feat: add PDF analysis tool with native provider support ( #31319 )
...
* feat: add PDF analysis tool with native provider support
New `pdf` tool for analyzing PDF documents with model-powered analysis.
Architecture:
- Native PDF path: sends raw PDF bytes directly to providers that support
inline document input (Anthropic via DocumentBlockParam, Google Gemini
via inlineData with application/pdf MIME type)
- Extraction fallback: for providers without native PDF support, extracts
text via pdfjs-dist and rasterizes pages to images via @napi-rs/canvas,
then sends through the standard vision/text completion path
Key features:
- Single PDF (`pdf` param) or multiple PDFs (`pdfs` array, up to 10)
- Page range selection (`pages` param, e.g. "1-5", "1,3,7-9")
- Model override (`model` param) and file size limits (`maxBytesMb`)
- Auto-detects provider capability and falls back gracefully
- Same security patterns as image tool (SSRF guards, sandbox support,
local path roots, workspace-only policy)
Config (agents.defaults):
- pdfModel: primary/fallbacks (defaults to imageModel, then session model)
- pdfMaxBytesMb: max PDF file size (default: 10)
- pdfMaxPages: max pages to process (default: 20)
Model catalog:
- Extended ModelInputType to include "document" alongside "text"/"image"
- Added modelSupportsDocument() capability check
Files:
- src/agents/tools/pdf-tool.ts - main tool factory
- src/agents/tools/pdf-tool.helpers.ts - helpers (page range, config, etc.)
- src/agents/tools/pdf-native-providers.ts - direct API calls for Anthropic/Google
- src/agents/tools/pdf-tool.test.ts - 43 tests covering all paths
- Modified: model-catalog.ts, openclaw-tools.ts, config schema/types/labels/help
* fix: prepare pdf tool for merge (#31319 ) (thanks @tyler6204)
2026-03-01 22:39:12 -08:00
Peter Steinberger
cc0806dfab
docs(discord): standardize eventQueue timeout guidance
2026-03-02 02:22:59 +00:00
Ash (Bug Lab)
5b64b96c6c
fix(discord): add ackReactionScope channel override + off/none values ( #28268 )
2026-03-02 02:04:39 +00:00
Peter Steinberger
41cc46bbb4
feat(diagnostics): add configurable stuck-session warning threshold
2026-03-02 00:07:29 +00:00
Onur
8292401719
ACP: rename stream char limits to output/sessionUpdate
2026-03-01 20:39:24 +01:00
Onur
053e5eb506
ACP: remove maxMetaEventsPerTurn limit
2026-03-01 20:39:24 +01:00
Onur
43c57005a6
ACP: start typing lifecycle at turn start and harden delivery
2026-03-01 20:39:24 +01:00
Onur
c8b958e573
ACP: add hidden-boundary separator for hidden tool events
2026-03-01 20:39:24 +01:00
Onur
c3a1fe01ae
ACP: make final_only defer all projected output
2026-03-01 20:39:24 +01:00
Onur
4e2efaf659
ACP: simplify stream config to repeatSuppression
2026-03-01 20:39:24 +01:00
Onur
2466a9bb13
ACP: carry dedupe/projector updates onto configurable acpx branch
2026-03-01 20:39:24 +01:00
NIO
ea3955cd78
fix(cron): add retry policy for one-shot jobs on transient errors ( #24355 ) (openclaw#24435) thanks @hugenshen
...
Verified:
- pnpm install --frozen-lockfile
- pnpm check
- pnpm test -- --run src/cron/service.issue-regressions.test.ts src/config/config-misc.test.ts
Co-authored-by: hugenshen <16300669+hugenshen@users.noreply.github.com>
Co-authored-by: Tak Hoffman <781889+Takhoffman@users.noreply.github.com>
2026-03-01 06:58:03 -06:00
Vincent Koc
f16ecd1dac
fix(ollama): unify context window handling across discovery, merge, and OpenAI-compat transport ( #29205 )
...
* fix(ollama): inject num_ctx for OpenAI-compatible transport
* fix(ollama): discover per-model context and preserve higher limits
* fix(agents): prefer matching provider model for fallback limits
* fix(types): require numeric token limits in provider model merge
* fix(types): accept unknown payload in ollama num_ctx wrapper
* fix(types): simplify ollama settled-result extraction
* config(models): add provider flag for Ollama OpenAI num_ctx injection
* config(schema): allow provider num_ctx injection flag
* config(labels): label provider num_ctx injection flag
* config(help): document provider num_ctx injection flag
* agents(ollama): gate OpenAI num_ctx injection with provider config
* tests(ollama): cover provider num_ctx injection flag behavior
* docs(config): list provider num_ctx injection option
* docs(ollama): document OpenAI num_ctx injection toggle
* docs(config): clarify merge token-limit precedence
* config(help): note merge uses higher model token limits
* fix(ollama): cap /api/show discovery concurrency
* fix(ollama): restrict num_ctx injection to OpenAI compat
* tests(ollama): cover ipv6 and compat num_ctx gating
* fix(ollama): detect remote compat endpoints for ollama-labeled providers
* fix(ollama): cap per-model /api/show lookups to bound discovery load
2026-02-27 17:20:47 -08:00
Rodrigo Uroz
0fe6cf06b2
Compaction: preserve opaque identifiers in summaries (openclaw#25553) thanks @rodrigouroz
...
Verified:
- pnpm install --frozen-lockfile
- pnpm build
- pnpm check
- pnpm test:macmini
Co-authored-by: rodrigouroz <384037+rodrigouroz@users.noreply.github.com>
Co-authored-by: Tak Hoffman <781889+Takhoffman@users.noreply.github.com>
2026-02-27 08:14:05 -06:00
Onur Solmaz
a7929abad8
Discord: thread bindings idle + max-age lifecycle ( #27845 ) (thanks @osolmaz)
...
* refactor discord thread bindings to idle and max-age lifecycle
* fix: migrate legacy thread binding expiry and reduce hot-path disk writes
* refactor: remove remaining thread-binding ttl legacy paths
* fix: harden thread-binding lifecycle persistence
* Discord: fix thread binding types in message/reply paths
* Infra: handle win32 unknown inode in file identity checks
* Infra: relax win32 guarded-open identity checks
* Config: migrate threadBindings ttlHours to idleHours
* Revert "Infra: relax win32 guarded-open identity checks"
This reverts commit de94126771db072ecda6a014e80700310e76df61.
* Revert "Infra: handle win32 unknown inode in file identity checks"
This reverts commit 96fc5ddfb39762aa078d70dd4b4d3754e49a159b.
* Discord: re-read live binding state before sweep unbind
* fix: add changelog note for thread binding lifecycle update (#27845 ) (thanks @osolmaz)
---------
Co-authored-by: Onur Solmaz <onur@textcortex.com>
2026-02-27 10:02:39 +01:00
Peter Steinberger
38b6cee020
feat(config): add embedded pi project settings policy
2026-02-26 21:46:39 +01:00
Onur Solmaz
a7d56e3554
feat: ACP thread-bound agents ( #23580 )
...
* docs: add ACP thread-bound agents plan doc
* docs: expand ACP implementation specification
* feat(acp): route ACP sessions through core dispatch and lifecycle cleanup
* feat(acp): add /acp commands and Discord spawn gate
* ACP: add acpx runtime plugin backend
* fix(subagents): defer transient lifecycle errors before announce
* Agents: harden ACP sessions_spawn and tighten spawn guidance
* Agents: require explicit ACP target for runtime spawns
* docs: expand ACP control-plane implementation plan
* ACP: harden metadata seeding and spawn guidance
* ACP: centralize runtime control-plane manager and fail-closed dispatch
* ACP: harden runtime manager and unify spawn helpers
* Commands: route ACP sessions through ACP runtime in agent command
* ACP: require persisted metadata for runtime spawns
* Sessions: preserve ACP metadata when updating entries
* Plugins: harden ACP backend registry across loaders
* ACPX: make availability probe compatible with adapters
* E2E: add manual Discord ACP plain-language smoke script
* ACPX: preserve streamed spacing across Discord delivery
* Docs: add ACP Discord streaming strategy
* ACP: harden Discord stream buffering for thread replies
* ACP: reuse shared block reply pipeline for projector
* ACP: unify streaming config and adopt coalesceIdleMs
* Docs: add temporary ACP production hardening plan
* Docs: trim temporary ACP hardening plan goals
* Docs: gate ACP thread controls by backend capabilities
* ACP: add capability-gated runtime controls and /acp operator commands
* Docs: remove temporary ACP hardening plan
* ACP: fix spawn target validation and close cache cleanup
* ACP: harden runtime dispatch and recovery paths
* ACP: split ACP command/runtime internals and centralize policy
* ACP: harden runtime lifecycle, validation, and observability
* ACP: surface runtime and backend session IDs in thread bindings
* docs: add temp plan for binding-service migration
* ACP: migrate thread binding flows to SessionBindingService
* ACP: address review feedback and preserve prompt wording
* ACPX plugin: pin runtime dependency and prefer bundled CLI
* Discord: complete binding-service migration cleanup and restore ACP plan
* Docs: add standalone ACP agents guide
* ACP: route harness intents to thread-bound ACP sessions
* ACP: fix spawn thread routing and queue-owner stall
* ACP: harden startup reconciliation and command bypass handling
* ACP: fix dispatch bypass type narrowing
* ACP: align runtime metadata to agentSessionId
* ACP: normalize session identifier handling and labels
* ACP: mark thread banner session ids provisional until first reply
* ACP: stabilize session identity mapping and startup reconciliation
* ACP: add resolved session-id notices and cwd in thread intros
* Discord: prefix thread meta notices consistently
* Discord: unify ACP/thread meta notices with gear prefix
* Discord: split thread persona naming from meta formatting
* Extensions: bump acpx plugin dependency to 0.1.9
* Agents: gate ACP prompt guidance behind acp.enabled
* Docs: remove temp experiment plan docs
* Docs: scope streaming plan to holy grail refactor
* Docs: refactor ACP agents guide for human-first flow
* Docs/Skill: add ACP feature-flag guidance and direct acpx telephone-game flow
* Docs/Skill: add OpenCode and Pi to ACP harness lists
* Docs/Skill: align ACP harness list with current acpx registry
* Dev/Test: move ACP plain-language smoke script and mark as keep
* Docs/Skill: reorder ACP harness lists with Pi first
* ACP: split control-plane manager into core/types/utils modules
* Docs: refresh ACP thread-bound agents plan
* ACP: extract dispatch lane and split manager domains
* ACP: centralize binding context and remove reverse deps
* Infra: unify system message formatting
* ACP: centralize error boundaries and session id rendering
* ACP: enforce init concurrency cap and strict meta clear
* Tests: fix ACP dispatch binding mock typing
* Tests: fix Discord thread-binding mock drift and ACP request id
* ACP: gate slash bypass and persist cleared overrides
* ACPX: await pre-abort cancel before runTurn return
* Extension: pin acpx runtime dependency to 0.1.11
* Docs: add pinned acpx install strategy for ACP extension
* Extensions/acpx: enforce strict local pinned startup
* Extensions/acpx: tighten acp-router install guidance
* ACPX: retry runtime test temp-dir cleanup
* Extensions/acpx: require proactive ACPX repair for thread spawns
* Extensions/acpx: require restart offer after acpx reinstall
* extensions/acpx: remove workspace protocol devDependency
* extensions/acpx: bump pinned acpx to 0.1.13
* extensions/acpx: sync lockfile after dependency bump
* ACPX: make runtime spawn Windows-safe
* fix: align doctor-config-flow repair tests with default-account migration (#23580 ) (thanks @osolmaz)
2026-02-26 11:00:09 +01:00
Sid
c289b5ff9f
fix(config): preserve agent-level apiKey/baseUrl during models.json merge ( #27293 )
...
Merged via /review-pr -> /prepare-pr -> /merge-pr.
Prepared head SHA: 6b4b37b03d74e40e14afc2c55fef24a1e59fb0b3
Co-authored-by: Sid-Qin <201593046+Sid-Qin@users.noreply.github.com>
Co-authored-by: gumadeiras <5599352+gumadeiras@users.noreply.github.com>
Reviewed-by: @gumadeiras
2026-02-26 03:46:36 -05:00
Peter Steinberger
8a006a3260
feat(heartbeat): add directPolicy and restore default direct delivery
2026-02-26 03:57:03 +01:00
Peter Steinberger
42f455739f
fix(security): clarify denyCommands exact-match guidance
2026-02-26 00:55:35 +01:00
Peter Steinberger
eb73e87f18
fix(session): prevent silent overflow on parent thread forks ( #26912 )
...
Lands #26912 from @markshields-tl with configurable session.parentForkMaxTokens and docs/tests/changelog updates.
Co-authored-by: Mark Shields <239231357+markshields-tl@users.noreply.github.com>
2026-02-25 23:54:02 +00:00
Peter Steinberger
9cd50c51b0
fix(discord): harden voice DAVE receive reliability ( #25861 )
...
Reimplements and consolidates related work:
- #24339 stale disconnect/destroyed session guards
- #25312 voice listener cleanup on stop
- #23036 restore @snazzah/davey runtime dependency
Adds Discord voice DAVE config passthrough, repeated decrypt failure
rejoin recovery, regression tests, docs, and changelog updates.
Co-authored-by: Frank Yang <frank.ekn@gmail.com>
Co-authored-by: Do Cao Hieu <admin@docaohieu.com>
2026-02-25 00:19:50 +00:00
Peter Steinberger
5552f9073f
refactor(sandbox): centralize network mode policy helpers
2026-02-24 23:26:46 +00:00
Peter Steinberger
0e155690be
fix(config): add operational guidance to legacy talk help
...
Co-authored-by: Nimrod Gutman <nimrod.g@singular.net>
2026-02-24 15:02:52 +00:00
Peter Steinberger
44162055a8
fix(config): dedupe talk schema help keys
2026-02-24 15:02:52 +00:00
Nimrod Gutman
d58f71571a
feat(talk): add provider-agnostic config with legacy compatibility
2026-02-24 15:02:52 +00:00
Nimrod Gutman
d1f28c954e
feat(gateway): surface talk elevenlabs config metadata
2026-02-24 15:02:52 +00:00
Peter Steinberger
223d7dc23d
feat(gateway)!: require explicit non-loopback control-ui origins
2026-02-24 01:57:11 +00:00
Peter Steinberger
5eb72ab769
fix(security): harden browser SSRF defaults and migrate legacy key
2026-02-24 01:52:01 +00:00
Gustavo Madeira Santana
eff3c5c707
Session/Cron maintenance hardening and cleanup UX ( #24753 )
...
Merged via /review-pr -> /prepare-pr -> /merge-pr.
Prepared head SHA: 7533b85156186863609fee9379cd9aedf74435af
Co-authored-by: gumadeiras <5599352+gumadeiras@users.noreply.github.com>
Co-authored-by: shakkernerd <165377636+shakkernerd@users.noreply.github.com>
Reviewed-by: @shakkernerd
2026-02-23 22:39:48 +00:00
Peter Steinberger
9af3ec92a5
fix(gateway): add HSTS header hardening and docs
2026-02-23 19:47:29 +00:00
Peter Steinberger
e02c470d5e
feat(tools): add kimi web_search provider
...
Co-authored-by: adshine <adshine@users.noreply.github.com>
2026-02-23 18:27:37 +00:00
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