LiLan0125
db0f6f09dc
fix(google): restore image tool results for prefixed Gemini 2 models ( #102382 )
...
* fix(google): handle prefixed Gemini 2 image fallback
* test(google): cover prefixed Gemini 3 image responses
* docs(changelog): note prefixed Gemini fallback
Co-authored-by: 李兰 0668001394 <li.lan3@xydigit.com >
---------
Co-authored-by: Peter Steinberger <steipete@gmail.com >
2026-07-09 15:09:05 +01:00
Alix-007
e5259fa8bb
fix(google): add timeout to Vertex ADC token refresh ( #102050 )
...
* fix(google): add timeout to Vertex ADC token refresh
* test(google): consolidate ADC timeout proof
* fix(google): bound all ADC token refreshes
* test(google): observe ADC timeout before advancing time
* fix(google): keep dependency timeout claims exact
* fix(google): bound library-managed ADC refreshes
* fix(google): recover after ADC refresh timeout
---------
Co-authored-by: Peter Steinberger <steipete@gmail.com >
2026-07-09 13:46:33 +01:00
Vishal Dharmadhikari
d708df47a3
improve(google): identify OpenClaw Gemini API traffic ( #101834 )
2026-07-07 16:09:02 -06:00
chenxiaoyu209
5e64c61368
fix(google): resolve thought_signature gate for Gemini latest aliases ( #100605 )
2026-07-06 09:12:35 +01:00
Peter Steinberger
aaf5ab910c
fix: land ten small reliability fixes ( #100483 )
...
* fix(agents): harden LSP process failures
Source: #100450
Co-authored-by: morluto <williamlin1327@gmail.com >
* fix(sandbox): report effective workspace layout
Sources: #100435 , #100439
Co-authored-by: Aniruddha Adak <aniruddhaadak80@users.noreply.github.com >
Co-authored-by: ZengWen-DT <ceng.wen@xydigit.com >
* fix(security): fail install checks on stream errors
Source: #100413
Co-authored-by: 陈宪彪0668000387 <chen.xianbiao@xydigit.com >
* fix(android): normalize all-day calendar events
Source: #100032
Co-authored-by: NianJiuZst <180004567+NianJiuZst@users.noreply.github.com >
* fix(ios): serialize push-to-talk lifecycle
Source: #99942
Co-authored-by: NianJiuZst <180004567+NianJiuZst@users.noreply.github.com >
* fix(talk): reject inherited provider names
Source: #99849
Co-authored-by: zenglingbiao <zeng.lingbiao@xydigit.com >
* fix(android): stop voice capture in background
Source: #99840
Co-authored-by: xialonglee <li.xialong@xydigit.com >
* fix(cron): preserve fallback result classification
Source: #99913
Co-authored-by: jincheng-xydt <xu.jincheng@xydigit.com >
* fix(google): bound Vertex response decompression
Source: #99812
Co-authored-by: 黄剑雄0668001315 <huang.jianxiong@xydigit.com >
* fix(plugins): report malformed discovery JSON
Source: #99892
Co-authored-by: 陈宪彪0668000387 <chen.xianbiao@xydigit.com >
* test(sandbox): configure non-default workspace fixture
* test: fix small-fix batch validation
---------
Co-authored-by: morluto <williamlin1327@gmail.com >
Co-authored-by: ZengWen-DT <ceng.wen@xydigit.com >
Co-authored-by: 陈宪彪0668000387 <chen.xianbiao@xydigit.com >
Co-authored-by: NianJiuZst <180004567+NianJiuZst@users.noreply.github.com >
Co-authored-by: zenglingbiao <zeng.lingbiao@xydigit.com >
Co-authored-by: xialonglee <li.xialong@xydigit.com >
Co-authored-by: jincheng-xydt <xu.jincheng@xydigit.com >
Co-authored-by: 黄剑雄0668001315 <huang.jianxiong@xydigit.com >
2026-07-06 00:08:51 +01:00
Ted Li
d259496425
fix(google): rotate Gemini API keys for LLM requests ( #97328 )
...
* fix(google): rotate Gemini API keys for LLM requests
* fix(google): scope Gemini key rotation to official endpoint
* fix(google): require HTTPS for Gemini key rotation
* fix(google): preserve explicit stream auth headers
---------
Co-authored-by: Peter Steinberger <steipete@gmail.com >
2026-07-03 14:28:55 -07:00
snowzlmbot
b63e06f68a
fix(llm): preserve structured tool result replay
...
Preserve structured tool-result replay text across provider transports while keeping provider-facing redaction and Anthropic media ordering intact.
Thanks @snowzlmbot!
2026-06-30 23:44:02 -07:00
Peter Steinberger
56259606d1
fix(agent-core): ignore truncated tool calls ( #97140 )
...
* fix(agent-core): ignore truncated tool calls
Co-authored-by: Galin Iliev <5711535+galiniliev@users.noreply.github.com >
* fix(agent-core): require explicit tool-call terminals
---------
Co-authored-by: Galin Iliev <5711535+galiniliev@users.noreply.github.com >
2026-06-27 03:31:42 +01:00
Vincent Koc
77d0deedf2
improve: speed up provider tool-call streaming ( #95957 )
...
Merged via squash.
Prepared head SHA: d8f510757b25068+vincentkoc@users.noreply.github.com >
Co-authored-by: vincentkoc <25068+vincentkoc@users.noreply.github.com >
Reviewed-by: @vincentkoc
2026-06-23 12:28:24 +08:00
Yuval Dinodia
891dd037b5
fix(google): keep parallel Gemini tool responses in the turn after the model ( #93780 )
...
* fix(google): keep parallel Gemini tool responses in the turn after the model
On Gemini < 3 vision models, a parallel tool-call turn whose non-last result
returns an image split function responses across user turns. The merge heuristic
only inspected contents[last], so the separate "Tool result image:" turn landed
between two parallel responses and stranded the second one in a fresh turn. The
turn right after the model then carried fewer functionResponse parts than the
model issued functionCall parts, so Gemini returned 400 INVALID_ARGUMENT. Because
the malformed turn is persisted, every later turn re-400s and the session sticks.
Replace the contents[last] heuristic with a run-scoped accumulator: all responses
for one model turn merge into the single user turn after it, and Gemini < 3 image
turns defer to the end of the tool-result run so they trail that response turn.
Covers both google.ts and google-vertex.ts, which share this convertMessages.
* fix(google): align provider transport tool result turns
---------
Co-authored-by: Vincent Koc <25068+vincentkoc@users.noreply.github.com >
2026-06-17 09:04:35 +08:00
bymle
22069bcc56
fix(google): strip provider prefix from Vertex model path
...
Summary:
- Strip the redundant `google/` provider prefix before embedding Google Vertex model ids under `/publishers/google/models/`.
- Keep bare Vertex model ids unchanged.
- Add regression coverage for the provider-qualified Vertex path.
Verification:
- `node_modules/.bin/oxfmt --check --threads=1 extensions/google/transport-stream.ts extensions/google/transport-stream.test.ts`
- `node scripts/run-oxlint.mjs extensions/google/transport-stream.ts extensions/google/transport-stream.test.ts`
- `node scripts/run-vitest.mjs extensions/google/transport-stream.test.ts --maxWorkers=1 -t 'strips redundant google provider prefixes from Google Vertex model paths'`
- Autoreview clean
- AWS Crabbox `run_649b209478d2` focused Node 24 regression proof
- AWS Crabbox `run_e193db2707ad` remote `check:changed`
- Exact-head CI green for `23aca6f46f596e220df37d939317b433f7044ec6`
- Contributor live Google Vertex proof recorded in the PR body
2026-06-14 01:13:43 +08:00
Peter Steinberger
3e4b10fa1c
fix: strip Google provider prefix from Gemini paths ( #91125 )
...
* fix: strip Google provider prefix from Gemini paths
* test: align qa exit code type
2026-06-07 01:49:45 -07:00
Andi Liao
97d68b6902
fix(google): handle compressed Vertex ADC token responses
...
Decode Google Vertex authorized_user ADC OAuth token refresh responses from bytes so gzip-compressed token payloads still expose access_token. Adds a regression test for the compressed token response path while preserving plain JSON handling and the custom fetch seam.
Proof: OPENCLAW_VITEST_MAX_WORKERS=1 node scripts/run-vitest.mjs extensions/google/transport-stream.test.ts; pnpm exec oxfmt --check extensions/google/vertex-adc.ts extensions/google/transport-stream.test.ts; pnpm tsgo:extensions; git diff --check origin/main...HEAD; autoreview --mode branch --base origin/main. PR CI check-test-types failure was reproduced on current origin/main 607bbe4f5c
2026-06-06 23:42:35 -07:00
Peter Steinberger
96e5812426
docs: document medium extension sources
2026-06-04 21:33:54 -04:00
Coder
4bb86877e2
fix(google): forward Gemini stop sequences
...
Forward configured stop sequences to Gemini generationConfig.stopSequences in the bundled Google transport, matching the shared Google provider behavior and the @google/genai request contract.\n\nThanks @coder999999999.
2026-06-02 09:02:27 -04:00
Peter Steinberger
27dde7a4d6
chore(lint): enable stricter error rules
2026-06-01 01:12:21 +01:00
Peter Steinberger
304e2c83c0
chore(lint): enable stricter oxlint rules
2026-05-31 18:59:02 +01:00
samzong
5b310a7b27
fix(agents): release abandoned provider streams
...
Fix streamed provider cleanup so abandoned managed fetch bodies no longer keep undici sockets open, and cancel Anthropic/Gemini SSE readers deterministically when parsing exits early.
Keep the FinalizationRegistry abort path as a last-resort GC safety net for unmanaged/abandoned responses, while parser-owned paths cancel readers explicitly on thrown errors or malformed events.
Also records the browser-only Control UI redactor alias in the optional deadcode allowlist and keeps mocked exec supervisor tests off shell snapshot wrapping after the branch was rebased onto default shell snapshots.
Fixes #67461
Verification:
- node scripts/run-vitest.mjs src/agents/provider-transport-fetch.test.ts src/agents/anthropic-transport-stream.test.ts extensions/google/transport-stream.test.ts src/agents/bash-tools.test.ts src/agents/bash-tools.exec.path.test.ts test/scripts/test-live-shard.test.ts
- pnpm check:test-types
- node scripts/run-oxlint-shards.mjs --threads=8
- .agents/skills/autoreview/scripts/autoreview --mode branch --base origin/main --parallel-tests "node scripts/run-vitest.mjs src/agents/provider-transport-fetch.test.ts src/agents/anthropic-transport-stream.test.ts extensions/google/transport-stream.test.ts src/agents/bash-tools.test.ts src/agents/bash-tools.exec.path.test.ts test/scripts/test-live-shard.test.ts"
- git diff --check origin/main...HEAD
- PR CI on a1db789652samzong.lu@gmail.com >
Signed-off-by: samzong <samzong.lu@gmail.com >
2026-05-31 17:17:53 +01:00
Peter Steinberger
697bafa9c9
fix(google): bound vertex adc token cache expiry
2026-05-30 11:52:19 -04:00
Peter Steinberger
e3be541a6c
fix(google): reject unsafe vertex adc lifetimes
2026-05-29 13:57:34 -04:00
Peter Steinberger
3142c97c22
fix(google): validate gemini retry timeout env
2026-05-29 09:05:38 -04:00
Peter Steinberger
bb46b79d3c
refactor: internalize OpenClaw agent runtime ( #85341 )
...
* refactor: extract agent core package
Introduce packages/agent-core as the OpenClaw-owned home for reusable agent loop, harness, session, prompt, and runtime dependency contracts.
* refactor: extract shared llm runtime
Move provider model registries, stream wrappers, OAuth helpers, and LLM utilities into src/llm with plugin-sdk barrels instead of depending on the old embedded runtime layout.
* refactor: remove pi runtime internals
Rename remaining Pi-shaped agent surfaces to OpenClaw agent runtime names, delete obsolete Pi docs and package graph checks, and add the third-party notice for incorporated code.
* refactor: tighten agent session runtime
Make agent-core/runtime dependencies explicit, consolidate compaction and session transcript helpers, and move model/session helpers behind OpenClaw-owned contracts.
* refactor: remove static model and pi auth paths
Drop static model catalogs and Pi auth bridges, move model/provider facts to manifest-owned runtime contracts, and harden internal embedded-agent utilities.
* refactor: remove legacy provider compat paths
* docs: remove agent parity notes
* fix: skip provider wildcard metadata parsing
* refactor: share session extension sdk loading
* refactor: inline acpx proxy error formatter
* refactor: fold edit recovery into edit tool
* fix: accept extension batch separator
* test: align startup provider plugin expectations
* fix: restore provider-scoped release discovery
* test: align static asset packaging expectations
* fix: run static provider catalogs during scoped discovery
* fix: add provider entry catalogs for scoped live discovery
* fix: load lightweight provider catalog entries
* fix: refresh provider-scoped plugin metadata
* fix: keep provider catalog entries on release live path
* fix: keep static manifest models in release live checks
* fix: harden release model discovery
* fix: reduce OpenAI live cache probe reasoning
* fix: disable OpenAI cache probe reasoning
* ci: extend OpenAI gateway live timeout
* fix: extend live gateway model budget
* fix: stabilize release validation regressions
* fix: honor provider aliases in model rows
* fix: stabilize release validation lanes
* fix: stabilize release memory qa
* ci: stabilize release validation lanes
* ci: prefer ipv4 for live docker node calls
* fix: restore shared tool-call stream wrapper
* ci: remove legacy pi test shard alias
* fix: clean up embedded agent test drift
* fix: stabilize runtime alias status
* fix: clean up embedded agent ci drift
* fix: restore release ci invariants
* fix: clean up post-rebase runtime drift
* fix: restore release ci checks
* fix: restore release ci after rebase
* fix: remove stale pi runtime path
* test: align compaction runtime expectations
* test: update plugin prerelease expectations
* fix: handle claude live tool approvals
* fix: stabilize release validation gates
* fix: finish agent runtime import
* test: finish post-rebase agent runtime mocks
* fix: keep codex compaction native
* fix: stabilize codex app-server hook tests
* test: isolate codex diagnostic active run
* test: remove codex diagnostic completion race
# Conflicts:
# extensions/codex/src/app-server/run-attempt.test.ts
* ci: fix full release manifest performance run id
* refactor: narrow llm plugin sdk boundary
* chore: drop generated google boundary stamps
* fix: repair rebase fallout
* fix: clean up rebased runtime references
* fix: decode codex jwt payloads as base64url
* fix: preserve shipped pi runtime alias
* fix: add scoped sdk virtual modules
* fix: decode llm codex oauth jwt as base64url
* fix: avoid stale vertex adc negative cache
* fix: harden tool arg decoding and codeql path
* fix: keep vertex adc negative checks live
* refactor: consolidate codex jwt and edit helpers
* fix: await codex oauth node runtime imports
* fix: preserve sdk tool and notice contracts
* fix: preserve shipped compat config boundaries
* fix: align codex oauth callback host
* fix: terminate agent-core loop streams on failure
* fix: keep codex oauth callback alive during fallback
* ci: include session tools in critical codeql scans
* fix: keep Cloudflare Anthropic provider auth header
* docs: redirect legacy pi runtime pages
* fix: honor bundled web provider compat discovery
* fix: protect session output spill files
* fix: keep legacy agent dir env blocked
* fix: contain auto-discovered skill symlinks
* fix: harden agent core sdk proxy surfaces
* fix: restore approval reaction sdk compat
* fix: keep live docker runs bounded
* fix: keep codex oauth redirect host aligned
* fix: resolve post-rebase agent runtime drift
* fix: redact anthropic oauth parse failures
* fix: preserve responses strict tool shaping
* fix: repair agent runtime rebase cleanup
* docs: redirect retired parity pages
* fix: bound auto-discovered resources to roots
* fix: repair post-rebase agent test drift
* fix: preserve bundled provider allowlist migration
* fix: preserve manifest-owned provider aliases
* fix: declare photon image dependency
* fix: keep provider headers out of proxy body
* fix: preserve shipped env aliases
* fix: refresh control ui i18n generated state
* fix: quote read fallback paths
* fix: preview edits through configured backend
* test: satisfy core test typecheck
* fix: preserve ZAI usage auth fallback
* test: repair codex diagnostic test
* fix: repair agent runtime rebase drift
* test: finish embedded runner import rename
* fix: repair agent runtime rebase integrations
* test: align compaction oauth fallback expectations
* fix: allow sdk-auth session models
* fix: update doctor tool schema import
* fix: preserve bedrock plugin region
* fix: stream harmony-like prose immediately
* ci: include session runtime in codeql shards
* fix: repair latest rebase integrations
* fix: honor explicit codex websocket transport
* fix: keep openai-compatible credentials provider-scoped
* fix: refresh sdk api baseline after rebase
* fix: route cli runtime aliases through openclaw harness
* test: rename stale harness mock expectation
* test: rename embedded agent overflow calls
* test: clean embedded auth test wording
* test: use openclaw stream types in deepinfra cache test
* fix: refresh sdk api baseline on latest main
* fix: honor bundled discovery compat allowlists
* fix: refresh sdk api baseline after latest rebase
* fix: remove stale rebase imports
* test: rename stale model catalog mock
* test: mock renamed doctor runtime modules
* fix: map canonical kimi env auth
* fix: use internal model registry in bench script
* fix: migrate deepinfra provider catalog entry
* fix: enforce builtin tool suppression
* fix: route compaction auth and proxy payloads safely
* refactor: prune unused llm registry leftovers
* test: update codex hooks session import
* test: fix model picker ci coverage
* test: align model picker auth mock types
2026-05-27 19:24:04 +01:00
Vincent Koc
b182b71d74
fix(e2e): align prerelease and google live guards
2026-05-27 19:30:27 +02:00
Neerav Makwana
148db14736
fix(google): omit request config with cached content
...
Fix Gemini cached-content GenerateContent payloads so cached requests no longer resend request-level systemInstruction, tools, or toolConfig.
Covers explicit cachedContent and managed cacheRetention prompt caching; fixes #84919 .
Proof: Real behavior proof passed on PR head 198a42bbc6
2026-05-25 21:42:21 +01:00
Damian Finol
f09b4ebe31
fix(google-vertex): support production ADC modes ( #83971 )
...
Fix Google Vertex production ADC mode support by routing explicit google-vertex models to the Vertex transport and relying on google-auth-library for request-time ADC resolution.
Verification:
- pnpm install --frozen-lockfile
- pnpm test extensions/google/transport-stream.test.ts extensions/google/index.test.ts src/config/zod-schema.models.test.ts src/agents/pi-embedded-runner/model.inline-provider.test.ts -- --reporter=verbose
- pnpm check:changed
- GitHub PR checks green on c4b7cad4dfdamian@felixpago.com >
2026-05-25 01:37:52 +01:00
Peter Steinberger
8dd91b14d3
fix(google): recover Gemini tool-call thought signatures
...
Fixes #72879 .
Supersedes contributor PR #80358 ; fork push was blocked despite maintainer edits being enabled.
Co-authored-by: abnershang <abner.shang@gmail.com >
2026-05-17 11:16:47 +01:00
Gio Della-Libera
8c9ec0724e
fix(agents): honor disabled reasoning in thinking policy ( #81454 )
...
* fix(agents): honor disabled reasoning in thinking policy
* test: refresh thinking policy CI fixtures
* test: align thinking policy CI guardrails
---------
Co-authored-by: Gio Della-Libera <giodl@microsoft.com >
2026-05-15 22:33:43 -07:00
Vincent Koc
1fc82347a7
fix(google): wrap malformed sse json
2026-05-14 19:28:13 +08:00
Peter Steinberger
93b1e7e282
test: guard google provider mock calls
2026-05-12 00:03:56 +01:00
Peter Steinberger
15cf49222f
build: refresh deps and route testbox through crabbox
2026-05-11 03:41:00 +01:00
Peter Steinberger
438861ee0f
test: clear google transport broad matchers
2026-05-10 08:23:58 +01:00
Josh Avant
3af81481b4
fix(google): retry stalled Gemini first response ( #79668 )
...
* fix(google): retry stalled gemini first response
* docs(changelog): note gemini first-response retry
* fix(google): clear gemini first-response deadline
2026-05-09 00:52:44 -05:00
Peter Steinberger
1ef85c7d4c
test: make suites safe without isolation ( #78834 )
...
* test: make suites safe without isolation
* fix: narrow auth profile credential types
* test: inject channel module loader factory locally
2026-05-07 08:43:29 +01:00
Peter Steinberger
a428568157
fix(gemini): gate thought-signature replay trust
2026-05-07 07:08:54 +01:00
Peter Steinberger
85b914a4e1
fix(model): repair provider replay edge cases
2026-05-07 06:41:59 +01:00
Ayaan Zaidi
a55b2af7a5
fix: keep Gemini thinking streams active ( #76080 ) (thanks @zhangguiping-xydt)
2026-05-02 19:26:54 +05:30
zhang-guiping
ea3416d8b5
fix(google): handle thoughtSignature-only parts to prevent Gemini stream hang
...
Gemini 3.1 Pro Preview may emit parts with only thoughtSignature
and no text content, causing the stream to stall. Emit a
thinking_signature event to keep the stream active, and start
a thinking block when these parts arrive before any text.
Fixes #76071
2026-05-02 19:26:54 +05:30
Eric Huang
edca8c721a
fix(google): narrow Gemini 2.5 minimal budget floor ( #70629 ) (thanks @ericberic)
...
* fix: raise Gemini 2.5 minimal thinking budget from 128 to 512
Google raised the minimum thinkingBudget for Gemini 2.5 Pro and Flash
models to 512. The hardcoded minimal: 128 now causes a 400 INVALID_ARGUMENT
("The thinking budget 128 is invalid. Please choose a value between 512
and 24576.") on every heartbeat using gemini-2.5-flash-lite with minimal
thinking.
* test(google): assert thinkingBudget minimum of 512 for Gemini 2.5 models
Add parametrized tests covering minimal/low/medium budget tiers for
gemini-2.5-flash-lite, gemini-2.5-flash, and gemini-2.5-pro — ensures
the 128→512 floor change is regression-tested.
Pre-existing typecheck failure in src/agents/model-auth.ts (TS2322) is
unrelated; confirmed present on upstream main without our changes.
Tests validated: pnpm test extensions/google/transport-stream.test.ts (21 pass).
* test(google): fix it.each format string placeholder order
* fix(google): narrow Gemini 2.5 minimal budget floor to flash-lite only
2026-05-02 16:11:22 +05:30
Peter Steinberger
1ad50a36ac
chore(release): forward-port 2026.4.29 fixes and bump 2026.4.30
2026-05-01 01:06:13 +01:00
clawsweeper[bot]
1a9763f578
fix(google): accept Windows ADC manifest paths
...
Co-authored-by: openclaw-clawsweeper[bot] <280122609+openclaw-clawsweeper[bot]@users.noreply.github.com>
2026-04-29 22:26:09 -07:00
Peter Steinberger
0b59964ec9
fix(google): support Vertex authorized_user ADC
2026-04-30 01:13:25 +01:00
Carl
5e384fed6d
fix(google): prevent empty contents error for gemini ( #74465 )
...
* fix(google): prevent empty contents error for gemini
* test(google): cover empty Gemini contents fallback
* docs(changelog): note Gemini empty content fallback
---------
Co-authored-by: Peter Steinberger <steipete@gmail.com >
2026-04-29 17:30:51 +01:00
Peter Steinberger
cc0f3067a0
fix: map google adaptive thinking dynamically
2026-04-25 02:04:40 +01:00
Peter Steinberger
85826c83e4
refactor(google): move Gemini transport into plugin
2026-04-18 21:41:54 +01:00
