vultr/openclaw
1
0
Fork 0
mirror of https://github.com/openclaw/openclaw.git synced 2026-07-16 20:11:36 +00:00
Code Issues Packages Projects Releases Wiki Activity
67,697 Commits 1,843 Branches 149 Tags
8aab4ff94de89a9b4d1ba241ef2c2baf66d92555
Commit Graph

28 Commits

Author SHA1 Message Date
mushuiyu886
ed57c6cd88 fix(agents): honor claude-cli contextTokens setting (#93198) 
* fix: honor claude-cli configured context tokens

* test: cover claude-cli native compaction budget

* test: cover ordinary claude-cli budget persistence

* test: migrate claude-cli budget fixtures to session accessor

* fix(agents): carry CLI provider into context budget

* fix(agents): guard optional CLI context metadata

* fix(agents): align Claude CLI native compaction budget

Co-authored-by: 杨浩宇0668001029 <yang.haoyu@xydigit.com>

* fix(agents): apply selected CLI context cap

Co-authored-by: 杨浩宇0668001029 <yang.haoyu@xydigit.com>

* fix(agents): preserve prepared CLI context budgets

Co-authored-by: 杨浩宇0668001029 <yang.haoyu@xydigit.com>

* fix(agents): resolve prepared CLI context ownership

Co-authored-by: 杨浩宇0668001029 <yang.haoyu@xydigit.com>

* test(agents): type CLI context budget cases

Co-authored-by: 杨浩宇0668001029 <yang.haoyu@xydigit.com>

---------

Co-authored-by: Peter Steinberger <steipete@gmail.com>
 2026-07-13 01:58:44 -07:00
Peter Steinberger
3255b3218a feat: unify external sessions with native catalog pagination (#104717) 
* feat(gateway): add generic sessions.catalog surface with plugin SDK registration seam

* feat(agents): support one-shot forked CLI session resume with successor rebinding

* feat(anthropic): adopt local Claude CLI sessions into native chats via catalog continue

* feat(codex): register the session catalog provider independently of supervision

* refactor(ui): delete the retired custom Claude/Codex session tab views

* feat(ui): render external session catalogs as native sidebar sessions and chat panes

* docs: describe the unified native session catalog

* fix: harden forked CLI resume and catalog transcript mapping after review

* fix: satisfy strict typecheck for catalog source guard and imported message cast

* chore(i18n): regenerate session catalog locales

* fix(codex): simplify session source guard type

* fix(ui): paginate sidebar session catalogs

* chore(i18n): refresh catalog metadata after main merge

* fix(ui): harden session catalog pagination refresh

* test(agents): use sqlite session accessor in fork tests

* fix(ci): refresh session catalog generated surfaces

* fix(ui): align session catalog locales

* fix: address session catalog review findings

* fix(sessions): roll back failed plugin catalog adoption

* test(sessions): preserve CLI binding literals

* fix(ui): restore native session pagination label

* docs: note external session catalogs

* Revert "docs: note external session catalogs"

This reverts commit cfb503f160.
 2026-07-11 17:26:26 -07:00
Peter Steinberger
96f0983a85 fix(onboarding): skip setup for configured gateways and require inference first (#102883) 
* fix(crestodian): keep onboarding RPCs restart-safe

* fix(profiles): isolate approval state migrations

* fix(crestodian): bypass configured gateway setup

* test(crestodian): type onboarding mocks

* fix(onboarding): require inference before Crestodian

* fix(onboarding): enforce verified inference handoff

* fix(macos): reset setup on gateway endpoint edits

* chore(i18n): refresh native source inventory

* fix(gateway): keep socket on request cancellation

* test(packaging): require workspace templates

* fix(onboarding): bind setup to verified inference

* fix(onboarding): align inference gate contracts

* fix(crestodian): classify concurrent policy rejection

* test(crestodian): expect registry restoration

* fix(onboarding): bind setup to configured gateways

* fix(codex): preserve startup phase deadlines

* test(crestodian): match fail-closed policy ordering

* test(onboarding): assert bound gateway handoff

* fix(codex): bind runtime resolution to spawn cwd

* test(crestodian): assert policy rejection order

* fix(cli): preserve gateway routing across restarts

* fix(macos): fail closed during gateway edits

* test(macos): cover gateway route generation races

* chore: keep release notes out of onboarding PR

* fix(ci): refresh onboarding generated checks

* style(swift): align gateway channel formatting

* fix(ci): refresh plugin SDK surface budgets

* fix(ci): resync native string inventory

* refactor(swift): split gateway channel support

* test(doctor): isolate plugin compatibility registry

* test(macos): isolate gateway onboarding fixtures

* test(macos): assert gateway lease health ordering

* fix(codex): reconcile computer-use startup changes
 2026-07-11 10:25:14 -07:00
anagnorisis2peripeteia
298a0cd55f fix(claude-cli): disable unsupported background tools (#95008) (thanks @anagnorisis2peripeteia) 
Disable Claude CLI native background Bash and Monitor in OpenClaw-managed print runs, matching the existing fail-closed scheduler-tool behavior. This keeps deferred work on OpenClaw-owned wake paths instead of native Claude callbacks OpenClaw cannot deliver.

Thanks @anagnorisis2peripeteia!
 2026-06-22 05:44:48 +05:30
Bakhtiyar
8e56cf591d fix(cli): disable ScheduleWakeup/CronCreate in --print claude runs (#84434) 
Claude Code built-ins ScheduleWakeup and CronCreate schedule a deferred
re-invocation managed by the persistent CLI runtime. In OpenClaw's
one-shot `claude -p` invocations the process exits at end_turn, so any
wakeup or cron registered during the run has no host to fire into and is
silently lost. Symptom: a CLI session spawns a background sub-agent,
calls ScheduleWakeup to poll for completion, ends the turn, and never
picks up the result — the work finishes unreviewed.

Append `--disallowedTools "ScheduleWakeup,CronCreate"` to both `args`
and `resumeArgs` in the anthropic CLI backend so the model cannot reach
for tools that don't survive the run mode. The right pattern in CLI
sessions is Monitor on the background output file, or a synchronous
sub-agent.
 2026-06-16 01:08:51 +08:00
Josh Avant
689ebc815b feat: support /btw in CLI-backed sessions (#92669) 
* feat: support CLI btw side questions

* test: fix CLI prepare test fixture types

* fix: lazy load local btw runner
 2026-06-13 19:36:53 +02:00
Peter Steinberger
d89ad16124 docs: document anthropic cli config helpers 2026-06-04 07:15:05 -04:00
Cameron Beeley
3d7523b618 feat(agents): generalized native compaction ownership for CLI backends 
Add `ownsNativeCompaction` capability to CliBackendPlugin so backends
that manage their own transcript compaction (e.g. Claude Code) can
declare it once and OpenClaw defers instead of fighting or failing.

Today only Codex declares compaction ownership (via the embedded runner
path + agentHarnessId). Claude-cli never reaches that path because it
runs as a CLI subprocess with no harness id set, so the safeguard
summarizer fires and hard-fails the turn.

This PR:
- Adds `ownsNativeCompaction?: boolean` to the backend plugin type
- Propagates it through all 4 backend resolution paths
- In `runCliTurnCompactionLifecycle`, when a backend declares ownership
  but has no harness endpoint, returns a no-op instead of falling
  through to the safeguard
- Sets the flag on claude-cli (first adopter)

Codex's existing native-harness path is unchanged: when
`isNativeHarnessCompactionSession` matches, the harness compaction
endpoint is still called as before.

Generalizes the partial fix in #87785 (codex-scoped) to a capability
any backend can opt into.
 2026-06-02 14:39:35 +05:30
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
JanusAsmussen
84e62824f6 fix(anthropic): pass system prompt on resumed claude-cli sessions 
Summary:
- send Claude CLI system prompt files on resumed turns when backend policy is always
- set Claude CLI default systemPromptWhen to always
- add argv/unit coverage plus live ALPHA-to-BRAVO resume proof for #80374

Verification:
- pnpm test src/agents/cli-runner/helpers.system-prompt-resume.test.ts extensions/anthropic/cli-shared.test.ts src/agents/cli-backends.test.ts test/scripts/test-live-shard.test.ts -- --reporter=verbose
- OPENCLAW_LIVE_TEST=1 OPENCLAW_LIVE_USE_REAL_HOME=1 OPENCLAW_LIVE_CLI_BACKEND=true OPENCLAW_LIVE_CLI_BACKEND_MODEL=claude-cli/claude-haiku-4-5 node scripts/run-vitest.mjs run --config test/vitest/vitest.live.config.ts src/gateway/gateway-cli-backend.system-prompt-resume.live.test.ts --reporter=verbose
- /Users/steipete/Projects/agent-scripts/skills/autoreview/scripts/autoreview --mode local
- git diff --check
- gitcrawl gh pr checks 86433 --repo openclaw/openclaw --watch=false --required

Co-authored-by: JanusAsmussen <jjasmussen@outlook.com>
Co-authored-by: Peter Steinberger <steipete@gmail.com>
 2026-05-27 01:31:13 +01:00
bitloi
dd8aa1dcce fix: reseed Claude CLI session context on rotation closes #80905 2026-05-13 12:54:40 +01:00
stain lu
74ab62c6a2 fix: pass claude cli thinking effort (#77410) 
Summary:
- Adds a plugin-owned CLI backend argument rewrite hook and wires Anthropic `claude-cli` to translate non-off `/think` levels into Claude Code `--effort`, with docs, changelog, API baseline, and tests.
- Reproducibility: yes. Current main has a high-confidence source reproduction: choose `claude-cli`, set a non ... builds argv from backend args that contain no `--effort` even though `thinkLevel` exists on the run params.

Automerge notes:
- No ClawSweeper repair was needed after automerge opt-in.

Validation:
- ClawSweeper review passed for head be17754009.
- Required merge gates passed before the squash merge.

Prepared head SHA: be17754009
Review: https://github.com/openclaw/openclaw/pull/77410#issuecomment-4372812685

Co-authored-by: stainlu <stainlu@newtype-ai.org>
 2026-05-04 18:13:53 +00:00
Vignesh
b277ae3f4c [codex] Fix commitments safety and coverage (#75302) 
* fix commitments safety and coverage

* Repair commitments safety PR review blockers

* fix(clawsweeper): address review for automerge-openclaw-openclaw-75302 (1)

* Repair commitments safety PR review blocker

---------

Co-authored-by: clawsweeper-repair <clawsweeper-repair@users.noreply.github.com>
 2026-05-01 01:14:07 +00:00
skylee-01
f7b71abf48 fix(agents): pass Claude system prompt via file 2026-04-25 17:59:25 +05:30
Peter Steinberger
f523bbfcd1 fix: align claude cli permissions with exec policy 
Derive Claude CLI bypass mode from OpenClaw exec YOLO policy, preserve raw Claude permission-mode overrides, update docs/changelog, and cover global/per-agent policy behavior.
 2026-04-23 23:11:34 +01:00
Vincent Koc
7d30894c4a fix(anthropic): stop forcing claude permission bypass 2026-04-23 12:03:00 -07:00
Ayaan Zaidi
81ca7bc40b fix: keep claude cli sessions warm (#69679) 
* feat(cli): keep claude cli sessions warm

* test(cli): cover claude live session reuse

* fix(cli): harden claude live session reuse

* fix(cli): redact mcp session key logs

* fix(cli): bound claude live session turns

* fix(cli): reuse claude live sessions on resume

* refactor(cli): canonicalize claude live argv

* fix(cli): preserve claude live resume state

* fix(cli): close dead claude live sessions

* fix(cli): serialize claude live session creates

* fix(cli): count pending claude live sessions

* fix(cli): tighten claude live resume abort

* fix(cli): reject closed claude live sessions

* fix(cli): refresh claude live fingerprints

* fix(cli): stabilize MCP resume hash

* fix: preserve claude live inline resume (#69679)

---------

Co-authored-by: Frank Yang <frank.ekn@gmail.com>
 2026-04-22 13:44:18 +05:30
Alex Alaniz
6bd64ca4a7 fix: stop marking Claude CLI runs as host-managed 
Stop injecting CLAUDE_CODE_PROVIDER_MANAGED_BY_HOST into Claude CLI runs and strip inherited/backend overrides before spawn.\n\nAlso repairs the Zalo setup allowlist prompt wiring needed by the current main check gate.\n\nThanks @Alex-Alaniz.
 2026-04-10 09:14:15 +01:00
Peter Steinberger
c2f9de3935 feat: unify live cli backend probes 2026-04-07 10:35:24 +01:00
Peter Steinberger
0af808b457 test: add cli backend live matrix metadata 2026-04-07 09:06:09 +01:00
Peter Steinberger
af62a2c2e4 style: fix extension lint violations 2026-04-06 14:53:55 +01:00
Peter Steinberger
ef923805f5 Revert "refactor(cli): remove custom cli backends" 
This reverts commit 6243806f7b.
 2026-04-06 13:40:42 +01:00
Peter Steinberger
2d7157b424 refactor(cli): delete removed backend files 2026-04-05 18:04:48 +01:00
Vincent Koc
3b84884793 fix(agents): harden host-managed claude-cli auth path (#61276) 2026-04-05 11:02:18 +01:00
Peter Steinberger
4e099689c0 feat: stream Claude CLI JSONL output 2026-04-04 19:33:08 +09:00
Peter Steinberger
48ae976333 refactor: split cli runner pipeline 2026-03-27 00:19:24 +00:00
felear2022
623f4d3056 fix: use stream-json output for Claude CLI backend to prevent watchdog timeouts 
The Claude CLI backend uses `--output-format json`, which produces no
stdout until the entire request completes. When session context is large
(100K+ tokens) or API response is slow, the no-output watchdog timer
(max 180s for resume sessions) kills the process before it finishes,
resulting in "CLI produced no output for 180s and was terminated" errors.

Switch to `--output-format stream-json --verbose` so Claude CLI emits
NDJSON events throughout processing (init, assistant, rate_limit, result).
Each event resets the watchdog timer, which is the intended behavior —
the watchdog detects truly stuck processes, not slow-but-progressing ones.

Changes:
- cli-backends.ts: `json` → `stream-json --verbose`, `output: "jsonl"`
- helpers.ts: teach parseCliJsonl to extract text from Claude's
  `{"type":"result","result":"..."}` NDJSON line

Note: `--verbose` is required for stream-json in `-p` (print) mode.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
 2026-03-26 16:39:15 -07:00
Peter Steinberger
a4a00aa1da feat: pluginize cli inference backends 2026-03-26 15:11:15 +00:00