vultr/openclaw
1
0
Fork 0
mirror of https://github.com/openclaw/openclaw.git synced 2026-08-02 16:11:37 +00:00
Code Issues Packages Projects Releases Wiki Activity
72,701 Commits 1,843 Branches 149 Tags
ea707382fd62eeaa1e9da72e2ef8bfe52e1ff19e
Commit Graph

52 Commits

Author SHA1 Message Date
Peter Steinberger
ea707382fd feat(code-mode): first-class nodes API (#114877) 
* feat(agents): add nodes to code mode

* fix(agents): add code mode nodes discovery hint
 2026-07-27 23:03:23 -04:00
Peter Steinberger
37cf0c6064 improve: reduce GPT-5.6 coding harness overhead (#114574) 
* improve: reduce GPT-5.6 coding harness overhead

* refactor: extract runtime parity timing helpers

* fix(qa): verify native apply-patch runtime parity

* fix(qa): use mock patch execution evidence

* fix(qa): preserve workspace templates in full syncs

* fix(qa): make rejected patch fixtures deterministic

* fix(qa): prove apply-patch workspace containment

* fix(qa): expose runtime prompt-cache usage

* fix(codex): confine forced private QA patch turns

* fix(qa): verify native patch execution and sandbox precedence

* fix(qa): execute native patches and prove disk mutation

* fix(codex): avoid duplicate native patch registration

* perf(agents): keep code mode catalog guidance compact

* fix(qa): make native Codex patch evidence deterministic

* fix(qa): recognize native sandbox denial errors

* fix(qa): advertise native Codex mock model capabilities

* fix(qa): seed native Codex mock model catalog at startup

* fix(qa): recognize native Codex patch denial results

* fix(ci): repair Codex harness parity checks

* fix(qa): distinguish unknown prompt-cache measurements

* fix(qa): accept native Codex project patch denials

* fix(ci): isolate runtime parity report contracts

* fix(codex): eliminate native runtime transport overhead

* fix(qa): consume runtime parity report contract

* fix(qa): compare matched runtime timing captures

* fix(qa): type native response delta context

* fix(qa): satisfy native codex websocket lint
 2026-07-27 19:24:52 -04:00
Peter Steinberger
b5bb29a36e fix(code-mode): preserve direct tools and secure suspended runs (#114778) 
Preserve trusted policy-required message delivery and native image/computer tools across Code Mode catalogs and provider transports. Keep preferred Gemini capability metadata during live discovery, escape MCP declaration keywords, and reject suspended-run resumes with missing owner identity. Add before-and-after regressions for each user path. Closes #114753.
 2026-07-27 18:47:33 -04:00
Peter Steinberger
3a39dbcdfd fix(agents): harden code mode module isolation (#114742) 2026-07-27 16:38:44 -04:00
Peter Steinberger
d9e6d00261 fix(agents): safely parse Code Mode module boundaries (#114651) 2026-07-27 13:50:40 -04:00
Sasan
7599bbe636 fix(agents): stop code-mode shell-command retry storms (#113070) 
Reject recognizable POSIX and Windows shell source before QuickJS execution while preserving valid JavaScript, TypeScript, syntax errors, standard globals, and real hoisted bindings. Add real-worker regression coverage and adversarial cross-platform stress proof. Fixes #113069.
 2026-07-27 08:10:37 -04:00
Peter Steinberger
55d66fbf98 chore(scripts): remove resolved investigation tools and orphans (#113532) 
* chore(scripts): remove orphaned wrappers

* chore(scripts): remove resolved investigation tools

* refactor(code-mode): remove orphaned plugin namespaces

* test(code-mode): remove stale namespace import
 2026-07-25 02:47:40 -07:00
Peter Steinberger
104691f822 feat(swarm): add QuickJS guest orchestration (#111298) 
* feat(swarm): add QuickJS guest orchestration (#110325)

* fix(agents): turn-stable swarm replay identity — distinct exec invocations cannot collide

* fix(agents): turn-stable swarm replay identity — distinct exec invocations cannot collide

* fix(agents): turn-stable swarm replay identity — distinct exec invocations cannot collide
 2026-07-19 03:58:59 -07:00
Peter Steinberger
e9f798ecc4 fix(agents): greedily pack the code mode quick index so one oversized entry cannot blank it (#110517) 2026-07-18 08:26:06 +01:00
Peter Steinberger
b9c5c7c9fc feat(agents): contract filesystem tools for code mode (#110395) 2026-07-18 06:26:04 +01:00
Peter Steinberger
010f662f48 fix(agents): keep declared-output tools visible in the truncated code mode index (#110317) 2026-07-18 03:48:28 +01:00
Peter Steinberger
3d1e8f9475 perf(agents): compose conversation tools in code mode (#110098) 2026-07-17 20:54:32 +01:00
Peter Steinberger
b319493a52 improve: let Code Mode use declared tool result shapes (#109813) 
* feat(agents): add Code Mode output contracts

* perf(agents): defer untrusted tool schemas

* chore(plugin-sdk): refresh API baseline

* fix(agents): preserve deferred schema markers

* fix(agents): preserve policy-blocked tool results

* fix(agents): preserve nullable output contracts

* fix(agents): reject policy blocks from success contracts

* fix(agents): preserve output contracts through normalization

* test(agents): type normalized tool fixtures

* fix(agents): validate catalog results before projection

* fix(agents): keep result snapshots internal

* fix(agents): fail closed on unrenderable unions

* fix(agents): preserve empty result markers

* test(agents): keep result fixture discriminator literal

* test(agents): use native own-property check
 2026-07-17 14:46:37 +01:00
Peter Steinberger
c742caee4b perf(agents): prime code mode with compact tool ids (#109651) 2026-07-16 23:09:03 -07:00
Peter Steinberger
57cc2ca308 improve: reduce compact tool orchestration turns (#109596) 
* perf(agents): streamline compact tool orchestration

* fix(agents): preserve compact schema narrowing

* refactor(agents): focus legacy tool-search guidance

* fix(agents): defer MCP compact schema hints

* chore: drop release-owned changelog edit
 2026-07-16 20:53:42 -07:00
Peter Steinberger
b39e1cf66f perf(agents): drain code-mode bridge calls inline within one exec turn (#109290) 
Code mode previously suspended to the model with a waiting result for every
awaited tools.search/describe/call, forcing one wait tool turn per await
(turns = tool calls + 1). Bridge calls now resolve inline within the exec
deadline and resume the QuickJS snapshot host-side, matching the namespace
auto-drain path. Restart-safe runs keep their existing no-drain semantics.
Live proof across OpenAI/Anthropic/Google: ~45% fewer turns and ~45% fewer
input tokens at equal success rate.

Also landed with the same contract:
- one shared wall-clock deadline per exec/wait call (initial worker, inline
  drain rounds, and resumed guest interrupt budget all share it)
- park the snapshot instead of resuming when the remaining budget could not
  survive VM restore, so near-deadline settles stay recoverable
- abort now terminates the guest worker, skips resume, and drops suspended
  runs instead of pinning process-global slots until TTL, reported with the
  existing aborted failure code
- exec description omits API.list/MCP/namespace guidance when the run catalog
  has no MCP tools or namespaces, so models stop probing an empty surface
- API.list tolerates a trailing-slash prefix like API.list("mcp/")
 2026-07-16 13:30:07 -07:00
Peter Steinberger
9497450511 refactor: eliminate dead-export baseline (#108376) 
Burn the grandfathered unused-export baseline to zero and enforce a hard-zero Knip gate.
 2026-07-15 17:05:07 +01:00
Peter Steinberger
3ea45589ba refactor(agents): trim CLI and transport export seams (#108309) 
* refactor(agents): trim CLI and transport export seams

* chore(deadcode): shrink agents CLI transport baseline
 2026-07-15 14:02:29 +01:00
Peter Steinberger
580938097f refactor(agents): privatize internal helper surfaces (#108219) 
* refactor(agents): privatize internal helper surfaces

* chore(deadcode): shrink unused-export baseline
 2026-07-15 02:47:05 -07:00
Peter Steinberger
f81f9d8570 chore: enforce max-lines suppression ratchet (#107315) 
* ci: enforce max-lines suppression ratchet

* chore: prune stale max-lines suppression

* fix: close max-lines ratchet enforcement gaps

* fix: harden max-lines ratchet checks

* fix(ci): satisfy max-lines ratchet checks

* style: format max-lines declarations

* fix(ci): match oxlint suppression grammar

* test: isolate max-lines git fixtures

* chore: prune resolved max-lines debt

* test: skip newline path fixture on Windows

* fix: harden max-lines suppression ratchet

* chore: refresh max-lines baseline

* fix: close max-lines ratchet bypasses

* fix: derive ratchet base from PR merge tree

* fix: support older Git in staged ratchet

* fix: align max-lines declarations and baseline

* chore: refresh max-lines baseline for current main

* fix: exclude generated wizard locales from max-lines

* chore: prune resolved max-lines debt
 2026-07-14 09:27:02 -07:00
Peter Steinberger
1b313dc4d4 chore(tooling): enforce indexed access in core tests (#105375) 
* test(tooling): enforce indexed access in core tests

* test(tui): constrain theme environment overrides

* test(doctor): enforce indexed access in migration fixtures
 2026-07-12 14:29:52 +01:00
Peter Steinberger
d14bb8ec44 fix: resume replay-safe work after gateway restarts (#104997) 
* fix: resume replay-safe work after gateway restart

* chore: leave restart note to release process

* fix: sync restart recovery protocol artifacts
 2026-07-12 06:37:22 +01:00
qingminlong
08da0d3861 fix(code-mode): report UTF-8 API file byte counts (#104244) 
* fix(code-mode): report UTF-8 API file byte counts

* fix(code-mode): report UTF-8 API file byte counts

* chore(changelog): keep release notes release-owned

---------

Co-authored-by: Peter Steinberger <steipete@gmail.com>
 2026-07-11 05:10:46 -07:00
Peter Steinberger
461772868d fix(computer): prevent stale, replayed, and post-cancel desktop actions (#103422) 
* fix(ai): preserve streamed tool-call identity

* fix(computer): bind actions to current tool authority

* fix(macos): serialize computer control lifecycle

* docs(computer): document hardened control contract

* chore: follow release-owned changelog policy

* test(agents): cover node list cancellation
 2026-07-10 06:47:56 +01:00
Peter Steinberger
3d404478b8 fix(discord): hide internal Code Mode wait progress (#99893) 
Hide invocation-specific Code Mode wait controls from channel progress while preserving telemetry and visible non-internal tools.
 2026-07-04 01:45:50 -07:00
Wynne668
dff45cae4c fix(code-mode): surface QuickJS error name and message to the model (#95906) 
* fix(code-mode): surface QuickJS error name and message to the model

* fix(code-mode): preserve host error diagnostics

---------

Co-authored-by: Vincent Koc <vincentkoc@ieee.org>
 2026-07-01 03:07:09 -07:00
mushuiyu886
01abe0a33d fix(agents): suggest recovery for unknown tool ids (#93374) 
Merged via squash.

Prepared head SHA: bee84e4eb8
Co-authored-by: mushuiyu886 <266724580+mushuiyu886@users.noreply.github.com>
Co-authored-by: vincentkoc <25068+vincentkoc@users.noreply.github.com>
Reviewed-by: @vincentkoc
 2026-06-23 14:20:09 +08:00
Peter Steinberger
bb6c3ce262 docs: document agent cli tests 2026-06-04 14:04:32 -04:00
Vincent Koc
a46181f168 test: stabilize timing-sensitive ARM suites 2026-06-03 03:47:48 -07:00
Peter Steinberger
22cb7fb6b7 chore(lint): enable no-promise-executor-return 2026-05-31 23:06:13 +01:00
Peter Steinberger
e681569536 feat: add code-mode MCP API files 
* feat: add code-mode MCP API files

* fix: satisfy code-mode MCP lint
 2026-05-31 21:29:06 +01:00
Peter Steinberger
4150c6ff82 feat: add typed MCP code-mode API (#88678) 
* feat: add typed MCP code-mode API

* fix: stabilize code-mode namespace drain

* fix: preserve code-mode run cap

* fix: reserve code-mode snapshot capacity
 2026-05-31 17:51:22 +01:00
Peter Steinberger
ec8cb8bcbf feat: add MCP code-mode namespace (#88636) 
* feat: add MCP code-mode namespace

* fix: unblock mcp namespace ci gates
 2026-05-31 15:02:19 +01:00
Peter Steinberger
23dac6c263 test: keep vitest cases under one second 2026-05-31 06:51:34 +01:00
Peter Steinberger
00d8d7ead0 refactor: extract normalization core package 
Extract shared normalization/coercion helpers into private @openclaw/normalization-core workspace package while preserving existing plugin SDK helper subpaths.\n\nAlso keeps direct normalization-core imports internal, wires UI/build/loader resolution, and replaces the slow PR network CodeQL lane with a fast added-line boundary scan while retaining full CodeQL for scheduled/manual runs.\n\nVerification: local moved tests, plugin SDK boundary tests, extension loader tests, agents-support shard, UI build/test, build artifacts, lint, workflow guards, autoreview, and GitHub CI passed on PR head 963d893715.
 2026-05-31 01:33:00 +01:00
Peter Steinberger
287687da20 feat: add internal code mode namespaces (#88043) 
* feat: add internal code mode namespaces

* test: add code mode namespace live proof

* test: add live code mode Docker repro

* chore: keep code mode docker repro out of package scripts

* fix: break code mode namespace type cycle

* fix: clean code mode namespace ci drift

* fix: route code mode namespaces through tools

* fix: preserve explicit agent global sessions

* docs: explain code mode namespace registry

* test: cap realtime websocket payload

* fix: normalize code mode timeout results

* fix: satisfy code mode timeout lint

* chore: rerun code mode CI

* ci: extend node shard silence watchdog

* test: avoid child process mock deadlocks

* test: fix code mode repro shebang

* fix: scope explicit agent sentinel sessions

* test: preserve child process mock actual loader

* fix: dispatch namespace tools by exact id

* test: satisfy restart execFile mock type
 2026-05-30 22:42:57 +01:00
Peter Steinberger
11b5728faa fix(agents): bound code mode snapshot expiry 2026-05-30 12:42:07 -04:00
Vincent Koc
61ef6b12dd test(agents): harden code mode wait timeout 2026-05-30 13:53:25 +01:00
Peter Steinberger
acb0e9c155 fix(agents): extend terminal outcome projections (#88162) 
* fix(agents): extend terminal outcome projections

* fix(agents): align terminal outcome follow-up checks

* fix(agents): satisfy terminal outcome mapper lint

* test(scripts): isolate websocket open timers

* test(security): drive sandbox browser timeout timers

* test(scripts): drive gh-read timeout timers

* test(agents): isolate code mode timers

* fix(agents): preserve hard timeouts on wait surfaces

* fix(agents): require timeout attribution for provider errors

* fix(sdk): require timeout attribution for provider errors

* fix(scripts): preserve changelog parse cause
 2026-05-30 03:13:01 +02:00
Dallin Romney
2ba725ef48 fix: stabilize code mode timeout and prompt snapshots (#87809) 
* fix: normalize code mode timeout interrupts

* test: refresh firecrawl prompt snapshots
 2026-05-28 16:26:12 -07:00
Peter Steinberger
d7e62a87f2 test: stabilize code mode wait timeout 
Increase the code-mode wait-timeout test timeout so CI shard load does not trip the worker startup guard before the test reaches the intended pending-tool wait path.
 2026-05-28 08:56:57 -04:00
Peter Steinberger
b9ade75fec test(agents): deflake code mode guest error check 2026-05-27 02:34:17 +01:00
Peter Steinberger
4118a32aad test: enforce per-test ci threshold 2026-05-26 04:35:20 +01:00
Peter Steinberger
6814525867 fix: preserve code mode failure output 2026-05-26 00:54:00 +01:00
Peter Steinberger
70dd31506b fix: land code-mode structured worker errors (#83444) (thanks @Kaspre) 2026-05-22 10:36:18 +01:00
Kaspre
edab653178 fix(code-mode): return structured worker error codes 2026-05-22 10:36:18 +01:00
Kaspre
1e1e45b72b fix(code-mode): align outer exec hook params 2026-05-22 09:46:27 +01:00
clawsweeper[bot]
0e2a06ae10 fix(code-mode): sharpen exec tool description so models stop wasting turns rediscovering constraints (#84368) 
Summary:
- The PR updates the code-mode exec tool description, adds regression coverage for the model-visible constraints, and records the fix in the changelog.
- Reproducibility: yes. at source level: current main's exec schema omits constraints that the current code-mo ...  also includes a live before/after recitation path showing the model receives the changed tool description.

Automerge notes:
- PR branch already contained follow-up commit before automerge: test(code-mode): cover exec tool guidance
- PR branch already contained follow-up commit before automerge: fix(code-mode): sharpen exec tool description so models stop wasting …

Validation:
- ClawSweeper review passed for head 8ff85071ce.
- Required merge gates passed before the squash merge.

Prepared head SHA: 8ff85071ce
Review: https://github.com/openclaw/openclaw/pull/84368#issuecomment-4493273853

Co-authored-by: Kaspre <kaspre@gmail.com>
Co-authored-by: clawsweeper <274271284+clawsweeper[bot]@users.noreply.github.com>
Co-authored-by: clawsweeper[bot] <274271284+clawsweeper[bot]@users.noreply.github.com>
Approved-by: takhoffman
Co-authored-by: takhoffman <781889+takhoffman@users.noreply.github.com>
 2026-05-20 01:25:04 +00:00
Peter Steinberger
4f4d108639 chore(lint): remove underscore-dangle allow list (#83542) 
* chore(lint): reduce underscore-dangle exceptions

* chore(lint): reduce more underscore exceptions

* chore(lint): remove underscore-dangle allow list

* fix(lint): repair underscore cleanup regressions

* test(lint): track version define suppression
 2026-05-18 14:56:06 +01:00
Kaspre
fd8877b5fd fix(code-mode): honor agent scoped code mode 
Fixes #83388.

- Honor per-agent `tools.codeMode` in config schema, runtime code-mode resolution, and model payload filtering.
- Preserve grouped OpenAI tool declarations when code-mode filtering keeps only `exec` and `wait`.
- Sync generated config/prompt baselines and carry a narrow media CI unblocker from current `main` fallout.

Co-authored-by: Kaspre <kaspre@gmail.com>
 2026-05-18 12:26:46 +01:00