1870 Commits
Author SHA1 Message Date
Bellman bd4043a83e Merge pull request #3379 from ultraworkers/release/v0.1.12
release: v0.1.12
v0.1.12
2026-11-09 05:08:25 +09:00
clawdbot 072892ff1e release: v0.1.12 2026-11-08 20:02:31 +00:00
Dror Meirovichandclawdbot 407a6c62f8 fix(windows): fix native runtime compatibility and enable workspace t… (#3378)
* fix(windows): fix native runtime compatibility and enable workspace tests

Fix shell discovery, hook quoting, native path handling and OAuth
randomness on Windows, make the test fixtures portable, and run the
full workspace test suite in the Windows CI job.

* test(plugins): make lifecycle fixtures Windows-compatible

* fix(windows): address workspace test failures

---------

Co-authored-by: clawdbot <clawdbot@ultraworkers.dev>
2026-11-08 19:45:52 +00:00
Rohan BhartiandClaude ca48ec7500 test(tools): cover NotebookEdit cell-type switching, id collisions and unknown ids (#3377)
Co-authored-by: Claude <noreply@anthropic.com>
2026-11-06 21:56:45 +00:00
Penguin Secret Agencyandsang nguyen ab8561dc37 docs: document UberLLM OpenAI-compatible gateway setup (#3376)
Co-authored-by: sang nguyen <sangnguyen@sangs-MacBook-Pro-5.local>
2026-11-05 07:01:42 +09:00
Bellman 747e160b59 Merge pull request #3374 from ultraworkers/release/v0.1.11
release: v0.1.11
v0.1.11
2026-11-04 22:02:52 +09:00
knowhyandknowhy 6ac59ab90b docs: document LLMTR OpenAI-compatible gateway setup (#3373)
Co-authored-by: knowhy <194148385+knowhycodata@users.noreply.github.com>
2026-11-04 13:00:45 +00:00
clawdbot 67e5783894 release: v0.1.11 2026-11-04 12:59:09 +00:00
Iain db58b190bd fix(tools): stop NotebookEdit reusing cell ids after a delete (#3371)
Inserted cells were named cell-{len+1}, which is still taken once any
cell but the last has been deleted, so a later edit by the returned id
went to the older cell instead.
2026-11-04 12:02:30 +00:00
Bellman 51cfca114c Merge pull request #3370 from ultraworkers/release/v0.1.10
release: v0.1.10
v0.1.10
2026-11-02 10:23:26 +09:00
clawdbot 1cae56fd3f release: v0.1.10 2026-11-02 01:14:53 +00:00
Iainandclawdbot a289024b35 fix(tools): cut RemoteTrigger responses on a char boundary (#3369)
* fix(tools): cut RemoteTrigger responses on a char boundary

A response over 8192 bytes with a multi-byte character across byte 8192 panicked on the slice.

* test(tools): add multibyte char boundary truncation test for RemoteTrigger

---------

Co-authored-by: clawdbot <clawdbot@ultraworkers.dev>
2026-11-02 00:03:39 +00:00
Bellman f4fff38de1 Merge pull request #3368 from ultraworkers/release/v0.1.9
release: v0.1.9
v0.1.9
2026-10-29 04:59:12 +09:00
clawdbot 3a802f7bf9 release: v0.1.9 2026-10-28 19:58:30 +00:00
Bougie 8523d59a84 fix(runtime): keep tool-use/tool-result pairs paired in Trident compaction (#3367)
Trident stage 1 dropped the assistant message that carried a file tool
use while keeping the tool result that answered it, so the compacted
session ended up with orphaned `tool_result` blocks. Providers reject
such requests with HTTP 400 ("tool_result blocks must be a response to
a preceding tool_use"), which breaks the auto-compact retry path that
runs Trident before resending a request.

Stage 1 also counted a tool result as an independent file operation,
which pushed `last_write` past the write the result belonged to and made
the newest write look obsolete.

Only tool uses count as file operations now, and a tool result is
dropped together with the tool use that produced it.
2026-10-28 19:01:54 +00:00
Bellman 8aab1d4e54 Merge pull request #3366 from ultraworkers/release/v0.1.8
release: v0.1.8
v0.1.8
2026-10-23 23:02:25 +09:00
clawdbot 26611f44c5 release: v0.1.8 2026-10-23 13:58:42 +00:00
Bellmanandclawdbot fd8527f899 Fix #3364: web search robustness - handle non-2xx responses and filter search engine self-links (#3365)
* Fix issue #3364: web search returns error on non-2xx response and filters search engine self-links

- Add HTTP status code check to execute_web_search: return error if response is not 2xx
  instead of proceeding with potentially junk results (e.g., DuckDuckGo challenge pages)
- Filter out links pointing back to the search engine host in extract_search_hits_from_generic_links
  to avoid returning search engine self-links when no proper search results are found
- Add regression tests for both scenarios

Refs #3364

* fix: implement registrable domain filtering and error on 202/blocked responses

- Replace exact host matching with registrable domain comparison to properly
  filter search engine self-links across subdomains (e.g., html.duckduckgo.com
  vs duckduckgo.com)
- Add error handling for 2xx responses with no search results (e.g., 202
  challenge pages from blocked search providers)
- Add regression tests for both 202 challenge page and mixed self-link scenarios
- Remove unrelated Cargo.lock version bumps (revert to 0.1.6)

Fixes #3364

* fix(tools): reject DuckDuckGo 202 challenge pages and drop search-engine links

The challenge page arrives as HTTP 202, which is_success() accepts, and its
links point at duckduckgo.com while the request goes to html.duckduckgo.com,
so the previous filter kept them. Only a 200 page is parsed now, and the
generic fallback drops any duckduckgo.com link or link to the configured
search host. Removes the registrable-domain heuristic and the 'no hits is an
error' path (a real query can legitimately return nothing), and replaces
tests that never exercised a self-link with ones that fail on the old code.

Refs #3364

---------

Co-authored-by: clawdbot <clawdbot@ultraworkers.dev>
2026-10-23 14:22:40 +01:00
Bellman 22fe36072a Merge pull request #3363 from ultraworkers/release/v0.1.7
release: v0.1.7
v0.1.7
2026-10-19 13:07:03 +09:00
clawdbot 0a899b630b test: update user-agent version check to 0.1.7 2026-10-19 04:04:04 +00:00
clawdbot 3e514dbf18 release: v0.1.7 2026-10-19 04:01:05 +00:00
twtrubiks 66418c6127 fix(runtime): name the session model in the system prompt (#3359)
The environment section rendered "Model family: Claude Opus 4.6" for
every Anthropic model, so claude-opus-5-5, claude-sonnet-4-6, and any
other Claude model told users it was Opus 4.6.

Render a neutral "Claude" family label followed by the resolved model
ID, and rebuild the system prompt on /model so the line follows a
mid-session switch instead of keeping the startup model.
2026-10-19 04:52:41 +01:00
twtrubiks 3cc90cfc7a feat(runtime): add OpenAI, xAI, and DashScope pricing (#3358)
Models from the OpenAI-compatible providers fell back to
default_sonnet_tier ($3/$15 per MTok), so e.g. gpt-5.4-nano was
estimated at 15x its input price and qwen-plus at about 26x.

Add a table of published rates keyed by model id, matching dated
snapshots and -latest aliases:

- OpenAI standard tier for current gpt-6 / gpt-5.x / gpt-4.1 / gpt-4o
  and o-series models (Responses-only pro models are omitted).
- xAI grok-4.x and grok-build. Slugs retired on 2026-05-15 (grok-3,
  grok-4-0709, grok-4-fast-*, grok-4-1-fast-*) are billed at grok-4.3
  rates, and grok-code-fast-* is served as grok-build.
- DashScope qwen-max, qwen-plus, qwen-flash and kimi-k2.5 at China
  (Beijing) rates, which is claw's default DashScope endpoint, with
  non-thinking output and the 20% implicit-cache hit rate.

Long-context and higher input tiers use the base rate because usage is
aggregated across requests.
2026-10-19 12:15:58 +09:00
clawdbot b8f93afbb3 fix: parallel tool-result pairing, terminal-scope path limit, credential hint
Merge PR #3360 from c01dsummer/claw-code (fix/roadmap-835-838)

Four fixes addressing issues #3361 and #3360:

1. Parallel tool-result pairing (835): The Anthropic Messages API requires all
   tool results of a turn to be in a single message. When a turn issued two tool
   calls at once, the results were sent in separate messages, causing a 400 error.
   Fixed by merging adjacent tool-result-only messages into one.

2. Terminal-scope path limit (836): Correlation keys up to 512 bytes expanded to
   1024+ hex characters, exceeding APFS's 1024-byte total path limit. Fixed by
   using SHA256 digest (32 hex chars) for path components while storing the full
   key in the record for exact matching.

3. Credential hint (838): When ANTHROPIC_BASE_URL points to a non-Anthropic
   endpoint (DeepSeek, corporate gateways), the missing-credentials error now
   explains that the endpoint expects its own credentials, not Anthropic's.

4. ROADMAP entries: Documents all three fixes with verification details.

All tests pass (370+ for rusty-claude-cli, 240+ for sdk, 122+ for tools, 209+ for
api). Formatting verified with cargo fmt. CI checks approved and passed.

Fixes #3361, #3360
2026-10-19 03:11:01 +00:00
twtrubiks c55c7e4710 fix(runtime): skip non-UTF-8 environment variables instead of panicking (#3356)
std::env::vars() panics on any non-UTF-8 value. zsh exports a metafied
$_ when the command path contains non-ASCII characters (e.g. 下載), so
claw panicked on startup. Use vars_os() and skip entries that are not
valid UTF-8.
2026-10-19 12:04:36 +09:00
Wu Shuwen 917a9e28ee fix(plugins): cfg-gate non-Windows hook path import (#3302) 2026-10-19 12:03:10 +09:00
twtrubiks 4b8c79e73c fix(runtime): update model pricing for Anthropic and DeepSeek APIs
* fix(runtime): update model pricing table to current rates

Align pricing_for_model with the published Anthropic pricing table:

- default_sonnet_tier was $15/$75 (the old Opus rate); it is now the
  Sonnet 4.x rate of $3/$15, which is what the `sonnet` alias resolves to.
- Add Sonnet 5 / 5.5, Haiku 5.5, Haiku 3.5, and Fable / Mythos rates.
- Opus 4.5+ is $5/$25 and Opus 5.5 is $4/$20; Opus 4/4.1 keep the $15/$75
  tier they are still billed at on Bedrock and Google Cloud.

Versions are parsed from the model id so dated, provider-prefixed, and
Vertex-style ids resolve to the right tier. Haiku 5.5's >100K-token tier
is not modeled because usage is aggregated across requests.

* fix(runtime): add DeepSeek API pricing

DeepSeek models fell back to default_sonnet_tier ($3/$15 per MTok),
overestimating V4 Flash by about 10x on input and 12x on output.

Price the ids served by the DeepSeek API at peak rates: deepseek-v4-pro
at $1.32/$3.96, and deepseek-flash, deepseek-v4-flash and the retired
deepseek-chat / deepseek-reasoner aliases at $0.30/$1.20. Off-peak usage
is billed at half. Other DeepSeek models on third-party hosts keep the
default because their prices vary by host.
2026-10-19 12:02:18 +09:00
twtrubiks 78ffd13d19 fix(cli): stop duplicating thinking blocks in streamed responses
push_output_block recorded a thinking event at content_block_start (an
empty placeholder) and the stream loop recorded the full block again at
content_block_stop. The empty duplicate was replayed on the next request
and rejected with 400 "each thinking block must contain thinking".
Only emit the event from the non-streaming path.
2026-10-19 03:01:20 +00:00
devilking7x 6d7412d958 docs: sync zh README star-history chart to dera.page mirror (#3354)
The English README migrated the star-history chart/link from
star-history.com / api.star-history.com to star-history.dera.page,
but README.zh.md (last synced at d229a9b) still used the old domains.
Update the 4 URLs so both language versions stay consistent.
2026-10-13 09:57:11 +01:00
Bellman 479e598cd3 Merge pull request #3353 from ultraworkers/lane/release-v0.1.6
release: v0.1.6
v0.1.6
2026-10-13 16:11:58 +09:00
clawdbot 89e717ec09 release: bump version to 0.1.6 and add CHANGELOG entry 2026-10-13 07:06:33 +00:00
Bellmanandclawdbot 01e9fc3229 [Slice 1.3] SDK session lifecycle & reconciliation (#3351)
* feat(sdk): implement session lifecycle and reconciliation

* fix(sdk): serialize session lifecycle recovery

* fix(sdk): preserve lifecycle outcomes and output

---------

Co-authored-by: clawdbot <clawdbot@ultraworkers.dev>
2026-10-13 07:02:25 +01:00
Bellman 02c22b4211 Merge pull request #3350 from ultraworkers/lane/release-v0.1.5
release: v0.1.5
v0.1.5
2026-10-13 12:08:42 +09:00
clawdbot 0e54dec1c9 test: make sandbox status check environment-aware
The /sandbox status can be 'ok' (with namespace isolation) or 'warn' (in
restricted environments like CI without unshare support). Update the test
to accept either value rather than hard-coding an expectation.
2026-10-13 03:05:56 +00:00
clawdbot c4ce758d5e test: fix version expectation in client_integration and sandbox status test
- Update client_integration.rs user-agent assertion to expect version 0.1.5
- Fix output_format_contract.rs /sandbox status expectation from 'warn' to 'ok'
2026-10-13 03:02:30 +00:00
clawdbot 4a920fb281 release: bump version to 0.1.5 and add CHANGELOG entry 2026-10-13 02:58:13 +00:00
Bellmanandclawdbot 192d40a860 feat(sdk): complete WebSocket client transport (#3349)
Co-authored-by: clawdbot <clawdbot@ultraworkers.dev>
2026-10-13 03:40:03 +01:00
Bellman a35caea528 Merge pull request #3348 from ultraworkers/lane/fmt-main
style: cargo fmt (main red after #3346)
2026-10-13 11:00:57 +09:00
clawdbot cf8f1da360 style: cargo fmt after #3346 2026-10-13 01:57:43 +00:00
Bellmanandclawdbot 0274174536 fix: isolate OPENAI_BASE_URL in provider hint test to prevent environment pollution (#3347)
The test explicit_model_provider_hint_controls_runtime_provider_dispatch
was failing when OPENAI_BASE_URL was set in the environment to a non-standard
URL (e.g., api.layofflabs.com). The test expects the OpenAI provider to use
the default base URL (api.openai.com) when no explicit base_url is provided
in the ProviderConfig.

This fix adds an EnvVarGuard struct to the tests module and uses it to
ensure OPENAI_BASE_URL is unset before running the test, preventing
environment pollution from affecting the test result.

Fixes: https://github.com/ultraworkers/claw-code/issues/3345

Co-authored-by: clawdbot <clawdbot@ultraworkers.dev>
2026-10-13 10:13:23 +09:00
Bellman da6a1692cf Merge pull request #3345 from ultraworkers/lane/skills-bundled-registry-chaining
feat(skills): implement bundled skills registry and chaining (#3324)
2026-10-13 10:10:35 +09:00
Bellman 6cddf08934 Merge pull request #3344 from ultraworkers/lane/issue-3321-sdk-operation-registry
feat(sdk): add operation registry and schema validation (#3321)
2026-10-13 10:08:59 +09:00
Bellman 5214beab31 Merge pull request #3343 from ultraworkers/lane/cc-pr-3329-review
docs: GJC compatibility gap matrix (updated)
2026-10-13 10:08:05 +09:00
Bellmanandclawdbot d9d5d5da08 feat(runtime): implement per-session settings override & schema validation (#3346)
Implement issue #3325 (Slice 3.1) Config: Settings Override & Schema Validation

Additions:
- Setting schema registry with support for multiple value types
- SessionSettings struct with three-level hierarchy (global, session, request)
- SettingApplicator for merging and applying settings
- ConfigHotreloadMonitor for filesystem monitoring
- 36 comprehensive tests covering:
  - Schema validation with allowed values
  - Override hierarchy (request > session > global > default)
  - Permission mode overrides per-session
  - Temperature/token overrides work correctly
  - Dynamic setting application mid-session
  - Settings propagation to all tools
  - Config hotreload detection
  - Default values and type validation
  - Non-overridable settings

Size: ~750 LOC with tests

References:
- Issue #3325: [Slice 3.1] Config: Settings Override & Schema Validation
- Crate: runtime (enhance existing config.rs)

Co-authored-by: clawdbot <clawdbot@ultraworkers.dev>
2026-10-13 10:07:54 +09:00
clawdbot 592beb5584 style: fix cargo fmt issues 2026-10-13 01:06:46 +00:00
clawdbot cd04270a17 feat(skills): implement bundled skills registry and skill chaining support (#3324)
- Add SkillOrigin::Bundled variant to support bundled skills registry
- Implement bundled_skill_root() function for discovering bundled skills
- Update skill discovery to include bundled skills from standard install paths
- Create example bundled skills (example-skill, chain-example)
- Add comprehensive tests for bundled skills discovery and metadata
- Bundled skills follow same directory structure as plugins
- Skills can now chain/invoke other skills using standard dispatch mechanisms
- Maintains backward compatibility with existing SkillsDir and LegacyCommandsDir
2026-10-13 01:05:22 +00:00
clawdbot e28d9c1e25 feat(sdk): add operation registry and schema validation (#3321)
- Implement OperationRegistry with standard query, control, and event operations
- Add Schema struct for defining input/output schemas
- Add OperationMetadata for rich operation descriptions
- Add Frame methods to extract operation and input from broker requests
- Add comprehensive tests demonstrating the gap and the fix
- Operations can be discovered, validated, and customized

This addresses issue #3321 (Slice 1.2): SDK operation registry & schema validation.

The gap: The original SDK allowed any operation name with no validation.
The fix: A registry-based system that defines valid operations and their schemas.
2026-10-13 01:03:43 +00:00
clawdbot c6a7c6ea54 docs: update GJC compatibility gap matrix with PR #3330-3339 progress
- Mark SDK wire protocol (Slice 1.1) as implemented (PR #3330)
- Update tool catalog status with read selectors (PR #3332/#3334)
- Add slash commands progress: /tools, /info (PR #3339)
- Document as historical planning reference with current implementation status
- Add PR references and status summary
- All section status notes now reflect merged work as of 2026-10-13
2026-10-13 01:02:43 +00:00
clawdbot 19030cbbda docs: add GJC compatibility gap matrix
Comprehensive analysis of GJC SDK surface (gajae-code) vs claw-code
implementation status across:
- SDK wire protocol (WebSocket JSON-RPC)
- Session lifecycle and reconciliation
- 55-tool catalog and implementations
- Skill discovery and invocation
- Settings and configuration
- Hooks and plugins
- AGENTS.md rules system
- 120+ slash commands
- Subagent delegation and task execution

Gap matrix includes:
- GJC source paths and behavior
- claw-code current status (have/partial/missing)
- Proposed Rust crate/module ownership
- Size estimates and complexity assessment
- Implementation roadmap (3 phases, 10 slices)
- Risk mitigation and verification checklist

Phase 1 (Foundation): SDK wire protocol + session lifecycle
Phase 2 (Core): Tool completion + skill enhancement
Phase 3 (Polish): Settings, commands, integration

Total estimated effort: 15,000 LOC across new SDK crate and
crate extensions.

Relates to: #3319
2026-10-13 01:02:43 +00:00
Bellman 09f3b366ba Merge pull request #3339 from ultraworkers/lane/gjc-s32-r4-commands-impl
feat: implement /tools and /info slash commands
2026-10-13 09:24:24 +09:00