Commit Graph
61 Commits
Author SHA1 Message Date
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
clawdbot 67e5783894 release: v0.1.11 2026-11-04 12:59:09 +00:00
clawdbot 1cae56fd3f release: v0.1.10 2026-11-02 01:14:53 +00:00
clawdbot 3a802f7bf9 release: v0.1.9 2026-10-28 19:58:30 +00:00
clawdbot 26611f44c5 release: v0.1.8 2026-10-23 13:58:42 +00:00
clawdbot 0a899b630b test: update user-agent version check to 0.1.7 2026-10-19 04:04:04 +00:00
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
clawdbot 89e717ec09 release: bump version to 0.1.6 and add CHANGELOG entry 2026-10-13 07:06:33 +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 eb1537ca92 docs: add CHANGELOG for v0.1.4 release 2026-10-13 00:03:23 +00:00
clawdbot f021597942 Revert "Merge pull request #3318 from ultraworkers/pr-3292"
This reverts commit 2d920ce915, reversing
changes made to 80bfe94b77.
2026-10-12 23:09:13 +00:00
reacechalmers cd01ffc5f3 fix(clippy): box ApiError::Api payload to clear result_large_err
`ApiError` is the `Err` half of nearly every `Result` in the api crate, and
its `Api` variant carried ~139 bytes inline (8 fields, four of them
`Option<String>`). That tripped clippy::result_large_err on 35 signatures
and, with -D warnings, made the whole crate unbuildable under the repo's
own documented verification command.

Move the payload into `ApiErrorDetails` behind a `Box`:
  - `ApiError::Api(Box<ApiErrorDetails>)`, with `ApiError::api(..)` to
    construct and `api_details()` to borrow
  - `ApiErrorDetails` re-exported from the crate root
  - adding a field here can no longer re-inflate every signature

This also simplifies `enrich_bearer_auth_error`, which previously
destructured and rebuilt all eight fields at five separate return points
just to append a hint; it now mutates the boxed payload in place.

Also clears the remaining pre-existing lints that blocked -D warnings:
unused test bindings, a redundant `use serde_json`, and an explicit
`.into_iter()` in claw-rag-service.

Verified: cargo test --workspace passes, 0 failures.

Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01Q9McEEH32ZtyM62GSXVSyJ
(cherry picked from commit e9210bd75eb76e5d88b2ae797f537102bcabd41d)
2026-10-12 22:58:19 +00:00
YeonGyu-Kim 7503c1c031 fix(providers): parse Ollama reasoning fields 2026-06-08 10:08:32 +09:00
YeonGyu-Kim a1da1ca8e6 test(cli): serialize env-sensitive model alias checks 2026-06-08 01:37:28 +09:00
bellman fa35018769 fix: validate env model selection 2026-06-04 00:30:13 +09:00
bellman c91a3062d5 fix: normalize Anthropic model routing 2026-06-03 22:20:23 +09:00
bellman 54d785d0c0 fix: preserve DeepSeek V4 thinking history 2026-06-03 21:53:54 +09:00
YeonGyu-Kim 6f5465aeaf fix(test): update client_integration version string 0.1.0 -> 0.1.3 2026-05-25 12:49:36 +09:00
bellman dccb3e72d9 Stabilize OpenAI-compatible mock transport verification
Keep the mock HTTP/SSE/proxy coverage deterministic under strict linting while preserving provider request behavior.\n\nConstraint: Task 4 scope is limited to OpenAI-compatible HTTP/SSE/proxy coverage and provider compatibility surfaces.\nRejected: Environment-variable proxy testing | It races with parallel integration tests and can route unrelated localhost mocks through a single proxy fixture.\nConfidence: high\nScope-risk: narrow\nDirective: Prefer explicit injected reqwest clients for proxy integration tests instead of mutating process proxy environment.\nTested: cargo fmt --check; cargo check -p api; cargo test -p api --test openai_compat_integration -- --nocapture; cargo test -p api\nNot-tested: cargo clippy --no-deps -p api --all-targets -- -D warnings fails on pre-existing anthropic.rs/providers/mod.rs lints outside task scope.\n\nCo-authored-by: OmX <omx@local>
2026-05-15 10:30:19 +09:00
bellman ea95bf2576 omx(team): auto-checkpoint worker-3 [unknown] 2026-05-15 10:30:16 +09:00
bellman a212c662e5 omx(team): auto-checkpoint worker-1 [1] 2026-05-15 10:30:00 +09:00
bellman e4ef0f7f19 omx(team): auto-checkpoint worker-4 [unknown] 2026-05-15 10:22:03 +09:00
bellman 76581f7239 omx(team): auto-checkpoint worker-3 [unknown] 2026-05-15 10:21:58 +09:00
bellman a6ca5c489b omx(team): auto-checkpoint worker-4 [unknown] 2026-05-15 10:21:28 +09:00
YeonGyu-Kim 75c08bc982 fix: REPL display, /compact panic, identity leak, DeepSeek reasoning, thinking blocks
Five interrelated fixes from parallel Hephaestus sessions:

1. fix(repl): display assistant text after spinner (#2981, #2982, #2937)
   - Added final_assistant_text() call after run_turn spinner completes
   - REPL now shows response text like run_prompt_json does

2. fix(compact): handle Thinking content blocks (#2985)
   - Added ContentBlock::Thinking variant throughout compact summarizer
   - Prevents panic when /compact encounters thinking blocks

3. fix(prompt): provider-aware model identity (#2822)
   - New ModelFamilyIdentity enum (Claude vs Generic)
   - Non-Anthropic models no longer say 'I am Claude'
   - model_family_identity_for() detects provider and sets identity

4. fix(openai): preserve DeepSeek reasoning_content (#2821)
   - Stream parser now captures reasoning_content from OpenAI-compat
   - Emits ThinkingDelta/SignatureDelta events for reasoning models
   - Thinking blocks included in conversation history for re-send

5. feat(runtime): Thinking block support across codebase
   - AssistantEvent::Thinking variant in conversation.rs
   - ContentBlock::Thinking in session serialization
   - Thinking-aware compact summarization
   - Tests for thinking block ordering and content

Closes #2981, #2982, #2937, #2985, #2822, #2821
2026-05-06 15:32:34 +09:00
YeonGyu-Kimandgaebal-gajae ff1df4c7ac fix(api): auth-provider error copy — prefix-routing hints + sk-ant-* bearer detection — closes ROADMAP #28
Two live users in #claw-code on 2026-04-08 hit adjacent auth confusion:
varleg set OPENAI_API_KEY for OpenRouter but prefix routing didn't
activate without openai/ model prefix, and stanley078852 put sk-ant-*
in ANTHROPIC_AUTH_TOKEN (Bearer path) instead of ANTHROPIC_API_KEY
(x-api-key path) and got 401 Invalid bearer token.

Changes:
1. ApiError::MissingCredentials gained optional hint field (error.rs)
2. anthropic_missing_credentials_hint() sniffs OPENAI/XAI/DASHSCOPE
   env vars and suggests prefix routing when present (providers/mod.rs)
3. All 4 Anthropic auth paths wire the hint helper (anthropic.rs)
4. 401 + sk-ant-* in bearer token detected and hint appended
5. 'Which env var goes where' section added to USAGE.md

Tests: unit tests for all three improvements (no HTTP calls needed).
Workspace: all tests green, fmt clean, clippy warnings-only.

Source: live users varleg + stanley078852 in #claw-code 2026-04-08.

Co-authored-by: gaebal-gajae <gaebal-gajae@layofflabs.com>
2026-04-08 16:29:03 +09:00
YeonGyu-Kim 82baaf3f22 fix(ci): update integration test MessageRequest initializers for new tuning fields
openai_compat_integration.rs and client_integration.rs had MessageRequest
constructions without the new tuning param fields (temperature, top_p,
frequency_penalty, presence_penalty, stop) added in c667d47.

Added ..Default::default() to all 4 sites. cargo fmt applied.

This was the root cause of CI red on main (E0063 compile error in
integration tests, not caught by --lib tests).
2026-04-08 11:43:51 +09:00
YeonGyu-Kim 1f968b359f feat: b6-openai-models — batch 6 2026-04-07 15:52:30 +09:00
YeonGyu-Kim 5bcbc86a2b feat: b5-slash-help — batch 5 upstream parity 2026-04-07 14:51:27 +09:00
YeonGyu-Kim ce360e0ff3 fix(api): strip anthropic beta fields from non-beta requests
mikejiang: 'betas: Extra inputs are not permitted' 400 error.
Only include beta headers when request targets beta endpoint.
2026-04-07 14:22:05 +09:00
YeonGyu-Kim ce22d8fb4f fix(api): add serde(default) to all usage/token parse paths in SSE stream
Sterling reported 'json_error: no field input/input_tokens' still firing
despite existing serde(default) in types.rs. Root cause: SSE streaming
path had a separate deserialization site that didn't use the same defaults.

- Add serde(default) to sse.rs UsageEvent deserialization
- Add serde(default) to types.rs Usage struct fields (input_tokens, output_tokens)
- Add regression test with empty-usage JSON response in streaming context
2026-04-07 13:44:22 +09:00
Yeachan-Heo fa72cd665e Block oversized requests before providers hard-fail
The runtime already tracked rough token estimates for compaction, but provider-bound
requests still relied on naive model output limits and could be sent upstream even
when the selected model could not fit the estimated prompt plus requested output.

This adds a small model token/context registry in the API layer, estimates request
size from the serialized prompt payload, and fails locally with a dedicated
context-window error before Anthropic or xAI calls are made. Focused integration
coverage asserts the preflight fires before any HTTP request leaves the process.

Constraint: Keep the first pass minimal and reusable across both Anthropic and OpenAI-compatible providers
Rejected: Auto-compact-and-retry in the same patch | broader control-flow change than the requested minimal preflight
Confidence: medium
Scope-risk: narrow
Reversibility: clean
Directive: Expand the model registry before enabling preflight for additional providers or aliases
Tested: cargo build -p api -p tools -p rusty-claude-cli; cargo test -p api
Not-tested: End-to-end CLI auto-compaction or retry behavior after a local context_window_blocked failure
2026-04-05 16:39:58 +00:00
Yeachan-Heo 5f1eddf03a Preserve usage accounting on OpenAI SSE streams
OpenAI chat-completions streams can emit a final usage chunk when the\nclient opts in, but the Rust transport was not requesting it. This\nkeeps provider config on the client and adds stream_options.include_usage\nonly for OpenAI streams so normalized message_delta usage reflects the\ntransport without changing xAI request bodies.\n\nConstraint: Keep xAI request bodies unchanged because provider-specific streaming knobs may differ\nRejected: Enable stream_options for every OpenAI-compatible provider | risks sending unsupported params to xAI-style endpoints\nConfidence: high\nScope-risk: narrow\nDirective: Keep provider-specific streaming flags tied to OpenAiCompatConfig instead of inferring provider behavior from URLs\nTested: cargo clippy -p api --tests -- -D warnings\nTested: cargo test -p api openai_streaming_requests -- --nocapture\nTested: cargo test -p api xai_streaming_requests_skip_openai_specific_usage_opt_in -- --nocapture\nTested: cargo test -p api request_translation_uses_openai_compatible_shape -- --nocapture\nTested: cargo test -p api stream_message_normalizes_text_and_multiple_tool_calls -- --exact --nocapture\nNot-tested: Live OpenAI or xAI network calls
2026-04-02 10:04:14 +00:00
Yeachan-Heo 79da7c0adf Make claw's REPL feel self-explanatory from analysis through commit
Claw already had the core slash-command and git primitives, but the UX
still made users work to discover them, understand current workspace
state, and trust what `/commit` was about to do. This change tightens
that flow in the same places Codex-style CLIs do: command discovery,
live status, typo recovery, and commit preflight/output.

The REPL banner and `/help` now surface a clearer starter path, unknown
slash commands suggest likely matches, `/status` includes actionable git
state, and `/commit` explains what it is staging and committing before
and after the model writes the Lore message. I also cleared the
workspace's existing clippy blockers so the verification lane can stay
fully green.

Constraint: Improve UX inside the existing Rust CLI surfaces without adding new dependencies
Rejected: Add more slash commands first | discoverability and feedback were the bigger friction points
Rejected: Split verification lint fixes into a second commit | user requested one solid commit
Confidence: high
Scope-risk: moderate
Directive: Keep slash discoverability, status reporting, and commit reporting aligned so `/help`, `/status`, and `/commit` tell the same workflow story
Tested: cargo fmt --all; cargo clippy --workspace --all-targets -- -D warnings; cargo test --workspace
Not-tested: Manual interactive REPL session against live Anthropic/xAI endpoints
2026-04-02 07:20:35 +00:00
YeonGyu-Kim ffb133851e fix: cover merged prompt cache behavior 2026-04-02 11:31:53 +09:00
YeonGyu-Kim 8476d713a8 Merge remote-tracking branch 'origin/rcc/cache-tracking' into integration/dori-cleanroom 2026-04-02 11:17:13 +09:00
YeonGyu-Kim 164bd518a1 Merge remote-tracking branch 'origin/rcc/telemetry' into integration/dori-cleanroom 2026-04-02 11:13:56 +09:00
YeonGyu-Kim c849c0672f fix: resolve all post-merge compile errors
- Fix unresolved imports (auto_compaction, AutoCompactionEvent)
- Add Thinking/RedactedThinking match arms
- Fix workspace.dependencies serde_json
- Fix enum exhaustiveness in OutputContentBlock matches
- cargo check --workspace passes
2026-04-01 18:59:55 +09:00
Yeachan-Heo 799c92eada feat: cache-tracking progress 2026-04-01 06:25:26 +00:00
Yeachan-Heo 61b4def7bc feat: telemetry progress 2026-04-01 06:15:15 +00:00
Yeachan-Heo dcca64d1bd wip: grok provider abstraction 2026-04-01 06:00:48 +00:00
Yeachan-Heo 1b42c6096c feat: anthropic SDK header matching + request profile 2026-04-01 05:55:25 +00:00
Yeachan-Heo 828597024e wip: telemetry claude code matching 2026-04-01 05:45:28 +00:00
Yeachan-Heo ebdc60b66c feat: provider tests + grok integration 2026-04-01 05:45:27 +00:00
Yeachan-Heo 26344c578b wip: cache-tracking progress 2026-04-01 04:40:17 +00:00
Yeachan-Heo 5170718306 wip: telemetry progress 2026-04-01 04:30:29 +00:00
Yeachan-Heo 0cf2204d43 wip: cache-tracking progress 2026-04-01 04:30:24 +00:00
Yeachan-Heo 5654efb7b2 feat: provider abstraction layer + Grok API support 2026-04-01 04:10:46 +00:00
Yeachan-Heo 387a8bb13f feat: git integration, sandbox isolation, init command (merged from rcc branches) 2026-04-01 01:23:47 +00:00