let5see/clawdbot
1
0
Fork 0
Code Issues Pull Requests Actions 4 Packages Projects Releases Wiki Activity
6,818 Commits 1 Branch 0 Tags
e110cf4fb1d8f214e5ecb7543ea75d8d44495c07
Commit Graph

6818 Commits

This Branch
This Branch
All Branches
Author SHA1 Message Date
Peter Steinberger
e110cf4fb1 chore: keep vitest workers at 4 2026-01-20 10:41:09 +00:00
Peter Steinberger
6942ceb7a9 test: update gateway node/e2e tests 2026-01-20 10:41:09 +00:00
Peter Steinberger
47cf28f6b6 fix: prevent duplicate cron runs across hot reloads 2026-01-20 10:36:46 +00:00
Peter Steinberger
da7da30b22 style: format agent defaults import 2026-01-20 10:31:16 +00:00
Peter Steinberger
213d9b47b0 refactor: centralize agent concurrency defaults 2026-01-20 10:31:16 +00:00
Peter Steinberger
d88b239d3c feat: add device token auth and devices cli 2026-01-20 10:30:53 +00:00
Peter Steinberger
1c02de1309 chore: raise default agent concurrency 2026-01-20 10:08:26 +00:00
Peter Steinberger
d3c2b83f88 fix: avoid context-window-too-small misclassification (#1266, thanks @humanwritten) 
Co-authored-by: humanwritten <humanwritten@users.noreply.github.com>
 2026-01-20 10:07:05 +00:00
humanwritten
93f80894a3 fix: prevent context-window-too-small error from being misclassified 
The regex `/context window/i` was matching "Model context window too small"
and rewriting it to generic "Context overflow" message, hiding the actual
problem from users.

Add exclusion for "too small|minimum is" patterns so the original
informative error message passes through.

🤖 AI-assisted (Claude) - tested on local instance

Co-Authored-By: Claude <noreply@anthropic.com>
 2026-01-20 10:07:05 +00:00
Peter Steinberger
c440cc2f84 fix: preserve gateway presence instanceId 2026-01-20 09:52:26 +00:00
Peter Steinberger
2439c31844 chore: tune vitest parallelism 2026-01-20 09:40:10 +00:00
Peter Steinberger
292f21ae78 docs: add changelog entry for codex-cli dedupe 2026-01-20 09:38:56 +00:00
Peter Steinberger
9c2c4b1138 fix(auth): dedupe codex-cli profiles 
Co-authored-by: Oliver Drobnik <oliver@cocoanetics.com>
 2026-01-20 09:38:56 +00:00
George Pickett
e0e33e12d1 Docs: frame skills eval gap in testing 2026-01-20 09:37:59 +00:00
Peter Steinberger
eb5145c5d1 docs: mention tool_result_persist hook 2026-01-20 09:36:10 +00:00
Peter Steinberger
aedf4ce328 fix: treat OAuth refresh failures as auth errors (#1261) (thanks @zknicker) 
Co-authored-by: Zach Knickerbocker <zknicker@users.noreply.github.com>
 2026-01-20 09:31:41 +00:00
Peter Steinberger
94af5a72fc fix: prevent duplicate agent event emission 2026-01-20 09:25:20 +00:00
Peter Steinberger
9dbc1435a6 fix: enforce ws3 roles + node allowlist 2026-01-20 09:24:01 +00:00
Peter Steinberger
32a668e4d9 refactor: streamline TUI stream assembly updates 2026-01-20 08:57:42 +00:00
Peter Steinberger
c17c7b4e24 Merge pull request #1235 from dougvk/feat/tool-dispatch-skill-commands 
Plugin API: tool-dispatched skill commands + tool_result_persist hook
 2026-01-20 08:52:05 +00:00
Peter Steinberger
c5e732951b fix: prefer bundled plugin schema 2026-01-20 08:47:56 +00:00
Peter Steinberger
069b50635b fix: lazy-load pdf/image input deps 2026-01-20 08:47:56 +00:00
Peter Steinberger
074db1905a fix: refactor TUI stream assembly (#1202, thanks @aaronveklabs) 
Co-authored-by: Aaron <aaron@vektor-labs.com>
 2026-01-20 08:36:54 +00:00
Aaron
9609a3af40 fix: check for error before early return in extractContentFromMessage 
Addresses Codex review feedback - ensures error messages are surfaced
even when content is missing/undefined
 2026-01-20 08:36:36 +00:00
Aaron
476087f879 fix(tui): buffer streaming messages by runId to prevent render ordering issues 
Fixes #1172

- Add per-runId message buffering in ChatLog
- Separate thinking stream from content stream handling
- Ensure proper sequencing (thinking always before content)
- Model-agnostic: works with or without thinking tokens
 2026-01-20 08:36:36 +00:00
Peter Steinberger
41b696fa83 chore: remove Peekaboo submodule 2026-01-20 08:31:06 +00:00
Peter Steinberger
a5adedea91 refactor: add aws-sdk auth mode and tighten provider auth 2026-01-20 08:28:40 +00:00
Peter Steinberger
9266e542ab chore: remove peekaboo submodule references 2026-01-20 08:26:56 +00:00
Peter Steinberger
f06ad4502b refactor: share responses input handling 2026-01-20 08:21:57 +00:00
Peter Steinberger
e26c647828 fix: defer pdf deps and profile flag detection 2026-01-20 08:20:07 +00:00
Peter Steinberger
bee72f1ae0 fix: guard systemd errors in doctor 2026-01-20 07:56:22 +00:00
Peter Steinberger
509bc81e28 Merge pull request #1288 from bradleypriest/pr/chat-session-url 
ui(chat): persist session in URL and stabilize picker
 2026-01-20 07:44:33 +00:00
Peter Steinberger
6d5195c890 refactor: normalize cli command hints 2026-01-20 07:43:00 +00:00
Peter Steinberger
11b9b6dba5 Merge pull request #1229 from RyanLisse/main 
feat(gateway): add OpenResponses /v1/responses endpoint
 2026-01-20 07:38:18 +00:00
Peter Steinberger
bbc67f3754 fix: expand /v1/responses inputs (#1229) (thanks @RyanLisse) 2026-01-20 07:37:30 +00:00
Ryan Lisse
4f02c74dca test(gateway): add OpenResponses parity E2E tests 
- Add schema validation tests for input_image, input_file, client tools
- Add buildAgentPrompt tests for turn-based tool flow
 2026-01-20 07:37:01 +00:00
Ryan Lisse
a5afe7bc2b feat(gateway): implement OpenResponses /v1/responses endpoint phase 2 
- Add input_image and input_file support with SSRF protection
- Add client-side tools (Hosted Tools) support
- Add turn-based tool flow with function_call_output handling
- Export buildAgentPrompt for testing
 2026-01-20 07:37:01 +00:00
Ryan Lisse
f4b03599f0 feat(gateway): add OpenResponses /v1/responses endpoint 
Add a new `/v1/responses` endpoint implementing the OpenResponses API
standard for agentic workflows. This provides:

- Item-based input (messages, function_call_output, reasoning)
- Semantic streaming events (response.created, response.output_text.delta,
  response.completed, etc.)
- Full SSE event support with both event: and data: lines
- Configuration via gateway.http.endpoints.responses.enabled

The endpoint is disabled by default and can be enabled independently
from the existing Chat Completions endpoint.

Phase 1 implementation supports:
- String or ItemParam[] input
- system/developer/user/assistant message roles
- function_call_output items
- instructions parameter
- Agent routing via headers or model parameter
- Session key management

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
 2026-01-20 07:37:01 +00:00
Ryan Lisse
7f6e87e918 build: update bundle hash and register Peekaboo submodule 2026-01-20 07:37:01 +00:00
Ryan Lisse
e14ff8f407 fix(ios): replace FileManager.default with FileManager() for Swift 6.2 compatibility 2026-01-20 07:37:01 +00:00
Ryan Lisse
87d995bcde refactor(macos): replace FileManager.default for Swift 6 2026-01-20 07:37:01 +00:00
Peter Steinberger
44d55667de docs: optimize PR review calls 2026-01-20 07:34:15 +00:00
Peter Steinberger
3e546e691d fix: infer perplexity baseUrl from api key 2026-01-20 07:27:32 +00:00
Peter Steinberger
52e9450a79 docs: require git pull before review 2026-01-20 07:18:26 +00:00
Peter Steinberger
aa7c291ad6 Merge pull request #1289 from clawdbot/docs/bedrock-docs 
docs: add Bedrock provider links
 2026-01-20 07:14:37 +00:00
Peter Steinberger
3f44f4167b fix: update Bedrock provider docs (#1289) (thanks @steipete) 2026-01-20 07:14:03 +00:00
Peter Steinberger
90a6ec12cc docs: update bedrock provider docs 2026-01-20 07:08:12 +00:00
Peter Steinberger
a91c653d8a Merge pull request #1286 from alauppe/feat/bedrock-converse-stream-api 
feat(models): Add AWS Bedrock Converse Stream API support
 2026-01-20 07:03:27 +00:00
Peter Steinberger
7f6fcbf637 fix: stabilize update.run test 2026-01-20 06:56:10 +00:00
Peter Steinberger
5d7e38a786 fix: avoid duplicate doctor config output 2026-01-20 06:32:50 +00:00