202 Commits

Author SHA1 Message Date
pullfrog[bot] 30812435f9 Fix file upload 401 by conditionally signing content-disposition header (#289)
* Fix file upload 401 by conditionally signing content-disposition header

* Bump version to 0.0.162

---------

Co-authored-by: pullfrog[bot] <226033991+pullfrog[bot]@users.noreply.github.com>
2026-02-13 19:14:32 +00:00
David Blass bc28c658f2 harden sandbox escape vectors for bash disabled/restricted modes (#257)
* harden sandbox escape vectors for bash disabled/restricted modes

block git config injection (-c flag as subcommand), dangerous subcommands
(config, submodule, rebase, bisect), code-executing arg flags (--exec,
--extcmd), .gitattributes/.gitmodules writes, and package lifecycle scripts.
add retry logic to test runner for transient failures. add security unit
tests and adhoc attack tests.

Co-authored-by: Cursor <cursoragent@cursor.com>

* only filter subcommands in nobash, remove nobash from ui

* use regex matching

* iterate on tests

* simplify githooks

---------

Co-authored-by: Cursor <cursoragent@cursor.com>
2026-02-11 02:02:41 +00:00
Colin McDonnell f37d02b292 upgrade Claude to Opus 4.6 with effort levels (#256)
* upgrade Claude to Opus 4.6 with --effort max for --max mode

- mini: haiku → sonnet
- auto: opusplan → opus (Opus 4.6)
- max: opus → opus + --effort max (Opus 4.6 max effort)
- bump @anthropic-ai/claude-agent-sdk 0.2.7 → 0.2.39

Co-authored-by: Cursor <cursoragent@cursor.com>

* update action lockfile for claude-agent-sdk 0.2.39

Co-authored-by: Cursor <cursoragent@cursor.com>

* add tool_use_summary handler for SDK 0.2.39

Co-authored-by: Cursor <cursoragent@cursor.com>

* integrate gpt-5.3-codex with runtime model availability detection

checks GET /v1/models at agent start to determine if gpt-5.3-codex is
available for the API key, falling back to gpt-5.2-codex when it isn't.
model resolution runs concurrently with CLI install for zero added latency.
also bumps @openai/codex-sdk from 0.80.0 to 0.98.0.

Co-authored-by: Cursor <cursoragent@cursor.com>

---------

Co-authored-by: Cursor <cursoragent@cursor.com>
2026-02-10 23:34:13 +00:00
David Blass 19df8372cd add file_read/file_write tools, sandbox tests, CI improvements (#239)
* migrate to flags

* init

* iterate on file write lockdown tests

* improve ci

* fix lockfile

* fix typecheck

* fix lint

* improve pushRestricted

* ok

* fix more

* ok

* remove process.env spreading rule

Co-authored-by: Cursor <cursoragent@cursor.com>

* enhanced fs rw tools

---------

Co-authored-by: Cursor <cursoragent@cursor.com>
Co-authored-by: Colin McDonnell <colinmcd94@gmail.com>
2026-02-10 06:35:47 +00:00
David Blass 943409c417 add #timeout, macro errors, refactor tests (#191) 2026-01-28 21:06:57 +00:00
Colin McDonnell f77fecc2a0 Update 2026-01-28 07:47:52 +00:00
Mateusz Burzyński 071e885d63 Add upload tool and related APIs (#187)
* Add utils for r2 upload

* Add the tool and new routes

* fix auth issue

* sign headers

* add comment

* use our own API key to auth signed uploads

* Restructure things slightly

* tweak

* tweak

* add comments

* tweak

* revert a thing

* twaek

* drop mime type filtering

* new incarnation of mime type filtering

* jsut allow all octet-streams

* simplify further

* tweak

* update lockfile

---------

Co-authored-by: Colin McDonnell <colinmcd94@gmail.com>
2026-01-28 05:34:58 +00:00
Colin McDonnell d545a84027 0.0.159 2026-01-25 22:30:34 +00:00
David Blass 9a8db3e07c add restricted tests, refactor test infrastructure (#150) 2026-01-22 21:06:19 +00:00
Colin McDonnell 41fb0e78be remove duplicate 2026-01-22 06:17:13 +00:00
Colin McDonnell 57895ae342 Update lock 2026-01-22 06:15:49 +00:00
Robin Tail cfd7f45db9 fix: Update lock file in the action dir due to #118. 2026-01-20 06:47:27 +00:00
Colin McDonnell 8f6912deda Fix macros 2026-01-19 21:42:23 +00:00
David Blass f34379415e add per-agent smoke tests (#100) 2026-01-16 08:00:16 +00:00
David Blass 1daf1571cf add macros (#68) 2026-01-14 22:52:54 +00:00
Colin McDonnell 3fa309853b Fix repo slug 2026-01-14 01:44:30 +00:00
Colin McDonnell 5604cf1868 Clean up submodule stuff 2026-01-13 22:05:24 +00:00
Robin Tail 900cf49871 fix(deps): Upgrading esbuild to 0.27.2 (deduplication). 2026-01-13 13:30:10 +01:00
Colin McDonnell b2735b2916 0.0.157 2026-01-13 06:09:13 +00:00
Robin Tail c89f1b9537 Establishing unit tests using vitest. 2026-01-12 15:05:30 +01:00
Colin McDonnell 78c22085bf 0.0.156 2026-01-08 15:05:05 -08:00
Colin McDonnell 879d33403c Switch to custom Bash tool. Mask secrets from Bashsubprocs. Simplify security handling. 2026-01-08 14:09:08 -08:00
Robin Tail ff913feb3c Upgrading fastmcp ad claude-agent-sdk for using Zod 4. 2026-01-08 13:29:19 +01:00
Mateusz Burzyński a483711fee Auto-retry ratelimited octokit requests 2026-01-07 17:17:20 +01:00
Colin McDonnell 0a7a38a9a5 155 2025-12-22 18:45:43 -08:00
Colin McDonnell 17ad3bd0e7 0.0.154 2025-12-22 14:55:32 -08:00
Colin McDonnell 25896559f0 Switch back to one-shot reviews 2025-12-22 14:55:19 -08:00
Colin McDonnell 5353d80388 Retries on oidc. 152 2025-12-22 14:33:18 -08:00
Colin McDonnell 04c695038f 151 2025-12-22 13:57:51 -08:00
Colin McDonnell e9a585ce47 Improve debug logging for reviews. v0.0.150 2025-12-22 13:50:39 -08:00
Colin McDonnell 6d572f3ce8 0.0.149 2025-12-21 22:42:58 -08:00
David Blass b33deb1b5a fix thumbs up message, sleep prompting 2025-12-19 16:54:13 -05:00
David Blass bd8fc8abdf bump version 2025-12-17 18:00:52 -05:00
David Blass 90ed2648be refactor main 2025-12-17 16:28:17 -05:00
David Blass d074ece31b iterate on prep 2025-12-16 17:47:37 -05:00
Colin McDonnell 853746ba65 Clean up fork setup 2025-12-16 00:15:57 -08:00
Colin McDonnell efb4ad186f Improve remote tracking 2025-12-15 23:56:47 -08:00
Colin McDonnell c2cedce1bc 0.0.142 2025-12-15 23:38:46 -08:00
Colin McDonnell b833cdd4af 0.0.141 2025-12-15 23:22:30 -08:00
Colin McDonnell 333ad29965 0.0.140 2025-12-15 23:04:52 -08:00
Colin McDonnell b038fc574f Get reviews with comments 2025-12-15 21:37:46 -08:00
Colin McDonnell 316b6cb83c 0.0.138 2025-12-15 21:21:57 -08:00
Colin McDonnell 1d69f0f3e4 0.0.137 2025-12-15 20:22:12 -08:00
Colin McDonnell dc93c89c24 0.0.136 2025-12-15 19:10:24 -08:00
Colin McDonnell 0cdbc95e17 Flesh out review prompt 2025-12-14 16:12:16 -08:00
Colin McDonnell 3724572346 0.0.134 2025-12-13 12:29:15 -08:00
David Blass 6371584c80 ok 2025-12-13 00:35:03 -05:00
David Blass bb55216a6b iterate on pr fix 2025-12-11 18:02:44 -05:00
David Blass 7959a51995 update deps 2025-12-11 15:08:10 -05:00
Shawn Morreau fb7d9e0d34 move croaked logic, ensure API key error populates comment 2025-12-11 14:55:07 -05:00