adam/open-swe
1
0
Fork 0
mirror of https://github.com/Sea-Haven-Industries/open-swe.git synced 2026-09-30 17:23:15 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions
767 commits 12 branches 0 tags 41 MiB
Commit graph

18 commits

Author SHA1 Message Date
open-swe[bot]
aaeed1d95f
chore: bump deepagents to 0.6.4 (#1333) 
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
Co-authored-by: Sydney Runkle <54324534+sydney-runkle@users.noreply.github.com>
 2026-05-26 12:16:33 -07:00
open-swe[bot]
0ceca8d0db
chore: bump deepagents to 0.6.3 (#1322) 
Pick up the patch release that restores message ID assignment for incoming messages without explicit IDs after the 0.6.2 regression.

Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
Co-authored-by: Sydney Runkle <54324534+sydney-runkle@users.noreply.github.com>
 2026-05-21 20:23:13 +00:00
Johannes du Plessis
82852f9eda
feat: tune reviewer for precision — web/wiki tools + recalibrated prompt (#1312) 
* feat: tune reviewer for precision — web/wiki tools + recalibrated prompt

Reviewer agent now has web_search, fetch_url, and http_request alongside the
finding tools, so it can verify library semantics and consult the DeepWiki
auto-generated wiki for public repos (https://deepwiki.com/<owner>/<repo>)
before flagging cross-file or architectural concerns.

Prompt rewritten to push precision over recall:
- explicit severity ladder pushing reviews toward bimodal high/low instead of
  defaulting to medium
- ≤200-char description target (gold set averages ~186 chars; we were at ~436)
- mandatory docs / wiki / code lookup before flagging concurrency, security,
  or perf — the three categories that dominated false positives
- "do not flag" list covering compiler/linter-catchable nits, speculative
  claims without a concrete attacker/interleaving/scale, style preferences
  the codebase doesn't share, and test-quality nits on non-test diffs
- smart file-selection guidance for large PRs (deprioritize generated /
  vendored / pure-rename hunks)

Eval config switched to openai:gpt-5.5 + high reasoning effort for the next
benchmark run.

* trim prompt

* subagent prompting

* confidence ratings

* added medium

* enforce confidence threshold

* .

* reviewer: precision-tuned prompt + drop confidence gate

Rewrites the reviewer system prompt around a defensibility bar (anchor +
failure mode + maintainer wouldn't say "not a bug"), an explicit do-not-file
list (style nits, speculation, scope-policing, same-bug fan-out), and a
checklist of 10 bug archetypes drawn from a per-PR audit of the eval golden
set. The audit showed 145 FPs in the last eval split ~28% speculative, ~26%
style-nit, ~31% real-but-unscored (mostly same-archetype fan-out); the new
prompt targets each class directly.

Confidence is still recorded on every finding for post-hoc calibration but
no longer gates publication — the audit showed the gate was a no-op (agent
self-rated 65% of findings "high" regardless), and the prompt's defensibility
bar is the actual discipline. Drops CONFIDENCE_ORDER, CONFIDENCE_THRESHOLD,
the confidence_threshold kwarg on filter_findings_for_publish, the
confidence_filtered score_mode, and the min_confidence kwarg on the eval
target's _extract_comments — all dead once the gate is gone.

Also removes the "informational" severity tier from the Severity enum,
SEVERITY_ORDER, and all validators / tests / docstrings. It was reserved for
FYI observations the dataset never rewards.

* benchmax

* adding google provider

* slight steering

* tuning

* more tuning

* fix

* cleanup

* reducing overfitting

* Add per-repo review style profiles and inject them into the reviewer.

Dashboard users can analyze historical PR review feedback per repository,
edit the resulting style guide, and have it loaded from LangGraph Store at
reviewer runtime (including Martian eval runs) keyed by owner/name.

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

* Fix review style job errors leaking exception details to clients.

Return generic dashboard messages while logging full stack traces server-side.

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

---------

Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
Co-authored-by: Cursor <cursoragent@cursor.com>
 2026-05-20 18:35:00 +00:00
open-swe[bot]
aca40ca397
chore: bump deepagents to 0.6.2 (#1316) 
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
Co-authored-by: Sydney Runkle <54324534+sydney-runkle@users.noreply.github.com>
 2026-05-20 15:33:31 +00:00
open-swe[bot]
c4d9ae4a67
feat: add idle TTL and delete-after-stop sandbox lifecycle controls (#1265) 
* feat: add idle TTL and delete-after-stop sandbox lifecycle controls

* bump langsmith>=0.8.3, lower default idle TTL to 10 min

---------

Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
 2026-05-08 00:30:14 -04:00
open-swe[bot]
d2717ed33c
chore: bump deepagents to 0.5.7 (#1240) 
Co-authored-by: Open SWE <open-swe@langchain.dev>
 2026-05-05 12:02:08 -07:00
Johannes du Plessis
c6ea869df8
chore: bump all dependencies to latest stable versions (#1230) 
Bump floors in pyproject.toml and refresh uv.lock. Notable changes:
- deepagents 0.5.3 -> 0.5.6
- langchain 1.2.15 -> 1.2.17, langchain-core -> 1.3.2
- langchain-anthropic 1.4.0 -> 1.4.2, anthropic -> 0.97.0
- langchain-openai 1.1.13 -> 1.2.1 (unpinned from ==)
- langgraph 1.1.6 -> 1.1.10, langgraph-api -> 0.8.5
- langsmith 0.7.32 -> 0.8.0
- fastapi 0.135.3 -> 0.136.1, starlette -> 1.0.0
- uvicorn 0.44.0 -> 0.46.0, pydantic -> 2.13.3

cryptography stays at <47 due to langgraph-api upper bound.

Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
 2026-05-01 13:43:34 -07:00
dependabot[bot]
213473dc08
chore(deps): bump the minor-and-patch group with 11 updates (#1198) 
Bumps the minor-and-patch group with 11 updates:

| Package | From | To |
| --- | --- | --- |
| [deepagents](https://github.com/langchain-ai/deepagents) | `0.5.0a4` | `0.5.3` |
| [fastapi](https://github.com/fastapi/fastapi) | `0.128.3` | `0.135.3` |
| [uvicorn](https://github.com/Kludex/uvicorn) | `0.40.0` | `0.44.0` |
| [langgraph-sdk](https://github.com/langchain-ai/langgraph) | `0.3.4` | `0.3.13` |
| [langsmith](https://github.com/langchain-ai/langsmith-sdk) | `0.7.31` | `0.7.32` |
| [langchain-openai](https://github.com/langchain-ai/langchain) | `1.1.10` | `1.1.13` |
| [langchain-daytona](https://github.com/langchain-ai/deepagents) | `0.0.3` | `0.0.5` |
| [langchain-modal](https://github.com/langchain-ai/deepagents) | `0.0.2` | `0.0.3` |
| [langchain-runloop](https://github.com/langchain-ai/deepagents) | `0.0.3` | `0.0.4` |
| [exa-py](https://github.com/exa-labs/exa-py) | `2.10.1` | `2.12.0` |
| [ruff](https://github.com/astral-sh/ruff) | `0.15.0` | `0.15.10` |


Updates `deepagents` from 0.5.0a4 to 0.5.3
- [Release notes](https://github.com/langchain-ai/deepagents/releases)
- [Commits](https://github.com/langchain-ai/deepagents/compare/deepagents==0.5.0a4...deepagents==0.5.3)

Updates `fastapi` from 0.128.3 to 0.135.3
- [Release notes](https://github.com/fastapi/fastapi/releases)
- [Commits](https://github.com/fastapi/fastapi/compare/0.128.3...0.135.3)

Updates `uvicorn` from 0.40.0 to 0.44.0
- [Release notes](https://github.com/Kludex/uvicorn/releases)
- [Changelog](https://github.com/Kludex/uvicorn/blob/main/docs/release-notes.md)
- [Commits](https://github.com/Kludex/uvicorn/compare/0.40.0...0.44.0)

Updates `langgraph-sdk` from 0.3.4 to 0.3.13
- [Release notes](https://github.com/langchain-ai/langgraph/releases)
- [Commits](https://github.com/langchain-ai/langgraph/compare/0.3.4...0.3.13)

Updates `langsmith` from 0.7.31 to 0.7.32
- [Release notes](https://github.com/langchain-ai/langsmith-sdk/releases)
- [Commits](https://github.com/langchain-ai/langsmith-sdk/compare/v0.7.31...v0.7.32)

Updates `langchain-openai` from 1.1.10 to 1.1.13
- [Release notes](https://github.com/langchain-ai/langchain/releases)
- [Commits](https://github.com/langchain-ai/langchain/compare/langchain-openai==1.1.10...langchain-openai==1.1.13)

Updates `langchain-daytona` from 0.0.3 to 0.0.5
- [Release notes](https://github.com/langchain-ai/deepagents/releases)
- [Commits](https://github.com/langchain-ai/deepagents/compare/langchain-daytona==0.0.3...langchain-daytona==0.0.5)

Updates `langchain-modal` from 0.0.2 to 0.0.3
- [Release notes](https://github.com/langchain-ai/deepagents/releases)
- [Commits](https://github.com/langchain-ai/deepagents/compare/langchain-modal==0.0.2...langchain-modal==0.0.3)

Updates `langchain-runloop` from 0.0.3 to 0.0.4
- [Release notes](https://github.com/langchain-ai/deepagents/releases)
- [Commits](https://github.com/langchain-ai/deepagents/compare/langchain-runloop==0.0.3...langchain-runloop==0.0.4)

Updates `exa-py` from 2.10.1 to 2.12.0
- [Commits](https://github.com/exa-labs/exa-py/commits)

Updates `ruff` from 0.15.0 to 0.15.10
- [Release notes](https://github.com/astral-sh/ruff/releases)
- [Changelog](https://github.com/astral-sh/ruff/blob/main/CHANGELOG.md)
- [Commits](https://github.com/astral-sh/ruff/compare/0.15.0...0.15.10)

---
updated-dependencies:
- dependency-name: deepagents
  dependency-version: 0.5.3
  dependency-type: direct:production
  update-type: version-update:semver-patch
  dependency-group: minor-and-patch
- dependency-name: fastapi
  dependency-version: 0.135.3
  dependency-type: direct:production
  update-type: version-update:semver-minor
  dependency-group: minor-and-patch
- dependency-name: uvicorn
  dependency-version: 0.44.0
  dependency-type: direct:production
  update-type: version-update:semver-minor
  dependency-group: minor-and-patch
- dependency-name: langgraph-sdk
  dependency-version: 0.3.13
  dependency-type: direct:production
  update-type: version-update:semver-patch
  dependency-group: minor-and-patch
- dependency-name: langsmith
  dependency-version: 0.7.32
  dependency-type: direct:production
  update-type: version-update:semver-patch
  dependency-group: minor-and-patch
- dependency-name: langchain-openai
  dependency-version: 1.1.13
  dependency-type: direct:production
  update-type: version-update:semver-patch
  dependency-group: minor-and-patch
- dependency-name: langchain-daytona
  dependency-version: 0.0.5
  dependency-type: direct:production
  update-type: version-update:semver-patch
  dependency-group: minor-and-patch
- dependency-name: langchain-modal
  dependency-version: 0.0.3
  dependency-type: direct:production
  update-type: version-update:semver-patch
  dependency-group: minor-and-patch
- dependency-name: langchain-runloop
  dependency-version: 0.0.4
  dependency-type: direct:production
  update-type: version-update:semver-patch
  dependency-group: minor-and-patch
- dependency-name: exa-py
  dependency-version: 2.12.0
  dependency-type: direct:production
  update-type: version-update:semver-minor
  dependency-group: minor-and-patch
- dependency-name: ruff
  dependency-version: 0.15.10
  dependency-type: direct:production
  update-type: version-update:semver-patch
  dependency-group: minor-and-patch
...

Signed-off-by: dependabot[bot] <support@github.com>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
 2026-04-16 07:09:02 +00:00
dependabot[bot]
aee6f20627
chore(deps): update langgraph-cli[inmem] requirement (#1199) 
Updates the requirements on [langgraph-cli[inmem]](https://github.com/langchain-ai/langgraph) to permit the latest version.
- [Release notes](https://github.com/langchain-ai/langgraph/releases)
- [Commits](https://github.com/langchain-ai/langgraph/compare/cli==0.4.12...cli==0.4.21)

---
updated-dependencies:
- dependency-name: langgraph-cli[inmem]
  dependency-version: 0.4.21
  dependency-type: direct:production
...

Signed-off-by: dependabot[bot] <support@github.com>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
 2026-04-15 23:46:19 -07:00
dependabot[bot]
32eecbcee2
chore(deps): bump the uv group across 1 directory with 3 updates (#1191) 
Bumps the uv group with 3 updates in the / directory: [langsmith](https://github.com/langchain-ai/langsmith-sdk), [pytest](https://github.com/pytest-dev/pytest) and [python-multipart](https://github.com/Kludex/python-multipart).


Updates `langsmith` from 0.7.25 to 0.7.31
- [Release notes](https://github.com/langchain-ai/langsmith-sdk/releases)
- [Commits](https://github.com/langchain-ai/langsmith-sdk/compare/v0.7.25...v0.7.31)

Updates `pytest` from 9.0.2 to 9.0.3
- [Release notes](https://github.com/pytest-dev/pytest/releases)
- [Changelog](https://github.com/pytest-dev/pytest/blob/main/CHANGELOG.rst)
- [Commits](https://github.com/pytest-dev/pytest/compare/9.0.2...9.0.3)

Updates `python-multipart` from 0.0.22 to 0.0.26
- [Release notes](https://github.com/Kludex/python-multipart/releases)
- [Changelog](https://github.com/Kludex/python-multipart/blob/master/CHANGELOG.md)
- [Commits](https://github.com/Kludex/python-multipart/compare/0.0.22...0.0.26)

---
updated-dependencies:
- dependency-name: langsmith
  dependency-version: 0.7.31
  dependency-type: direct:production
  dependency-group: uv
- dependency-name: pytest
  dependency-version: 9.0.3
  dependency-type: direct:production
  dependency-group: uv
- dependency-name: python-multipart
  dependency-version: 0.0.26
  dependency-type: indirect
  dependency-group: uv
...

Signed-off-by: dependabot[bot] <support@github.com>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
 2026-04-15 23:31:23 -07:00
Aran Yogesh
4d4f5fbfc7
fix: proxy config restored the branch yogesh/GitHub auth proxy (#1173) 
* feat: authenticate git operations via sandbox proxy instead of credential files

* feat: authenticate git operations via sandbox proxy instead of credential files

* feat: authenticate git operations via sandbox proxy instead of credential files

* removing logger.info

* formatting and linting

* fix: resolve lint errors in server.py (imports, unused vars, undefined names)

* feat: use opaque proxy headers for GitHub auth in sandbox

* linting formatting and test changes

* linting

* Delete .claude directory

* Delete tests/evals directory

* fix: address PR review — guard missing tokens, quote shell paths, add proxy auth tests

* fix: restore authorship, branch_name support, and installation token for PR creation

* linitng

* fix: move installation token fetch before commit, clean up dead proxy validation code

* fix: drop github_token arg from sandbox creation, use generic create_sandbox factory with langsmith-only proxy config

* fix: use _get_langsmith_api_key() for prod key fallback, warn when API key missing for proxy config

* linting

* linting

* fix: resolve merge conflicts with main, adopt deepagents v0.5.0a4 LangSmithSandbox
 2026-04-08 15:02:52 -07:00
Aran Yogesh
9aba4d0545
Revert "feat: authenticate git operations via sandbox proxy instead of creden…" (#1170) 
This reverts commit 6305e13dc6.
 2026-04-07 18:45:33 -07:00
Aran Yogesh
6305e13dc6
feat: authenticate git operations via sandbox proxy instead of credential files [closes: OPE-20] (#1070) 
* feat: authenticate git operations via sandbox proxy instead of credential files

* feat: authenticate git operations via sandbox proxy instead of credential files

* feat: authenticate git operations via sandbox proxy instead of credential files

* removing logger.info

* formatting and linting

* fix: resolve lint errors in server.py (imports, unused vars, undefined names)

* feat: use opaque proxy headers for GitHub auth in sandbox

* linting formatting and test changes

* linting

* Delete .claude directory

* Delete tests/evals directory

* fix: address PR review — guard missing tokens, quote shell paths, add proxy auth tests

* fix: restore authorship, branch_name support, and installation token for PR creation

* linitng

* fix: move installation token fetch before commit, clean up dead proxy validation code

* fix: drop github_token arg from sandbox creation, use generic create_sandbox factory with langsmith-only proxy config

* fix: use _get_langsmith_api_key() for prod key fallback, warn when API key missing for proxy config

* linting

* linting

* fix: resolve merge conflicts with main, adopt deepagents v0.5.0a4 LangSmithSandbox
 2026-04-07 16:41:48 -07:00
open-swe[bot]
24a6343352
chore: upgrade deepagents to v0.5.0a4 (#1161) 
Replace custom LangSmithBackend with built-in LangSmithSandbox from
deepagents. Update deprecated protocol method names in docs.

Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
Co-authored-by: Sydney Runkle <54324534+sydney-runkle@users.noreply.github.com>
 2026-04-06 10:24:50 -07:00
John Kennedy
d3506598fe
fix: upgrade deps to patch Pygments ReDoS and PyJWT crit header vulns (#1164) 
- Bump deepagents >=0.4.3 → >=0.4.12
- Bump PyJWT >=2.8.0 → >=2.12.0 (fixes CVE-2026-32597, GHSA-752w-5fwx-jx9f)
- Pin Pygments >=2.20.0 in dev deps (fixes CVE-2026-4539, GHSA-5239-wwwm-4pmq)
- Regenerate uv.lock (also pulls langchain 1.2.15, langgraph 1.1.6)

Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
 2026-04-03 20:42:51 -07:00
Aran Yogesh
7d1004ad66
fix: add Exa web search tool [closes: OPE-29] (#1133) 
* fix: add Exa web search tool

* chore: update uv.lock for exa-py dependency

* linting

* chore: remove web_search from system prompt

* chore: drop search_type and category params from web_search
 2026-03-25 16:24:31 -07:00
Brace Sproul
d7d9bc5179
fix: better custom backend support (#1071) 
* fix: better custom backend support

* cr
 2026-03-17 11:55:36 -07:00
Brace Sproul
bd52e5e09d
chore: Drop monorepo (#1029) 
* chore: Drop monorepo

* cr
 2026-03-06 16:10:34 -08:00
Renamed from apps/agent/pyproject.toml (Browse further)