mirror of
https://github.com/langchain-ai/deepagents.git
synced 2026-07-21 17:25:26 -04:00
nm/dcode-tools-allowlist
2881 Commits
| Author | SHA1 | Message | Date | |
|---|---|---|---|---|
 Mason Daugherty
|
7adece0209 | Merge remote-tracking branch 'origin/main' into nm/dcode-tools-allowlist | ||
|
Mason Daugherty
|
0b071ef71a |
fix(code): avoid tracking inline restart callers (#4894)
After `/reload` or a pending `/mcp reconnect` restarts the owned server, quitting now allows coordinated graceful teardown to finish instead of canceling Textual’s application loop early. --- Restart tracking now distinguishes Textual workers and explicitly detached tasks from inline callers on the long-lived message loop. The deferred web-search restart prompt is also registered at its scheduling site, preserving cancellation and waiting for genuine background restart work before the server stops. <details> <summary>Test plan</summary> - `python -m pytest -q tests/unit_tests/test_app.py::TestExitGracefulWorkerHandoff tests/unit_tests/test_app.py::TestRespawnServer` (49 passed) - Ruff check and format validation for the edited files - `make -C libs/code type` </details> |
||
|
dependabot[bot]
|
4fe8a49c15 |
chore(deps): bump js-yaml from 4.2.0 to 4.3.0 in /libs/talon/deepagents_talon/channels/whatsapp_bridge (#4891)
Bumps [js-yaml](https://github.com/nodeca/js-yaml) from 4.2.0 to 4.3.0. <details> <summary>Changelog</summary> <p><em>Sourced from <a href="https://github.com/nodeca/js-yaml/blob/master/CHANGELOG.md">js-yaml's changelog</a>.</em></p> <blockquote> <h2>4.3.0, 3.15.0 - 2026-06-27</h2> <h3>Security</h3> <ul> <li>Backported <code>maxTotalMergeKeys</code> option.</li> </ul> <h2>[5.2.0] - 2026-06-26</h2> <h3>Added</h3> <ul> <li>Added <code>maxTotalMergeKeys</code> (10000) loader option to limit the total number of keys processed by YAML merge (<code><<</code>) across one <code>load()</code> / <code>loadAll()</code> call.</li> <li>Added <code>maxAliases</code> (-1) loader option to limit the number of YAML aliases per document.</li> </ul> <h3>Removed</h3> <ul> <li><code>maxMergeSeqLength</code> replaced with <code>maxTotalMergeKeys</code> for limiting YAML merge processing.</li> </ul> <h3>Fixed</h3> <ul> <li>Round-trip of integers with exponential form (>= <code>1e21</code>)</li> </ul> <h2>[5.1.0] - 2026-06-23</h2> <h3>Added</h3> <ul> <li>Collection tags can finalize an incrementally populated carrier into a different result value.</li> </ul> <h3>Changed</h3> <ul> <li>[breaking] <code>quoteStyle</code> now selects the preferred quote style; use the restored <code>forceQuotes</code> option to force quoting non-key strings.</li> </ul> <h2>[5.0.0] - 2026-06-20</h2> <h3>Added</h3> <ul> <li>Added named exports for schemas, tags, parser events and AST utilities.</li> <li>Reworked <code>JSON_SCHEMA</code> and <code>CORE_SCHEMA</code> with spec-compliant scalar resolution rules, and added <code>YAML11_SCHEMA</code>.</li> <li>Added <code>realMapTag</code> for lossless mappings with non-string and complex keys. Object-based mappings now reject complex keys instead of stringifying them.</li> <li>Added <code>dump()</code> <code>transform</code> option for changing the generated AST before rendering.</li> <li>Added <code>dump()</code> options <code>seqInlineFirst</code>, <code>flowBracketPadding</code>, <code>flowSkipCommaSpace</code>, <code>flowSkipColonSpace</code>, <code>quoteFlowKeys</code>, <code>quoteStyle</code> and <code>tagBeforeAnchor</code>.</li> <li>Added formal data layers (events and AST) for modular data pipelines. <ul> <li>Added low-level parser (to events), presenter and visitor APIs.</li> </ul> </li> <li>Added the <a href="https://github.com/yaml/yaml-test-suite">YAML Test Suite</a> to the test set.</li> </ul> <h3>Changed</h3> <ul> <li>See the <a href="https://github.com/nodeca/js-yaml/blob/master/docs/migrate_v4_to_v5.md">migration guide</a> for upgrade notes.</li> <li>Rewritten in TypeScript and reorganized the public API around flat named exports.</li> </ul> <!-- raw HTML omitted --> </blockquote> <p>... (truncated)</p> </details> <details> <summary>Commits</summary> <ul> <li><a href="https://github.com/nodeca/js-yaml/commit/33d05b5d29a8c21360f620f7e1c1706e24522eda"><code>33d05b5</code></a> 4.3.0 released</li> <li><a href="https://github.com/nodeca/js-yaml/commit/663bfab6db2b4a146a9366fd685f069345be4ddb"><code>663bfab</code></a> Drop demo publish, to not override new v5 one.</li> <li><a href="https://github.com/nodeca/js-yaml/commit/1cb8c7b94bf75e15116869c1c0482dcb22785986"><code>1cb8c7b</code></a> Add v4-legacy tag for publish</li> <li><a href="https://github.com/nodeca/js-yaml/commit/02f27afad532763263cd2b6be35c24ee8e1f6157"><code>02f27af</code></a> Restore umd builds back to es5</li> <li><a href="https://github.com/nodeca/js-yaml/commit/8be84edaf15e7c394fa3b813179d1bcc280e87fb"><code>8be84ed</code></a> Fix es5 compatibility</li> <li><a href="https://github.com/nodeca/js-yaml/commit/59423c6f8cdc78742ac00e25a4dd39ef16b702e4"><code>59423c6</code></a> Replace <code>maxMergeSeqLength</code> option with <code>maxTotalMergeKeys</code> (more robust). Ba...</li> <li><a href="https://github.com/nodeca/js-yaml/commit/6842ef6a02df01ca7282ea01dc3c70787710c05d"><code>6842ef6</code></a> doc polish</li> <li>See full diff in <a href="https://github.com/nodeca/js-yaml/compare/4.2.0...4.3.0">compare view</a></li> </ul> </details> <br /> [](https://docs.github.com/en/github/managing-security-vulnerabilities/about-dependabot-security-updates#about-compatibility-scores) Dependabot will resolve any conflicts with this PR as long as you don't alter it yourself. You can also trigger a rebase manually by commenting `@dependabot rebase`. [//]: # (dependabot-automerge-start) [//]: # (dependabot-automerge-end) --- <details> <summary>Dependabot commands and options</summary> <br /> You can trigger Dependabot actions by commenting on this PR: - `@dependabot rebase` will rebase this PR - `@dependabot recreate` will recreate this PR, overwriting any edits that have been made to it - `@dependabot show <dependency name> ignore conditions` will show all of the ignore conditions of the specified dependency - `@dependabot ignore this major version` will close this PR and stop Dependabot creating any more for this major version (unless you reopen the PR or upgrade to it yourself) - `@dependabot ignore this minor version` will close this PR and stop Dependabot creating any more for this minor version (unless you reopen the PR or upgrade to it yourself) - `@dependabot ignore this dependency` will close this PR and stop Dependabot creating any more for this dependency (unless you reopen the PR or upgrade to it yourself) You can disable automated security fix PRs for this repo from the [Security Alerts page](https://github.com/langchain-ai/deepagents/network/alerts). </details> Signed-off-by: dependabot[bot] <support@github.com> Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com> |
||
|
Mason Daugherty
|
c9c565970a | Merge branch 'main' into nm/dcode-tools-allowlist | ||
|
Mason Daugherty
|
a2e501b71f |
perf(code): coordinate async shutdown teardown to cut exit latency (#4831)
Interactive shutdown is faster because independent cleanup now overlaps instead of running sequentially, without skipping any cleanup. --- `session.end` hooks run off the Textual event loop. Interrupted-agent cleanup still finishes before server shutdown; afterward, pending hooks drain while the server stops. Server stop and restart paths are synchronized to prevent duplicate or racing teardown. Existing timeouts and cleanup guarantees are unchanged, and debug logs record phase timings. Made by [Open SWE](https://openswe.vercel.app/agents/ce9a3224-140d-08bc-25d2-202982da0203) --------- Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com> |
||
|
Mason Daugherty
|
5c99687bde |
feat(code): replace Gemini 3.5 Flash with 3.6 Flash in model switcher (#4890)
Gemini 3.6 Flash supersedes 3.5 Flash, so surface the newer model in the `/model` selector instead of the older one. Swaps both the `google_genai` and `openrouter` Gemini `3.5 Flash` entries in the `deepagents-code` recommended-model list for `3.6 Flash`, and moves the model-specific default thinking-level keying in `reasoning_effort` over to the new id so the recommended model keeps its `medium` default. Representative unit-test references are updated to match. Made by [Open SWE](https://openswe.vercel.app/agents/0441ce8a-bfb9-b73a-31c9-9754af24aaad) Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com> |
||
|
dependabot[bot]
|
1444ee2de0 |
chore(deps-dev): bump pillow from 12.2.0 to 12.3.0 in /libs/talon (#4875)
Bumps [pillow](https://github.com/python-pillow/Pillow) from 12.2.0 to 12.3.0. <details> <summary>Release notes</summary> <p><em>Sourced from <a href="https://github.com/python-pillow/Pillow/releases">pillow's releases</a>.</em></p> <blockquote> <h2>12.3.0</h2> <p><a href="https://pillow.readthedocs.io/en/stable/releasenotes/12.3.0.html">https://pillow.readthedocs.io/en/stable/releasenotes/12.3.0.html</a></p> <h2>Removals</h2> <ul> <li>Remove non-image ImageCms modes <a href="https://redirect.github.com/python-pillow/Pillow/issues/9697">#9697</a> [<a href="https://github.com/radarhere"><code>@radarhere</code></a>]</li> </ul> <h2>Documentation</h2> <ul> <li>Add release notes for SBOM and performance improvements <a href="https://redirect.github.com/python-pillow/Pillow/issues/9747">#9747</a> [<a href="https://github.com/radarhere"><code>@radarhere</code></a>]</li> <li>Add security release notes <a href="https://redirect.github.com/python-pillow/Pillow/issues/9741">#9741</a> [<a href="https://github.com/radarhere"><code>@radarhere</code></a>]</li> <li>Add release notes for Python 3.15 beta wheels <a href="https://redirect.github.com/python-pillow/Pillow/issues/9696">#9696</a> [<a href="https://github.com/radarhere"><code>@radarhere</code></a>]</li> <li>ImageFont can also be used with ImageText <a href="https://redirect.github.com/python-pillow/Pillow/issues/9597">#9597</a> [<a href="https://github.com/radarhere"><code>@radarhere</code></a>]</li> <li>Additional guidelines for security reports <a href="https://redirect.github.com/python-pillow/Pillow/issues/9659">#9659</a> [<a href="https://github.com/wiredfool"><code>@wiredfool</code></a>]</li> <li>Fixed typo <a href="https://redirect.github.com/python-pillow/Pillow/issues/9636">#9636</a> [<a href="https://github.com/radarhere"><code>@radarhere</code></a>]</li> <li>Added CVEs to 12.2.0 release notes <a href="https://redirect.github.com/python-pillow/Pillow/issues/9591">#9591</a> [<a href="https://github.com/radarhere"><code>@radarhere</code></a>]</li> <li>Revise development support information in README <a href="https://redirect.github.com/python-pillow/Pillow/issues/9583">#9583</a> [<a href="https://github.com/aclark4life"><code>@aclark4life</code></a>]</li> <li>Add INCIDENT_RESPONSE.md <a href="https://redirect.github.com/python-pillow/Pillow/issues/9555">#9555</a> [<a href="https://github.com/aclark4life"><code>@aclark4life</code></a>]</li> <li>Add STRIDE threat model to security docs <a href="https://redirect.github.com/python-pillow/Pillow/issues/9562">#9562</a> [<a href="https://github.com/aclark4life"><code>@aclark4life</code></a>]</li> <li>Add CVEs to 12.2.0 release notes <a href="https://redirect.github.com/python-pillow/Pillow/issues/9556">#9556</a> [<a href="https://github.com/radarhere"><code>@radarhere</code></a>]</li> <li>Update README with revised security policy <a href="https://redirect.github.com/python-pillow/Pillow/issues/9553">#9553</a> [<a href="https://github.com/radarhere"><code>@radarhere</code></a>]</li> <li>Update security policy <a href="https://redirect.github.com/python-pillow/Pillow/issues/9552">#9552</a> [<a href="https://github.com/aclark4life"><code>@aclark4life</code></a>]</li> <li>Update macOS tested Python versions <a href="https://redirect.github.com/python-pillow/Pillow/issues/9534">#9534</a> [<a href="https://github.com/radarhere"><code>@radarhere</code></a>]</li> </ul> <h2>Dependencies</h2> <ul> <li>Update dependency harfbuzz to v14.2.1 <a href="https://redirect.github.com/python-pillow/Pillow/issues/9720">#9720</a> [@<a href="https://github.com/apps/renovate">renovate[bot]</a>]</li> <li>Update dependency mypy to v2 <a href="https://redirect.github.com/python-pillow/Pillow/issues/9653">#9653</a> [@<a href="https://github.com/apps/renovate">renovate[bot]</a>]</li> <li>Update dependency cibuildwheel to v4 <a href="https://redirect.github.com/python-pillow/Pillow/issues/9665">#9665</a> [@<a href="https://github.com/apps/renovate">renovate[bot]</a>]</li> <li>Update github-actions <a href="https://redirect.github.com/python-pillow/Pillow/issues/9655">#9655</a> [@<a href="https://github.com/apps/renovate">renovate[bot]</a>]</li> <li>Update dependency libavif to v1.4.2 <a href="https://redirect.github.com/python-pillow/Pillow/issues/9652">#9652</a> [@<a href="https://github.com/apps/renovate">renovate[bot]</a>]</li> <li>Update dependency lcms2 to v2.19.1 <a href="https://redirect.github.com/python-pillow/Pillow/issues/9651">#9651</a> [@<a href="https://github.com/apps/renovate">renovate[bot]</a>]</li> <li>Update dependency check-jsonschema to v0.37.2 <a href="https://redirect.github.com/python-pillow/Pillow/issues/9650">#9650</a> [@<a href="https://github.com/apps/renovate">renovate[bot]</a>]</li> <li>Update google/oss-fuzz digest to d872252 <a href="https://redirect.github.com/python-pillow/Pillow/issues/9614">#9614</a> [@<a href="https://github.com/apps/renovate">renovate[bot]</a>]</li> <li>Update dependency lcms2 to v2.19 <a href="https://redirect.github.com/python-pillow/Pillow/issues/9609">#9609</a> [@<a href="https://github.com/apps/renovate">renovate[bot]</a>]</li> <li>Update dependency libpng to v1.6.58 - autoclosed <a href="https://redirect.github.com/python-pillow/Pillow/issues/9608">#9608</a> [@<a href="https://github.com/apps/renovate">renovate[bot]</a>]</li> <li>Update dependency harfbuzz to v14 <a href="https://redirect.github.com/python-pillow/Pillow/issues/9610">#9610</a> [@<a href="https://github.com/apps/renovate">renovate[bot]</a>]</li> <li>Update dependency mypy to v1.20.2 <a href="https://redirect.github.com/python-pillow/Pillow/issues/9599">#9599</a> [@<a href="https://github.com/apps/renovate">renovate[bot]</a>]</li> <li>Update github-actions <a href="https://redirect.github.com/python-pillow/Pillow/issues/9611">#9611</a> [@<a href="https://github.com/apps/renovate">renovate[bot]</a>]</li> <li>Update dependency cibuildwheel to v3.4.1 <a href="https://redirect.github.com/python-pillow/Pillow/issues/9607">#9607</a> [@<a href="https://github.com/apps/renovate">renovate[bot]</a>]</li> <li>Move dependency versions to single JSON and enable Renovate <a href="https://redirect.github.com/python-pillow/Pillow/issues/9559">#9559</a> [<a href="https://github.com/hugovk"><code>@hugovk</code></a>]</li> <li>Updated raqm to 0.10.5 <a href="https://redirect.github.com/python-pillow/Pillow/issues/9557">#9557</a> [<a href="https://github.com/radarhere"><code>@radarhere</code></a>]</li> <li>Update dependency cibuildwheel to v3.4.0 <a href="https://redirect.github.com/python-pillow/Pillow/issues/9532">#9532</a> [@<a href="https://github.com/apps/renovate">renovate[bot]</a>]</li> </ul> <h2>Testing</h2> <ul> <li>Remove matrix.os from benchmark <a href="https://redirect.github.com/python-pillow/Pillow/issues/9735">#9735</a> [<a href="https://github.com/radarhere"><code>@radarhere</code></a>]</li> <li>Remove references to libavif patch <a href="https://redirect.github.com/python-pillow/Pillow/issues/9734">#9734</a> [<a href="https://github.com/radarhere"><code>@radarhere</code></a>]</li> <li>Add benchmark tests <a href="https://redirect.github.com/python-pillow/Pillow/issues/9654">#9654</a> [<a href="https://github.com/akx"><code>@akx</code></a>]</li> <li>Use reshape() instead of setting NumPy array shape directly <a href="https://redirect.github.com/python-pillow/Pillow/issues/9728">#9728</a> [<a href="https://github.com/radarhere"><code>@radarhere</code></a>]</li> </ul> <!-- raw HTML omitted --> </blockquote> <p>... (truncated)</p> </details> <details> <summary>Commits</summary> <ul> <li><a href="https://github.com/python-pillow/Pillow/commit/bb1d8e8ab8d29048624d96e3ee53cecf7c13d13d"><code>bb1d8e8</code></a> 12.3.0 version bump</li> <li><a href="https://github.com/python-pillow/Pillow/commit/e63fc481dc2e07e21d5403deafb8f1ed98a513af"><code>e63fc48</code></a> Add release notes for SBOM and performance improvements (<a href="https://redirect.github.com/python-pillow/Pillow/issues/9747">#9747</a>)</li> <li><a href="https://github.com/python-pillow/Pillow/commit/13b701bbab291eec4bc87ea17ba06c94e5fe3054"><code>13b701b</code></a> Add release notes for <a href="https://redirect.github.com/python-pillow/Pillow/issues/9679">#9679</a></li> <li><a href="https://github.com/python-pillow/Pillow/commit/5564ca72fcd59d040e270af5dcf17a0d7161c364"><code>5564ca7</code></a> List methods</li> <li><a href="https://github.com/python-pillow/Pillow/commit/a0920fd384f800b5d0ba3dd29ecdeae4f1d4043b"><code>a0920fd</code></a> Speed up ImageChops operations (<a href="https://redirect.github.com/python-pillow/Pillow/issues/9738">#9738</a>)</li> <li><a href="https://github.com/python-pillow/Pillow/commit/07e9a6cd5336dc6cf8cae9165cd70cdd2b3e42fc"><code>07e9a6c</code></a> Speed up <code>Image.filter()</code> (<a href="https://redirect.github.com/python-pillow/Pillow/issues/9736">#9736</a>)</li> <li><a href="https://github.com/python-pillow/Pillow/commit/a94578cf9649ea13e426cf7fb2b71b39ffc0dd50"><code>a94578c</code></a> Speed up <code>Image.getchannel()</code>, <code>Image.merge()</code>, <code>Image.putalpha()</code> and `Image...</li> <li><a href="https://github.com/python-pillow/Pillow/commit/53e02c43c919d149b2a154a5180079f9df18fbbb"><code>53e02c4</code></a> Speed up <code>Image.fill()</code>, <code>Image.linear_gradient()</code> and `Image.radial_gradient...</li> <li><a href="https://github.com/python-pillow/Pillow/commit/af037475be8634ba739744243164ba9e2c8346a6"><code>af03747</code></a> Speed up <code>Image.resample()</code> (<a href="https://redirect.github.com/python-pillow/Pillow/issues/9739">#9739</a>)</li> <li><a href="https://github.com/python-pillow/Pillow/commit/5c9ca56c3e5fba52b647809fbb0986c87e73a571"><code>5c9ca56</code></a> Speed up <code>alpha_composite</code>, <code>matrix</code>, <code>negative</code>, <code>quantize</code> (<a href="https://redirect.github.com/python-pillow/Pillow/issues/9740">#9740</a>)</li> <li>Additional commits viewable in <a href="https://github.com/python-pillow/Pillow/compare/12.2.0...12.3.0">compare view</a></li> </ul> </details> <br /> Signed-off-by: dependabot[bot] <support@github.com> Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com> |
||
|
dependabot[bot]
|
7a11fb8a17 |
chore(deps): bump pillow from 12.2.0 to 12.3.0 in /examples/content-builder-agent (#4879)
Bumps [pillow](https://github.com/python-pillow/Pillow) from 12.2.0 to 12.3.0. <details> <summary>Release notes</summary> <p><em>Sourced from <a href="https://github.com/python-pillow/Pillow/releases">pillow's releases</a>.</em></p> <blockquote> <h2>12.3.0</h2> <p><a href="https://pillow.readthedocs.io/en/stable/releasenotes/12.3.0.html">https://pillow.readthedocs.io/en/stable/releasenotes/12.3.0.html</a></p> <h2>Removals</h2> <ul> <li>Remove non-image ImageCms modes <a href="https://redirect.github.com/python-pillow/Pillow/issues/9697">#9697</a> [<a href="https://github.com/radarhere"><code>@radarhere</code></a>]</li> </ul> <h2>Documentation</h2> <ul> <li>Add release notes for SBOM and performance improvements <a href="https://redirect.github.com/python-pillow/Pillow/issues/9747">#9747</a> [<a href="https://github.com/radarhere"><code>@radarhere</code></a>]</li> <li>Add security release notes <a href="https://redirect.github.com/python-pillow/Pillow/issues/9741">#9741</a> [<a href="https://github.com/radarhere"><code>@radarhere</code></a>]</li> <li>Add release notes for Python 3.15 beta wheels <a href="https://redirect.github.com/python-pillow/Pillow/issues/9696">#9696</a> [<a href="https://github.com/radarhere"><code>@radarhere</code></a>]</li> <li>ImageFont can also be used with ImageText <a href="https://redirect.github.com/python-pillow/Pillow/issues/9597">#9597</a> [<a href="https://github.com/radarhere"><code>@radarhere</code></a>]</li> <li>Additional guidelines for security reports <a href="https://redirect.github.com/python-pillow/Pillow/issues/9659">#9659</a> [<a href="https://github.com/wiredfool"><code>@wiredfool</code></a>]</li> <li>Fixed typo <a href="https://redirect.github.com/python-pillow/Pillow/issues/9636">#9636</a> [<a href="https://github.com/radarhere"><code>@radarhere</code></a>]</li> <li>Added CVEs to 12.2.0 release notes <a href="https://redirect.github.com/python-pillow/Pillow/issues/9591">#9591</a> [<a href="https://github.com/radarhere"><code>@radarhere</code></a>]</li> <li>Revise development support information in README <a href="https://redirect.github.com/python-pillow/Pillow/issues/9583">#9583</a> [<a href="https://github.com/aclark4life"><code>@aclark4life</code></a>]</li> <li>Add INCIDENT_RESPONSE.md <a href="https://redirect.github.com/python-pillow/Pillow/issues/9555">#9555</a> [<a href="https://github.com/aclark4life"><code>@aclark4life</code></a>]</li> <li>Add STRIDE threat model to security docs <a href="https://redirect.github.com/python-pillow/Pillow/issues/9562">#9562</a> [<a href="https://github.com/aclark4life"><code>@aclark4life</code></a>]</li> <li>Add CVEs to 12.2.0 release notes <a href="https://redirect.github.com/python-pillow/Pillow/issues/9556">#9556</a> [<a href="https://github.com/radarhere"><code>@radarhere</code></a>]</li> <li>Update README with revised security policy <a href="https://redirect.github.com/python-pillow/Pillow/issues/9553">#9553</a> [<a href="https://github.com/radarhere"><code>@radarhere</code></a>]</li> <li>Update security policy <a href="https://redirect.github.com/python-pillow/Pillow/issues/9552">#9552</a> [<a href="https://github.com/aclark4life"><code>@aclark4life</code></a>]</li> <li>Update macOS tested Python versions <a href="https://redirect.github.com/python-pillow/Pillow/issues/9534">#9534</a> [<a href="https://github.com/radarhere"><code>@radarhere</code></a>]</li> </ul> <h2>Dependencies</h2> <ul> <li>Update dependency harfbuzz to v14.2.1 <a href="https://redirect.github.com/python-pillow/Pillow/issues/9720">#9720</a> [@<a href="https://github.com/apps/renovate">renovate[bot]</a>]</li> <li>Update dependency mypy to v2 <a href="https://redirect.github.com/python-pillow/Pillow/issues/9653">#9653</a> [@<a href="https://github.com/apps/renovate">renovate[bot]</a>]</li> <li>Update dependency cibuildwheel to v4 <a href="https://redirect.github.com/python-pillow/Pillow/issues/9665">#9665</a> [@<a href="https://github.com/apps/renovate">renovate[bot]</a>]</li> <li>Update github-actions <a href="https://redirect.github.com/python-pillow/Pillow/issues/9655">#9655</a> [@<a href="https://github.com/apps/renovate">renovate[bot]</a>]</li> <li>Update dependency libavif to v1.4.2 <a href="https://redirect.github.com/python-pillow/Pillow/issues/9652">#9652</a> [@<a href="https://github.com/apps/renovate">renovate[bot]</a>]</li> <li>Update dependency lcms2 to v2.19.1 <a href="https://redirect.github.com/python-pillow/Pillow/issues/9651">#9651</a> [@<a href="https://github.com/apps/renovate">renovate[bot]</a>]</li> <li>Update dependency check-jsonschema to v0.37.2 <a href="https://redirect.github.com/python-pillow/Pillow/issues/9650">#9650</a> [@<a href="https://github.com/apps/renovate">renovate[bot]</a>]</li> <li>Update google/oss-fuzz digest to d872252 <a href="https://redirect.github.com/python-pillow/Pillow/issues/9614">#9614</a> [@<a href="https://github.com/apps/renovate">renovate[bot]</a>]</li> <li>Update dependency lcms2 to v2.19 <a href="https://redirect.github.com/python-pillow/Pillow/issues/9609">#9609</a> [@<a href="https://github.com/apps/renovate">renovate[bot]</a>]</li> <li>Update dependency libpng to v1.6.58 - autoclosed <a href="https://redirect.github.com/python-pillow/Pillow/issues/9608">#9608</a> [@<a href="https://github.com/apps/renovate">renovate[bot]</a>]</li> <li>Update dependency harfbuzz to v14 <a href="https://redirect.github.com/python-pillow/Pillow/issues/9610">#9610</a> [@<a href="https://github.com/apps/renovate">renovate[bot]</a>]</li> <li>Update dependency mypy to v1.20.2 <a href="https://redirect.github.com/python-pillow/Pillow/issues/9599">#9599</a> [@<a href="https://github.com/apps/renovate">renovate[bot]</a>]</li> <li>Update github-actions <a href="https://redirect.github.com/python-pillow/Pillow/issues/9611">#9611</a> [@<a href="https://github.com/apps/renovate">renovate[bot]</a>]</li> <li>Update dependency cibuildwheel to v3.4.1 <a href="https://redirect.github.com/python-pillow/Pillow/issues/9607">#9607</a> [@<a href="https://github.com/apps/renovate">renovate[bot]</a>]</li> <li>Move dependency versions to single JSON and enable Renovate <a href="https://redirect.github.com/python-pillow/Pillow/issues/9559">#9559</a> [<a href="https://github.com/hugovk"><code>@hugovk</code></a>]</li> <li>Updated raqm to 0.10.5 <a href="https://redirect.github.com/python-pillow/Pillow/issues/9557">#9557</a> [<a href="https://github.com/radarhere"><code>@radarhere</code></a>]</li> <li>Update dependency cibuildwheel to v3.4.0 <a href="https://redirect.github.com/python-pillow/Pillow/issues/9532">#9532</a> [@<a href="https://github.com/apps/renovate">renovate[bot]</a>]</li> </ul> <h2>Testing</h2> <ul> <li>Remove matrix.os from benchmark <a href="https://redirect.github.com/python-pillow/Pillow/issues/9735">#9735</a> [<a href="https://github.com/radarhere"><code>@radarhere</code></a>]</li> <li>Remove references to libavif patch <a href="https://redirect.github.com/python-pillow/Pillow/issues/9734">#9734</a> [<a href="https://github.com/radarhere"><code>@radarhere</code></a>]</li> <li>Add benchmark tests <a href="https://redirect.github.com/python-pillow/Pillow/issues/9654">#9654</a> [<a href="https://github.com/akx"><code>@akx</code></a>]</li> <li>Use reshape() instead of setting NumPy array shape directly <a href="https://redirect.github.com/python-pillow/Pillow/issues/9728">#9728</a> [<a href="https://github.com/radarhere"><code>@radarhere</code></a>]</li> </ul> <!-- raw HTML omitted --> </blockquote> <p>... (truncated)</p> </details> <details> <summary>Commits</summary> <ul> <li><a href="https://github.com/python-pillow/Pillow/commit/bb1d8e8ab8d29048624d96e3ee53cecf7c13d13d"><code>bb1d8e8</code></a> 12.3.0 version bump</li> <li><a href="https://github.com/python-pillow/Pillow/commit/e63fc481dc2e07e21d5403deafb8f1ed98a513af"><code>e63fc48</code></a> Add release notes for SBOM and performance improvements (<a href="https://redirect.github.com/python-pillow/Pillow/issues/9747">#9747</a>)</li> <li><a href="https://github.com/python-pillow/Pillow/commit/13b701bbab291eec4bc87ea17ba06c94e5fe3054"><code>13b701b</code></a> Add release notes for <a href="https://redirect.github.com/python-pillow/Pillow/issues/9679">#9679</a></li> <li><a href="https://github.com/python-pillow/Pillow/commit/5564ca72fcd59d040e270af5dcf17a0d7161c364"><code>5564ca7</code></a> List methods</li> <li><a href="https://github.com/python-pillow/Pillow/commit/a0920fd384f800b5d0ba3dd29ecdeae4f1d4043b"><code>a0920fd</code></a> Speed up ImageChops operations (<a href="https://redirect.github.com/python-pillow/Pillow/issues/9738">#9738</a>)</li> <li><a href="https://github.com/python-pillow/Pillow/commit/07e9a6cd5336dc6cf8cae9165cd70cdd2b3e42fc"><code>07e9a6c</code></a> Speed up <code>Image.filter()</code> (<a href="https://redirect.github.com/python-pillow/Pillow/issues/9736">#9736</a>)</li> <li><a href="https://github.com/python-pillow/Pillow/commit/a94578cf9649ea13e426cf7fb2b71b39ffc0dd50"><code>a94578c</code></a> Speed up <code>Image.getchannel()</code>, <code>Image.merge()</code>, <code>Image.putalpha()</code> and `Image...</li> <li><a href="https://github.com/python-pillow/Pillow/commit/53e02c43c919d149b2a154a5180079f9df18fbbb"><code>53e02c4</code></a> Speed up <code>Image.fill()</code>, <code>Image.linear_gradient()</code> and `Image.radial_gradient...</li> <li><a href="https://github.com/python-pillow/Pillow/commit/af037475be8634ba739744243164ba9e2c8346a6"><code>af03747</code></a> Speed up <code>Image.resample()</code> (<a href="https://redirect.github.com/python-pillow/Pillow/issues/9739">#9739</a>)</li> <li><a href="https://github.com/python-pillow/Pillow/commit/5c9ca56c3e5fba52b647809fbb0986c87e73a571"><code>5c9ca56</code></a> Speed up <code>alpha_composite</code>, <code>matrix</code>, <code>negative</code>, <code>quantize</code> (<a href="https://redirect.github.com/python-pillow/Pillow/issues/9740">#9740</a>)</li> <li>Additional commits viewable in <a href="https://github.com/python-pillow/Pillow/compare/12.2.0...12.3.0">compare view</a></li> </ul> </details> <br /> Signed-off-by: dependabot[bot] <support@github.com> Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com> |
||
|
corridor-security[bot]
|
eea0a84d96 |
fix(code): honor MCP server disables for plugins (#4848)
Deep Agents Code now respects explicit MCP server disables for servers bundled with installed plugins. --- Installing or enabling a plugin is the user's trust decision for all of its bundled components, including MCP servers. First-time plugin servers therefore continue to load without requiring a separate project approval. Plugin-provided MCP servers now pass through the user-level deny policy before loading. An explicitly disabled server remains disabled even when it is supplied by an installed plugin. If the MCP trust policy cannot be read, plugin servers fail closed rather than risking bypassing a saved disable. Invalid plugin MCP configuration shapes are surfaced as configuration errors. --------- Co-authored-by: corridor-security[bot] <203152403+corridor-security[bot]@users.noreply.github.com> Co-authored-by: langsmith-fleet[bot] <langsmith-fleet[bot]@users.noreply.github.com> Co-authored-by: Mason Daugherty <github@mdrxy.com> Co-authored-by: Mason Daugherty <mason@langchain.dev> |
||
|
Mason Daugherty
|
b513bf3b2a |
fix(code): preserve remembered MCP approvals with env allowlist (#4889)
Users who configure a process-wide MCP allowlist and also choose “Allow for this project — until changed” are now prompted only once (fixes an issue where this was previously discarded). --- A user can intentionally have two kinds of MCP approval at the same time: - Process-wide server names in `DEEPAGENTS_CODE_DANGEROUSLY_ENABLE_PROJECT_MCP_SERVERS`, which bypass project and server-definition binding. - Project-scoped approvals saved by the startup prompt, which match only the same project root, server name, and server-definition fingerprint. ### Before 1. The user starts `dcode` in a project whose MCP servers are not in the process-wide allowlist. 2. They choose “Allow for this project — until changed.” 3. `dcode` writes valid scoped approvals and reports: Allowing 2 project MCP servers for this session; remembering 2 for this project. 4. On the next launch, the presence of the process-wide env var causes the loader to ignore every saved scoped approval, even when the env var contains unrelated names. 5. The same “Approve project MCP servers” prompt appears again. ### After - Process-wide names and scoped remembered approvals are independent grants, so both remain active. - The next launch recognizes the saved project/server fingerprints and does not prompt again. - An explicitly empty process-wide allowlist contributes no global names but does not clear remembered project approvals. - A changed server command or URL still requires re-approval, and disabled server names still take precedence over every approval source. Regression coverage reproduces the repeated-launch case and verifies both populated and empty process-wide allowlists. |
||
|
Mason Daugherty
|
46bb1a86c8 |
fix(code): abort project MCP approval on Esc (#4888)
Pressing Esc in the project MCP approval prompt now aborts startup and returns to the terminal instead of treating Esc as **Deny** and continuing into the TUI. --- Esc now produces the same launch-cancellation outcome in both project MCP selectors. The explicit **Deny** option remains available and selected by default, so declining trust still requires choosing it and pressing Enter. |
||
|
Mason Daugherty
|
ccaab2c6b2 | feat(code): support a configurable tools allowlist | ||
|
Mason Daugherty
|
2d729b30c5 |
feat(code): add built-in thread inspector skill (#4769)
Deep Agents Code now includes a built-in `deepagents-thread-inspector` skill for inspecting and summarizing local conversation threads. |
||
|
Mason Daugherty
|
4330534d18 |
fix(code): allow safe OS-temp scratch artifacts (#4869)
Related #4860 Auto mode can now use a uniquely allocated OS temporary text file when a command requires file-based input, then remove that exact artifact without asking separately. Predictable or pre-existing temp paths and all other outside-worktree writes remain denied. --- dcode owns the scratch lifecycle: the model supplies content and an optional suffix, while dcode chooses and exclusively creates the path. A successful allocation records private provenance scoped to the current thread and user turn. Only the exact same file identity can be removed; failed calls, prior proposals, other turns, parent directories, and generic file tools receive no authority. The classifier may use this provenance only to establish what the artifact is. Literal user text remains the sole source of consent for the action that consumes it or any destination it affects. <details> <summary>Test plan</summary> - `python -m pytest -q tests/unit_tests/test_auto_mode.py` - `make -C libs/code lint` - `make -C libs/code type` </details> |
||
|
Mason Daugherty
|
67bcb564ff |
refactor(code): share newline affordances across input surfaces (#4852)
Fixes the newline-entry inconsistencies across dcode's text-entry surfaces, and refactors so any future surface inherits the affordances. Three gaps came out of a comparison with Codex and opencode: - The goal-criteria editor advertised a hardcoded "Shift+Enter newline" in its footer. On terminals that cannot report Shift+Enter (e.g. macOS Terminal.app) that chord submits, so the hint pointed at the wrong key. - The VSCode `backslash+enter`→newline fallback (for terminals that emulate Shift+Enter that way) lived only in the chat input, so Shift+Enter submitted with a stray backslash in the goal editor and the `ask_user` free-text prompt. - The `ask_user` free-text prompt never told users how to insert a newline at all. Rather than patch each surface, the shared newline affordances now live in the common `PasteBurstTextArea` base: the modifier-Enter / Ctrl+J bindings, the derived newline-key set, and the backslash+enter fallback (via small `_consume_backslash_enter_newline` / `_track_backslash_pending` / `_consume_modifier_newline` helpers). Both the chat input and the inline prompts inherit them, and any future `TextArea`-based input surface that extends the base gets them for free. A shared `newline_hint()` helper renders the terminal-aware shortcut (`Ctrl+J` / `Option+Enter` / `Shift+Enter`) consistently, now used by both the goal editor and the `ask_user` footer. The chat input's existing behavior — including the completion-active gating on the backslash path and key ordering — is preserved. Made by [Open SWE](https://openswe.vercel.app/agents/a7bdfa65-aba1-0246-373d-5a12d84a9860) --------- Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com> |
||
|
Mason Daugherty
|
9a5bbeb755 |
fix(code): harden installer downloads and paths (#4871)
The install script now respects the configured uv tool binary directory, retries transient downloads, and avoids unsafe fallback files and broad ownership changes. Existing installations that are current but shadowed on `PATH` are reinstalled into the uv tool directory instead of being incorrectly treated as up to date. --- The installer previously assumed uv placed executables in `~/.local/bin`, so custom uv configuration could make version detection, verification, `PATH` setup, and ownership repair target the wrong files. A single transient PyPI or uv bootstrap failure also immediately fell back or failed, and predictable `/tmp` fallbacks were used when `mktemp` was unavailable. This resolves the tool bin through `uv tool dir --bin` with legacy fallbacks, compares executable paths by inode, preserves existing regular files when adding links, retries downloads three times, and fails closed for required temporary files. Root and MDM installs avoid running pre-existing user executables and narrow ownership changes to paths created by the installer. Regression tests cover custom and legacy uv bin locations, shadowed installs, root execution, retries, and secure temporary-file failures. |
||
|
Mason Daugherty
|
69e33acb0e | Merge branch 'main' into nm/dcode-tools-allowlist | ||
|
Mason Daugherty
|
a4854042e5 |
feat(code): gate debug console click-to-copy behind a checkbox (#4810)
The `Ctrl+\` debug console now only copies a log line or snapshot value on click when a new "Click to copy" checkbox is checked, and that choice is remembered across restarts. The checkbox defaults to off, so clicks no longer clobber the clipboard while scrolling or selecting text. Keyboard Enter-to-copy for the selected log line stays always on. --- Previously every click in the console (a log line, or a copyable snapshot value such as the thread ID) copied to the clipboard, which was easy to trigger accidentally. This puts that behavior behind an opt-in toolbar checkbox while preserving the primary keyboard copy path. Snapshot `(langsmith)` links still open on click regardless of the toggle, and the checkbox is reachable via the existing Tab focus cycle. The preference is persisted to `[ui].debug_console_click_to_copy` in `~/.deepagents/config.toml` (mirroring the `[ui].show_scrollbar` pattern), with a `DEEPAGENTS_CODE_DEBUG_CONSOLE_CLICK_TO_COPY` env override and a matching config-manifest entry so `dcode config` can introspect it. The config write runs off the UI thread and degrades to a toast on failure. Made by [Open SWE](https://openswe.vercel.app/agents/349c457d-f7ec-252c-cdc3-54fa375ad517) --------- Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com> |
||
|
Mason Daugherty
|
7a9b27242c |
style(code): dim the /plugins modal backdrop (#4851)
The `/plugins` modal now dims the background behind it, consistent with other modals. --- The `/plugins` (`PluginManagerScreen`) modal overrode Textual's default `ModalScreen` backdrop with `background: transparent`, making it fully see-through instead of dimming the content behind it like every other modal. Removing the override lets it inherit the standard `background: $background 60%` dim backdrop (which still degrades to transparent under ansi themes). Made by [Open SWE](https://openswe.vercel.app/agents/8d011f9e-b11e-7cc1-e8a6-6138c7381983) --------- Signed-off-by: Mason Daugherty <github@mdrxy.com> Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com> |
||
|
dependabot[bot]
|
b708207243 |
chore(deps-dev): bump pillow from 12.2.0 to 12.3.0 in /libs/evals (#4876)
Bumps [pillow](https://github.com/python-pillow/Pillow) from 12.2.0 to 12.3.0. <details> <summary>Release notes</summary> <p><em>Sourced from <a href="https://github.com/python-pillow/Pillow/releases">pillow's releases</a>.</em></p> <blockquote> <h2>12.3.0</h2> <p><a href="https://pillow.readthedocs.io/en/stable/releasenotes/12.3.0.html">https://pillow.readthedocs.io/en/stable/releasenotes/12.3.0.html</a></p> <h2>Removals</h2> <ul> <li>Remove non-image ImageCms modes <a href="https://redirect.github.com/python-pillow/Pillow/issues/9697">#9697</a> [<a href="https://github.com/radarhere"><code>@radarhere</code></a>]</li> </ul> <h2>Documentation</h2> <ul> <li>Add release notes for SBOM and performance improvements <a href="https://redirect.github.com/python-pillow/Pillow/issues/9747">#9747</a> [<a href="https://github.com/radarhere"><code>@radarhere</code></a>]</li> <li>Add security release notes <a href="https://redirect.github.com/python-pillow/Pillow/issues/9741">#9741</a> [<a href="https://github.com/radarhere"><code>@radarhere</code></a>]</li> <li>Add release notes for Python 3.15 beta wheels <a href="https://redirect.github.com/python-pillow/Pillow/issues/9696">#9696</a> [<a href="https://github.com/radarhere"><code>@radarhere</code></a>]</li> <li>ImageFont can also be used with ImageText <a href="https://redirect.github.com/python-pillow/Pillow/issues/9597">#9597</a> [<a href="https://github.com/radarhere"><code>@radarhere</code></a>]</li> <li>Additional guidelines for security reports <a href="https://redirect.github.com/python-pillow/Pillow/issues/9659">#9659</a> [<a href="https://github.com/wiredfool"><code>@wiredfool</code></a>]</li> <li>Fixed typo <a href="https://redirect.github.com/python-pillow/Pillow/issues/9636">#9636</a> [<a href="https://github.com/radarhere"><code>@radarhere</code></a>]</li> <li>Added CVEs to 12.2.0 release notes <a href="https://redirect.github.com/python-pillow/Pillow/issues/9591">#9591</a> [<a href="https://github.com/radarhere"><code>@radarhere</code></a>]</li> <li>Revise development support information in README <a href="https://redirect.github.com/python-pillow/Pillow/issues/9583">#9583</a> [<a href="https://github.com/aclark4life"><code>@aclark4life</code></a>]</li> <li>Add INCIDENT_RESPONSE.md <a href="https://redirect.github.com/python-pillow/Pillow/issues/9555">#9555</a> [<a href="https://github.com/aclark4life"><code>@aclark4life</code></a>]</li> <li>Add STRIDE threat model to security docs <a href="https://redirect.github.com/python-pillow/Pillow/issues/9562">#9562</a> [<a href="https://github.com/aclark4life"><code>@aclark4life</code></a>]</li> <li>Add CVEs to 12.2.0 release notes <a href="https://redirect.github.com/python-pillow/Pillow/issues/9556">#9556</a> [<a href="https://github.com/radarhere"><code>@radarhere</code></a>]</li> <li>Update README with revised security policy <a href="https://redirect.github.com/python-pillow/Pillow/issues/9553">#9553</a> [<a href="https://github.com/radarhere"><code>@radarhere</code></a>]</li> <li>Update security policy <a href="https://redirect.github.com/python-pillow/Pillow/issues/9552">#9552</a> [<a href="https://github.com/aclark4life"><code>@aclark4life</code></a>]</li> <li>Update macOS tested Python versions <a href="https://redirect.github.com/python-pillow/Pillow/issues/9534">#9534</a> [<a href="https://github.com/radarhere"><code>@radarhere</code></a>]</li> </ul> <h2>Dependencies</h2> <ul> <li>Update dependency harfbuzz to v14.2.1 <a href="https://redirect.github.com/python-pillow/Pillow/issues/9720">#9720</a> [@<a href="https://github.com/apps/renovate">renovate[bot]</a>]</li> <li>Update dependency mypy to v2 <a href="https://redirect.github.com/python-pillow/Pillow/issues/9653">#9653</a> [@<a href="https://github.com/apps/renovate">renovate[bot]</a>]</li> <li>Update dependency cibuildwheel to v4 <a href="https://redirect.github.com/python-pillow/Pillow/issues/9665">#9665</a> [@<a href="https://github.com/apps/renovate">renovate[bot]</a>]</li> <li>Update github-actions <a href="https://redirect.github.com/python-pillow/Pillow/issues/9655">#9655</a> [@<a href="https://github.com/apps/renovate">renovate[bot]</a>]</li> <li>Update dependency libavif to v1.4.2 <a href="https://redirect.github.com/python-pillow/Pillow/issues/9652">#9652</a> [@<a href="https://github.com/apps/renovate">renovate[bot]</a>]</li> <li>Update dependency lcms2 to v2.19.1 <a href="https://redirect.github.com/python-pillow/Pillow/issues/9651">#9651</a> [@<a href="https://github.com/apps/renovate">renovate[bot]</a>]</li> <li>Update dependency check-jsonschema to v0.37.2 <a href="https://redirect.github.com/python-pillow/Pillow/issues/9650">#9650</a> [@<a href="https://github.com/apps/renovate">renovate[bot]</a>]</li> <li>Update google/oss-fuzz digest to d872252 <a href="https://redirect.github.com/python-pillow/Pillow/issues/9614">#9614</a> [@<a href="https://github.com/apps/renovate">renovate[bot]</a>]</li> <li>Update dependency lcms2 to v2.19 <a href="https://redirect.github.com/python-pillow/Pillow/issues/9609">#9609</a> [@<a href="https://github.com/apps/renovate">renovate[bot]</a>]</li> <li>Update dependency libpng to v1.6.58 - autoclosed <a href="https://redirect.github.com/python-pillow/Pillow/issues/9608">#9608</a> [@<a href="https://github.com/apps/renovate">renovate[bot]</a>]</li> <li>Update dependency harfbuzz to v14 <a href="https://redirect.github.com/python-pillow/Pillow/issues/9610">#9610</a> [@<a href="https://github.com/apps/renovate">renovate[bot]</a>]</li> <li>Update dependency mypy to v1.20.2 <a href="https://redirect.github.com/python-pillow/Pillow/issues/9599">#9599</a> [@<a href="https://github.com/apps/renovate">renovate[bot]</a>]</li> <li>Update github-actions <a href="https://redirect.github.com/python-pillow/Pillow/issues/9611">#9611</a> [@<a href="https://github.com/apps/renovate">renovate[bot]</a>]</li> <li>Update dependency cibuildwheel to v3.4.1 <a href="https://redirect.github.com/python-pillow/Pillow/issues/9607">#9607</a> [@<a href="https://github.com/apps/renovate">renovate[bot]</a>]</li> <li>Move dependency versions to single JSON and enable Renovate <a href="https://redirect.github.com/python-pillow/Pillow/issues/9559">#9559</a> [<a href="https://github.com/hugovk"><code>@hugovk</code></a>]</li> <li>Updated raqm to 0.10.5 <a href="https://redirect.github.com/python-pillow/Pillow/issues/9557">#9557</a> [<a href="https://github.com/radarhere"><code>@radarhere</code></a>]</li> <li>Update dependency cibuildwheel to v3.4.0 <a href="https://redirect.github.com/python-pillow/Pillow/issues/9532">#9532</a> [@<a href="https://github.com/apps/renovate">renovate[bot]</a>]</li> </ul> <h2>Testing</h2> <ul> <li>Remove matrix.os from benchmark <a href="https://redirect.github.com/python-pillow/Pillow/issues/9735">#9735</a> [<a href="https://github.com/radarhere"><code>@radarhere</code></a>]</li> <li>Remove references to libavif patch <a href="https://redirect.github.com/python-pillow/Pillow/issues/9734">#9734</a> [<a href="https://github.com/radarhere"><code>@radarhere</code></a>]</li> <li>Add benchmark tests <a href="https://redirect.github.com/python-pillow/Pillow/issues/9654">#9654</a> [<a href="https://github.com/akx"><code>@akx</code></a>]</li> <li>Use reshape() instead of setting NumPy array shape directly <a href="https://redirect.github.com/python-pillow/Pillow/issues/9728">#9728</a> [<a href="https://github.com/radarhere"><code>@radarhere</code></a>]</li> </ul> <!-- raw HTML omitted --> </blockquote> <p>... (truncated)</p> </details> <details> <summary>Commits</summary> <ul> <li><a href="https://github.com/python-pillow/Pillow/commit/bb1d8e8ab8d29048624d96e3ee53cecf7c13d13d"><code>bb1d8e8</code></a> 12.3.0 version bump</li> <li><a href="https://github.com/python-pillow/Pillow/commit/e63fc481dc2e07e21d5403deafb8f1ed98a513af"><code>e63fc48</code></a> Add release notes for SBOM and performance improvements (<a href="https://redirect.github.com/python-pillow/Pillow/issues/9747">#9747</a>)</li> <li><a href="https://github.com/python-pillow/Pillow/commit/13b701bbab291eec4bc87ea17ba06c94e5fe3054"><code>13b701b</code></a> Add release notes for <a href="https://redirect.github.com/python-pillow/Pillow/issues/9679">#9679</a></li> <li><a href="https://github.com/python-pillow/Pillow/commit/5564ca72fcd59d040e270af5dcf17a0d7161c364"><code>5564ca7</code></a> List methods</li> <li><a href="https://github.com/python-pillow/Pillow/commit/a0920fd384f800b5d0ba3dd29ecdeae4f1d4043b"><code>a0920fd</code></a> Speed up ImageChops operations (<a href="https://redirect.github.com/python-pillow/Pillow/issues/9738">#9738</a>)</li> <li><a href="https://github.com/python-pillow/Pillow/commit/07e9a6cd5336dc6cf8cae9165cd70cdd2b3e42fc"><code>07e9a6c</code></a> Speed up <code>Image.filter()</code> (<a href="https://redirect.github.com/python-pillow/Pillow/issues/9736">#9736</a>)</li> <li><a href="https://github.com/python-pillow/Pillow/commit/a94578cf9649ea13e426cf7fb2b71b39ffc0dd50"><code>a94578c</code></a> Speed up <code>Image.getchannel()</code>, <code>Image.merge()</code>, <code>Image.putalpha()</code> and `Image...</li> <li><a href="https://github.com/python-pillow/Pillow/commit/53e02c43c919d149b2a154a5180079f9df18fbbb"><code>53e02c4</code></a> Speed up <code>Image.fill()</code>, <code>Image.linear_gradient()</code> and `Image.radial_gradient...</li> <li><a href="https://github.com/python-pillow/Pillow/commit/af037475be8634ba739744243164ba9e2c8346a6"><code>af03747</code></a> Speed up <code>Image.resample()</code> (<a href="https://redirect.github.com/python-pillow/Pillow/issues/9739">#9739</a>)</li> <li><a href="https://github.com/python-pillow/Pillow/commit/5c9ca56c3e5fba52b647809fbb0986c87e73a571"><code>5c9ca56</code></a> Speed up <code>alpha_composite</code>, <code>matrix</code>, <code>negative</code>, <code>quantize</code> (<a href="https://redirect.github.com/python-pillow/Pillow/issues/9740">#9740</a>)</li> <li>Additional commits viewable in <a href="https://github.com/python-pillow/Pillow/compare/12.2.0...12.3.0">compare view</a></li> </ul> </details> <br /> [](https://docs.github.com/en/github/managing-security-vulnerabilities/about-dependabot-security-updates#about-compatibility-scores) Dependabot will resolve any conflicts with this PR as long as you don't alter it yourself. You can also trigger a rebase manually by commenting `@dependabot rebase`. [//]: # (dependabot-automerge-start) [//]: # (dependabot-automerge-end) --- <details> <summary>Dependabot commands and options</summary> <br /> You can trigger Dependabot actions by commenting on this PR: - `@dependabot rebase` will rebase this PR - `@dependabot recreate` will recreate this PR, overwriting any edits that have been made to it - `@dependabot show <dependency name> ignore conditions` will show all of the ignore conditions of the specified dependency - `@dependabot ignore this major version` will close this PR and stop Dependabot creating any more for this major version (unless you reopen the PR or upgrade to it yourself) - `@dependabot ignore this minor version` will close this PR and stop Dependabot creating any more for this minor version (unless you reopen the PR or upgrade to it yourself) - `@dependabot ignore this dependency` will close this PR and stop Dependabot creating any more for this dependency (unless you reopen the PR or upgrade to it yourself) You can disable automated security fix PRs for this repo from the [Security Alerts page](https://github.com/langchain-ai/deepagents/network/alerts). </details> --------- Signed-off-by: dependabot[bot] <support@github.com> Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com> Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com> |
||
|
Brace Sproul
|
8e8835693f |
feat(repo): openwiki (#4853)
Adds OpenWiki to the repo: an auto-generated, in-tree code wiki that coding agents — and humans — can read for grounded context before working in the monorepo. <img width="885" height="666" alt="Screenshot 2026-07-20 at 9 34 34 AM" src="https://github.com/user-attachments/assets/c51f488b-58e8-4377-93f8-11a4e9c955c7" /> --- **What it is:** OpenWiki reads the codebase and git history to generate concise, navigable reference pages — a quickstart, architecture overview, key workflows, and operations/testing notes — that live in the repo under `openwiki/`. **Why:** Gives coding agents reliable, repo-grounded documentation to consult on each task instead of re-discovering structure and conventions from scratch, which improves their accuracy when working here. **What it adds:** - `openwiki/` — the generated wiki (quickstart, architecture, workflows, engineering ops/testing), with `openwiki/quickstart.md` as the entry point. - A scheduled `OpenWiki Update` GitHub Actions workflow that regenerates the wiki daily and opens a PR with the refresh, so the docs stay current automatically. - An `AGENTS.md` pointer directing agents to start from `openwiki/quickstart.md` and to avoid hand-editing generated pages (update source code/docs and let OpenWiki regenerate). |
||
|
Mason Daugherty
|
c224a238e6 |
ci(infra): link release summaries to PRs (#4866)
Package release run summaries now include a direct link to the pull request associated with the exact release SHA. Runs without an associated PR continue normally, and a failed GitHub lookup does not block a release. --- The package release workflow is dispatched separately from the release PR, so GitHub does not provide pull-request event context in the publish run. Resolve the merged PR from the validated release commit instead and add it to the existing release-target table. The lookup uses read-only pull-request permission and remains best-effort so manual and prerelease workflows retain their existing behavior. |
||
|
Johannes du Plessis
|
f49337595a |
refactor(code): centralize JSON type aliases (#4868)
Centralize recursive JSON aliases in a neutral module so config and plugin code share one definition while preserving plugin import compatibility. The aliases remain static types only; existing runtime ingress validation is unchanged. <details> <summary>Test plan</summary> - `make -C libs/code format` - `make -C libs/code lint` - Focused JSON, hooks, model config, and MCP login tests (546 passed; one unrelated root-permission assertion failed) </details> Made by [Open SWE](https://openswe.vercel.app/agents/019f8107-bf8c-7545-9a37-299374653ddc) --------- Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com> |
||
|
Mason Daugherty
|
911fc28198 |
fix(infra): allow release-run comments (#4865)
Related #4817 Merged release PRs once again receive a direct link to the package release workflow run. --- Release PR #4857 demonstrated that the dispatch and run lookup paths worked, but GitHub rejected the PR comment with `403 Resource not accessible by integration`. The `trigger-releases` token had `Issues: write` and only `PullRequests: read`; commenting on a pull request requires `pull-requests: write`. This grants that permission only to `trigger-releases`. Its existing `actions` and `issues` permissions, release dispatch behavior, and best-effort handling for comment failures are unchanged. A workflow regression test locks the exact permission map. |
||
|
Mason Daugherty
|
44d9dec39b |
feat(code): show experimental mode in splash and debug console (#4863)
When `DEEPAGENTS_CODE_EXPERIMENTAL` is set, `dcode` now surfaces that unstable behavior is active — an `(experimental mode)` tag on the startup splash (alongside the existing `(debug enabled)` tag) and an `Experimental` on/off row in the Debug Console snapshot. --- Experimental behavior was previously invisible, so users couldn't tell when the flag was in effect. The splash tag mirrors the `(debug enabled)` pattern (its own themed style helper, ANSI fallback, rendered even when the version is hidden, ordered debug → experimental → local). The Debug Console gains an always-present `Experimental` field so the diagnostic snapshot reports the flag state directly. Made by [Open SWE](https://openswe.vercel.app/agents/6cb12589-9525-8da6-05db-a4134a7ea44a) --------- Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com> |
||
|
Mason Daugherty
|
22969c0538 |
docs(repo): improve libs README and call out dcode by name (#4864)
Improves the `libs/` monorepo README so newcomers can quickly find their footing and understand what each package is. --- The previous README listed packages in a plain code block. This reworks it into a linked table (each package points at its directory and PyPI project) and adds a getting-started callout for the prebuilt terminal coding agent, Deep Agents Code — calling out `deepagents-code` and its `dcode` command by name so readers know the fastest way to try Deep Agents. Documentation-only change. Made by [Open SWE](https://openswe.vercel.app/agents/5f35224b-a63a-8e01-68f8-3cad100b4cbe) --------- Signed-off-by: Mason Daugherty <github@mdrxy.com> Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com> |
||
|
Mason Daugherty
|
3733526f5f |
fix(code): bust CDN cache on forced dcode update checks (#4862)
`dcode update` now returns fresh results even in the seconds right after a new release lands on PyPI. --- `dcode update` already calls `is_update_available(bypass_cache=True)`, which skips the local on-disk version cache. But PyPI's JSON API is served through a CDN (Fastly), so immediately after a release an edge node can keep serving a stale copy until the purge propagates. That's why a first `dcode update` reported "Already on the latest version (v0.1.43)" while a retry seconds later found v0.1.44. When the local cache is bypassed, the PyPI requests now also defeat the CDN edge cache: they send `Cache-Control: no-cache` / `Pragma: no-cache` request headers and append a unique cache-busting query parameter so the CDN cache key misses and the response comes fresh from origin. A shared `_pypi_request_kwargs` helper applies this consistently to the version check, the per-release pre-release-pin lookup, and the SDK release-time lookup. Routine (non-forced) refreshes are unchanged. Made by [Open SWE](https://openswe.vercel.app/agents/f2647aaa-94ac-f901-c39d-e081d0eb1f79) Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com> |
||
|
Shrikar Seshadri
|
54ccd67ca8 |
fix(evals): verify and record comparison SHAs (#4834)
Builds on #4824 by Nick (merged into main). ### Workflow 1. Each branch is resolved to one SHA. 2. Each shard fetches that exact SHA. 3. The workflow overlays these source directories: - `libs/deepagents` - `libs/code` - `libs/partners/quickjs` 4. These are copied into the Harbor LangGraph project's `.local_deps`. 5. Harbor installs those local source packages when constructing the sandbox environment. 6. The sandboxed agent imports the installed packages normally. ### What this PR adds - Resolves the branch's head via `git ls-remote --exit-code refs/heads/<branch>` and hardens it as the SHA (previously used `refs/<branch>` and took the first result). - Verifies `FETCH_HEAD` matches `BRANCH_SHA`; fails the shard on mismatch. - Adds branch-to-SHA mappings to the GitHub workflow summary — all leaves include a `source_sha`, and prep emits a sources list of `{branch, sha}` pairs. - Adds SHA provenance throughout result files: - `_harbor_run.yml` passes `branch_sha` to the shard aggregator. - Each leaf `summary.json` records `source_sha`. - Each combined Unified result row records `source_sha`. - Missing-leaf placeholder rows retain the expected SHA, making it easy to identify the redeployment command if a shard fails. - Adds test coverage for all of the above. ### Notes - No product wheels — unnecessary for this change. - Evaluator harness stays pinned to the workflow reference (main branch). - `unified_evals.yml` still supports single-branch testing via the standard workflow input. - No trace analysis, retry/timeout controls, or LangSmith usage/cost analysis (planned for future PRs). ### Tests - 141 focused prep, workflow, provenance, and aggregation tests passed. - Ruff checks passed on all changed Python files. - Both modified workflow YAML files parsed successfully. - One unrelated macOS temp-directory test was excluded — system Python creates an xcrun cache entry in its asserted-empty temp directory. --------- Co-authored-by: Nick Hollon <nick.hollon@langchain.dev> Co-authored-by: Mason Daugherty <github@mdrxy.com> |
||
|
Nick Hollon
|
cf3cfc2afe |
docs(evals): add 2026-07-17 6-model lite scorecard run (#4828)
Adds lite pass@k / avg@k for four models to `libs/evals/UNIFIED_SCORECARD.md` (run [29593952741](https://github.com/langchain-ai/deepagents/actions/runs/29593952741)): `openai:gpt-5.6-sol`, `anthropic:claude-opus-4-8`, `anthropic:claude-sonnet-5`, `fireworks:…/glm-5p2`. Context is graded by exact string match on the answer file, so the context column is output-format-sensitive. Docs-only; numbers are the GH aggregate from the run's artifacts. |
||
|
github-actions[bot]
|
2b9cd08f04 |
release(deepagents-code): 0.1.44 (#4857)
> [!CAUTION] > Merging this PR will automatically publish to **PyPI** and create a **GitHub release**. For the full release process, see [`.github/RELEASING.md`](https://github.com/langchain-ai/deepagents/blob/main/.github/RELEASING.md). --- _Release notes preview: keep this section in sync with the package `CHANGELOG.md`. The published GitHub release body is extracted from the merged `CHANGELOG.md` by `release.yml`, not from this PR description._ --- ## [0.1.44](https://github.com/langchain-ai/deepagents/compare/deepagents-code==0.1.43...deepagents-code==0.1.44) (2026-07-20) ### Bug Fixes - Improved approval handling by hiding the `Auto` option when it isn't eligible and moving Auto mode path checks off the event loop. ([#4839](https://github.com/langchain-ai/deepagents/issues/4839), [#4856](https://github.com/langchain-ai/deepagents/issues/4856)) - Warmed MCP auth imports off the event loop to avoid blocking runtime work. ([#4855](https://github.com/langchain-ai/deepagents/issues/4855)) _End release notes preview._ --- > [!NOTE] > A **New Contributors** section is appended to the GitHub release notes automatically at publish time (see [Release Pipeline](https://github.com/langchain-ai/deepagents/blob/main/.github/RELEASING.md#release-pipeline), step 2). --------- Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com> Co-authored-by: langchain-oss-automated-triage[bot] <248757908+langchain-oss-automated-triage[bot]@users.noreply.github.com>deepagents-code==0.1.44 |
||
|
Mason Daugherty
|
75d37c3475 |
fix(code): warm MCP auth imports off event loop (#4855)
Related #4786 When `dcode` starts with MCP servers enabled, it loads the code used to connect to those servers. Loading the optional authentication support for the first time can perform filesystem work. Previously, that work happened on the async server's event loop, where blocking calls are rejected, so startup could fail with: BlockingError: Blocking call to os.getcwd `dcode` now loads MCP authentication support in a worker thread before the server needs it. This keeps the potentially blocking work away from the event loop so the runtime no longer rejects it during startup. --- #4786 addressed the immediate failure by limiting `filelock` to versions before 3.30. This follow-up hardens `dcode` against the broader problem instead of relying only on one dependency version. The version limit remains in place for now. If the optional authentication support cannot be loaded, the failure is still reported only for an MCP server that needs it; it does not prevent unrelated or stdio MCP servers from loading. A startup smoke test uses the same blocking-call detector as the runtime to verify that first-time authentication loading happens in a worker thread, so CI catches regressions. |
||
|
Mason Daugherty
|
752af303d5 |
style(code): pad between marketplace entries in plugin manager (#4850)
Marketplace entries in the plugin manager now have spacing between them, matching the plugins list. --- The marketplaces tab rendered entries back-to-back, while the plugins list (`_plugin_options`) inserts a disabled spacer `Option` between rows. This applies the same disabled-spacer pattern between marketplace rows so both surfaces are visually consistent. The spacers are disabled, so keyboard navigation still skips over them. Made by [Open SWE](https://openswe.vercel.app/agents/045a43e2-f199-47e8-a7f0-ffb5dbff5762) --------- Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com> |
||
|
Mason Daugherty
|
acb1a0eeec |
style(code): align Auto activation warnings (#4858)
Auto mode now shows the same warning whether it is enabled at startup or toggled during a session. --- The startup path used implementation-specific copy that differed from the toggle path. Reuse one warning constant so both paths stay aligned and future edits cannot drift. |
||
|
Mason Daugherty
|
1a1f06f506 |
fix(code): hide Auto option in approval widget when ineligible (#4839)
Approval prompts no longer suggest enabling Auto mode when it is unavailable (experimental opt-in off). --- The HITL approval widget always offered "Enable Auto for this thread (a)" even when Auto mode is ineligible (e.g. `DEEPAGENTS_CODE_EXPERIMENTAL` is off or a sandbox is active), where choosing it only surfaced the "Auto is available only in the opt-in local TUI beta" warning and did nothing. `ApprovalMenu` now takes `auto_mode_eligible` (passed from `App._auto_mode_eligible`) and omits the Auto option when it can't be enabled, dynamically renumbering options and quick keys. A live Auto fallback still shows its Switch-to-Manual affordance. Made by [Open SWE](https://openswe.vercel.app/agents/6c5eb368-e615-f9d7-b8d0-bbce9ebaa3ff) --------- Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com> |
||
|
Nick Hollon
|
63d5e03bb7 |
refactor(evals): make langgraph.json the single agent registry (#4854)
Adding an eval agent is now `langgraph.json` + a factory: `agent_impl == graph key`, the workflow YAML and Makefile become passthroughs, and `unified_prep.py` derives its allowlists from the registry. |
||
|
Mason Daugherty
|
511203a2c2 |
fix(code): move Auto mode path checks off the event loop (#4856)
Auto mode no longer raises `BlockingError` while resolving proposed file paths on the LangGraph server event loop. --- Auto mode still uses canonical, symlink-aware `Path.resolve()` before deciding whether a write stays inside the worktree. The async planning path now runs the complete deterministic policy check in a worker thread, so current and future filesystem-backed policy checks cannot block the event loop. Regression coverage drives `awrap_model_call()` with the original absolute `/tmp/langchain-groq-reasoning-model-pr.md` target and verifies resolution happens off the event-loop thread. It also confirms routine in-worktree writes remain deterministic allows and symlink escapes still require classifier review. |
||
|
Nick Hollon
|
ae96a90824 |
feat(evals): compare branch variants with a neutral harness (#4824)
- Add branch-aware unified eval dispatch that compares selected Deep Agents product sources while keeping the evaluator, datasets, and verifiers fixed. - Scope matrix planning, artifacts, LangSmith experiments, and scorecard rows by branch and harness configuration, with bounded packed-shard scheduling. - Let the bare and Tau3 evaluation graphs use the compared branch's own base agent prompt instead of injecting a harness prompt. --------- Co-authored-by: Mason Daugherty <github@mdrxy.com> |
||
|
github-actions[bot]
|
e14e0adcbe |
release(deepagents-code): 0.1.43 (#4825)
> [!CAUTION] > Merging this PR will automatically publish to **PyPI** and create a **GitHub release**. For the full release process, see [`.github/RELEASING.md`](https://github.com/langchain-ai/deepagents/blob/main/.github/RELEASING.md). --- _Release notes preview: keep this section in sync with the package `CHANGELOG.md`. The published GitHub release body is extracted from the merged `CHANGELOG.md` by `release.yml`, not from this PR description._ --- ## [0.1.43](https://github.com/langchain-ai/deepagents/compare/deepagents-code==0.1.42...deepagents-code==0.1.43) (2026-07-17) ### Features - Added classifier-backed Auto approval mode behind `DEEPAGENTS_CODE_EXPERIMENTAL=1` ([#4804](https://github.com/langchain-ai/deepagents/issues/4804)). - Added a shutdown toast for deferred exits ([#4830](https://github.com/langchain-ai/deepagents/issues/4830)). - Task descriptions that were truncated can now be expanded by clicking or pressing `Ctrl+O` ([#4811](https://github.com/langchain-ai/deepagents/issues/4811)). - Debug Console clears with `Ctrl+L` now persist after reopening ([#4812](https://github.com/langchain-ai/deepagents/issues/4812)). - Added debug logging for skill-name override collisions ([#4772](https://github.com/langchain-ai/deepagents/issues/4772)). ### Bug Fixes - Keep chat input responsive during `/restart` ([#4808](https://github.com/langchain-ai/deepagents/issues/4808)). - Fixed paste placeholders disappearing when backspacing a newline below them ([#4757](https://github.com/langchain-ai/deepagents/issues/4757)). - Made markdown `AppMessage` output selectable ([#4814](https://github.com/langchain-ai/deepagents/issues/4814)). - Fixed live tool-group counts to include only running tools ([#4809](https://github.com/langchain-ai/deepagents/issues/4809)). - Kept `task` timers monotonic across nested subagent human-in-the-loop flows ([#4771](https://github.com/langchain-ai/deepagents/issues/4771)). - Preserved goal criteria proposals when marker clearing fails ([#4785](https://github.com/langchain-ai/deepagents/issues/4785)). - Reduced repeated probing of an unreachable Ollama daemon to once per reload ([#4806](https://github.com/langchain-ai/deepagents/issues/4806)). - Quieted MCP auth-skip debug logging for known patterns ([#4805](https://github.com/langchain-ai/deepagents/issues/4805)). - Improved `/version` diagnostics for editable installs and core dependency reporting, including surfacing `langchain-quickjs` ([#4816](https://github.com/langchain-ai/deepagents/issues/4816), [#4813](https://github.com/langchain-ai/deepagents/issues/4813)). - Removed the `uv install` tip from the `/version` update hint ([#4822](https://github.com/langchain-ai/deepagents/issues/4822)). _End release notes preview._ --- > [!NOTE] > A **New Contributors** section is appended to the GitHub release notes automatically at publish time (see [Release Pipeline](https://github.com/langchain-ai/deepagents/blob/main/.github/RELEASING.md#release-pipeline), step 2). --------- Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com> Co-authored-by: langchain-oss-automated-triage[bot] <248757908+langchain-oss-automated-triage[bot]@users.noreply.github.com>deepagents-code==0.1.43 |
||
|
Mason Daugherty
|
eae7c28f11 |
feat(code): classifier-backed Auto approval mode (#4804)
Deep Agents Code now offers an opt-in **Auto** approval mode. Auto
immediately runs a narrow, deterministic set of routine actions. For
other approval-gated actions, the active model checks whether they match
the user's literal request. It runs approved actions and blocks the
rest. After repeated denials or classifier failures, Auto sends the next
batch to the normal approval UI, then continues in Auto mode.
Auto is experimental and currently limited to interactive, local TUI
sessions using `FilesystemBackend`. Manual remains the default.
> [!WARNING]
> Auto is an authorization heuristic for a local coding agent. It is
**not** sandbox containment, an operating-system boundary, or a
guarantee that model-generated actions are safe.
## Enable Auto
1. Set `DEEPAGENTS_CODE_EXPERIMENTAL=1`.
2. Select Auto in one of these ways:
- In-app: use <kbd>Shift</kbd>+<kbd>Tab</kbd> or
<kbd>Ctrl</kbd>+<kbd>T</kbd> to toggle between Manual and Auto.
- At launch: pass `-y` or `--auto-approve`.
- By default: set `[startup].mode = "auto"` in
`~/.deepagents/config.toml`.
`-y` and `--auto-approve` now select Auto rather than unrestricted
execution. Users who want the previous unrestricted behavior must choose
`--yolo`. The removed `dangerously-auto` startup value is no longer
recognized and falls back to Manual.
---
## Why
The previous approval modes forced a binary choice:
- **Manual** preserved a human checkpoint, but repeatedly interrupted
routine coding work.
- **YOLO** removed that checkpoint entirely, including for actions that
exceeded the user's request (blanket approval).
Auto introduces a third policy: keep the low-friction path for clearly
routine work, but make authorization explicit for potentially
consequential actions.
| Mode | Policy | Entry points | Availability |
|---|---|---|---|
| **Manual** | Uses the normal human approval UI for gated actions |
Default; `[startup].mode = "manual"` | All interactive sessions |
| **Auto** | Uses narrow deterministic rules, then classifier review,
with human fallback after repeated denials or failures | `-y`,
`--auto-approve`, `[startup].mode = "auto"`, or the live keyboard toggle
| Experimental, local, unsandboxed TUI sessions |
| **YOLO** | Runs gated actions without review | `--yolo` or
`[startup].mode = "yolo"` | Interactive sessions after a one-time
acknowledgement |
## How Auto handles a proposed action
```mermaid
flowchart TD
A[Model proposes tool calls] --> B{Covered by the approval policy?}
B -->|No| X[Existing tool behavior is unchanged]
B -->|Yes| S{Is this thread still in Auto, with readable denial/failure history?}
S -->|No| J[Open the existing approval HITL widget]
S -->|Yes| C{Narrow deterministic allow?}
C -->|Yes| R[Execute without a classifier call]
C -->|No| D[Build one structured decision batch]
D --> H{Was this batch already reviewed, or do earlier denials/failures require human review?}
H -->|Yes| J
H -->|No| E[Active model reviews effects against user request/input]
E -->|Allow| R
E -->|Deny| Q{Total-denial threshold reached?}
Q -->|No| F[Return a sanitized error result]
Q -->|Yes| J
E -->|Unavailable or invalid| G[Return a compact unavailable result]
F --> I[Agent can revise its plan]
G --> I
J -->|Approve| R
J -->|Reject| K[Return a rejection result]
J -->|Switch to Manual| L[Persist Manual, then review the full gated batch]
R --> M[Reconcile the result and continue]
K --> M
I --> M
L --> M
```
In practice:
1. **Auto starts with Manual's existing human-in-the-loop (HITL)
rules.** It changes only how HITL-gated actions are reviewed.
- These built-in tools are not HITL-gated: `ls`, `read_file`, `glob`,
`grep`, `ask_user`, `get_goal`, `get_rubric`, and `update_goal`.
- MCP tools with valid read-only annotations, the optional `js_eval`
tool, and caller-supplied tools without HITL configuration continue to
run normally.
2. **Only narrow cases resolve locally.** The deterministic policy can
allow, never deny:
- A routine write such as `src/parser.py` can proceed based on its
resolved path and suffix; a sensitive target such as
`.github/workflows/ci.yml` goes to classifier review.
- A read-only Git command such as `git status` can proceed; a mutating
command such as `git commit -m change` goes to classifier review.
Explicit shell allow-list entries still apply after Auto removes broad
and wildcard rules.
- An MCP tool with a valid read-only annotation can proceed; tools
without read-only annotations, or with contradictory or malformed
annotations, go to classifier review.
<details>
<summary>How MCP read-only annotations are evaluated</summary>
MCP servers can attach standard `ToolAnnotations` when advertising a
tool. Deep Agents Code copies those annotations into the wrapped tool's
metadata and lets the tool bypass classifier review only when:
- `readOnlyHint` is the literal Boolean `true`;
- `destructiveHint` is absent, `null`, or `false`; and
- every supplied standard hint (`readOnlyHint`, `destructiveHint`,
`idempotentHint`, or `openWorldHint`) is a Boolean or `null`, rather
than a string or another type.
For example:
- `readOnlyHint: true, destructiveHint: false` proceeds without
classifier review.
- No `readOnlyHint` goes to review because the tool never explicitly
claimed to be read-only.
- `readOnlyHint: true, destructiveHint: true` goes to review because the
hints contradict each other.
- `readOnlyHint: true, destructiveHint: "false"` goes to review because
`"false"` is a string, not a Boolean.
In Auto, tools that do not pass this check enter the classifier batch.
In Manual, they use the normal approval UI; headless runtimes reject
them because they have no approval UI. The annotation is a
server-provided assertion that Deep Agents Code does not independently
verify.
</details>
3. **The classifier reviews all unresolved calls together.** Only
pre-expansion literal user text can authorize an action. Referenced
paths, summarized arguments, prior tool calls, and MCP metadata provide
effect context but cannot grant permission. Expanded files, assistant
prose, and tool results are excluded.
- **Example:** For the literal request `Research issue #123, update
@src/parser.py, and open a PR`, proposed `fetch_url` and `git push`
calls can be reviewed in one batch and receive separate decisions. The
referenced path and summarized call arguments help identify what each
action would affect, but the expanded file contents are not sent.
Instructions found in that file, assistant prose, or a prior tool result
therefore cannot widen the user's request or authorize another action.
4. **Auto revalidates before side effects.** The decision plan is bound
to the thread, mode, batch, and exact gated calls. Missing or invalid
state, a mode race, or a replay falls back to human review. Denied calls
are skipped and receive sanitized error results so the agent can revise
its plan.
- **Examples:** If the user switches to Manual while classifier review
is in progress, an earlier Auto decision cannot execute silently; the
normal approval UI opens instead. A plan associated with another thread,
a different set of tool-call IDs, missing decisions, or a previously
processed batch also requires human review. If Auto denies a proposed
`delete`, it returns an error result with that call's ID instead of
invoking the tool, allowing the agent to propose a safer next step.
## Limits and user-visible behavior
- The Manual approval menu can enable Auto for the current thread.
Threshold fallback can switch permanently to Manual or perform a one-off
review while leaving Auto enabled.
- Denials, classifier failures, and fallbacks appear as short sanitized
transcript events rather than raw classifier output.
- Auto requested without the experimental opt-in, or in a sandboxed
session, falls back to Manual with a warning. Explicit autonomous-mode
flags are rejected in non-interactive and ACP entry points.
- The active model is not an independent security authority. MCP
read-only annotations are trusted as a deliberate beta tradeoff.
- Parent-level Auto review does not cover actions performed inside
delegated subagents or broader explicitly configured PTC/`js_eval`
fan-out. Model providers and tracing backends may still observe
classifier inputs and outputs even though the TUI hides them.
<details>
<summary><strong>Implementation and reviewer details</strong></summary>
### Approval boundary and decision inputs
The following tools are HITL-gated:
- `execute`, `write_file`, `edit_file`, and `delete`;
- `web_search` and `fetch_url`;
- `task`;
- `start_async_task`, `update_async_task`, and `cancel_async_task`;
- `compact_conversation` when optional compaction approval is enabled;
and
- MCP tools without valid read-only annotations.
For deterministic writes and edits, the fast path uses only the resolved
target path and suffix; it does not inspect proposed content. Dependency
and lock files, sensitive names and locations, shell scripts,
unsupported file types, and paths outside the trusted root do not
qualify. Selected Git inspection commands must also pass shell-control
and outside-worktree path checks. Configured shell entries remain an
explicit user trust exception, but broad commands and wildcard entries
are ignored by Auto.
The classifier receives one typed batch containing:
- up to 20 client-attached, pre-expansion prompt rows, including literal
prompts, referenced path names, and turn IDs;
- trusted project-root and redacted-origin facts; and
- depth- and length-limited effect context from current arguments, prior
AI tool calls after the latest trusted prompt, and selected MCP
annotations.
Only `literal_user_text` is authorizing. Content-bearing write/edit
arguments are reduced to character counts. The classifier must return
exactly one unique decision for every unresolved tool-call ID; missing,
duplicated, unknown, or malformed decisions make the classifier
unavailable rather than partially authorizing the batch.
Before routing calls, Auto re-reads the live mode and validates its
private decision plan. Manual mode, invalid control state, mismatched
calls, or replayed batches require human review. Classifier review uses
a second call to the active session model with a 20-second timeout. Raw
classifier text and tool-call chunks are hidden from the transcript,
while usage accounting and tracing are retained.
Denial reasons are sanitized before persistence or display by removing
control characters, known credential values, credential-like
assignments, and URL credentials or query values. MCP tools without
valid read-only annotations are HITL-gated; headless runtimes reject
them because no approval UI is available.
### Failure and fallback behavior
| Condition | Result |
|---|---|
| Selected mode cannot be persisted | Persist Manual instead; if that
also fails, block graph execution |
| Classifier timeout, provider error, or invalid response | Block the
affected calls and return a compact unavailable result |
| Three consecutive policy denials in one user turn | Send the next
classifier-review-eligible calls to one-off human review |
| Two consecutive classifier-unavailable results | Send the next
classifier-review-eligible calls to one-off human review |
| A denial raises the thread's total denial count to 20 | Require human
review for that call immediately |
| Counter state cannot be read or reset before classification | Require
human review for every gated call in the batch |
| Counter state cannot be written after classification | Require human
review for classifier-path decisions; deterministic fast-path allows
remain eligible |
| Decision plan is missing, malformed, replayed, or bound to another
thread | Require Manual review |
| User chooses **Switch to Manual** during fallback | Persist Manual
before presenting the full gated batch for review |
### Python API and state compatibility
- Existing Boolean compatibility input retains its previous meaning:
`auto_approve=True` maps to YOLO, not Auto.
- Per-thread Store records persist the typed mode instead of a Boolean.
Missing, legacy, or malformed records fail closed.
- Startup and live mode changes take effect only after the Store write
succeeds.
- YOLO requires a versioned local acknowledgement and cannot be entered
through the live keyboard toggle.
### Reviewer guide
Suggested review order:
1. **Mode semantics and persistence** — `ApprovalMode`, Store payloads,
acknowledgement, startup resolution, and live mode writes.
2. **Authorization policy** — `AutoModeHITLMiddleware`, literal prompt
metadata, deterministic routing, structured classification,
sanitization, counters, and checkpoint validation.
3. **Graph boundary** — middleware replacement, the gated-tool
inventory, MCP annotation handling, headless rejection, PTC, and
delegated-subagent scope.
4. **Client behavior** — stream metadata, classifier-output filtering,
fallback interrupts, keyboard toggles, status presentation, and
transcript events.
Highest-risk invariants:
- every consequential tool in the supported boundary is gated or
explicitly outside scope;
- path-based writes and selected Git fast paths stay within their
documented checks;
- only literal user prompts can authorize classifier-reviewed effects;
- malformed output, Store failures, mode races, and checkpoint replay
fail closed; and
- hidden classifier chunks never create transcript content while usage
accounting remains intact.
</details>
|
||
|
Mason Daugherty
|
02f6eae1d3 |
Merge remote-tracking branch 'origin/main' into nm/dcode-tools-allowlist
# Conflicts: # libs/code/deepagents_code/agent.py # libs/code/deepagents_code/main.py # libs/code/tests/unit_tests/test_agent.py # libs/code/tests/unit_tests/test_main_acp_mode.py |
||
|
Mason Daugherty
|
a8a05f58f2 |
feat(code): shutdown toast for deferred exits (#4830)
When quitting waits for unfinished work, `deepagents-code` now shows a brief "Finishing pending work before exit…" toast so the pause reads as intentional rather than a hang. --- `DeepAgentsApp.exit()` only defers teardown when it must wait for an in-flight agent worker or pending fire-and-forget hooks. That wait was previously silent, so a user pressing quit could think the app had frozen. This adds a single toast on exactly that deferred path. The notification is emitted before scheduling the `_graceful_exit` coroutine. Because scheduling returns control to the event loop and teardown is deferred behind at least one `await`, Textual's message pump gets an opportunity to render the toast before `super().exit()` runs. Immediate/idle exits skip this branch entirely, no delay is introduced, and the existing two-second grace period is untouched. A repeated/forced exit hits the existing force-quit guard before reaching the notify, so the toast is never duplicated (including when both wait conditions apply). Made by [Open SWE](https://openswe.vercel.app/agents/26e6d24a-3180-4334-b655-4075767ae45b) --------- Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com> |
||
|
Mason Daugherty
|
3f82114c37 |
refactor(code): drop config list/ls aliases for config show (#4783)
`dcode config list`/`dcode config ls` are removed; use `dcode config show` (add `--verbose` to see all option keys). --- `config list`/`config ls` duplicated `config show`, so this removes both parser aliases and makes `config show` the sole command for displaying effective config values and their sources. Drops `list_mode`, the `config list` JSON label/catalog special-casing, backward-compat comments, and now-dead paths; `config show --json` keeps effective-only fields (catalog folded in only with `--verbose`) and always labels the payload `"config show"`. User-facing suggestions now point at `config show`/`config show --verbose`. Backward compatibility is intentionally not preserved. ### Breaking change `config list --json` was the machine-readable catalog endpoint (its JSON envelope `command` field was `"config list"` and it always folded in catalog fields). It is gone: the command no longer parses, and the catalog fields are now available via `config show --verbose --json` (payload labeled `"config show"`). Any machine consumer of `config list --json` must migrate. Made by [Open SWE](https://openswe.vercel.app/agents/7351f382-9468-b4dc-2df4-03eaf75ef12f) --------- Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com> |
||
|
Mason Daugherty
|
6604820235 |
fix(infra): preserve merge base in Dependabot lockfile fixer (#4829)
Related #4827 The Dependabot lockfile fixer now keeps enough Git history to inspect dependency PRs that have fallen behind `main`. --- The preflight checkout already retrieves complete history, but its explicit fetch of the event-time base used `--depth=1`. That marked the base commit as a shallow boundary, so the three-dot diff could not walk back to the common ancestor when `main` had advanced after Dependabot created its branch. Fetch the exact base SHA without limiting its depth. This retains the event snapshot while preserving the ancestry needed by the path-scope guard. The fix was validated against the base and head SHAs from #4827, where the diff now resolves to the two expected `libs/talon` files. |
||
|
dependabot[bot]
|
68adab563c |
chore(deps): bump torch from 2.12.1 to 2.13.0 in /libs/talon (#4827)
Bumps [torch](https://github.com/pytorch/pytorch) from 2.12.1 to 2.13.0. <details> <summary>Release notes</summary> <p><em>Sourced from <a href="https://github.com/pytorch/pytorch/releases">torch's releases</a>.</em></p> <blockquote> <h1>PyTorch 2.13.0 Release Notes</h1> <ul> <li><a href="https://github.com/pytorch/pytorch/blob/HEAD/#highlights">Highlights</a></li> <li><a href="https://github.com/pytorch/pytorch/blob/HEAD/#backwards-incompatible-changes">Backwards Incompatible Changes</a></li> <li><a href="https://github.com/pytorch/pytorch/blob/HEAD/#deprecations">Deprecations</a></li> <li><a href="https://github.com/pytorch/pytorch/blob/HEAD/#new-features">New Features</a></li> <li><a href="https://github.com/pytorch/pytorch/blob/HEAD/#improvements">Improvements</a></li> <li><a href="https://github.com/pytorch/pytorch/blob/HEAD/#bug-fixes">Bug fixes</a></li> <li><a href="https://github.com/pytorch/pytorch/blob/HEAD/#performance">Performance</a></li> <li><a href="https://github.com/pytorch/pytorch/blob/HEAD/#documentation">Documentation</a></li> <li><a href="https://github.com/pytorch/pytorch/blob/HEAD/#developers">Developers</a></li> </ul> <h1>Highlights</h1> <!-- raw HTML omitted --> <p>For more details about these highlighted features, you can look at the release blogpost. Below are the full release notes for this release.</p> <h1>Tracked Regressions</h1> <h3>ROCm wheels break <code>torch.compile</code> on CPU in environments without a GPU</h3> <p>Running a <code>torch==2.13.0+rocm7.2</code> wheel in an environment where no GPU is available (<code>torch.cuda.is_available()</code> is <code>False</code>) breaks <code>torch.compile</code> on the CPU path: the first compile raises <code>RuntimeError: Can't detect vectorized ISA for CPU</code> (<a href="https://redirect.github.com/pytorch/pytorch/issues/189194">#189194</a>). This is a regression from <code>torch==2.12.1+rocm7.2</code>, which compiles CPU code fine (detecting e.g. <code>VecAVX2</code>) in the same setup. The 2.13 ROCm wheel appears to rely on something present in the ROCm builder image to detect the CPU vectorized ISA, so it works when run on a ROCm image but fails on a plain CPU-only image.</p> <p>Workaround: run the <code>+rocm</code> wheel on a ROCm image, or install a standard CPU/CUDA build for GPU-less environments.</p> <h1>Backwards Incompatible Changes</h1> <ul> <li> <p>Stop building CPython 3.13t (free-threaded) binaries (<a href="https://redirect.github.com/pytorch/pytorch/issues/182951">#182951</a>)</p> <p>Upstream <code>pypa/manylinux</code> removed CPython 3.13t (free-threaded) on 2026-05-07, because 3.13t was experimental and has been superseded by the now-non-experimental CPython 3.14t. As a result, PyTorch 2.13 no longer ships <code>cp313t</code> wheels (Linux, Triton, and related artifacts). Users on the free-threaded interpreter should move to Python 3.14t.</p> <p>PyTorch 2.12:</p> <pre lang="bash"><code># cp313t (free-threaded 3.13) wheels were available python3.13t -m pip install torch </code></pre> <p>PyTorch 2.13:</p> </li> </ul> <!-- raw HTML omitted --> </blockquote> <p>... (truncated)</p> </details> <details> <summary>Commits</summary> <ul> <li><a href="https://github.com/pytorch/pytorch/commit/cf30153c4c131c8164ee7798e5022d810682e2cb"><code>cf30153</code></a> [release/2.13] Strip +PTX from CUDA arch list on release/RC builds (<a href="https://redirect.github.com/pytorch/pytorch/issues/188914">#188914</a>) ...</li> <li><a href="https://github.com/pytorch/pytorch/commit/3e3e24bd95b010f8f74915f0c30476906e60d4fc"><code>3e3e24b</code></a> [release/2.13] Restrict cuda-bindings to Python < 3.15 for CUDA 12.9 builds (...</li> <li><a href="https://github.com/pytorch/pytorch/commit/7986b068032abf5e22ea51fe7fea63ef5bcaf3b1"><code>7986b06</code></a> [release/2.13] Bump binary build timeout 280 -> 400 minutes (<a href="https://redirect.github.com/pytorch/pytorch/issues/188551">#188551</a>)</li> <li><a href="https://github.com/pytorch/pytorch/commit/0bdbc268e08fba9debac8f35a8a12e9c008ec0fd"><code>0bdbc26</code></a> [release/2.13] Add CUDA 12.9 to TORCH_CUDA_ARCH_LIST tables (<a href="https://redirect.github.com/pytorch/pytorch/issues/188443">#188443</a>)</li> <li><a href="https://github.com/pytorch/pytorch/commit/9cabb45ca6e6ed3bb4645c929bcfd07691651f74"><code>9cabb45</code></a> [release/2.13] Update manywheel docker image pin to 78e737ad (<a href="https://redirect.github.com/pytorch/pytorch/issues/188409">#188409</a>)</li> <li><a href="https://github.com/pytorch/pytorch/commit/78e737ad29420ffc4800e677c51e2a852caf8359"><code>78e737a</code></a> [release/2.13] Revert "Tighten generalized scatter graph target (<a href="https://redirect.github.com/pytorch/pytorch/issues/184075">#184075</a>)" (#...</li> <li><a href="https://github.com/pytorch/pytorch/commit/0bb9b5bc24bed3278488372d62d9f2235e9e77e3"><code>0bb9b5b</code></a> [release/2.13] Revert "dynamo: round-trip torch.cuda.stream ctx mgr across gr...</li> <li><a href="https://github.com/pytorch/pytorch/commit/aaac2bfe460c04a4d41e83e03452d2347f7142b9"><code>aaac2bf</code></a> [release/2.13] Revert "[Reland] Port D104346887/PR 182675 for index_add fast ...</li> <li><a href="https://github.com/pytorch/pytorch/commit/933081368c3ab64fa2e953217e413b3ba52844e3"><code>9330813</code></a> Fix build_with_debinfo.py broken by CONFIGURE_DEPENDS globbing (<a href="https://redirect.github.com/pytorch/pytorch/issues/188192">#188192</a>)</li> <li><a href="https://github.com/pytorch/pytorch/commit/4e077a7dcf29167db9e97d86cc62f431905e09f7"><code>4e077a7</code></a> Remove setuptools upper bound (<a href="https://redirect.github.com/pytorch/pytorch/issues/188190">#188190</a>)</li> <li>Additional commits viewable in <a href="https://github.com/pytorch/pytorch/compare/v2.12.1...v2.13.0">compare view</a></li> </ul> </details> <br /> [](https://docs.github.com/en/github/managing-security-vulnerabilities/about-dependabot-security-updates#about-compatibility-scores) Dependabot will resolve any conflicts with this PR as long as you don't alter it yourself. You can also trigger a rebase manually by commenting `@dependabot rebase`. [//]: # (dependabot-automerge-start) [//]: # (dependabot-automerge-end) --- <details> <summary>Dependabot commands and options</summary> <br /> You can trigger Dependabot actions by commenting on this PR: - `@dependabot rebase` will rebase this PR - `@dependabot recreate` will recreate this PR, overwriting any edits that have been made to it - `@dependabot show <dependency name> ignore conditions` will show all of the ignore conditions of the specified dependency - `@dependabot ignore this major version` will close this PR and stop Dependabot creating any more for this major version (unless you reopen the PR or upgrade to it yourself) - `@dependabot ignore this minor version` will close this PR and stop Dependabot creating any more for this minor version (unless you reopen the PR or upgrade to it yourself) - `@dependabot ignore this dependency` will close this PR and stop Dependabot creating any more for this dependency (unless you reopen the PR or upgrade to it yourself) You can disable automated security fix PRs for this repo from the [Security Alerts page](https://github.com/langchain-ai/deepagents/network/alerts). </details> Signed-off-by: dependabot[bot] <support@github.com> Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com> |
||
|
Mason Daugherty
|
a915c590df |
fix(code): keep chat input responsive during /restart (#4808)
Typing in the chat input is no longer blocked while the `/restart` command respawns the server. --- Running `/restart` froze the chat input until the server finished respawning. `_handle_restart_command` awaited the multi-second `_restart_server_manual` (`server_proc.restart()`) directly on the Textual message pump, so key events stopped being forwarded and the chat input was "blocked". This is the same class of bug fixed for the MCP viewer `Ctrl+R` reconnect path in #4753 — the fix runs the respawn as a detached `asyncio.create_task` (mirroring the MCP viewer/force-reconnect paths), keeping the pump free so keystrokes stay live and queued messages drain once `ServerReady` fires. Made by [Open SWE](https://openswe.vercel.app/agents/a27e2ef4-b392-c236-f410-c1b9ebc533aa) --------- Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com> |
||
|
Mason Daugherty
|
7408378896 |
fix(code): disentangle version diagnostics for editable installs (#4816)
Editable installs conflated three distinct version facts, so `/version`, `--version`, and `doctor` could silently report a single number that hid stale metadata or a broken SDK dependency pin. Version diagnostics now separate the live source version, the installed distribution metadata version, and the `deepagents` requirement that `deepagents-code` declares — reporting the source version as primary for editable installs, showing the installed metadata alongside it when they drift, and flagging an actionable mismatch when the installed SDK metadata does not satisfy the declared requirement. --- A new structured `DistributionVersion`/`VersionReport` representation in `extras_info` is the single source of truth these surfaces render. `resolve_sdk_version()` is preserved as a thin compatibility wrapper so existing callers are untouched. - `/version`, `--version`, and `doctor` render the same facts: an editable SDK is now clearly identified (not just editable `deepagents-code`), source/metadata drift shows both versions, and an unsatisfied requirement (compared via `packaging.Requirement`) is surfaced as `required by deepagents-code: <version> — mismatch`. - `doctor` marks a dependency-requirement mismatch unhealthy, while treating source/metadata drift as informational since it is normal while editing SDK source. - Normal non-editable output is unchanged when all versions agree, and version collection stays fully offline and best-effort (no `uv`/`pip`/PyPI, no subprocess). - No package versions or dependency pins were changed. Two existing `doctor` integration tests now isolate the SDK requirement check so they stay deterministic regardless of the workspace's intentional prerelease pin; the mismatch and drift paths have dedicated new coverage. Made by [Open SWE](https://openswe.vercel.app/agents/1145d1a5-ba8a-abbb-e5b7-039e9c2a5b04) --------- Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com> |
||
|
Mason Daugherty
|
69520118a7 |
fix(code): keep task timers monotonic across nested subagent HITL (#4771)
Fixed dcode TUI `task` elapsed timers resetting when a nested subagent reached a human-in-the-loop approval checkpoint. --- A long-running `task [general-purpose]` row's elapsed timer reset to zero whenever a nested subagent hit a HITL approval checkpoint. The interrupt handler paused/resumed *every* tracked tool row, and `ToolCallMessage.pause_running()`/`set_running()` clear and reassign `_start_time` — so an unrelated nested child's (or sibling subagent's) approval restarted the outer `task` timers. This scopes pause/resume to only the rows an interrupt actually owns (matched by tool name + args via the new `_interrupt_owned_tool_rows` helper). Untracked nested-child interrupts now own no outer row, so outer and sibling `task` timers stay monotonic and completed `Took …` durations reflect full execution time. A tool awaiting its own initial approval still pauses then resumes as before. Made by [Open SWE](https://openswe.vercel.app/agents/5c0ae962-c16b-6e04-ada4-d4d76826adb9) --------- Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com> |
||
|
Mason Daugherty
|
4e618f07b4 |
fix(code): drop uv install tip from /version update hint (#4822)
The `/version` command's update-available line hard-coded `uv tool install -U deepagents-code`, which is stale guidance now that dcode auto-updates on relaunch and offers `/update` and `dcode update`. It now points at the relaunch/auto-update path when auto-update is enabled, and at `/update` or `dcode update` otherwise. --- Made by [Open SWE](https://openswe.vercel.app/agents/a8b54b7c-cc2f-e6cc-a034-61a8578b8a04) --------- Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com> |
||
|
Mason Daugherty
|
487b25f885 |
fix(code): keep goal criteria proposal when marker clear fails (#4785)
Fixed `/goal` criteria being discarded when clearing the completed criteria request from the thread failed. --- Follow-up to #4784. When a YOLO `/goal` criteria run succeeds, cleanup clears the `goal_criteria_request` marker before syncing but ignored a failed clear (checkpoint write failure). A stale marker still naming the just-completed request then made the sync (`_sync_goal_rubric_state_from_thread`) and restore (`_restore_goal_rubric_state`) paths strip the freshly generated `_pending_goal_*` payload, so no review/YOLO acceptance mounted and the criteria were silently lost. The marker now supersedes a proposal only when it names a *different* request than the pending proposal's request id. Made by [Open SWE](https://openswe.vercel.app/agents/6f2018c7-ffa3-ac12-4dab-8eed1142e4c4) --------- Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com> |
||
|
Mason Daugherty
|
c2c27d621b |
fix(code): quiet MCP auth-skip debug logging for known patterns (#4805)
Reduce noisy full-traceback DEBUG logs when an MCP server is skipped because it requires authentication; the actionable warning and a concise debug line remain. --- When an MCP server is skipped during discovery because it needs authentication — either a token-refresh (`reauth`) failure or an RFC 9728 `401` OAuth challenge — `deepagents-code` logged the entire anyio `ExceptionGroup` / httpx traceback at DEBUG via `exc_info`, on top of the actionable WARNING. For these already-classified, expected outcomes the traceback adds no diagnostic value and just floods debug output. These two recognized branches now emit a concise single-line DEBUG breadcrumb (the exception class name only). The full traceback is still logged for genuinely unknown discovery errors (the `else` branch) and for classifier failures, so real anomalies stay debuggable. The user-facing WARNING is unchanged apart from dropping the now-inaccurate "the original error is in debug logs" note from the reauth message. Made by [Open SWE](https://openswe.vercel.app/agents/a5ab799b-1747-0d65-16b6-ee0ccccee0c4) --------- Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com> |