⬆️(deps): Update langchain-litellm requirement from <0.6.0,>=0.4.0 to >=0.4.0,<0.7.0 in /packages/meeseeks_core - #91
Merged
bearlike merged 1 commit intoApr 1, 2026
Conversation
Updates the requirements on [langchain-litellm](https://github.com/langchain-ai/langchain-litellm) to permit the latest version. - [Release notes](https://github.com/langchain-ai/langchain-litellm/releases) - [Changelog](https://github.com/langchain-ai/langchain-litellm/blob/main/CHANGELOG.md) - [Commits](langchain-ai/langchain-litellm@v0.4.0...v0.6.2) --- updated-dependencies: - dependency-name: langchain-litellm dependency-version: 0.6.2 dependency-type: direct:production ... Signed-off-by: dependabot[bot] <support@github.com>
dependabot
Bot
added
dependencies
Codecov Report✅ All modified and coverable lines are covered by tests. Additional details and impacted files@@ Coverage Diff @@
## main #91 +/- ##
=======================================
Coverage 87.41% 87.41%
=======================================
Files 49 49
Lines 7272 7272
=======================================
Hits 6357 6357
Misses 915 915
🚀 New features to boost your workflow:
|
bearlike
deleted the
dependabot/pip/packages/meeseeks_core/langchain-litellm-gte-0.4.0-and-lt-0.7.0
branch
April 1, 2026 15:49
bearlike
pushed a commit
that referenced
this pull request
Apr 10, 2026
… >=0.4.0,<0.7.0 in /packages/meeseeks_core (#91) Updates the requirements on [langchain-litellm](https://github.com/langchain-ai/langchain-litellm) to permit the latest version. <details> <summary>Release notes</summary> <p><em>Sourced from <a href="https://github.com/langchain-ai/langchain-litellm/releases">langchain-litellm's releases</a>.</em></p> <blockquote> <h2>v0.6.2</h2> <h2><a href="https://github.com/langchain-ai/langchain-litellm/compare/v0.6.1...v0.6.2">0.6.2</a> (2026-03-24)</h2> <h3>Bug Fixes</h3> <ul> <li>exclude compromised litellm versions from deps (<a href="https://redirect.github.com/langchain-ai/langchain-litellm/issues/103">#103</a>) (<a href="https://github.com/langchain-ai/langchain-litellm/commit/701e1523eeeefa8826a298d3dc275d3ca7ff106e">701e152</a>)</li> </ul> </blockquote> </details> <details> <summary>Changelog</summary> <p><em>Sourced from <a href="https://github.com/langchain-ai/langchain-litellm/blob/main/CHANGELOG.md">langchain-litellm's changelog</a>.</em></p> <blockquote> <h2><a href="https://github.com/langchain-ai/langchain-litellm/compare/v0.6.1...v0.6.2">0.6.2</a> (2026-03-24)</h2> <h3>Bug Fixes</h3> <ul> <li>exclude compromised litellm versions from deps (<a href="https://redirect.github.com/langchain-ai/langchain-litellm/issues/103">#103</a>) (<a href="https://github.com/langchain-ai/langchain-litellm/commit/701e1523eeeefa8826a298d3dc275d3ca7ff106e">701e152</a>)</li> </ul> <h2><a href="https://github.com/langchain-ai/langchain-litellm/compare/v0.6.0...v0.6.1">0.6.1</a> (2026-03-01)</h2> <h3>Bug Fixes</h3> <ul> <li>clean up build artifacts to unblock PyPI publication (<a href="https://redirect.github.com/langchain-ai/langchain-litellm/issues/95">#95</a>) (<a href="https://github.com/langchain-ai/langchain-litellm/commit/02e74567ea3a22e18bf011a52e51aae7b2f2f5a5">02e7456</a>)</li> </ul> <h2><a href="https://github.com/langchain-ai/langchain-litellm/compare/v0.5.1...v0.6.0">0.6.0</a> (2026-03-01)</h2> <h3>Features</h3> <ul> <li>add LiteLLMEmbeddings and LiteLLMEmbeddingsRouter (<a href="https://redirect.github.com/langchain-ai/langchain-litellm/issues/88">#88</a>) (<a href="https://github.com/langchain-ai/langchain-litellm/commit/2bace9185918964a5e6047190ef86e9495ff7e64">2bace91</a>)</li> </ul> </blockquote> </details> <details> <summary>Commits</summary> <ul> <li><a href="https://github.com/langchain-ai/langchain-litellm/commit/33449cd71be4541add8895e43051b9a6358abcb1"><code>33449cd</code></a> chore(main): release 0.6.2 (<a href="https://redirect.github.com/langchain-ai/langchain-litellm/issues/104">#104</a>)</li> <li><a href="https://github.com/langchain-ai/langchain-litellm/commit/701e1523eeeefa8826a298d3dc275d3ca7ff106e"><code>701e152</code></a> fix: exclude compromised litellm versions from deps (<a href="https://redirect.github.com/langchain-ai/langchain-litellm/issues/103">#103</a>)</li> <li><a href="https://github.com/langchain-ai/langchain-litellm/commit/53965c454987f2b2271cec38aa34e560f4465f90"><code>53965c4</code></a> Bump the uv group across 1 directory with 2 updates (<a href="https://redirect.github.com/langchain-ai/langchain-litellm/issues/100">#100</a>)</li> <li><a href="https://github.com/langchain-ai/langchain-litellm/commit/9c62638fcd4e9e81c2d1e30fcae1d4ccd7406c9a"><code>9c62638</code></a> docs: update Advanced Features --> Embeddings section to include vers… (<a href="https://redirect.github.com/langchain-ai/langchain-litellm/issues/98">#98</a>)</li> <li><a href="https://github.com/langchain-ai/langchain-litellm/commit/e81b1b5708a1a5a5eba3343a040960c3a4f01d69"><code>e81b1b5</code></a> docs: update platform badge to OS Independent (<a href="https://redirect.github.com/langchain-ai/langchain-litellm/issues/97">#97</a>)</li> <li><a href="https://github.com/langchain-ai/langchain-litellm/commit/013698d441c2975edf4609f9204ccf484c971e32"><code>013698d</code></a> chore(main): release 0.6.1 (<a href="https://redirect.github.com/langchain-ai/langchain-litellm/issues/96">#96</a>)</li> <li><a href="https://github.com/langchain-ai/langchain-litellm/commit/02e74567ea3a22e18bf011a52e51aae7b2f2f5a5"><code>02e7456</code></a> fix: clean up build artifacts to unblock PyPI publication (<a href="https://redirect.github.com/langchain-ai/langchain-litellm/issues/95">#95</a>)</li> <li><a href="https://github.com/langchain-ai/langchain-litellm/commit/4990c7cce2d58bc2ef5c97d6d3ff7e1a6980369b"><code>4990c7c</code></a> chore: remove dist folder from version control and add to gitignore (<a href="https://redirect.github.com/langchain-ai/langchain-litellm/issues/94">#94</a>)</li> <li><a href="https://github.com/langchain-ai/langchain-litellm/commit/80eef94465aefd037ae80b6ef51541edb21df4b3"><code>80eef94</code></a> chore(main): release 0.6.0 (<a href="https://redirect.github.com/langchain-ai/langchain-litellm/issues/93">#93</a>)</li> <li><a href="https://github.com/langchain-ai/langchain-litellm/commit/c5d8fe121db13b15b8c728d40540eac47f1636d5"><code>c5d8fe1</code></a> chore(ci): configure release-please to bump minor version for features (<a href="https://redirect.github.com/langchain-ai/langchain-litellm/issues/92">#92</a>)</li> <li>Additional commits viewable in <a href="https://github.com/langchain-ai/langchain-litellm/compare/v0.4.0...v0.6.2">compare view</a></li> </ul> </details> <br /> 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) </details> Signed-off-by: dependabot[bot] <support@github.com> Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
bearlike
added a commit
that referenced
this pull request
Jun 20, 2026
…nator trace lane, agent-emitted result cards, honest run stats; async workspace indexing; external session cwd (#100) Root-caused from live run `run-02ad562781` (`/search?run=run-02ad562781&ws=ws-00f72e0c`): a fast-tier orchestrated run completed with an accurate synthesis but a blank instrument panel — `trace: []`, `results: []`, `confidence 0.0`, `sources_count 0`, `total_ms 0` (real elapsed ~170s, 33 tool calls). Mongo + Langfuse confirmed the root `scg-search` agent inlined ALL the work and never spawned a probe, and the entire event-log projection keyed off `sub_agent` events alone. This PR makes the run surface honest end-to-end and folds in the three companion regressions found during the same sweep. All wire changes are additive (no `OUTPUT_CONTRACT_VERSION` bump). ## New features - **Coordinator trace lane** (#95-A): root-agent tool activity projects onto the run event log live (`RunEventStreamer`) and at settle through ONE shared `CoordinatorTrace` projection — zero-probe runs render a real trace. Lines are digests only (tool id + capped input hint, `ok|error`); the tool's result payload is never read (connector returns can carry secrets). - **Agent-emitted result cards** (#95-B): new `scg_results` SessionTool in `mewbo_graph.plugins.scg` — transcript-as-transport: the tool only validates (≤50 entries, `extra="forbid"`, relevance/confidence 0..1) and the api projects entries → `result` events + `RunPayload.results` (stable `r-<run8>-<n>` ids = live↔settle dedup key). The `scg-search` playbook now emits the cards before the final synthesis (root-only). - **Honest settle metrics** (#95-C): `total_ms` computed `started_at→settle` on `run_done`, the payload, and the fail path; `confidence`/`sources_count` cover root-inline runs (data-bearing probe lanes ∪ emitted results' distinct sources) with documented provenance; unknown still suppresses, never fabricates. - **Results-page top band rebuilt** (#96): the query lives ONLY in the composer (the duplicated italic-mono echo is gone); `RunStats` joins only earned parts — a finished run never shows `0.0s` or `0 results` (snapshot elapsed falls back `total_ms` → `created_at→completed_at`); Copy-link + Configure sit in a calm right-aligned meta row; coordinator lanes render a `Workflow` glyph across ProgressStrip/RightRail/TraceDrawer, never a blank avatar or a misleading `0` chip. - **External session cwd** (#91): `POST /api/sessions` + `/query` accept an optional `cwd` behind `api.allow_external_cwd` (default OFF) via one `ExternalCwdPolicy` seam — explicit cwd wins over project resolution, persists in session context, and is honored on `/message` re-engagement and the diff endpoints. Lets external workspace managers (Grove) anchor sessions in their own worktrees without provided-path v_projects (which the reaper deletes). ## Stability - **Workspace create/edit is register-and-return** (#97, serious UX regression): the auto-map fan-out (live MCP descriptor builds + drift checks) ran in the Flask request thread — "Create Workspace" blocked for N MCP handshakes and read as browser-dependent indexing. Step 1 (virtual-config refresh) stays sync; everything else runs on a named daemon worker. `join_last_fan_out` gives route tests deterministic settling. Map jobs were already durable/background. - **Recents dedupe + unique cmdk identity** (#98-A): duplicate past queries no longer hover/select together — `CommandItem value` was the bare query text (cmdk identity collision); now `pastQueryKey` (run_id) + `dedupePastQueries` (normalized text, most-recent wins) shared by SearchBar + LandingPanel. - **Workspace card polish** (#98-B): single-line meta shelf by contract (`mt-auto flex-nowrap`, `flex-none` action cluster + "N past" pill, `min-w-0 overflow-hidden` avatar rail), footer pinned so rows in the grid read consistently. ## Docs - CLAUDE.md refresh across `agentic_search` (api + scg + console), the scg plugin suite, and `apps/mewbo_api`: coordinator-lane/`scg_results`/metrics decisions, the open `resolve_entity`-in-search gap (#95-D — gating entity tools on wiki-ctx presence is the future fix, not a manifest hack), RunStats honesty rules, the cmdk value-collision trap, the async fan-out invariant, and the #91 endpoint contract. ## Validation - Python: ruff clean, mypy clean (230 files), **4373 passed / 3 skipped** (includes 13 new `scg_results` tests, 12 new `external_cwd` tests, 2 new async fan-out tests, reenrich suite adapted to the async seam). - Console: vitest **342 passed / 4 skipped** (full suite; +14 new across ResultsPanel/SearchBar/LandingPanel), `tsc --noEmit` clean, eslint clean. - Caveat: validated locally + by test suites; not yet re-verified against the deployed stack (api/graph are bind-mounted — `docker compose up -d`; console needs `npm run build` + restart). Closes #95. Closes #96. Closes #97. Closes #98. Closes #91. Reviewed-on: https://git.hurricane.home/bearlike/Assistant/pulls/100
bearlike
added a commit
that referenced
this pull request
Jun 20, 2026
…nator trace lane, agent-emitted result cards, honest run stats; async workspace indexing; external session cwd (#100) Root-caused from live run `run-02ad562781` (`/search?run=run-02ad562781&ws=ws-00f72e0c`): a fast-tier orchestrated run completed with an accurate synthesis but a blank instrument panel — `trace: []`, `results: []`, `confidence 0.0`, `sources_count 0`, `total_ms 0` (real elapsed ~170s, 33 tool calls). Mongo + Langfuse confirmed the root `scg-search` agent inlined ALL the work and never spawned a probe, and the entire event-log projection keyed off `sub_agent` events alone. This PR makes the run surface honest end-to-end and folds in the three companion regressions found during the same sweep. All wire changes are additive (no `OUTPUT_CONTRACT_VERSION` bump). ## New features - **Coordinator trace lane** (#95-A): root-agent tool activity projects onto the run event log live (`RunEventStreamer`) and at settle through ONE shared `CoordinatorTrace` projection — zero-probe runs render a real trace. Lines are digests only (tool id + capped input hint, `ok|error`); the tool's result payload is never read (connector returns can carry secrets). - **Agent-emitted result cards** (#95-B): new `scg_results` SessionTool in `mewbo_graph.plugins.scg` — transcript-as-transport: the tool only validates (≤50 entries, `extra="forbid"`, relevance/confidence 0..1) and the api projects entries → `result` events + `RunPayload.results` (stable `r-<run8>-<n>` ids = live↔settle dedup key). The `scg-search` playbook now emits the cards before the final synthesis (root-only). - **Honest settle metrics** (#95-C): `total_ms` computed `started_at→settle` on `run_done`, the payload, and the fail path; `confidence`/`sources_count` cover root-inline runs (data-bearing probe lanes ∪ emitted results' distinct sources) with documented provenance; unknown still suppresses, never fabricates. - **Results-page top band rebuilt** (#96): the query lives ONLY in the composer (the duplicated italic-mono echo is gone); `RunStats` joins only earned parts — a finished run never shows `0.0s` or `0 results` (snapshot elapsed falls back `total_ms` → `created_at→completed_at`); Copy-link + Configure sit in a calm right-aligned meta row; coordinator lanes render a `Workflow` glyph across ProgressStrip/RightRail/TraceDrawer, never a blank avatar or a misleading `0` chip. - **External session cwd** (#91): `POST /api/sessions` + `/query` accept an optional `cwd` behind `api.allow_external_cwd` (default OFF) via one `ExternalCwdPolicy` seam — explicit cwd wins over project resolution, persists in session context, and is honored on `/message` re-engagement and the diff endpoints. Lets external workspace managers (Grove) anchor sessions in their own worktrees without provided-path v_projects (which the reaper deletes). ## Stability - **Workspace create/edit is register-and-return** (#97, serious UX regression): the auto-map fan-out (live MCP descriptor builds + drift checks) ran in the Flask request thread — "Create Workspace" blocked for N MCP handshakes and read as browser-dependent indexing. Step 1 (virtual-config refresh) stays sync; everything else runs on a named daemon worker. `join_last_fan_out` gives route tests deterministic settling. Map jobs were already durable/background. - **Recents dedupe + unique cmdk identity** (#98-A): duplicate past queries no longer hover/select together — `CommandItem value` was the bare query text (cmdk identity collision); now `pastQueryKey` (run_id) + `dedupePastQueries` (normalized text, most-recent wins) shared by SearchBar + LandingPanel. - **Workspace card polish** (#98-B): single-line meta shelf by contract (`mt-auto flex-nowrap`, `flex-none` action cluster + "N past" pill, `min-w-0 overflow-hidden` avatar rail), footer pinned so rows in the grid read consistently. ## Docs - CLAUDE.md refresh across `agentic_search` (api + scg + console), the scg plugin suite, and `apps/mewbo_api`: coordinator-lane/`scg_results`/metrics decisions, the open `resolve_entity`-in-search gap (#95-D — gating entity tools on wiki-ctx presence is the future fix, not a manifest hack), RunStats honesty rules, the cmdk value-collision trap, the async fan-out invariant, and the #91 endpoint contract. ## Validation - Python: ruff clean, mypy clean (230 files), **4373 passed / 3 skipped** (includes 13 new `scg_results` tests, 12 new `external_cwd` tests, 2 new async fan-out tests, reenrich suite adapted to the async seam). - Console: vitest **342 passed / 4 skipped** (full suite; +14 new across ResultsPanel/SearchBar/LandingPanel), `tsc --noEmit` clean, eslint clean. - Caveat: validated locally + by test suites; not yet re-verified against the deployed stack (api/graph are bind-mounted — `docker compose up -d`; console needs `npm run build` + restart). Closes #95. Closes #96. Closes #97. Closes #98. Closes #91. Reviewed-on: https://git.hurricane.home/bearlike/Assistant/pulls/100
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Updates the requirements on langchain-litellm to permit the latest version.
Release notes
Sourced from langchain-litellm's releases.
Changelog
Sourced from langchain-litellm's changelog.
Commits
33449cdchore(main): release 0.6.2 (#104)701e152fix: exclude compromised litellm versions from deps (#103)53965c4Bump the uv group across 1 directory with 2 updates (#100)9c62638docs: update Advanced Features --> Embeddings section to include vers… (#98)e81b1b5docs: update platform badge to OS Independent (#97)013698dchore(main): release 0.6.1 (#96)02e7456fix: clean up build artifacts to unblock PyPI publication (#95)4990c7cchore: remove dist folder from version control and add to gitignore (#94)80eef94chore(main): release 0.6.0 (#93)c5d8fe1chore(ci): configure release-please to bump minor version for features (#92)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 commands and options
You can trigger Dependabot actions by commenting on this PR:
@dependabot rebasewill rebase this PR@dependabot recreatewill recreate this PR, overwriting any edits that have been made to it@dependabot show <dependency name> ignore conditionswill show all of the ignore conditions of the specified dependency@dependabot ignore this major versionwill 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 versionwill 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 dependencywill close this PR and stop Dependabot creating any more for this dependency (unless you reopen the PR or upgrade to it yourself)