⬆️ Bump the uv group across 1 directory with 2 updates - #102
Merged
Merged
Conversation
Bumps the uv group with 2 updates in the / directory: [cryptography](https://github.com/pyca/cryptography) and [langchain-core](https://github.com/langchain-ai/langchain). Updates `cryptography` from 46.0.5 to 46.0.6 - [Changelog](https://github.com/pyca/cryptography/blob/main/CHANGELOG.rst) - [Commits](pyca/cryptography@46.0.5...46.0.6) Updates `langchain-core` from 1.2.11 to 1.2.22 - [Release notes](https://github.com/langchain-ai/langchain/releases) - [Commits](langchain-ai/langchain@langchain-core==1.2.11...langchain-core==1.2.22) --- updated-dependencies: - dependency-name: cryptography dependency-version: 46.0.6 dependency-type: indirect dependency-group: uv - dependency-name: langchain-core dependency-version: 1.2.22 dependency-type: indirect dependency-group: uv ... 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 #102 +/- ##
=======================================
Coverage 87.10% 87.10%
=======================================
Files 52 52
Lines 8462 8462
=======================================
Hits 7371 7371
Misses 1091 1091
🚀 New features to boost your workflow:
|
bearlike
pushed a commit
that referenced
this pull request
Apr 10, 2026
Bumps the uv group with 2 updates in the / directory: [cryptography](https://github.com/pyca/cryptography) and [langchain-core](https://github.com/langchain-ai/langchain). Updates `cryptography` from 46.0.5 to 46.0.6 <details> <summary>Changelog</summary> <p><em>Sourced from <a href="https://github.com/pyca/cryptography/blob/main/CHANGELOG.rst">cryptography's changelog</a>.</em></p> <blockquote> <p>46.0.6 - 2026-03-25</p> <pre><code> * **SECURITY ISSUE**: Fixed a bug where name constraints were not applied to peer names during verification when the leaf certificate contains a wildcard DNS SAN. Ordinary X.509 topologies are not affected by this bug, including those used by the Web PKI. Credit to **Oleh Konko (1seal)** for reporting the issue. **CVE-2026-34073** <p>.. _v46-0-5:<br /> </code></pre></p> </blockquote> </details> <details> <summary>Commits</summary> <ul> <li><a href="https://github.com/pyca/cryptography/commit/91d728897bdad30cd5c79a2b23e207f1f050d587"><code>91d7288</code></a> Cherry-pick <a href="https://redirect.github.com/pyca/cryptography/issues/14542">#14542</a> (<a href="https://redirect.github.com/pyca/cryptography/issues/14543">#14543</a>)</li> <li>See full diff in <a href="https://github.com/pyca/cryptography/compare/46.0.5...46.0.6">compare view</a></li> </ul> </details> <br /> Updates `langchain-core` from 1.2.11 to 1.2.22 <details> <summary>Release notes</summary> <p><em>Sourced from <a href="https://github.com/langchain-ai/langchain/releases">langchain-core's releases</a>.</em></p> <blockquote> <h2>langchain-core==1.2.22</h2> <p>Changes since langchain-core==1.2.21</p> <p>release(core): 1.2.22 (<a href="https://redirect.github.com/langchain-ai/langchain/issues/36201">#36201</a>) fix(core): validate paths in <code>prompt.save</code> and <code>load_prompt</code>, deprecate methods (<a href="https://redirect.github.com/langchain-ai/langchain/issues/36200">#36200</a>)</p> <h2>langchain-core==1.2.21</h2> <p>Changes since langchain-core==1.2.20</p> <p>release(core): 1.2.21 (<a href="https://redirect.github.com/langchain-ai/langchain/issues/36179">#36179</a>) fix(core,model-profiles): add missing <code>ModelProfile</code> fields, warn on schema drift (<a href="https://redirect.github.com/langchain-ai/langchain/issues/36129">#36129</a>) chore(core): remove stale blockbuster allowlist for deleted context module (<a href="https://redirect.github.com/langchain-ai/langchain/issues/36168">#36168</a>) ci: suppress pytest streaming output in CI (<a href="https://redirect.github.com/langchain-ai/langchain/issues/36092">#36092</a>)</p> <h2>langchain-core==1.2.20</h2> <p>Changes since langchain-core==1.2.19</p> <p>release(core): 1.2.20 (<a href="https://redirect.github.com/langchain-ai/langchain/issues/36085">#36085</a>) fix(core): trace invocation params in metadata (<a href="https://redirect.github.com/langchain-ai/langchain/issues/36080">#36080</a>) feat: Add LangSmith integration metadata to create_agent and init_chat_model (<a href="https://redirect.github.com/langchain-ai/langchain/issues/35810">#35810</a>) feat(core): harden anti-ssrf (<a href="https://redirect.github.com/langchain-ai/langchain/issues/35960">#35960</a>) ci: avoid unnecessary dep installs in lint targets (<a href="https://redirect.github.com/langchain-ai/langchain/issues/36046">#36046</a>) docs(core): document <code>base_url</code> in mermaid api (<a href="https://redirect.github.com/langchain-ai/langchain/issues/35961">#35961</a>) chore: bump orjson from 3.11.5 to 3.11.6 in /libs/core (<a href="https://redirect.github.com/langchain-ai/langchain/issues/35805">#35805</a>) chore: housekeeping (<a href="https://redirect.github.com/langchain-ai/langchain/issues/35850">#35850</a>)</p> <h2>langchain-core==1.2.19</h2> <p>Changes since langchain-core==1.2.18</p> <p>release(core): 1.2.19 (<a href="https://redirect.github.com/langchain-ai/langchain/issues/35832">#35832</a>) chore(core): move BaseCrossEncoder to langchain-core (<a href="https://redirect.github.com/langchain-ai/langchain/issues/35809">#35809</a>) chore: bump tornado from 6.5.2 to 6.5.5 in /libs/core (<a href="https://redirect.github.com/langchain-ai/langchain/issues/35775">#35775</a>)</p> <h2>langchain-core==1.2.18</h2> <p>Changes since langchain-core==1.2.17</p> <p>release(core): 1.2.18 (<a href="https://redirect.github.com/langchain-ai/langchain/issues/35704">#35704</a>) fix(core): fix double backticks in deprecation docstring for alternative_import (<a href="https://redirect.github.com/langchain-ai/langchain/issues/35658">#35658</a>) fix(core): preserve default_factory when generating tool call schema (<a href="https://redirect.github.com/langchain-ai/langchain/issues/35550">#35550</a>) feat(openai): support tool search (<a href="https://redirect.github.com/langchain-ai/langchain/issues/35582">#35582</a>) chore: bump the minor-and-patch group across 3 directories with 7 updates (<a href="https://redirect.github.com/langchain-ai/langchain/issues/35605">#35605</a>)</p> <h2>langchain-core==1.2.17</h2> <p>Changes since langchain-core==1.2.16</p> <p>release(core): 1.2.17 (<a href="https://redirect.github.com/langchain-ai/langchain/issues/35527">#35527</a>) fix(core): extract usage metadata from serialized tracer message outputs (<a href="https://redirect.github.com/langchain-ai/langchain/issues/35526">#35526</a>) chore: bump the langchain-deps group across 3 directories with 7 updates (<a href="https://redirect.github.com/langchain-ai/langchain/issues/35513">#35513</a>) chore: bump the langchain-deps group across 3 directories with 14 updates (<a href="https://redirect.github.com/langchain-ai/langchain/issues/35441">#35441</a>)</p> <!-- raw HTML omitted --> </blockquote> <p>... (truncated)</p> </details> <details> <summary>Commits</summary> <ul> <li><a href="https://github.com/langchain-ai/langchain/commit/d22df94537e4267f72dc1bbfc8e3849baf20d9f7"><code>d22df94</code></a> release(core): 1.2.22 (<a href="https://redirect.github.com/langchain-ai/langchain/issues/36201">#36201</a>)</li> <li><a href="https://github.com/langchain-ai/langchain/commit/27add913474e01e33bededf4096151130ba0d47c"><code>27add91</code></a> fix(core): validate paths in <code>prompt.save</code> and <code>load_prompt</code>, deprecate metho...</li> <li><a href="https://github.com/langchain-ai/langchain/commit/7563fceb40ce31165524f3f57ec65e487c02b1a7"><code>7563fce</code></a> chore(model-profiles): refresh model profile data (<a href="https://redirect.github.com/langchain-ai/langchain/issues/36195">#36195</a>)</li> <li><a href="https://github.com/langchain-ai/langchain/commit/3e64c255b84b283b3a65216b19b9838734258c96"><code>3e64c25</code></a> chore: use repo permissions instead of org membership for maintainer override...</li> <li><a href="https://github.com/langchain-ai/langchain/commit/1778b082ecd64a9dedd48674d874ca1bfcbe4c7d"><code>1778b08</code></a> chore(partners): bump <code>langchain-core</code> min to <code>1.2.21</code> (<a href="https://redirect.github.com/langchain-ai/langchain/issues/36183">#36183</a>)</li> <li><a href="https://github.com/langchain-ai/langchain/commit/ad574fce0d52740c249b0db7bde871d779ffb93d"><code>ad574fc</code></a> fix(openai): bump min core version (<a href="https://redirect.github.com/langchain-ai/langchain/issues/36180">#36180</a>)</li> <li><a href="https://github.com/langchain-ai/langchain/commit/19f81cf6f1d73f7adf156491ba0617497a526b8c"><code>19f81cf</code></a> release(core): 1.2.21 (<a href="https://redirect.github.com/langchain-ai/langchain/issues/36179">#36179</a>)</li> <li><a href="https://github.com/langchain-ai/langchain/commit/6d07ef28a7023dc7b832fe52862f7a6fc0a187f3"><code>6d07ef2</code></a> release(openai): 1.1.12 (<a href="https://redirect.github.com/langchain-ai/langchain/issues/36178">#36178</a>)</li> <li><a href="https://github.com/langchain-ai/langchain/commit/2f64d80cc65091985873c339ca76a59af7baf739"><code>2f64d80</code></a> fix(core,model-profiles): add missing <code>ModelProfile</code> fields, warn on schema d...</li> <li><a href="https://github.com/langchain-ai/langchain/commit/5ffece5c033365baf4a3df52ffed5c6bfbed27ee"><code>5ffece5</code></a> chore(core): remove stale blockbuster allowlist for deleted context module (#...</li> <li>Additional commits viewable in <a href="https://github.com/langchain-ai/langchain/compare/langchain-core==1.2.11...langchain-core==1.2.22">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 <dependency name> major version` will close this group update PR and stop Dependabot creating any more for the specific dependency's major version (unless you unignore this specific dependency's major version or upgrade to it yourself) - `@dependabot ignore <dependency name> minor version` will close this group update PR and stop Dependabot creating any more for the specific dependency's minor version (unless you unignore this specific dependency's minor version or upgrade to it yourself) - `@dependabot ignore <dependency name>` will close this group update PR and stop Dependabot creating any more for the specific dependency (unless you unignore this specific dependency or upgrade to it yourself) - `@dependabot unignore <dependency name>` will remove all of the ignore conditions of the specified dependency - `@dependabot unignore <dependency name> <ignore condition>` will remove the ignore condition of the specified dependency and ignore conditions You can disable automated security fix PRs for this repo from the [Security Alerts page](https://github.com/bearlike/Assistant/network/alerts). </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
…— agent-aware scg_results projection + per-result confidence (#102) (#103) Implements #102 — search probes now return their findings as structured result cards that render on the search page, with the richest per-item detail the connector yields (title, source, snippet, url, kind, relevance, **confidence**). ## New features - **Probe-emitted result cards.** Each `scg-path-probe` emits the hits its pathway grounded through the existing `scg_results` validate-only tool (already bound to probes via the capability gate — **no new transport, no new tool**), once, right before its evidence block. The root's step 5.5 narrows to inline-grounded hits so probes own their cards (playbook-level dedup). Probe emits project as `result` SSE events + `RunPayload.results` with probe-salted stable ids `r-<run8>-<agent8>-<n>` — collision-free across concurrent emitters, deterministic live↔settle (same transcript event ⇒ same id ⇒ dedup holds). - **Per-result `confidence` on the wire** (additive): `SearchResult.confidence` carries the emitting agent's per-card certainty verbatim (BE `schemas.py` + FE `agenticSearch.ts`); the existing relevance fold is preserved. `ResultCard` renders a mono `%` chip beside the relevance dot only when present — honest-or-absent, never an invented 0%. ## Stability — corrected root cause The #95 premise "*probes run in their own sessions; their tool_results never appear here*" is **false**: a child loop inherits the parent's `event_logger` (`mewbo_core/agent_context.py:85`) and every `tool_result` payload is stamped with its `agent_id` (`tool_use_loop.py:2305`). Verified live in Mongo — e.g. session `eb132add…` (run-35a4f94e39) carries **89 probe tool_results** in the root transcript; 8/8 sampled search runs agree. Consequences fixed: - **Coordinator-lane mislabeling (live bug):** probe tool calls were being digested into the coordinator lane as root activity. Live streamer (`_probe_emitter`/`_project_probe_tool`) and settle (`probe_ids` threaded through `_build_coordinator_lines`/`_assign_lane_slots`/`_build_results`) now classify every `tool_result` by `agent_id ∈ probe lanes` — same classifier both sides, so live and settle agree. - **Id collisions:** a probe emit would previously mint the same `r-<run8>-<n>` ids as the root's and be silently dropped by the dedup. **Deliberate non-goal:** `scg_results` stays **non-terminal** for probes — the probe's terminal is its `EVIDENCE`/`NO DATA` stop summary (the #86 seam feeding per-lane evidence + synthesis metrics); a terminal emit would erase it. ## Validation (observed locally) - `pytest tests` — **3561 passed** (incl. 4 new cases: probe live attribution + settle parity, coordinator-pollution regression, mixed-emit id-collision regression, confidence wire semantics). - `ruff check .` — All checks passed; `make typecheck` — Success: no issues found in 230 source files. - Console: `npx tsc --noEmit` exit 0, eslint exit 0, `vitest run src/components/agentic_search` — 24 passed (incl. the new confidence-chip test). - **Caveat:** validated via unit/contract tests over real-shaped transcripts (mirroring live Mongo event shapes); a live end-to-end LLM search run was not exercised. Probe emission also depends on the model following the updated playbook — the projection handles zero-emit probes gracefully (no behavior change for them). ## Docs `agentic_search/scg/CLAUDE.md` + `plugins/scg/CLAUDE.md` correct the false own-sessions premise and record the classification + id-salting invariants; console `agentic_search/CLAUDE.md` notes the per-card confidence stance. Closes #102 Reviewed-on: https://git.hurricane.home/bearlike/Assistant/pulls/103 Co-authored-by: Krishnakanth Alagiri <mail@kanth.tech> Co-committed-by: Krishnakanth Alagiri <mail@kanth.tech>
bearlike
added a commit
that referenced
this pull request
Jun 20, 2026
…— agent-aware scg_results projection + per-result confidence (#102) (#103) Implements #102 — search probes now return their findings as structured result cards that render on the search page, with the richest per-item detail the connector yields (title, source, snippet, url, kind, relevance, **confidence**). ## New features - **Probe-emitted result cards.** Each `scg-path-probe` emits the hits its pathway grounded through the existing `scg_results` validate-only tool (already bound to probes via the capability gate — **no new transport, no new tool**), once, right before its evidence block. The root's step 5.5 narrows to inline-grounded hits so probes own their cards (playbook-level dedup). Probe emits project as `result` SSE events + `RunPayload.results` with probe-salted stable ids `r-<run8>-<agent8>-<n>` — collision-free across concurrent emitters, deterministic live↔settle (same transcript event ⇒ same id ⇒ dedup holds). - **Per-result `confidence` on the wire** (additive): `SearchResult.confidence` carries the emitting agent's per-card certainty verbatim (BE `schemas.py` + FE `agenticSearch.ts`); the existing relevance fold is preserved. `ResultCard` renders a mono `%` chip beside the relevance dot only when present — honest-or-absent, never an invented 0%. ## Stability — corrected root cause The #95 premise "*probes run in their own sessions; their tool_results never appear here*" is **false**: a child loop inherits the parent's `event_logger` (`mewbo_core/agent_context.py:85`) and every `tool_result` payload is stamped with its `agent_id` (`tool_use_loop.py:2305`). Verified live in Mongo — e.g. session `eb132add…` (run-35a4f94e39) carries **89 probe tool_results** in the root transcript; 8/8 sampled search runs agree. Consequences fixed: - **Coordinator-lane mislabeling (live bug):** probe tool calls were being digested into the coordinator lane as root activity. Live streamer (`_probe_emitter`/`_project_probe_tool`) and settle (`probe_ids` threaded through `_build_coordinator_lines`/`_assign_lane_slots`/`_build_results`) now classify every `tool_result` by `agent_id ∈ probe lanes` — same classifier both sides, so live and settle agree. - **Id collisions:** a probe emit would previously mint the same `r-<run8>-<n>` ids as the root's and be silently dropped by the dedup. **Deliberate non-goal:** `scg_results` stays **non-terminal** for probes — the probe's terminal is its `EVIDENCE`/`NO DATA` stop summary (the #86 seam feeding per-lane evidence + synthesis metrics); a terminal emit would erase it. ## Validation (observed locally) - `pytest tests` — **3561 passed** (incl. 4 new cases: probe live attribution + settle parity, coordinator-pollution regression, mixed-emit id-collision regression, confidence wire semantics). - `ruff check .` — All checks passed; `make typecheck` — Success: no issues found in 230 source files. - Console: `npx tsc --noEmit` exit 0, eslint exit 0, `vitest run src/components/agentic_search` — 24 passed (incl. the new confidence-chip test). - **Caveat:** validated via unit/contract tests over real-shaped transcripts (mirroring live Mongo event shapes); a live end-to-end LLM search run was not exercised. Probe emission also depends on the model following the updated playbook — the projection handles zero-emit probes gracefully (no behavior change for them). ## Docs `agentic_search/scg/CLAUDE.md` + `plugins/scg/CLAUDE.md` correct the false own-sessions premise and record the classification + id-salting invariants; console `agentic_search/CLAUDE.md` notes the per-card confidence stance. Closes #102 Reviewed-on: https://git.hurricane.home/bearlike/Assistant/pulls/103 Co-authored-by: Krishnakanth Alagiri <mail@kanth.tech> Co-committed-by: Krishnakanth Alagiri <mail@kanth.tech>
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.
Bumps the uv group with 2 updates in the / directory: cryptography and langchain-core.
Updates
cryptographyfrom 46.0.5 to 46.0.6Changelog
Sourced from cryptography's changelog.
Commits
91d7288Cherry-pick #14542 (#14543)Updates
langchain-corefrom 1.2.11 to 1.2.22Release notes
Sourced from langchain-core's releases.
... (truncated)
Commits
d22df94release(core): 1.2.22 (#36201)27add91fix(core): validate paths inprompt.saveandload_prompt, deprecate metho...7563fcechore(model-profiles): refresh model profile data (#36195)3e64c25chore: use repo permissions instead of org membership for maintainer override...1778b08chore(partners): bumplangchain-coremin to1.2.21(#36183)ad574fcfix(openai): bump min core version (#36180)19f81cfrelease(core): 1.2.21 (#36179)6d07ef2release(openai): 1.1.12 (#36178)2f64d80fix(core,model-profiles): add missingModelProfilefields, warn on schema d...5ffece5chore(core): remove stale blockbuster allowlist for deleted context module (#...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 <dependency name> major versionwill close this group update PR and stop Dependabot creating any more for the specific dependency's major version (unless you unignore this specific dependency's major version or upgrade to it yourself)@dependabot ignore <dependency name> minor versionwill close this group update PR and stop Dependabot creating any more for the specific dependency's minor version (unless you unignore this specific dependency's minor version or upgrade to it yourself)@dependabot ignore <dependency name>will close this group update PR and stop Dependabot creating any more for the specific dependency (unless you unignore this specific dependency or upgrade to it yourself)@dependabot unignore <dependency name>will remove all of the ignore conditions of the specified dependency@dependabot unignore <dependency name> <ignore condition>will remove the ignore condition of the specified dependency and ignore conditionsYou can disable automated security fix PRs for this repo from the Security Alerts page.