CodeQual

Evolution Advisory

Project: langchain-ai/langchain

Period: Jan 27, 2023 at 04:57 PM to Mar 14, 2026 at 03:09 AM

Advisory ID: a9490167b7d4dedb

Generated: Mar 15, 2026 at 02:03 AM

Executive Summary

5
Significant Changes
3
Areas Affected
23
Patterns Matched
0
New Observations

Affected areas: ⚙️ CI / Build 🚀 Deployment 📝 Version Control

Based on 20 prior commits

What EE Can See

5 connected

⚙️
CI / Build
via GitHub Actions
Active
📝
Version Control
via Git
Active
🚀
Deployment
via GitHub Releases
Active
🔒
Security
via GitHub Security
Platform Mismatch
GITLAB_TOKEN is set but remote points to github. Setup guide →
🧪
Testing
via Jest
Connected
Token set. This data is analyzed automatically when running via GitHub Action or GitLab CI. Setup guide →

Key Findings

What Changed in Your Codebase

We've detected 5 changes that differ from your project's normal patterns. Each change shows what typically happens versus what we observed this time.

0 of 5 resolved
⚙️
Build Duration
CI / Build
What this means: Build took longer than usual.
Typical:
9.50
This Time:
3,306.0
889.4x above typical range
Trigger: af15037a
→ Still elevated (latest deviation: 27.6σ)
Supporting Evidence
⚠️ Action Required

when CI builds and code changes happen together, change focus and build time tend to move together.

What this means: Builds are taking longer. Slower CI feedback loops reduce developer productivity and delay catching issues. Escalated from Worth Monitoring — multiple correlated patterns converge on the same signal families. Changes span files that don't normally change together, suggesting cross-cutting concerns that may be harder to test. Escalated from Worth Monitoring — multiple correlated patterns converge on the same signal families.
Recommendation: Profile the build pipeline to identify bottlenecks. Check for newly added expensive tests or build steps. Review whether these cross-cutting changes have adequate test coverage.
⚠️ Action Required

when CI builds and code changes happen together, file count and build time tend to move together.

What this means: Commits are touching more files than usual, increasing review burden and risk of regressions. Escalated from Worth Monitoring — multiple correlated patterns converge on the same signal families.
Recommendation: Monitor PR sizes. If this persists, investigate whether large refactors need better decomposition.
⚠️ Action Required

when CI builds and code changes happen together, novelty of file pairings and build time tend to move together.

What this means: Files that don't normally change together are being modified in the same commits. This indicates novel, untested interactions that may introduce bugs. Escalated from Needs Attention — multiple correlated patterns converge on the same signal families. Builds are taking longer. Slower CI feedback loops reduce developer productivity and delay catching issues. Escalated from Worth Monitoring — multiple correlated patterns converge on the same signal families.
Recommendation: Investigate which files are being combined unexpectedly. Prioritize testing these changes. Profile the build pipeline to identify bottlenecks. Check for newly added expensive tests or build steps.
Show 1 more supporting evidence
👁️ Worth Monitoring

when CI builds occur, build time tends to decrease.

What this means: Builds are taking longer. Slower CI feedback loops reduce developer productivity and delay catching issues.
Recommendation: Profile the build pipeline to identify bottlenecks. Check for newly added expensive tests or build steps.
Drift Investigation Prompt 
Development pattern shift detected in CI / Build.\n\nSIGNAL: Build Duration is 889.4x above the typical baseline (observed: 3,306.0, typical: 9.50).\nTRIGGER COMMIT: af15037a — \n\nRECENT COMMITS (20 total, showing top 5):\n  dcfd9c0e — fix(infra): use `langchain_v1` for dev container deps (#3453 (3 files)\n  5517ef37 — docs(core): add docstrings to internal helper functions (#34 (7 files)\n  0b917742 — fix(xai): stream usage metadata by default (#34531)

 (5 files)\n  458a1865 — chore(core): Update LangChainTracer to use Pydantic v2 metho (13 files)\n  659eab26 — release(core): 1.2.6 (#34586)

 (3 files)\n  ... and 15 more commits\n\nCORRELATED PATTERNS:\n  [CRITICAL] when CI builds and code changes happen together, change focus and build time tend to move together.\n    → Profile the build pipeline to identify bottlenecks. Check for newly added expensive tests or build steps.\n    → Review whether these cross-cutting changes have adequate test coverage.\n  [CRITICAL] when CI builds and code changes happen together, file count and build time tend to move together.\n    → Monitor PR sizes. If this persists, investigate whether large refactors need better decomposition.\n  [CRITICAL] when CI builds and code changes happen together, novelty of file pairings and build time tend to move together.\n    → Investigate which files are being combined unexpectedly. Prioritize testing these changes.\n    → Profile the build pipeline to identify bottlenecks. Check for newly added expensive tests or build steps.\n  [INFO] when CI builds occur, build time tends to decrease.\n    → Confirm test coverage hasn't decreased alongside faster builds.\n\nINVESTIGATE:\n1. Was this change intentional or did the AI drift from goals?\n2. Review commit af15037a — what specifically caused the deviation?\n3. Suggest a course correction (not a bug fix — a realignment).\n\nAFTER FIX:\nRun `evo analyze . --verify` to re-analyze and compare against this run.\nIf the change was intentional, no fix needed — accept it in the report.
Use with: Cursor — paste in chat Claude Code — paste in terminal Copilot — paste in chat panel
After investigation:
  1. AI suggests fixes → apply the changes to your code
  2. Run evo analyze . --verify to re-analyze and compare against this run
  3. If the change was intentional, click Accept above to dismiss it
Show technical details

The run duration for this change was 3,306.0. Historically, similar changes had a value of 9.50 ± 2.50.

🚀
Release Cadence
Deployment
What this means: Longer time between releases than usual.
Typical:
0.4990
This Time:
145.8
220.0x above typical range
Trigger: 7234fd0f
↘ Returned to baseline
Supporting Evidence
⚠️ Action Required

when deployments and code changes happen together, file count and release frequency tend to move together.

What this means: Commits are touching more files than usual, increasing review burden and risk of regressions. Escalated from Worth Monitoring — multiple correlated patterns converge on the same signal families.
Recommendation: Monitor PR sizes. If this persists, investigate whether large refactors need better decomposition.
⚠️ Action Required

when deployments and code changes happen together, change focus and release frequency tend to move together.

What this means: Time between releases is increasing. This could indicate a bottleneck in the release process or accumulating risk in larger releases. Escalated from Worth Monitoring — multiple correlated patterns converge on the same signal families.
Recommendation: Check if process changes or staffing issues are delaying releases.
👁️ Worth Monitoring

when deployments occur, release frequency tends to increase.

What this means: Time between releases is increasing. This could indicate a bottleneck in the release process or accumulating risk in larger releases.
Recommendation: Check if process changes or staffing issues are delaying releases.
Drift Investigation Prompt 
Development pattern shift detected in Deployment.\n\nSIGNAL: Release Cadence is 220.0x above the typical baseline (observed: 145.8, typical: 0.4990).\nTRIGGER COMMIT: 7234fd0f — \n\nRECENT COMMITS (20 total, showing top 5):\n  dcfd9c0e — fix(infra): use `langchain_v1` for dev container deps (#3453 (3 files)\n  5517ef37 — docs(core): add docstrings to internal helper functions (#34 (7 files)\n  0b917742 — fix(xai): stream usage metadata by default (#34531)

 (5 files)\n  458a1865 — chore(core): Update LangChainTracer to use Pydantic v2 metho (13 files)\n  659eab26 — release(core): 1.2.6 (#34586)

 (3 files)\n  ... and 15 more commits\n\nCORRELATED PATTERNS:\n  [CRITICAL] when deployments and code changes happen together, file count and release frequency tend to move together.\n    → Monitor PR sizes. If this persists, investigate whether large refactors need better decomposition.\n  [CRITICAL] when deployments and code changes happen together, change focus and release frequency tend to move together.\n    → Check if process changes or staffing issues are delaying releases.\n  [WATCH] when deployments occur, release frequency tends to increase.\n    → Check if process changes or staffing issues are delaying releases.\n\nINVESTIGATE:\n1. Was this change intentional or did the AI drift from goals?\n2. Review commit 7234fd0f — what specifically caused the deviation?\n3. Suggest a course correction (not a bug fix — a realignment).\n\nAFTER FIX:\nRun `evo analyze . --verify` to re-analyze and compare against this run.\nIf the change was intentional, no fix needed — accept it in the report.
Use with: Cursor — paste in chat Claude Code — paste in terminal Copilot — paste in chat panel
After investigation:
  1. AI suggests fixes → apply the changes to your code
  2. Run evo analyze . --verify to re-analyze and compare against this run
  3. If the change was intentional, click Accept above to dismiss it
Show technical details

The release cadence hours for this change was 145.8. Historically, similar changes had a value of 0.4990 ± 0.4454.

📝
Co-change Novelty
Version Control
What this means: Unusually low novelty — changes are more repetitive than normal, touching only well-known file combinations.
Typical:
0.9924
This Time:
0.0000
88.4x below typical range
Trigger: cdf140e7 release(core): 1.2.17 (#35527)
↘ Returned to baseline
Supporting Evidence
⚠️ Action Required

when CI builds and code changes happen together, novelty of file pairings and build time tend to move together.

What this means: File co-change novelty is unusually low. While familiar patterns reduce risk, this could indicate repetitive or mechanical changes rather than normal development. Escalated from Needs Attention — multiple correlated patterns converge on the same signal families. Builds are taking longer. Slower CI feedback loops reduce developer productivity and delay catching issues. Escalated from Worth Monitoring — multiple correlated patterns converge on the same signal families.
Recommendation: Review whether recent commits are routine maintenance or a sign of narrow, repetitive modifications that lack expected variety. Profile the build pipeline to identify bottlenecks. Check for newly added expensive tests or build steps.
ℹ️ Informational

when deployments and code changes happen together, novelty of file pairings tends to move in opposite directions.

What this means: File co-change novelty is unusually low. While familiar patterns reduce risk, this could indicate repetitive or mechanical changes rather than normal development.
Recommendation: Review whether recent commits are routine maintenance or a sign of narrow, repetitive modifications that lack expected variety.
ℹ️ Informational

when code changes occur, novelty of file pairings tends to decrease.

What this means: File co-change novelty is unusually low. While familiar patterns reduce risk, this could indicate repetitive or mechanical changes rather than normal development.
Recommendation: Review whether recent commits are routine maintenance or a sign of narrow, repetitive modifications that lack expected variety.
Drift Investigation Prompt 
Development pattern shift detected in Version Control.\n\nSIGNAL: Co-change Novelty is 88.4x below the typical baseline (observed: 0.0000, typical: 0.9924).\nTRIGGER COMMIT: cdf140e7 — release(core): 1.2.17 (#35527)\n\nFILES CHANGED IN TRIGGER (2):\n  - libs/core/langchain_core/version.py\n  - libs/core/pyproject.toml\n\nRECENT COMMITS (20 total, showing top 5):\n  dcfd9c0e — fix(infra): use `langchain_v1` for dev container deps (#3453 (3 files)\n  5517ef37 — docs(core): add docstrings to internal helper functions (#34 (7 files)\n  0b917742 — fix(xai): stream usage metadata by default (#34531)

 (5 files)\n  458a1865 — chore(core): Update LangChainTracer to use Pydantic v2 metho (13 files)\n  659eab26 — release(core): 1.2.6 (#34586)

 (3 files)\n  ... and 15 more commits\n\nCORRELATED PATTERNS:\n  [CRITICAL] when CI builds and code changes happen together, novelty of file pairings and build time tend to move together.\n    → Investigate which files are being combined unexpectedly. Prioritize testing these changes.\n    → Profile the build pipeline to identify bottlenecks. Check for newly added expensive tests or build steps.\n  [INFO] when deployments and code changes happen together, novelty of file pairings tends to move in opposite directions.\n    → Review whether recent commits are routine maintenance or a sign of narrow, repetitive modifications that lack expected variety.\n  [INFO] when code changes occur, novelty of file pairings tends to decrease.\n    → Review whether recent commits are routine maintenance or a sign of narrow, repetitive modifications that lack expected variety.\n\nINVESTIGATE:\n1. Was this change intentional or did the AI drift from goals?\n2. Review commit cdf140e7 — what specifically caused the deviation?\n3. Suggest a course correction (not a bug fix — a realignment).\n\nAFTER FIX:\nRun `evo analyze . --verify` to re-analyze and compare against this run.\nIf the change was intentional, no fix needed — accept it in the report.
Use with: Cursor — paste in chat Claude Code — paste in terminal Copilot — paste in chat panel
After investigation:
  1. AI suggests fixes → apply the changes to your code
  2. Run evo analyze . --verify to re-analyze and compare against this run
  3. If the change was intentional, click Accept above to dismiss it
Show technical details

The cochange novelty ratio for this change was 0.0000. Historically, similar changes had a value of 0.9924 ± 0.0076.

📝
Files Changed
Version Control
What this means: More files changed than usual in this commit.
Typical:
2.00
This Time:
131
87.0x above typical range
Trigger: 4e9a1eb2 chore: delete CLI (#34855)
↘ Returned to baseline
Supporting Evidence
⚠️ Action Required

when CI builds and code changes happen together, file count and build time tend to move together.

What this means: Commits are touching more files than usual, increasing review burden and risk of regressions. Escalated from Worth Monitoring — multiple correlated patterns converge on the same signal families.
Recommendation: Monitor PR sizes. If this persists, investigate whether large refactors need better decomposition.
⚠️ Action Required

when deployments and code changes happen together, file count and release frequency tend to move together.

What this means: Commits are touching more files than usual, increasing review burden and risk of regressions. Escalated from Worth Monitoring — multiple correlated patterns converge on the same signal families.
Recommendation: Monitor PR sizes. If this persists, investigate whether large refactors need better decomposition.
👁️ Worth Monitoring

when code changes occur, file count tends to increase.

What this means: Commits are touching more files than usual, increasing review burden and risk of regressions.
Recommendation: Monitor PR sizes. If this persists, investigate whether large refactors need better decomposition.
Drift Investigation Prompt 
Development pattern shift detected in Version Control.\n\nSIGNAL: Files Changed is 87.0x above the typical baseline (observed: 131, typical: 2.00).\nTRIGGER COMMIT: 4e9a1eb2 — chore: delete CLI (#34855)\n\nFILES CHANGED IN TRIGGER (131):\n  - .github/ISSUE_TEMPLATE/bug-report.yml\n  - .github/ISSUE_TEMPLATE/feature-request.yml\n  - .github/ISSUE_TEMPLATE/privileged.yml\n  - .github/ISSUE_TEMPLATE/task.yml\n  - .github/pr-file-labeler.yml\n  - .github/scripts/check_diff.py\n  - .github/workflows/auto-label-by-package.yml\n  - .github/workflows/pr_lint.yml\n  - AGENTS.md\n  - CLAUDE.md\n  - libs/cli/.gitignore\n  - libs/cli/DOCS.md\n  - libs/cli/LICENSE\n  - libs/cli/Makefile\n  - libs/cli/README.md\n  ... and 116 more\n\nRECENT COMMITS (20 total, showing top 5):\n  dcfd9c0e — fix(infra): use `langchain_v1` for dev container deps (#3453 (3 files)\n  5517ef37 — docs(core): add docstrings to internal helper functions (#34 (7 files)\n  0b917742 — fix(xai): stream usage metadata by default (#34531)

 (5 files)\n  458a1865 — chore(core): Update LangChainTracer to use Pydantic v2 metho (13 files)\n  659eab26 — release(core): 1.2.6 (#34586)

 (3 files)\n  ... and 15 more commits\n\nCORRELATED PATTERNS:\n  [CRITICAL] when CI builds and code changes happen together, file count and build time tend to move together.\n    → Monitor PR sizes. If this persists, investigate whether large refactors need better decomposition.\n  [CRITICAL] when deployments and code changes happen together, file count and release frequency tend to move together.\n    → Monitor PR sizes. If this persists, investigate whether large refactors need better decomposition.\n  [WATCH] when code changes occur, file count tends to increase.\n    → Monitor PR sizes. If this persists, investigate whether large refactors need better decomposition.\n\nINVESTIGATE:\n1. Was this change intentional or did the AI drift from goals?\n2. Review commit 4e9a1eb2 — what specifically caused the deviation?\n3. Suggest a course correction (not a bug fix — a realignment).\n\nAFTER FIX:\nRun `evo analyze . --verify` to re-analyze and compare against this run.\nIf the change was intentional, no fix needed — accept it in the report.
Use with: Cursor — paste in chat Claude Code — paste in terminal Copilot — paste in chat panel
After investigation:
  1. AI suggests fixes → apply the changes to your code
  2. Run evo analyze . --verify to re-analyze and compare against this run
  3. If the change was intentional, click Accept above to dismiss it
Show technical details

The files touched for this change was 131. Historically, similar changes had a value of 2.00 ± 1.00.

📝
Change Locality
Version Control
What this means: The changed files frequently change together, suggesting a focused modification.
Typical:
0.0000
This Time:
1.00
6.8x above typical range
Trigger: e5d4acf6 style(langchain): add ruff rule PLC0415 (#34559)
↘ Returned to baseline
Supporting Evidence
⚠️ Action Required

when CI builds and code changes happen together, change focus and build time tend to move together.

What this means: Builds are taking longer. Slower CI feedback loops reduce developer productivity and delay catching issues. Escalated from Worth Monitoring — multiple correlated patterns converge on the same signal families. Changes span files that don't normally change together, suggesting cross-cutting concerns that may be harder to test. Escalated from Worth Monitoring — multiple correlated patterns converge on the same signal families.
Recommendation: Profile the build pipeline to identify bottlenecks. Check for newly added expensive tests or build steps. Review whether these cross-cutting changes have adequate test coverage.
⚠️ Action Required

when deployments and code changes happen together, change focus and release frequency tend to move together.

What this means: Time between releases is increasing. This could indicate a bottleneck in the release process or accumulating risk in larger releases. Escalated from Worth Monitoring — multiple correlated patterns converge on the same signal families.
Recommendation: Check if process changes or staffing issues are delaying releases.
ℹ️ Informational

when code changes occur, change focus tends to increase.

What this means: Changed files frequently change together, suggesting focused modifications to tightly-coupled components.
Recommendation: No immediate action. Monitor if tight coupling becomes a maintenance concern.
Drift Investigation Prompt 
Development pattern shift detected in Version Control.\n\nSIGNAL: Change Locality is 6.8x above the typical baseline (observed: 1.00, typical: 0.0000).\nTRIGGER COMMIT: e5d4acf6 — style(langchain): add ruff rule PLC0415 (#34559)\n\nFILES CHANGED IN TRIGGER (1):\n  - libs/langchain_v1/pyproject.toml\n\nRECENT COMMITS (19 total, showing top 5):\n  dcfd9c0e — fix(infra): use `langchain_v1` for dev container deps (#3453 (3 files)\n  5517ef37 — docs(core): add docstrings to internal helper functions (#34 (7 files)\n  0b917742 — fix(xai): stream usage metadata by default (#34531)

 (5 files)\n  458a1865 — chore(core): Update LangChainTracer to use Pydantic v2 metho (13 files)\n  659eab26 — release(core): 1.2.6 (#34586)

 (3 files)\n  ... and 14 more commits\n\nCORRELATED PATTERNS:\n  [CRITICAL] when CI builds and code changes happen together, change focus and build time tend to move together.\n    → Profile the build pipeline to identify bottlenecks. Check for newly added expensive tests or build steps.\n    → Review whether these cross-cutting changes have adequate test coverage.\n  [CRITICAL] when deployments and code changes happen together, change focus and release frequency tend to move together.\n    → Check if process changes or staffing issues are delaying releases.\n  [INFO] when code changes occur, change focus tends to increase.\n    → No immediate action. Monitor if tight coupling becomes a maintenance concern.\n\nINVESTIGATE:\n1. Was this change intentional or did the AI drift from goals?\n2. Review commit e5d4acf6 — what specifically caused the deviation?\n3. Suggest a course correction (not a bug fix — a realignment).\n\nAFTER FIX:\nRun `evo analyze . --verify` to re-analyze and compare against this run.\nIf the change was intentional, no fix needed — accept it in the report.
Use with: Cursor — paste in chat Claude Code — paste in terminal Copilot — paste in chat panel
After investigation:
  1. AI suggests fixes → apply the changes to your code
  2. Run evo analyze . --verify to re-analyze and compare against this run
  3. If the change was intentional, click Accept above to dismiss it

Next Steps

1
Investigate

Copy the prompt below and paste it into your AI assistant (Claude Code, Cursor, Copilot, ChatGPT). It will identify root causes and suggest fixes.

2
Fix

Apply the suggested changes. If a deviation was intentional, click Accept on its card above instead.

3
Verify

Run evo analyze . --verify to re-analyze and compare. A verification banner will show which deviations resolved, improved, or persist.

Investigation Prompt

Development drift analysis for langchain-ai/langchain (Jan 27, 2023 at 04:57 PM to Mar 14, 2026 at 03:09 AM). DEVIATIONS FROM BASELINE: - CI / Build: Build Duration — 9.50 -> 3,306.0 - Deployment: Release Cadence — 0.4990 -> 145.8 - Version Control: Co-change Novelty — 0.9924 -> 0.0000 - Version Control: Files Changed — 2.00 -> 131 - Version Control: Change Locality — 0.0000 -> 1.00 Click "Show Full Prompt" to see the complete investigation prompt with evidence...
Development drift analysis for langchain-ai/langchain (Jan 27, 2023 at 04:57 PM to Mar 14, 2026 at 03:09 AM).

DEVIATIONS FROM BASELINE:

- CI / Build / Build Duration: 3,306.0 (typical: 9.50, 889.4x above)
- Deployment / Release Cadence: 145.8 (typical: 0.4990, 220.0x above)
- Version Control / Co-change Novelty: 0.0000 (typical: 0.9924, 88.4x below)
- Version Control / Files Changed: 131 (typical: 2.00, 87.0x above)
- Version Control / Change Locality: 1.00 (typical: 0.0000, 6.8x above)

RISK PATTERNS (actionable only):

- [Action Required] when CI builds and code changes happen together, change focus tends to move in opposite directions.
  Impact: Changes span files that don't normally change together, suggesting cross-cutting concerns that may be harder to test. Escalated from Worth Monitoring — multiple correlated patterns converge on the same signal families.
  Action: Review whether these cross-cutting changes have adequate test coverage.

- [Action Required] 3 patterns:
    * when deployments and code changes happen together, novelty of file pairings tends to move together.
    * when CI builds and code changes happen together, novelty of file pairings and build time tend to move together.
    * when CI builds and code changes happen together, novelty of file pairings tends to move together.
  Impact: Files that don't normally change together are being modified in the same commits. This indicates novel, untested interactions that may introduce bugs. Escalated from Needs Attention — multiple correlated patterns converge on the same signal families.
  Action: Investigate which files are being combined unexpectedly. Prioritize testing these changes.

- [Action Required] 2 patterns:
    * when deployments and code changes happen together, change focus and release frequency tend to move together.
    * when deployments and code changes happen together, release frequency tends to move together.
  Impact: Time between releases is increasing. This could indicate a bottleneck in the release process or accumulating risk in larger releases. Escalated from Worth Monitoring — multiple correlated patterns converge on the same signal families.
  Action: Check if process changes or staffing issues are delaying releases.

- [Action Required] 2 patterns:
    * when CI builds and code changes happen together, change focus and build time tend to move together.
    * when CI builds and code changes happen together, build time tends to move together.
  Impact: Builds are taking longer. Slower CI feedback loops reduce developer productivity and delay catching issues. Escalated from Worth Monitoring — multiple correlated patterns converge on the same signal families.
  Action: Profile the build pipeline to identify bottlenecks. Check for newly added expensive tests or build steps.

- [Action Required] 4 patterns:
    * when deployments and code changes happen together, file count tends to move together.
    * when CI builds and code changes happen together, file count and build time tend to move together.
    * when deployments and code changes happen together, file count and release frequency tend to move together.
    * when CI builds and code changes happen together, file count tends to move together.
  Impact: Commits are touching more files than usual, increasing review burden and risk of regressions. Escalated from Worth Monitoring — multiple correlated patterns converge on the same signal families.
  Action: Monitor PR sizes. If this persists, investigate whether large refactors need better decomposition.

- [Worth Monitoring] when deployments occur, release frequency tends to increase.
  (2 independent confirmations)
  Impact: Time between releases is increasing. This could indicate a bottleneck in the release process or accumulating risk in larger releases.
  Action: Check if process changes or staffing issues are delaying releases.

- [Worth Monitoring] when code changes occur, change focus tends to decrease.
  Impact: Changes span files that don't normally change together, suggesting cross-cutting concerns that may be harder to test.
  Action: Review whether these cross-cutting changes have adequate test coverage.

- [Worth Monitoring] when code changes occur, file count tends to increase.
  Impact: Commits are touching more files than usual, increasing review burden and risk of regressions.
  Action: Monitor PR sizes. If this persists, investigate whether large refactors need better decomposition.


COMMITS (20):

  dcfd9c0e — fix(infra): use `langchain_v1` for dev container deps (#34534) (3 files)
  5517ef37 — docs(core): add docstrings to internal helper functions (#34525) (7 files)
  0b917742 — fix(xai): stream usage metadata by default (#34531) (5 files)
  458a1865 — chore(core): Update LangChainTracer to use Pydantic v2 methods (#34541) (13 files)
  659eab26 — release(core): 1.2.6 (#34586) (3 files)
  e5d4acf6 — style(langchain): add ruff rule PLC0415 (#34559) (1 files)
  cd5b3645 — fix(text-splitters): HTMLSemanticPreservingSplitter nested preserved … (#34587) (3 files)
  944b43dd — fix(xai): count reasoning tokens in output total (#34603) (2 files)
  b5c5ba0a — release(xai): 1.2.1 (#34604) (2 files)
  225e0fa8 — release(anthropic): 1.3.1 (#34605) (2 files)
  ... and 10 more

SOURCE FILES CHANGED (50):

  - .devcontainer/devcontainer.json (modified)
  - libs/langchain/dev.Dockerfile (modified)
  - libs/langchain_v1/uv.lock (modified)
  - libs/core/langchain_core/_api/__init__.py (modified)
  - libs/core/langchain_core/indexing/api.py (modified)
  - libs/core/langchain_core/utils/json.py (modified)
  - libs/core/langchain_core/utils/json_schema.py (modified)
  - libs/core/langchain_core/utils/mustache.py (modified)
  - libs/core/langchain_core/utils/usage.py (modified)
  - libs/core/langchain_core/vectorstores/__init__.py (modified)
  - libs/partners/xai/langchain_xai/chat_models.py (modified)
  - libs/partners/xai/tests/integration_tests/test_chat_models_standard.py (modified)
  - libs/partners/xai/tests/unit_tests/__snapshots__/test_chat_models_standard.ambr (modified)
  - libs/partners/xai/tests/unit_tests/test_chat_models.py (modified)
  - libs/partners/xai/uv.lock (modified)
  - libs/core/langchain_core/document_loaders/langsmith.py (modified)
  - libs/core/langchain_core/tracers/_compat.py (modified)
  - libs/core/langchain_core/tracers/core.py (modified)
  - libs/core/langchain_core/tracers/evaluation.py (modified)
  - libs/core/langchain_core/tracers/langchain.py (modified)
  ... and 30 more

TASKS:

1. ROOT CAUSE: For each deviation, identify the commit(s) that caused it.
   Focus on [Action Required] and [Needs Attention] items first.

2. FIXES: Provide concrete fixes with file paths and code changes.
   Goal: bring metrics back toward baseline without disrupting velocity.

3. PRIORITY: Rank fixes by urgency (immediate vs. next sprint).

4. AFTER FIXING: Run `evo analyze . --verify` to confirm deviations decreased.
   If a change was intentional, accept it: `evo accept . <N>`.

5. FINDING SUMMARIES: At the end, include a section like this:
   ## Finding Summaries
   - [family/metric]: One plain-English sentence for a non-technical reader.
   (This lets the user run `evo enrich . --from response.txt` to store friendly descriptions.)

Expand Your Coverage

Evolution Engine has 44 universal patterns learned from 200+ open-source repositories. The more signal families you connect, the more cross-family patterns can be detected.

Available Adapters

Enable these adapters to unlock additional signal families and cross-family pattern detection.

📦
pip
Dependencies
Python dependency tracking from requirements.txt and Pipfile.lock
Auto-detected from files Setup guide →
📦
npm
Dependencies
Node.js dependency tracking from package-lock.json with depth analysis
Auto-detected from files Setup guide →
📦
go
Dependencies
Go module tracking from go.sum with dependency depth
Auto-detected from files Setup guide →
📦
cargo
Dependencies
Rust crate tracking from Cargo.lock with depth analysis
Auto-detected from files Setup guide →
📦
bundler
Dependencies
Ruby gem tracking from Gemfile.lock
Auto-detected from files Setup guide →
📦
composer
Dependencies
PHP dependency tracking from composer.lock
Auto-detected from files Setup guide →
📦
gradle
Dependencies
Java/Kotlin dependency tracking from Gradle lockfiles
Auto-detected from files Setup guide →
📦
maven
Dependencies
Java dependency tracking from Maven pom.xml
Auto-detected from files Setup guide →
📦
swift
Dependencies
Swift dependency tracking from Package.resolved
Auto-detected from files Setup guide →
📦
pnpm
Dependencies
Node.js dependency tracking from pnpm-lock.yaml
Auto-detected from files Setup guide →
📊
cobertura
Code Coverage
Code coverage from Cobertura XML reports — line rate, branch rate
Auto-detected from files Setup guide →
🚨
sentry
Error Tracking
Error tracking and release health from Sentry — event count, user impact, unhandled errors
Set SENTRY_AUTH_TOKEN Setup guide →

How to Connect an Adapter

  1. Set the environment variable shown on the adapter card. For example: export GITHUB_TOKEN=$(gh auth token)
  2. For file-based adapters (Testing, Coverage): generate reports in your project first. For example, pytest --junitxml=junit.xml or pytest --cov --cov-report=xml
  3. Run analysis: evo analyze . — new adapters are detected automatically
  4. Verify: evo sources to confirm which adapters are active
Coming soon: CI / Build, Deployment, Feature Flags, Incidents, Monitoring, Quality Gate, Security Scan, Work Items