chore: sync workflow templates

[stranske]

Sync Summary

Files Updated

• progress_reviewer.py: Progress reviewer - evaluates agent progress for keepalive rounds
• llm_provider.py: LLM provider configuration - GitHub Models and OpenAI client setup

Files Skipped

• renovate.json: File exists and sync_mode is create_only
• cross-repo-smoke.yml: File exists and sync_mode is create_only
• llm_slots.json: None

---

Review Checklist

• CI passes with updated workflows
• No repo-specific customizations were overwritten

Source: stranske/Workflows
Source SHA: 680260c913e1c136e0b0ba11c07a760e23c26b0c
Template hash: 1243c652ce3c
Sync branch: sync/workflows-1243c652ce3c
Consumer repo: stranske/Template
Manifest: .github/sync-manifest.yml

Summary by CodeRabbit

• Refactor
  • Updated LLM client construction for OpenAI and Anthropic providers.
  • Improved dynamic model name resolution across LLM utilities.

[coderabbitai]

No actionable comments were generated in the recent review. 🎉

ℹ️ Recent review info

⚙️ Run configuration

Configuration used: Organization UI

Review profile: ASSERTIVE

Plan: Pro Plus

Run ID: 7ed0a83b-7745-4f99-850f-e06c687edaf7

📥 Commits

Reviewing files that changed from the base of the PR and between 89d68b1 and 9e25328.

📒 Files selected for processing (2)

• scripts/langchain/progress_reviewer.py
• tools/llm_provider.py

🔗 Linked repositories identified

CodeRabbit considers these linked repositories for cross-repo context during reviews:

• stranske/Workflows (auto-detected)

📜 Recent review details

⏰ Context from checks skipped due to timeout. (1)

• GitHub Check: check

🧰 Additional context used

📓 Path-based instructions (1)

**/*.py

📄 CodeRabbit inference engine (.github/copilot-instructions.md)

In Manager-Database repository using Prefect 2.x, import schedules from prefect.client.schemas.schedules rather than other locations

Files:

• scripts/langchain/progress_reviewer.py
• tools/llm_provider.py

🔀 Multi-repo context stranske/Workflows

Based on my exploration of the stranske/Workflows repository, I can now provide you with the cross-repository context for this sync PR.

Linked repositories findings

stranske/Workflows (Source Repository)

Key changes being synced:

1. progress_reviewer.py - Import path change [::stranske/Workflows::]

   • Line ~330-335: Changed from importing build_chat_client from tools.langchain_client to importing build_client from scripts.langchain._llm_client
   • Pattern: resolved = build_client(model=model) if build_client else None
   • This is a higher-level abstraction over the tools layer

2. llm_provider.py - OpenAI and Anthropic provider updates [::stranske/Workflows::]

   • OpenAIProvider._get_client() (line ~580-586): Now uses build_chat_client(provider="openai", model=model_name) with resolved model from _configured_langchain_model()
   • AnthropicProvider._get_client() (line ~640-646): Same pattern with anthropic provider
   • Both now store self._model_name = resolved.model for later use
   • In analyze_completion(), the returned CompletionAnalysis now sets model_name to the resolved model instead of hardcoded defaults

3. New helper function [::stranske/Workflows::]

   • _configured_langchain_model(provider, fallback) in llm_provider.py (line ~58-62) that:
     • Tries to import tools.llm_registry.configured_model_for_provider
     • Falls back gracefully if import fails
     • Returns resolved model for the provider or fallback

Cross-repo dependencies identified:

1. scripts/langchain/_llm_client.py must export build_client [::stranske/Workflows::]

   • Used by progress_reviewer.py at line ~328
   • Used by followup_issue_generator.py at lines ~100-111
   • Returns object with .client and .provider and .model attributes

2. tools/langchain_client.py must export build_chat_client [::stranske/Workflows::]

   • Used by llm_provider.py OpenAIProvider (line ~583)
   • Used by llm_provider.py AnthropicProvider (line ~643)
   • Returns object with .client and .model attributes
   • Also used in test mocks (tests/tools/test_llm_provider.py lines ~27-29, ~40-42)

3. tools/llm_registry.py must export configured_model_for_provider [::stranske/Workflows::]

   • Used by llm_provider.py._configured_langchain_model() at line ~60
   • Signature: configured_model_for_provider(provider, fallback=...)
   • Must return a model string or None/falsy value

Test coverage [::stranske/Workflows::]

• tests/scripts/test_progress_reviewer.py: Mocks scripts.langchain._llm_client.build_client (line ~22)
• tests/tools/test_llm_provider.py: Mocks both tools.llm_registry.configured_model_for_provider and tools.langchain_client.build_chat_client (lines ~27-29, ~40-42)

Critical compatibility notes:

• The changes maintain backward compatibility through try/except blocks with fallback behavior
• If scripts.langchain._llm_client is unavailable, progress_reviewer falls back to heuristic-only mode
• If tools.llm_registry.configured_model_for_provider is unavailable, llm_provider returns the fallback model
• The resolved object must have .client, .provider, and .model attributes for proper operation

🔇 Additional comments (2)

tools/llm_provider.py (1)

45-52: LGTM!

Also applies to: 596-606, 638-642, 667-677, 719-723

scripts/langchain/progress_reviewer.py (1)

430-434: LGTM!

---

📝 Walkthrough

Walkthrough

tools/llm_provider.py gains a _configured_langchain_model helper that resolves model names via an optional registry import with fallback. OpenAIProvider and AnthropicProvider now construct their clients through build_chat_client and emit dynamic model_name values in analyze_completion. scripts/langchain/progress_reviewer.py switches its conditional import from build_chat_client to build_client from the internal scripts.langchain._llm_client module.

Changes

LangChain client centralization and dynamic model resolution

Layer / File(s)	Summary
Model resolution helper and provider client construction tools/llm_provider.py	Adds _configured_langchain_model(provider, *, fallback) that optionally queries tools.llm_registry.configured_model_for_provider and falls back to the provided string. Updates OpenAIProvider._get_client and AnthropicProvider._get_client to use build_chat_client from tools.langchain_client with the resolved model, storing it on self._model_name. Changes analyze_completion in both providers to return self._model_name or the registry lookup instead of a hard-coded model string.
progress_reviewer import switch scripts/langchain/progress_reviewer.py	Replaces the conditional import of build_chat_client from tools.langchain_client with a conditional import of build_client from scripts.langchain._llm_client, updating the resolved construction call to match.

Estimated code review effort

🎯 2 (Simple) | ⏱️ ~10 minutes

Possibly related PRs

• stranske/Template#841: Introduces configured_model_for_provider in tools/llm_registry and the updated build_chat_client behavior in tools/langchain_client that this PR depends on directly.

🚥 Pre-merge checks | ✅ 3 | ❌ 2

❌ Failed checks (2 warnings)

Check name	Status	Explanation	Resolution
Title check	⚠️ Warning	The PR title 'chore: sync workflow templates' does not match the actual changes, which involve updating LLM client imports and model resolution logic in progress_reviewer.py and llm_provider.py files—not workflow templates.	Update the title to accurately reflect the main changes, such as 'chore: update LLM client resolution and model name handling' or 'refactor: consolidate LLM client configuration'.
Docstring Coverage	⚠️ Warning	Docstring coverage is 42.86% which is insufficient. The required threshold is 80.00%.	Write docstrings for the functions missing them to satisfy the coverage threshold.

✅ Passed checks (3 passed)

Check name	Status	Explanation
Description Check	✅ Passed	Check skipped - CodeRabbit’s high-level summary is enabled.
Linked Issues check	✅ Passed	Check skipped because no linked issues were found for this pull request.
Out of Scope Changes check	✅ Passed	Check skipped because no linked issues were found for this pull request.

_{✏️ Tip: You can configure your own custom pre-merge checks in the settings.}

✨ Finishing Touches

📝 Generate docstrings

• Create stacked PR
• Commit on current branch

🧪 Generate unit tests (beta)

• Create PR with unit tests
• Commit unit tests in branch sync/workflows-1243c652ce3c

---

_{Comment @coderabbitai help to get the list of available commands and usage tips.}

[agents-workflows-bot]

Automated Status Summary

Head SHA: 87095a5
Latest Runs: ⏳ pending — Gate
Required: core tests (3.12): ⏳ pending, core tests (3.13): ⏳ pending, docker smoke: ⏳ pending, gate: ⏳ pending

Workflow / Job	Result	Logs
(no jobs reported)	⏳ pending	—

Coverage Overview

• Coverage history entries: 1

Coverage Trend

Metric	Value
Current	100.00%
Baseline	0.00%
Delta	+100.00%
Minimum	70.00%
Status	✅ Pass

Top Coverage Hotspots (lowest coverage)

File	Coverage	Missing
src/my_project/__init__.py	100.0%	0

Updated automatically; will refresh on subsequent CI/Docker completions.

---

Keepalive checklist

Scope

No scope information available

Tasks

• No tasks defined

Acceptance criteria

• No acceptance criteria defined

[stranske]

Closing as superseded by the newer post-Workflows#2501 sync wave sync/workflows-c11e0664a4d8.