fix: consume blocked llm override before fallback

[stranske]

Summary

• consume blocked global LLM overrides before moving to fallback providers
• add regression coverage for missing first-provider credentials
• keep the consumer template LangChain client copy aligned

Validation

• UV_CACHE_DIR=/tmp/uv-cache-workflows-sync-fix uv run pytest tests/tools/test_langchain_client.py tests/scripts/test_runner_lib.py tests/scripts/test_check_agents_md_freshness.py -q
• UV_CACHE_DIR=/tmp/uv-cache-workflows-sync-fix uv run ruff check tools/langchain_client.py templates/consumer-repo/tools/langchain_client.py tests/tools/test_langchain_client.py
• UV_CACHE_DIR=/tmp/uv-cache-workflows-sync-fix uv run black --check tools/langchain_client.py templates/consumer-repo/tools/langchain_client.py tests/tools/test_langchain_client.py
• UV_CACHE_DIR=/tmp/uv-cache-workflows-sync-fix uv run --extra dev python scripts/validate_template_sync.py
• git diff --check

Summary by CodeRabbit

• Bug Fixes

  • Improved model selection logic to properly fall back to default models when overrides are unavailable or blocked.

• Refactor

  • Streamlined provider availability detection for more efficient chat client initialization.

[coderabbitai]

Caution

Review failed

Pull request was closed or merged during review

No actionable comments were generated in the recent review. 🎉

ℹ️ Recent review info

⚙️ Run configuration

Configuration used: Path: .coderabbit.yaml

Review profile: ASSERTIVE

Plan: Pro Plus

Run ID: a7860ea0-4337-431d-9232-1d0419824f0d

📥 Commits

Reviewing files that changed from the base of the PR and between 8211687 and 89c5a4d.

📒 Files selected for processing (3)

• templates/consumer-repo/tools/langchain_client.py
• tests/tools/test_langchain_client.py
• tools/langchain_client.py

🔗 Linked repositories identified

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

• stranske/Template (auto-detected)
• stranske/Ready (auto-detected)
• stranske/Workflows-Integration-Tests (auto-detected)

---

📝 Walkthrough

Walkthrough

build_chat_client's slot-iteration loop is updated in both tools/langchain_client.py and its template copy to detect blocked model overrides per slot, log and consume the override, fall back to the slot's default model, and remove the prior slot_available pre-check. A new test validates that a blocked override is consumed without retrying against subsequent providers.

Changes

Blocked override handling and slot_available removal

Layer / File(s)	Summary
Blocked override handling and slot_available removal in build_chat_client tools/langchain_client.py, templates/consumer-repo/tools/langchain_client.py	Both copies of the loop now assign slot_model from the first unused model override, check if that override is blocked for the current slot provider, and if so log a warning, mark the override as used, and fall back to slot.model before applying the general blocked-model skip. The slot_available pre-check block that gated slot entry on provider credentials is removed; per-provider token-guarded construction handles availability implicitly.
Test for blocked override consumed across providers tests/tools/test_langchain_client.py	The existing test_build_chat_client_env_model_override test sets ENV_MODEL_REGISTRY_CONFIG to a missing path. A new test test_build_chat_client_blocked_override_consumed_when_first_provider_unavailable writes a registry marking the OpenAI model as blocked, clears OpenAI/GitHub env vars, provides Anthropic credentials, and asserts the returned client uses the Anthropic provider, model, and expected kwargs.

Estimated code review effort

🎯 2 (Simple) | ⏱️ ~10 minutes

🚥 Pre-merge checks | ✅ 4 | ❌ 1

❌ Failed checks (1 warning)

Check name	Status	Explanation	Resolution
Docstring Coverage	⚠️ Warning	Docstring coverage is 50.00% which is insufficient. The required threshold is 80.00%.	Write docstrings for the functions missing them to satisfy the coverage threshold.

✅ Passed checks (4 passed)

Check name	Status	Explanation
Description Check	✅ Passed	Check skipped - CodeRabbit’s high-level summary is enabled.
Title check	✅ Passed	The title 'fix: consume blocked llm override before fallback' directly and clearly describes the main change in the PR: how blocked LLM overrides are now consumed before the system falls back to alternative providers.
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 fix/llm-blocked-override-fallback

---

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

[stranske-keepalive]

Workflow source needed

PR #2499 needs either a linked GitHub issue or one valid non-issue Workflow Source before PR metadata automation can manage it safely.

Please do one of:

• Add <!-- meta:issue:123 --> or a normal Closes #123 / Related to #123 line.
• Check one Workflow Source option in the PR body.
• Add a hidden marker such as <!-- workflow-source:local_request -->, <!-- workflow-source:manual_remote -->, <!-- workflow-source:review_followup -->, <!-- workflow-source:sync_campaign -->, or <!-- workflow-source:dependabot -->.
• Add a workflow source label such as workflow:source-direct-pr, workflow:source-local-request, workflow:source-review-followup, workflow:source-sync, or workflow:no-automation.

Once a valid source is present, this warning will not be reposted.

[stranske-keepalive]

Automated Status Summary

Head SHA: 6188344
Latest Runs: ⏳ pending — Gate
Required contexts: Gate / gate, Health 45 Agents Guard / guard
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	70.49%
Baseline	85.00%
Delta	-14.51%
Minimum	70.00%
Status	✅ Pass

Top Coverage Hotspots (lowest coverage)

File	Coverage	Missing
scripts/check_api_wrapper_guard.py	0.0%	123
scripts/cleanup_labels.py	0.0%	127
scripts/issue_dedup_smoke.py	0.0%	4
scripts/list_registered_consumer_repos.py	0.0%	33
scripts/repo_review_backlog_scan.py	0.0%	203
scripts/repo_review_round1_runner.py	0.0%	225
scripts/repo_review_round1_schema.py	0.0%	194
scripts/runner_lib/__main__.py	0.0%	3
scripts/update_langchain_versions.py	0.0%	34
scripts/validate_dependency_test_setup.py	0.0%	112
scripts/validate_template_completeness.py	0.0%	88
scripts/validate_template_sync.py	0.0%	77
scripts/validate_workflow_yaml.py	0.0%	98
scripts/repo_review_round2_schema.py	8.8%	185
scripts/langchain/topic_splitter.py	19.1%	57

Low Coverage Files (<50.0%)

File	Coverage	Missing
scripts/check_api_wrapper_guard.py	0.0%	123
scripts/cleanup_labels.py	0.0%	127
scripts/issue_dedup_smoke.py	0.0%	4
scripts/list_registered_consumer_repos.py	0.0%	33
scripts/repo_review_backlog_scan.py	0.0%	203
scripts/repo_review_round1_runner.py	0.0%	225
scripts/repo_review_round1_schema.py	0.0%	194
scripts/runner_lib/__main__.py	0.0%	3
scripts/update_langchain_versions.py	0.0%	34
scripts/validate_dependency_test_setup.py	0.0%	112
scripts/validate_template_completeness.py	0.0%	88
scripts/validate_template_sync.py	0.0%	77
scripts/validate_workflow_yaml.py	0.0%	98
scripts/repo_review_round2_schema.py	8.8%	185
scripts/langchain/topic_splitter.py	19.1%	57

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