fix(llm): install provider clients for model pilot

[stranske]

Follow-up to #2740, #2766, and pilot run #29221382906.

The repaired pilot reached evaluation but all 180 rows were invalid because the workflow installed only the dev extra; the provider clients are in the langchain extra. This installs both extras and makes the runner fail if any configured candidate produces zero schema-valid rows, preventing a green run with unusable evidence.

Validation:

• provider dependencies import successfully under uv run --extra dev --extra langchain
• 4 focused tests passed
• workflow YAML, Ruff, Black, diff-quality, and whitespace checks passed

[coderabbitai]

Warning

Review limit reached

You’ve reached a temporary PR review limit under our Fair Usage Limits Policy.

Your recent review volume is higher than typical usage, so adaptive limits are currently applied.

Next review available in: 34 minutes

Your organization has reached its usage spending cap. Adjust your spending cap in the billing tab.

How can I continue?

After more reviews become available, a review can be triggered using the @coderabbitai review command as a PR comment. Alternatively, push new commits to this PR.

To avoid repeated limits, reduce automatic review volume by pausing incremental auto-reviews earlier, using label-based review opt-in, excluding WIP or generated PR titles, or requesting reviews manually when the PR is ready. If your team needs uninterrupted high-volume reviews, an organization admin can enable usage-based reviews.

How do review limits work?

CodeRabbit enforces per-developer PR review limits for each organization. Most developers receive the normal plan review availability.

For paid Pro and Pro+ PR reviews, CodeRabbit uses adaptive limits for sustained high-volume activity. When a developer's recent PR review activity reaches the 95th percentile or higher among CodeRabbit users, additional reviews become available more gradually as earlier reviews age out of the rolling window.

Please refer docs for additional details.

Review details

⚙️ Run configuration

Configuration used: Path: .coderabbit.yaml

Review profile: ASSERTIVE

Plan: Pro

Run ID: 8135c8de-fc7e-4953-a736-638b5dca878c

📥 Commits

Reviewing files that changed from the base of the PR and between 449f42d and 788bafe.

📒 Files selected for processing (4)

• .github/workflows/maint-78-model-evaluation-pilot.yml
• tests/tools/test_run_model_eval_pilot.py
• tests/workflows/test_model_eval_pilot_workflow.py
• tools/run_model_eval_pilot.py

✨ Finishing Touches

🧪 Generate unit tests (beta)

• Create PR with unit tests
• Commit unit tests in branch codex/2740-pilot-provider-deps

---

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

[agents-workflows-bot]

Workflow source needed

PR #2767 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.

[Copilot]

Pull request overview

This PR hardens the model-evaluation pilot workflow so it installs the provider client dependencies required by the verifier’s LangChain integration, and adds a failure gate to prevent “green” pilot runs that produce unusable evaluation evidence.

Changes:

• Update the maint-78 pilot workflow to run with both dev and langchain extras so provider clients are available.
• Add a post-run gate in the pilot runner to fail the run when a candidate produces zero schema-valid rows.
• Extend workflow and tool tests to assert the updated invocation and validate unusable-candidate detection.

Reviewed changes

Copilot reviewed 4 out of 4 changed files in this pull request and generated 1 comment.

File	Description
tools/run_model_eval_pilot.py	Adds unusable-candidate detection and fails the runner when evidence is unusable.
tests/workflows/test_model_eval_pilot_workflow.py	Verifies the workflow runs the pilot with the langchain extra and still uses module execution.
tests/tools/test_run_model_eval_pilot.py	Adds unit coverage for unusable-candidate detection logic.
.github/workflows/maint-78-model-evaluation-pilot.yml	Installs langchain extra during pilot execution to ensure provider clients are present.

[chatgpt-codex-connector]

💡 Codex Review

Here are some automated review suggestions for this pull request.

Reviewed commit: 6842ff14dd

ℹ️ About Codex in GitHub

Your team has set up Codex to review pull requests in this repo. Reviews are triggered when you

• Open a pull request for review
• Mark a draft as ready
• Comment "@codex review".

If Codex has suggestions, it will comment; otherwise it will react with 👍.

Codex can also answer questions or update the PR. Try commenting "@codex address that feedback".

[stranske-keepalive]

Automated Status Summary

Head SHA: b70dc36
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	75.57%
Baseline	85.00%
Delta	-9.43%
Minimum	70.00%
Status	✅ Pass

Top Coverage Hotspots (lowest coverage)

File	Coverage	Missing
scripts/issue_dedup_smoke.py	0.0%	4
scripts/runner_lib/__main__.py	0.0%	3
scripts/validate_template_sync.py	0.0%	81
scripts/langchain/topic_splitter.py	19.1%	57
tools/codex_log_analyzer.py	19.6%	140
scripts/repo_review_round2_runner.py	25.1%	344
scripts/prune_agent_stubs.py	39.7%	26
scripts/repo_review_round1_runner.py	40.7%	133
tools/ensure_workflow_timeout_variables.py	42.1%	74
scripts/sync_label_docs.py	42.9%	64
tools/discover_model_catalog.py	43.8%	54
tools/ci_failure_triage.py	44.2%	123
scripts/repo_review_backlog_scan.py	45.3%	116
scripts/repo_review_body_writer.py	46.5%	86
tools/codex_session_analyzer.py	47.9%	59

Low Coverage Files (<50.0%)

File	Coverage	Missing
scripts/issue_dedup_smoke.py	0.0%	4
scripts/runner_lib/__main__.py	0.0%	3
scripts/validate_template_sync.py	0.0%	81
scripts/langchain/topic_splitter.py	19.1%	57
tools/codex_log_analyzer.py	19.6%	140
scripts/repo_review_round2_runner.py	25.1%	344
scripts/prune_agent_stubs.py	39.7%	26
scripts/repo_review_round1_runner.py	40.7%	133
tools/ensure_workflow_timeout_variables.py	42.1%	74
scripts/sync_label_docs.py	42.9%	64
tools/discover_model_catalog.py	43.8%	54
tools/ci_failure_triage.py	44.2%	123
scripts/repo_review_backlog_scan.py	45.3%	116
scripts/repo_review_body_writer.py	46.5%	86
tools/codex_session_analyzer.py	47.9%	59

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