feat: auto-push eval results to configurable git repo (needs design)

[christso]

Summary

Add a configuration option to automatically push eval result artifacts to a git repository after each eval run. The agent creates a PR (not auto-merge) so a human still reviews and merges.

Motivation

Currently eval results live in .agentv/results/runs/ locally and are lost unless manually committed. For reproducibility and historical comparison, results should be automatically pushed to a dedicated repo (e.g., EntityProcess/agentv-evals).

Similar to Entire.io's approach where evaluation artifacts are versioned and browsable.

Design

Configuration

In .agentv/config.yaml or agentv.config.yaml:

results:
  export:
    repo: EntityProcess/agentv-evals     # GitHub repo path
    path: autopilot-dev/runs             # Directory within the repo
    auto_push: true                      # Enable auto-push after each run
    branch_prefix: eval-results          # Branch naming prefix

Workflow

1. After agentv eval run completes, if auto_push is enabled:
2. Clone/fetch the target repo
3. Create a branch: eval-results/<timestamp>
4. Copy result artifacts to the configured path
5. Commit with a structured message including eval summary (pass/fail counts, mean score)
6. Push branch and create a draft PR with results summary in the body
7. Human reviews and merges the PR

PR Format

feat(results): ad-explore claude-cli — 3/3 PASS (1.000)

## Results
| Test | Score | Status |
|---|---|---|
| discovers-existing-implementation | 1.000 | PASS |
| finds-all-consumers | 1.000 | PASS |
| structured-summary | 1.000 | PASS |

Run: 2026-03-29T01-15-06-826Z
Target: claude-cli
Eval: evals/autopilot-dev/ad-explore.eval.yaml

Acceptance Signals

• config.yaml supports results.export section
• After eval run, artifacts are pushed to configured repo as a PR
• PR includes structured results summary
• Human must merge — no auto-merge
• Works with agentv eval run and agentv pipeline commands
• Graceful fallback if repo is not accessible (warning, not error)

Non-Goals

• Auto-merging PRs (human review required)
• Real-time streaming of results
• Dashboard integration (separate concern — feat: AgentV Studio — eval management platform with historical trends, quality gates, and orchestration #563)

Related

• EntityProcess/agentv-evals — current manual results repo
• feat: AgentV Studio — eval management platform with historical trends, quality gates, and orchestration #563 — Studio eval management platform
• refactor(pipeline): align output paths, drop target from path, rename to subagent mode #801 — artifact structure standardization