Capstone — Autonomous Coding Agent (Issue → Tested, HITL-Gated PR)

# capstone/pipeline.py — glue for the six stages
from langfuse import observe          # tracing from Module 7

@observe()
def solve_issue(issue_url_or_path: str, repo_full: str) -> dict:
    issue = load_issue(issue_url_or_path)        # TODO: GitHub API or local file

    workspace = make_sandbox(repo_full)          # TODO: git worktree OR container
    try:
        plan = explore_and_plan(issue.text)      # checkpointed to plan.json
        outcome = repair(plan, issue.text)       # bounded red->green loop (max 5)

        tests = run_tests()                       # final verification
        diff = git_diff(workspace)               # TODO: git diff in the sandbox
        cost = current_trace_cost()              # TODO: pull from your tracing

        if outcome["status"] == "success" and tests["passed"]:
            url = open_pr_if_approved(            # HITL gate — draft PR only on 'y'
                repo_full, branch=workspace.branch, base="main",
                title=pr_title(issue), body=pr_body(issue, outcome),
                diff=diff, cost_usd=cost,
            )
            return {"issue": issue.id, "result": "pr_proposed", "url": url,
                    "cost_usd": cost}
        return {"issue": issue.id, "result": outcome["status"],
                "cost_usd": cost}
    finally:
        cleanup_sandbox(workspace)               # discard the throwaway tree

# capstone/evaluate.py — run across the issue set, score with the taxonomy
def evaluate(issue_set) -> dict:
    results = []
    for spec in issue_set:                       # TODO: >= 10, real + seeded
        run = solve_issue(spec.url, spec.repo)
        results.append(score_to_taxonomy(run, spec.ground_truth))
    return report(results)                        # success rate + taxonomy + cost/time