Add task detail view, pipeline visualization, approve/reject workflow

API (web/api.py) — 5 new endpoints:
  GET  /api/tasks/{id}/pipeline — agent_logs as pipeline steps
  GET  /api/tasks/{id}/full — task + steps + related decisions
  POST /api/tasks/{id}/approve — mark done, optionally add decision
  POST /api/tasks/{id}/reject — return to pending with reason
  POST /api/tasks/{id}/run — launch pipeline in background (202)

Frontend:
  TaskDetail (/task/:id) — full task page with:
    - Pipeline graph: role cards with icons, arrows, status colors
    - Click step → expand output (pre-formatted, JSON detected)
    - Action bar: Approve (with optional decision), Reject, Run Pipeline
    - Polling for live pipeline updates
  Dashboard: review_tasks badge ("awaiting review" in yellow)
  ProjectView: task rows are now clickable links to /task/:id

Runner: output_summary no longer truncated (full output for GUI).
Models: get_project_summary includes review_tasks count.

13 new API tests, 105 total, all passing. Frontend builds clean.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

tests/test_api.py

@@ -0,0 +1,147 @@
+"""Tests for web/api.py — new task endpoints (pipeline, approve, reject, full)."""
+
+import pytest
+from pathlib import Path
+from fastapi.testclient import TestClient
+
+# Patch DB_PATH before importing app
+import web.api as api_module
+
+@pytest.fixture
+def client(tmp_path):
+    db_path = tmp_path / "test.db"
+    api_module.DB_PATH = db_path
+    from web.api import app
+    c = TestClient(app)
+    # Seed data
+    c.post("/api/projects", json={"id": "p1", "name": "P1", "path": "/p1"})
+    c.post("/api/tasks", json={"project_id": "p1", "title": "Fix bug"})
+    return c
+
+
+def test_get_task(client):
+    r = client.get("/api/tasks/P1-001")
+    assert r.status_code == 200
+    assert r.json()["title"] == "Fix bug"
+
+
+def test_get_task_not_found(client):
+    r = client.get("/api/tasks/NOPE")
+    assert r.status_code == 404
+
+
+def test_task_pipeline_empty(client):
+    r = client.get("/api/tasks/P1-001/pipeline")
+    assert r.status_code == 200
+    assert r.json() == []
+
+
+def test_task_pipeline_with_logs(client):
+    # Insert agent logs directly
+    from core.db import init_db
+    from core import models
+    conn = init_db(api_module.DB_PATH)
+    models.log_agent_run(conn, "p1", "debugger", "execute",
+                         task_id="P1-001", output_summary="Found bug",
+                         tokens_used=1000, duration_seconds=5, success=True)
+    models.log_agent_run(conn, "p1", "tester", "execute",
+                         task_id="P1-001", output_summary="Tests pass",
+                         tokens_used=500, duration_seconds=3, success=True)
+    conn.close()
+
+    r = client.get("/api/tasks/P1-001/pipeline")
+    assert r.status_code == 200
+    steps = r.json()
+    assert len(steps) == 2
+    assert steps[0]["agent_role"] == "debugger"
+    assert steps[0]["output_summary"] == "Found bug"
+    assert steps[1]["agent_role"] == "tester"
+
+
+def test_task_full(client):
+    r = client.get("/api/tasks/P1-001/full")
+    assert r.status_code == 200
+    data = r.json()
+    assert data["id"] == "P1-001"
+    assert "pipeline_steps" in data
+    assert "related_decisions" in data
+
+
+def test_task_full_not_found(client):
+    r = client.get("/api/tasks/NOPE/full")
+    assert r.status_code == 404
+
+
+def test_approve_task(client):
+    # First set task to review
+    from core.db import init_db
+    from core import models
+    conn = init_db(api_module.DB_PATH)
+    models.update_task(conn, "P1-001", status="review")
+    conn.close()
+
+    r = client.post("/api/tasks/P1-001/approve", json={})
+    assert r.status_code == 200
+    assert r.json()["status"] == "done"
+
+    # Verify task is done
+    r = client.get("/api/tasks/P1-001")
+    assert r.json()["status"] == "done"
+
+
+def test_approve_with_decision(client):
+    r = client.post("/api/tasks/P1-001/approve", json={
+        "decision_title": "Use AbortController",
+        "decision_description": "Fix race condition with AbortController",
+        "decision_type": "decision",
+    })
+    assert r.status_code == 200
+    assert r.json()["decision"] is not None
+    assert r.json()["decision"]["title"] == "Use AbortController"
+
+
+def test_approve_not_found(client):
+    r = client.post("/api/tasks/NOPE/approve", json={})
+    assert r.status_code == 404
+
+
+def test_reject_task(client):
+    from core.db import init_db
+    from core import models
+    conn = init_db(api_module.DB_PATH)
+    models.update_task(conn, "P1-001", status="review")
+    conn.close()
+
+    r = client.post("/api/tasks/P1-001/reject", json={
+        "reason": "Didn't fix the root cause"
+    })
+    assert r.status_code == 200
+    assert r.json()["status"] == "pending"
+
+    # Verify task is pending with review reason
+    r = client.get("/api/tasks/P1-001")
+    data = r.json()
+    assert data["status"] == "pending"
+    assert data["review"]["rejected"] == "Didn't fix the root cause"
+
+
+def test_reject_not_found(client):
+    r = client.post("/api/tasks/NOPE/reject", json={"reason": "bad"})
+    assert r.status_code == 404
+
+
+def test_task_pipeline_not_found(client):
+    r = client.get("/api/tasks/NOPE/pipeline")
+    assert r.status_code == 404
+
+
+def test_project_summary_includes_review(client):
+    from core.db import init_db
+    from core import models
+    conn = init_db(api_module.DB_PATH)
+    models.update_task(conn, "P1-001", status="review")
+    conn.close()
+
+    r = client.get("/api/projects")
+    projects = r.json()
+    assert projects[0]["review_tasks"] == 1