DeepReport - Intelligence Gathering Agent #159
deep-report.lock.yml
on: schedule
activation
1m 39s
push_repo_memory
17s
safe_outputs
1m 12s
update_cache_memory
17s
conclusion
16s
Annotations
2 errors and 2 warnings
|
agent
`. We need pre-checks and accurate counter accounting.\n\n#### 2. Workflow infrastructure had a rough day on 2026-05-16\n\n- **30% failure rate** across 63 audited runs ([#32712](https://github.com/github/gh-aw/discussions/32712))\n- **Smoke CI: 64% failure** (7/11), **LintMonster: 75%** (3/4), **PR Sous Chef: 38%** (3/8)\n- **9 OPEN [aw] failure issues** as of today: Daily Cache Strategy Analyzer (#32876), Design Decision Gate (#32870), Daily Issues Report Generator (#32830), Draft PR Cleanup (#32797), Dev (#32790), Daily Hippo Learn (#32776), Detection Runs (#32316), No-Op Runs (#32279), agentic workflows out of sync (#32270)\n- Top cause: **Safe Outputs MCP HTTP Server startup failure** (4+ recurrences in 24h)\n- Cost outlier: **Daily Safe Output Tool Optimizer** at $5.99 / 28.6M tokens (~34% of daily spend, failed)\n\n#### 3. Schema vs. parser disagreements\n\nThe Schema Consistency Audit ([#32772](https://github.com/github/gh-aw/discussions/32772)) caught two new high-signal drifts:\n\n- **`tools.serena`**: schema declares `x-removed: true`, parser still treats it as a built-in MCP tool with explicit handling at `pkg/parser/mcp.go:186, 214, 425`. IDE schema integration shows REMOVED; runtime silently accepts.\n- **`engine.bare` for Codex/Gemini**: docs feature matrix says ✅, schema description says supported, compiler at `agent_validation.go:229` warns and ignores. Three sources disagree.\n\n#### 4. Helper underadoption (Sergo's persistent theme)\n\nFour of five prior Sergo findings are fixed in main, validating that the agent's recommendations land ([#32753](https://github.com/github/gh-aw/discussions/32753)). Two persist:\n\n- **`isPermissionError`** centralized at `pkg/cli/audit.go:250` — 3 sites already drifted (`logs_download.go:312/802`, `logs_github_api.go:286-291` with different superset)\n- **`isNotFoundError`** — `pkg/parser/remote_fetch.go:610` is unexported and takes `string`; 4 `pkg/cli` sites reimplement inline; `outcome_eval_comment.go:34` is silently buggy due to case-sensitive matching\n- **HTTP 30s timeout literal** at 4 sites — Run 8 finding `#aw_sg8a2`, **open 13+ days**, no `DefaultHTTPClientTimeout` in `pkg/constants`\n\n#### 5. Skill-extraction debt unchanged from prior briefings\n\nThe Workflow Skill Extractor ([#32054](https://github.com/github/gh-aw/discussions/32054)) re-confirmed three high-impact patterns still un-DRY'd:\n\n| Pattern | Workflows | Lines |\n|---|---|---|\n| `cli-proxy + github: gh-proxy + toolsets: [default]` | **63** | ~252 |\n| `strict: true + features: copilot-requests: true` | 29 | ~87 |\n| `agentic-workflows + cli-proxy + timeout: 300` | 19 | ~76 |\n\nCombined: ~415 lines across 111 distinct workflows. The existing `shared/gh.md` covers `mode` only, so the largest pattern can't be DRYed today.\n\n#### 6. Documentation drift for non-Copilot users\n\nThe Claude Code User Documentation Review ([#32807](https://github.com/github/gh-aw/discussions/32807)) flagged the same items for the **third day running**:\n\n- README has **zero engine signal** — no mention of Claude/Anthropic/Codex/Gemini\n- `gh aw init` silently installs Copilot-only `.github/agents/agentic-workflows.agent.md`\n- `engines.md:28` still recommends *against* the user's chosen engine: *\"If you are unsure, start with Copilot.\"*\n- Quick Start ordering puts the Copilot setup callout (lines 76–80) before the Anthropic key callout (lines 82–86)\n\nTrend: **stable — no regressions, no measurable fixes either.**\n\n---\n\n### 📊 Trends Worth Watching\n\n#### Encouraging signals\n\n- **Copilot agent merge rate**: 80.2% across 998 PRs in a 2.5-week window. Inline sub-agent cluster at 100% (n=22).\n- **PR velocity**: avg merge time 1.1h, issue resolution 16.8h — both excellent.\n- **Secrets posture**: 100% workflows with explicit `permissions:` blocks, 100% with redaction steps, 860 token-cascade fallbacks, zero raw `github.event.*` interpolations.\n- **Cache strategy**: 12/12 cache-memory runs scored a cache hit today; only watch-item is Chaos PR Bundle Fuzzer (already tracked).\n- **Hippo m
|
|
safe_outputs
Unable to download artifact(s): Artifact not found for name: safe-outputs-upload-artifacts
Please ensure that your artifact is not expired and the artifact was uploaded using a compatible version of toolkit/upload-artifact.
For more information, visit the GitHub Artifacts FAQ: https://github.com/actions/toolkit/blob/main/packages/artifact/docs/faq.md
|
|
push_repo_memory
Skipping file that does not match allowed patterns: memory/default/flagged_items.md
|
|
push_repo_memory
Skipping file that does not match allowed patterns: memory/deep-report/flagged_items.md
|
Artifacts
Produced during runtime
| Name | Size | Digest | |
|---|---|---|---|
|
activation
Expired
|
5.39 MB |
sha256:e8b5f1eea12bbb1e5bacd1b3d03a3a8d74ac0ebd22d7ed887f41c95d93afd2d7
|
|
|
agent
|
378 KB |
sha256:237ffeb85a74cb7700e6d04dcc765d4f6e5490eadaaa2487e8b855ce69946c79
|
|
|
cache-memory
|
3.72 MB |
sha256:9b3ec63c3425263ce40a49586f6e17f5af0711b8543a42e5a974718ce615d26d
|
|
|
deepreport-experiment
Expired
|
665 Bytes |
sha256:997967cf21de11db0fe61a86ddfd98ce406a7d6347ccdcc3722f81eeb1f3cf81
|
|
|
detection
|
21.1 KB |
sha256:da5f34080ef83c1054d27c9a95ae19bd7747812baf8932faaebfb0be8933f399
|
|
|
github~gh-aw~RD362M.dockerbuild
|
23.1 KB |
sha256:8732483297bb6ed1c8b62b853118b9e72fa09338dab579b8dc80de1e68e86f53
|
|
|
repo-memory-default
Expired
|
12.3 KB |
sha256:a1775fc379687b30365cd0043bbffa0cf7398b862195539e2d65b951a9326609
|
|
|
safe-outputs-items
|
748 Bytes |
sha256:19738b667f00c2a67f96a693c30ba4707dac295874a38bcce9d39aab5b57e524
|
|