[Copilot]

Haiku wraps valid classifier JSON in Markdown fences, causing Haiku-only pools to route without classification and record invalid_classifier_output.

• Normalization: Strip one complete wrapping fence, optionally labelled json, with surrounding whitespace. Apply the existing JSON parser and schema validation to its contents.
• Strictness: Continue rejecting surrounding prose, multiple fenced blocks, other labels, malformed JSON, and invalid schemas. Extraction, retry behavior, and degraded reasons remain unchanged.
• Regression coverage: Add named contract tests and controller coverage for classified Haiku selections and still-invalid fenced replies.

The validator would accept:

```json
{"labels":{"task_type":"explain","scope":"local","task_complexity":"unknown"},"mode":"economy"}
```

• Fixes [Routing]: Classifier replies wrapped in a Markdown code fence are rejected, so Haiku-only pools always route unclassified #9926

[Copilot]

🟢 Approval recommended

The focused implementation satisfies the stated strictness requirements with comprehensive regression coverage.

0 open findings

What changed in this PR

Adds strict normalization for Haiku classifier responses wrapped in Markdown fences while preserving existing schema validation and degraded-routing behavior.

Changes:

• Unwraps one complete json or unlabelled code fence.
• Rejects prose, multiple blocks, unsupported labels, malformed JSON, and invalid schemas.
• Adds contract and controller regression coverage.

File	Description
containers/​api-proxy/​routing-contract.js	Normalizes fenced classifier output before parsing.
containers/​api-proxy/​routing-contract.test.js	Covers accepted and rejected fence variants.
containers/​api-proxy/​routing-controller.test.js	Verifies classification and degradation records.

🧠 Review effort: Balanced

---

💡 Add a code-review agent skill or configure MCP servers for context-aware, tailored reviews. Learn more in the docs.

[github-actions]

✅ Copilot review passed with no inline comments.

@copilot Add the ready-for-aw label to this PR to trigger agentic CI smoke tests.

[github-actions]

✅ Coverage Check Passed

Overall Coverage

Metric	Base	PR	Delta
Lines	93.16%	93.17%	📈 +0.01%
Statements	91.71%	91.72%	📈 +0.01%
Functions	90.38%	90.38%	➡️ +0.00%
Branches	85.47%	85.48%	📈 +0.01%

📁 Per-file Coverage Changes (1 files)

File	Lines (Before → After)	Statements (Before → After)
src/log-directory-setup.ts	96.8% → 100.0% (+3.18%)	96.9% → 100.0% (+3.13%)

---

Coverage comparison generated by scripts/ci/compare-coverage.ts

[github-actions]

✨ The prophecy is fulfilled... Smoke Codex has completed its mystical journey. The stars align. 🌟

🔮 The oracle has spoken through Smoke Codex

[github-actions]

🪪 Smoke Copilot BYOK AOAI (Entra) is testing Azure OpenAI BYOK (Entra / GitHub OIDC) mode on this pull request...

[github-actions]

✅ Build Test Suite completed successfully!

Generated by Build Test Suite for #9930

[github-actions]

✅ Smoke Claude passed

Generated by Smoke Claude for #9930

[github-actions]

💎 Smoke Gemini is crystallizing results on this pull request...

[github-actions]

✅ Smoke Copilot BYOK completed. Copilot BYOK mode operational. 🔓

🔑 BYOK report filed by Smoke Copilot BYOK

[github-actions]

Smoke Cloud Hypervisor completed. Cloud Hypervisor + Copilot passed.

Cloud Hypervisor + Copilot smoke test by Smoke Cloud Hypervisor

[github-actions]

Chroot tests passed! Smoke Chroot - All security and functionality tests succeeded.

Tested by Smoke Chroot

[github-actions]

🛡️ Smoke Copilot Network Isolation confirmed the egress allowlist is enforced. ✅

🛡️ Egress verdict from Smoke Copilot Network Isolation

[github-actions]

🔌 Smoke Services — All services reachable! ✅

🔌 Service connectivity validated by Smoke Services

[github-actions]

📰 VERDICT: Smoke Copilot has concluded. All systems operational. This is a developing story. 🎤

📰 BREAKING: Report filed by Smoke Copilot

[github-actions]

📡 Smoke OTel Tracing completed. All tracing scenarios validated. ✅

📡 OTel tracing validated by Smoke OTel Tracing

[github-actions]

🔑 Smoke Copilot BYOK AOAI (api-key) is testing Azure OpenAI BYOK (api-key) mode on this pull request...

[github-actions]

✅ Security Guard completed successfully!

Security Guard

Outcome: reported_no_action

The agent completed and reported no action. A no-op output alone does not verify that all required work was completed or that publication was possible.

Agent messages are omitted from this comment. The category uses structured run status, not interpretation of agent prose.

Generated from Security Guard · haiku45 · 4.06 AIC · ⊞ 6.0K · ◷

Generated by Security Guard for #9930

[github-actions]

EGRESS_RESULT allow=pass deny=pass

• ✅ Allowed domain (api.github.com): HTTP 200
• ✅ Blocked domain (example.com): blocked (curl failed with SSL cert error, no response returned)

Overall: PASS. cc @lpcox

🛡️ Egress verdict from Smoke Copilot Network Isolation
_{Add label ready-for-aw to run again}

[github-actions]

Smoke Test: Cloud Hypervisor + Copilot

1. PASS — list_pull_requests returned closed PR feat: add staged Phase 4 pilot tiers #9931
2. PASS — https://github.com returned 200
3. PASS — wrote/read unique line in /tmp/gh-aw/agent/smoke-cloud-hypervisor-38448333600.txt
4. PASS — (example.com/redacted) blocked with 000 (connection refused by firewall)

All checks passed.

Cloud Hypervisor + Copilot smoke test by Smoke Cloud Hypervisor
_{Add label ready-for-aw to run again}

[github-actions]

Smoke Test: Claude Engine Validation

Check	Status
API	✅ PASS
gh CLI	✅ PASS
File	✅ PASS

Overall result: PASS

Generated by Smoke Claude for #9930 · claude · haiku45 · 24.1 AIC · ⊞ 6.1K · ◷
_{Add label ready-for-aw to run again}

[github-actions]

Smoke Test: Copilot BYOK (Direct Mode)

✅ All tests passed — Direct BYOK mode active (COPILOT_PROVIDER_API_KEY → api-proxy → api.githubcopilot.com)

• ✅ MCP: GitHub connectivity confirmed
• ✅ HTTP: Code 200 (github.com accessible)
• ✅ File: Smoke test file written and readable
• ✅ BYOK Inference: Direct mode working (Copilot responding via api-proxy sidecar)

Status: PASS
@lpcox

🔑 BYOK report filed by Smoke Copilot BYOK
_{Add label ready-for-aw to run again}

[github-actions]

Smoke Copilot: PASS

• PR: "fix(api-proxy): accept fenced classifier JSON replies"
• ✅ GitHub MCP
• ✅ github.com (HTTP 200)
• ✅ File write/read
  @Copilot (author), assignees: @lpcox @Copilot

📰 BREAKING: Report filed by Smoke Copilot
_{Add label ready-for-aw to run again}

[github-actions]

OTEL smoke test

• ✅ S1 Module loading: otel.js exports startRequestSpan, setTokenAttributes, setBudgetAttributes, endSpan, endSpanError, shutdown, isEnabled (+ internals)
• ✅ S2 Tests: 68/68 passed (3 suites)
• ✅ S3 Env forwarding: trace context in env-passthrough.ts; OTEL vars in api-proxy-env-config.ts
• ✅ S4 Token tracker: onUsage hook present in token-tracker-http.js
• ✅ S5 Diagnostics: /tmp/gh-aw/otel.jsonl has 1 record

📡 OTel tracing validated by Smoke OTel Tracing
_{Add label ready-for-aw to run again}

[github-actions]

Services smoke test: ✅ Redis PONG, ✅ pg_isready accepting connections, ✅ SELECT 1 = 1. PASS

🔌 Service connectivity validated by Smoke Services
_{Add label ready-for-aw to run again}

[github-actions]

Chroot Version Comparison

Runtime	Host Version	Chroot Version	Match?
Python	Python 3.12.15	Python 3.12.15	✅ YES
Node.js	v24.21.0	v22.23.2	❌ NO
Go	go1.22.12	go1.22.12	✅ YES

Result: Not all tests passed (Node.js version mismatch), so the smoke-chroot label was not added.

Tested by Smoke Chroot
_{Add label ready-for-aw to run again}

[github-actions]

🏗️ Build Test Suite Results

Ecosystem	Project	Build/Install	Tests	Status
Bun	elysia	❌	not run	❌ FAIL
Bun	hono	❌	not run	❌ FAIL
C++	fmt	✅	N/A	✅ PASS
C++	json	✅	N/A	✅ PASS
Deno	oak	N/A	not run	❌ FAIL
Deno	std	N/A	not run	❌ FAIL
.NET	hello-world	✅	N/A	✅ PASS
.NET	json-parse	✅	N/A	✅ PASS
Go	color	✅	pass	✅ PASS
Go	env	✅	pass	✅ PASS
Go	uuid	✅	pass	✅ PASS
Java	gson	✅	1/1 passed	✅ PASS
Java	caffeine	✅	1/1 passed	✅ PASS
Node.js	clsx	✅	passed	✅ PASS
Node.js	execa	✅	passed	✅ PASS
Node.js	p-limit	✅	passed	✅ PASS
Rust	fd	✅	1/1 passed	✅ PASS
Rust	zoxide	✅	1/1 passed	✅ PASS

Overall: 6/8 ecosystems passed — FAIL

Failures

• Bun and Deno: the curl | bash / curl | sh installers were blocked by the sandbox (permission denied). Bun and Deno are not preinstalled, so no tests ran.
• Java note: ~/.m2 is not writable (LocalRepositoryNotAccessibleException). Java passed using -Dmaven.repo.local=/tmp/gh-aw/agent/m2.

Generated by Build Test Suite for #9930 · copilot · auto · 17 AIC · ⊞ 11.9K · ◷
_{Add label ready-for-aw to run again}

[github-actions]

feat: add staged Phase 4 pilot tiers
Fix Codex tool-output IDs in Copilot Responses translation
Merged PR review ✅
PR detail lookup ✅
Playwright title check ❌
File write/read ✅
Discussion lookup/comment ✅
Build AWF ✅
Overall status: FAIL

🔮 The oracle has spoken through Smoke Codex
_{Add label ready-for-aw to run again}