fix: finish full bounded GLM review

Author: srinitude

.github/workflows/pi-runtime-review.lock.yml

@@ -25,7 +25,7 @@ engine:
   env:
     OPENAI_BASE_URL: https://api.z.ai/api/coding/paas/v4
 strict: true
-max-turns: 32
+max-turns: 40
 max-ai-credits: 100
 timeout-minutes: 30
 network:

.github/workflows/pi-runtime-review.md

@@ -224,7 +224,7 @@ Any `extensions/**` change starts a separate read-only gh-aw review using:
 - repository secret `OPENAI_API_KEY` containing the personal Z.AI Coding Plan key, as required by gh-aw's universal OpenCode provider contract;
 - network access limited to required GitHub/AWF and `api.z.ai` endpoints.
 
-OpenCode is used because Z.AI lists it as a supported Coding Plan tool. The Coding Plan key is not routed through Copilot CLI. Pinned gh-aw `0.82.14` incorrectly emits its Copilot proxy as OpenCode's default provider even when `openai/glm-5.2` is selected; the deterministic post-compile patch rewrites both generated OpenCode configs to `awf-proxy/glm-5.2` on the OpenAI proxy, and an invariant test rejects any Copilot fallback. Remove this workaround only after a pinned gh-aw upgrade proves the generated provider correct. The review allows at most 32 LLM invocations because OpenCode spends one invocation generating a title and the full lockstep review empirically required more than 16 bounded follow-up invocations after read-only tool calls; the independent `$1` AI-credit cap remains the harder cost bound. The generated OpenCode provider configuration must demonstrably forward `reasoning_effort: xhigh`; silent fallback to a default effort fails preflight. A strict compilation and live tool/structured-output smoke test must pass before auto-merge is enabled.
+OpenCode is used because Z.AI lists it as a supported Coding Plan tool. The Coding Plan key is not routed through Copilot CLI. Pinned gh-aw `0.82.14` incorrectly emits its Copilot proxy as OpenCode's default provider even when `openai/glm-5.2` is selected; the deterministic post-compile patch rewrites both generated OpenCode configs to `awf-proxy/glm-5.2` on the OpenAI proxy, and an invariant test rejects any Copilot fallback. Remove this workaround only after a pinned gh-aw upgrade proves the generated provider correct. The review allows at most 40 LLM invocations because OpenCode spends one invocation generating a title and the full lockstep review empirically exhausted 32 bounded follow-up invocations while inspecting the large rewrite; the independent `$1` AI-credit cap remains the harder cost bound. The generated OpenCode provider configuration must demonstrably forward `reasoning_effort: xhigh`; silent fallback to a default effort fails preflight. A strict compilation and live tool/structured-output smoke test must pass before auto-merge is enabled.
 
 The reviewer sees the contract, diff, test changes, and CI evidence. It cannot edit, push, approve with a GitHub identity, or access the App key. It emits a strict verdict and findings. Rejection, malformed output, quota exhaustion, or unavailability blocks auto-merge and escalates.
 

docs/superpowers/specs/2026-07-22-pi-081-lockstep-rewrite-design.md

@@ -49,7 +49,7 @@ describe("Pi lockstep agentic workflows", () => {
 		expect(source).toContain('version: "1.2.14"');
 		expect(source).toContain('input: "1.1268e-06"');
 		expect(source).toContain('output: "3.9438e-06"');
-		expect(source).toContain("max-turns: 32");
+		expect(source).toContain("max-turns: 40");
 		expect(source).toContain("max-ai-credits: 100");
 		expect(source).toContain("https://api.z.ai/api/coding/paas/v4");
 		expect(source).toContain("OPENAI_BASE_URL");