@phi-code-admin/phi-code 0.90.0 → 0.92.0

package/CHANGELOG.md

@@ -1,5 +1,59 @@
 # Changelog
 
+## [0.92.0] - 2026-07-11
+
+### Fixed — the two defects the n=13 SWE-bench measurement exposed
+
+The measured head-to-head (baseline 7/13 vs /debug 6/13, official harness) traced
+/debug's two lost points to concrete, reparable defects — both fixed here.
+
+- **Hasty BLOCKED (sympy-11897, halted at 51s).** The generic /debug//build
+  driver now routes phase completion through the same pure decision machine as
+  /plan (`decidePhaseTransition`), gaining what it measurably lacked: a fatal
+  401 stops the run, a transient provider error (timeout / 5xx / 429 / broken
+  stream) retries the SAME phase once on the fallback model instead of being
+  swallowed, and — new — a BLOCKED verdict gets ONE second chance on the
+  fallback model (a different family re-checks the reproduction) before the
+  halt. A confirmed second BLOCKED still halts honestly: no fabricated fix.
+  REPRODUCE's instructions now state BLOCKED is a last resort — adjust and
+  retry once before concluding.
+- **Timeout-blind VERIFY (sympy-11870, fix passed its repro but hung the real
+  suite for 900s).** VERIFY's instructions now treat a TIMEOUT of the
+  reproduction or the suite as a FAILURE of the candidate — a massive slowdown
+  or infinite loop IS a regression — with verdict BLOCKED, never FIXED. A
+  dramatic duration increase below the timeout is flagged as a red flag too.
+
+8 integration tests cover the new behaviours (BLOCKED retry → honest halt,
+BLOCKED retry → proceed on success, transient-error retry); full suite green
+(1439).
+
+## [0.91.0] - 2026-07-11
+
+### Added — Alibaba Cloud Coding Plan, first-class and one-command
+
+The Alibaba Coding Plan support (endpoints, live catalog, ping, wizard) already
+existed but was only reachable through the interactive `/setup` wizard — a user
+could not simply add the provider. Verified against the official docs
+(https://www.alibabacloud.com/help/en/model-studio/coding-plan) and a live API
+round-trip (catalog listing + a real `qwen3.7-plus` completion).
+
+- **`/keys set` now bootstraps known providers.** `providers/provider-bootstrap.ts`
+  (pure, 11 tests) builds a complete first-time models.json entry — baseUrl, api
+  protocol, bundled model list — from a single API key, with each provider's own
+  key-format validation applied up front (`sk-sp-` prefix for Alibaba). One
+  command configures the provider end to end:
+  `/keys set alibaba-codingplan sk-sp-…` — then the session-start refresh
+  replaces the bundled list with the live catalog. Bootstrappable ids:
+  `alibaba-codingplan`, `alibaba-codingplan-anthropic`, `opencode-go`,
+  `opencode-go-anthropic`. Unknown providers keep the previous /setup guidance.
+- **`/keys test` now actually works.** `registerProviderPing` existed but nothing
+  ever called it; keys.ts now registers the built-in pings (Alibaba, OpenCode Go)
+  at load, so `/keys test alibaba-codingplan` validates the key against the real
+  `/v1/models` endpoint.
+- **Provider display names.** `alibaba-codingplan`, `alibaba-codingplan-anthropic`
+  and `opencode-go-anthropic` now render with proper names in the /model picker
+  (they fell back to raw ids).
+
 ## [0.90.0] - 2026-07-11
 
 ### Added — the execution sandbox (the guaranteed oracle)

package/dist/core/provider-display-names.d.ts.map

@@ -1 +1 @@
-{"version":3,"file":"provider-display-names.d.ts","sourceRoot":"","sources":["../../src/core/provider-display-names.ts"],"names":[],"mappings":"AAAA,eAAO,MAAM,+BAA+B,EAAE,MAAM,CAAC,MAAM,EAAE,MAAM,CA+BlE,CAAC","sourcesContent":["export const BUILT_IN_PROVIDER_DISPLAY_NAMES: Record<string, string> = {\n\tanthropic: \"Anthropic\",\n\t\"amazon-bedrock\": \"Amazon Bedrock\",\n\t\"azure-openai-responses\": \"Azure OpenAI Responses\",\n\tcerebras: \"Cerebras\",\n\t\"cloudflare-ai-gateway\": \"Cloudflare AI Gateway\",\n\t\"cloudflare-workers-ai\": \"Cloudflare Workers AI\",\n\tdeepseek: \"DeepSeek\",\n\tfireworks: \"Fireworks\",\n\tgoogle: \"Google Gemini\",\n\t\"google-vertex\": \"Google Vertex AI\",\n\tgroq: \"Groq\",\n\thuggingface: \"Hugging Face\",\n\t\"kimi-coding\": \"Kimi For Coding\",\n\tmistral: \"Mistral\",\n\tminimax: \"MiniMax\",\n\t\"minimax-cn\": \"MiniMax (China)\",\n\tmoonshotai: \"Moonshot AI\",\n\t\"moonshotai-cn\": \"Moonshot AI (China)\",\n\topencode: \"OpenCode Zen\",\n\t\"opencode-go\": \"OpenCode Go\",\n\topenai: \"OpenAI\",\n\topenrouter: \"OpenRouter\",\n\ttogether: \"Together AI\",\n\t\"vercel-ai-gateway\": \"Vercel AI Gateway\",\n\txai: \"xAI\",\n\tzai: \"ZAI\",\n\txiaomi: \"Xiaomi MiMo\",\n\t\"xiaomi-token-plan-cn\": \"Xiaomi MiMo Token Plan (China)\",\n\t\"xiaomi-token-plan-ams\": \"Xiaomi MiMo Token Plan (Amsterdam)\",\n\t\"xiaomi-token-plan-sgp\": \"Xiaomi MiMo Token Plan (Singapore)\",\n};\n"]}
+{"version":3,"file":"provider-display-names.d.ts","sourceRoot":"","sources":["../../src/core/provider-display-names.ts"],"names":[],"mappings":"AAAA,eAAO,MAAM,+BAA+B,EAAE,MAAM,CAAC,MAAM,EAAE,MAAM,CAkClE,CAAC","sourcesContent":["export const BUILT_IN_PROVIDER_DISPLAY_NAMES: Record<string, string> = {\n\t\"alibaba-codingplan\": \"Alibaba Coding Plan\",\n\t\"alibaba-codingplan-anthropic\": \"Alibaba Coding Plan (Anthropic-compat)\",\n\tanthropic: \"Anthropic\",\n\t\"amazon-bedrock\": \"Amazon Bedrock\",\n\t\"azure-openai-responses\": \"Azure OpenAI Responses\",\n\tcerebras: \"Cerebras\",\n\t\"cloudflare-ai-gateway\": \"Cloudflare AI Gateway\",\n\t\"cloudflare-workers-ai\": \"Cloudflare Workers AI\",\n\tdeepseek: \"DeepSeek\",\n\tfireworks: \"Fireworks\",\n\tgoogle: \"Google Gemini\",\n\t\"google-vertex\": \"Google Vertex AI\",\n\tgroq: \"Groq\",\n\thuggingface: \"Hugging Face\",\n\t\"kimi-coding\": \"Kimi For Coding\",\n\tmistral: \"Mistral\",\n\tminimax: \"MiniMax\",\n\t\"minimax-cn\": \"MiniMax (China)\",\n\tmoonshotai: \"Moonshot AI\",\n\t\"moonshotai-cn\": \"Moonshot AI (China)\",\n\topencode: \"OpenCode Zen\",\n\t\"opencode-go\": \"OpenCode Go\",\n\t\"opencode-go-anthropic\": \"OpenCode Go (Anthropic-compat)\",\n\topenai: \"OpenAI\",\n\topenrouter: \"OpenRouter\",\n\ttogether: \"Together AI\",\n\t\"vercel-ai-gateway\": \"Vercel AI Gateway\",\n\txai: \"xAI\",\n\tzai: \"ZAI\",\n\txiaomi: \"Xiaomi MiMo\",\n\t\"xiaomi-token-plan-cn\": \"Xiaomi MiMo Token Plan (China)\",\n\t\"xiaomi-token-plan-ams\": \"Xiaomi MiMo Token Plan (Amsterdam)\",\n\t\"xiaomi-token-plan-sgp\": \"Xiaomi MiMo Token Plan (Singapore)\",\n};\n"]}

package/dist/core/provider-display-names.js

@@ -1,4 +1,6 @@
 export const BUILT_IN_PROVIDER_DISPLAY_NAMES = {
+    "alibaba-codingplan": "Alibaba Coding Plan",
+    "alibaba-codingplan-anthropic": "Alibaba Coding Plan (Anthropic-compat)",
     anthropic: "Anthropic",
     "amazon-bedrock": "Amazon Bedrock",
     "azure-openai-responses": "Azure OpenAI Responses",
@@ -19,6 +21,7 @@ export const BUILT_IN_PROVIDER_DISPLAY_NAMES = {
     "moonshotai-cn": "Moonshot AI (China)",
     opencode: "OpenCode Zen",
     "opencode-go": "OpenCode Go",
+    "opencode-go-anthropic": "OpenCode Go (Anthropic-compat)",
     openai: "OpenAI",
     openrouter: "OpenRouter",
     together: "Together AI",

package/dist/core/provider-display-names.js.map

@@ -1 +1 @@
-{"version":3,"file":"provider-display-names.js","sourceRoot":"","sources":["../../src/core/provider-display-names.ts"],"names":[],"mappings":"AAAA,MAAM,CAAC,MAAM,+BAA+B,GAA2B;IACtE,SAAS,EAAE,WAAW;IACtB,gBAAgB,EAAE,gBAAgB;IAClC,wBAAwB,EAAE,wBAAwB;IAClD,QAAQ,EAAE,UAAU;IACpB,uBAAuB,EAAE,uBAAuB;IAChD,uBAAuB,EAAE,uBAAuB;IAChD,QAAQ,EAAE,UAAU;IACpB,SAAS,EAAE,WAAW;IACtB,MAAM,EAAE,eAAe;IACvB,eAAe,EAAE,kBAAkB;IACnC,IAAI,EAAE,MAAM;IACZ,WAAW,EAAE,cAAc;IAC3B,aAAa,EAAE,iBAAiB;IAChC,OAAO,EAAE,SAAS;IAClB,OAAO,EAAE,SAAS;IAClB,YAAY,EAAE,iBAAiB;IAC/B,UAAU,EAAE,aAAa;IACzB,eAAe,EAAE,qBAAqB;IACtC,QAAQ,EAAE,cAAc;IACxB,aAAa,EAAE,aAAa;IAC5B,MAAM,EAAE,QAAQ;IAChB,UAAU,EAAE,YAAY;IACxB,QAAQ,EAAE,aAAa;IACvB,mBAAmB,EAAE,mBAAmB;IACxC,GAAG,EAAE,KAAK;IACV,GAAG,EAAE,KAAK;IACV,MAAM,EAAE,aAAa;IACrB,sBAAsB,EAAE,gCAAgC;IACxD,uBAAuB,EAAE,oCAAoC;IAC7D,uBAAuB,EAAE,oCAAoC;CAC7D,CAAC","sourcesContent":["export const BUILT_IN_PROVIDER_DISPLAY_NAMES: Record<string, string> = {\n\tanthropic: \"Anthropic\",\n\t\"amazon-bedrock\": \"Amazon Bedrock\",\n\t\"azure-openai-responses\": \"Azure OpenAI Responses\",\n\tcerebras: \"Cerebras\",\n\t\"cloudflare-ai-gateway\": \"Cloudflare AI Gateway\",\n\t\"cloudflare-workers-ai\": \"Cloudflare Workers AI\",\n\tdeepseek: \"DeepSeek\",\n\tfireworks: \"Fireworks\",\n\tgoogle: \"Google Gemini\",\n\t\"google-vertex\": \"Google Vertex AI\",\n\tgroq: \"Groq\",\n\thuggingface: \"Hugging Face\",\n\t\"kimi-coding\": \"Kimi For Coding\",\n\tmistral: \"Mistral\",\n\tminimax: \"MiniMax\",\n\t\"minimax-cn\": \"MiniMax (China)\",\n\tmoonshotai: \"Moonshot AI\",\n\t\"moonshotai-cn\": \"Moonshot AI (China)\",\n\topencode: \"OpenCode Zen\",\n\t\"opencode-go\": \"OpenCode Go\",\n\topenai: \"OpenAI\",\n\topenrouter: \"OpenRouter\",\n\ttogether: \"Together AI\",\n\t\"vercel-ai-gateway\": \"Vercel AI Gateway\",\n\txai: \"xAI\",\n\tzai: \"ZAI\",\n\txiaomi: \"Xiaomi MiMo\",\n\t\"xiaomi-token-plan-cn\": \"Xiaomi MiMo Token Plan (China)\",\n\t\"xiaomi-token-plan-ams\": \"Xiaomi MiMo Token Plan (Amsterdam)\",\n\t\"xiaomi-token-plan-sgp\": \"Xiaomi MiMo Token Plan (Singapore)\",\n};\n"]}
+{"version":3,"file":"provider-display-names.js","sourceRoot":"","sources":["../../src/core/provider-display-names.ts"],"names":[],"mappings":"AAAA,MAAM,CAAC,MAAM,+BAA+B,GAA2B;IACtE,oBAAoB,EAAE,qBAAqB;IAC3C,8BAA8B,EAAE,wCAAwC;IACxE,SAAS,EAAE,WAAW;IACtB,gBAAgB,EAAE,gBAAgB;IAClC,wBAAwB,EAAE,wBAAwB;IAClD,QAAQ,EAAE,UAAU;IACpB,uBAAuB,EAAE,uBAAuB;IAChD,uBAAuB,EAAE,uBAAuB;IAChD,QAAQ,EAAE,UAAU;IACpB,SAAS,EAAE,WAAW;IACtB,MAAM,EAAE,eAAe;IACvB,eAAe,EAAE,kBAAkB;IACnC,IAAI,EAAE,MAAM;IACZ,WAAW,EAAE,cAAc;IAC3B,aAAa,EAAE,iBAAiB;IAChC,OAAO,EAAE,SAAS;IAClB,OAAO,EAAE,SAAS;IAClB,YAAY,EAAE,iBAAiB;IAC/B,UAAU,EAAE,aAAa;IACzB,eAAe,EAAE,qBAAqB;IACtC,QAAQ,EAAE,cAAc;IACxB,aAAa,EAAE,aAAa;IAC5B,uBAAuB,EAAE,gCAAgC;IACzD,MAAM,EAAE,QAAQ;IAChB,UAAU,EAAE,YAAY;IACxB,QAAQ,EAAE,aAAa;IACvB,mBAAmB,EAAE,mBAAmB;IACxC,GAAG,EAAE,KAAK;IACV,GAAG,EAAE,KAAK;IACV,MAAM,EAAE,aAAa;IACrB,sBAAsB,EAAE,gCAAgC;IACxD,uBAAuB,EAAE,oCAAoC;IAC7D,uBAAuB,EAAE,oCAAoC;CAC7D,CAAC","sourcesContent":["export const BUILT_IN_PROVIDER_DISPLAY_NAMES: Record<string, string> = {\n\t\"alibaba-codingplan\": \"Alibaba Coding Plan\",\n\t\"alibaba-codingplan-anthropic\": \"Alibaba Coding Plan (Anthropic-compat)\",\n\tanthropic: \"Anthropic\",\n\t\"amazon-bedrock\": \"Amazon Bedrock\",\n\t\"azure-openai-responses\": \"Azure OpenAI Responses\",\n\tcerebras: \"Cerebras\",\n\t\"cloudflare-ai-gateway\": \"Cloudflare AI Gateway\",\n\t\"cloudflare-workers-ai\": \"Cloudflare Workers AI\",\n\tdeepseek: \"DeepSeek\",\n\tfireworks: \"Fireworks\",\n\tgoogle: \"Google Gemini\",\n\t\"google-vertex\": \"Google Vertex AI\",\n\tgroq: \"Groq\",\n\thuggingface: \"Hugging Face\",\n\t\"kimi-coding\": \"Kimi For Coding\",\n\tmistral: \"Mistral\",\n\tminimax: \"MiniMax\",\n\t\"minimax-cn\": \"MiniMax (China)\",\n\tmoonshotai: \"Moonshot AI\",\n\t\"moonshotai-cn\": \"Moonshot AI (China)\",\n\topencode: \"OpenCode Zen\",\n\t\"opencode-go\": \"OpenCode Go\",\n\t\"opencode-go-anthropic\": \"OpenCode Go (Anthropic-compat)\",\n\topenai: \"OpenAI\",\n\topenrouter: \"OpenRouter\",\n\ttogether: \"Together AI\",\n\t\"vercel-ai-gateway\": \"Vercel AI Gateway\",\n\txai: \"xAI\",\n\tzai: \"ZAI\",\n\txiaomi: \"Xiaomi MiMo\",\n\t\"xiaomi-token-plan-cn\": \"Xiaomi MiMo Token Plan (China)\",\n\t\"xiaomi-token-plan-ams\": \"Xiaomi MiMo Token Plan (Amsterdam)\",\n\t\"xiaomi-token-plan-sgp\": \"Xiaomi MiMo Token Plan (Singapore)\",\n};\n"]}

package/extensions/phi/keys.ts

@@ -21,6 +21,9 @@
  */
 
 import { ApiKeyStore, type ExtensionAPI, getApiKeyStore, getConfigWatcher } from "phi-code";
+import { pingAlibaba } from "./providers/alibaba.js";
+import { pingOpenCodeGo } from "./providers/opencode-go.js";
+import { bootstrapProviderConfig, isBootstrappableProvider } from "./providers/provider-bootstrap.js";
 
 type ProviderPingFn = (key: string, timeoutMs?: number) => Promise<{ ok: boolean; error?: string }>;
 
@@ -38,6 +41,13 @@ export default function keysExtension(pi: ExtensionAPI) {
 	const store = getApiKeyStore();
 	const watcher = getConfigWatcher();
 
+	// Built-in pings so `/keys test <id>` works out of the box for the providers
+	// phi ships builders for (previously nothing ever registered a ping).
+	registerProviderPing("alibaba-codingplan", pingAlibaba);
+	registerProviderPing("alibaba-codingplan-anthropic", pingAlibaba);
+	registerProviderPing("opencode-go", pingOpenCodeGo);
+	registerProviderPing("opencode-go-anthropic", pingOpenCodeGo);
+
 	pi.registerCommand("keys", {
 		description: "Manage API keys (list / set / remove / test / reload)",
 		handler: async (args, ctx) => {
@@ -75,15 +85,35 @@ export default function keysExtension(pi: ExtensionAPI) {
 						return;
 					}
 					// A bare `set` only updates the key; it cannot supply baseUrl/api/models.
-					// For a never-configured id this would persist an unusable provider
-					// (apiKey but no endpoint), so require an existing entry with a baseUrl.
+					// For a never-configured id: bootstrap the full entry when phi ships a
+					// builder for it (Alibaba Coding Plan, OpenCode Go); otherwise keep the
+					// old behaviour and point at /setup.
 					const existing = store.getProvider(id);
 					if (!existing?.baseUrl) {
+						if (!isBootstrappableProvider(id)) {
+							ctx.ui.notify(
+								`\`${id}\` is not a configured provider (no baseUrl on file). ` +
+									`Run \`/setup\` to add it with an endpoint and models first; ` +
+									`\`/keys set\` only updates the key of an already-configured provider.`,
+								"warning",
+							);
+							return;
+						}
+						const boot = bootstrapProviderConfig(id, key);
+						if (!boot.ok) {
+							ctx.ui.notify(`Cannot configure \`${id}\`: ${boot.error}`, "warning");
+							return;
+						}
+						watcher.muteForWrite("models_json_changed");
+						store.setKey(id, key, {
+							baseUrl: boot.config.baseUrl,
+							api: boot.config.api,
+							models: boot.config.models,
+						});
 						ctx.ui.notify(
-							`\`${id}\` is not a configured provider (no baseUrl on file). ` +
-								`Run \`/setup\` to add it with an endpoint and models first; ` +
-								`\`/keys set\` only updates the key of an already-configured provider.`,
-							"warning",
+							`Configured \`${id}\` (\`${ApiKeyStore.maskKey(key)}\`) — ${boot.note}\n` +
+								`Stored in ${store.configPath}. Use \`/keys test ${id}\` to validate, then pick a model with \`/model\`.`,
+							"info",
 						);
 						return;
 					}

package/extensions/phi/orchestrator.ts

@@ -284,6 +284,11 @@ export default function orchestratorExtension(pi: ExtensionAPI) {
 		// Set true once this phase has been retried once (transient proxy failure /
 		// timeout / 0-tool-call). Hard cap of one retry per phase.
 		retried?: boolean;
+		// Generic driver (/debug, /build) only: set true once this phase was re-run
+		// after a BLOCKED verdict. One second chance on the fallback model — a hasty
+		// BLOCKED (measured: 51s on sympy-11897) is cheaper to re-check than to
+		// trust — then the halt is honest.
+		blockedRetried?: boolean;
 		// When true, switchModelForPhase resolves the fallback model first (used on retry
 		// to swap to a different model family rather than re-hit the one that just failed).
 		useFallback?: boolean;
@@ -1323,13 +1328,63 @@ Tag the note with relevant keywords for vector search.
 			phaseTimeoutId = null;
 		}
 
-		// A BLOCKED verdict (REPRODUCE cannot reproduce / VERIFY could not confirm)
-		// halts the pipeline honestly — no fabricated success.
+		// Route through the SAME pure decision machine as /plan so the generic
+		// driver gets the protections it was measured to lack (sympy-11897, a 51s
+		// hasty halt): fatal 401 stop, one retry on a transient provider error.
 		const structuredForThisPhase = currentPhaseResultKey === (currentPhase?.key ?? null) ? currentPhaseResult : null;
 		const outcome = resolvePhaseOutcome(structuredForThisPhase, null);
-		if (outcome.verdict === "BLOCKED" && currentPhase) {
+		const decision = decidePhaseTransition({
+			analysis,
+			phase: currentPhase ? { key: currentPhase.key, retried: currentPhase.retried } : null,
+			verdict: outcome.verdict,
+			// The generic driver has no review-fix cycle; pass the cap as spent.
+			reviewFixRounds: 1,
+			maxToolCallsPerPhase: MAX_TOOL_CALLS_PER_PHASE,
+		});
+
+		if (decision.action === "stop") {
+			ctx.ui.notify(
+				`\n❌ **/${orchestrationMode} aborted:** API authentication error (401). Check your API key.`,
+				"error",
+			);
+			finishGenericOrchestration(ctx, `❌ **/${orchestrationMode} aborted (auth error).**`);
+			return;
+		}
+
+		if (decision.action === "retry-fallback" && currentPhase) {
+			// Transient provider failure (timeout / 5xx / 429 / broken stream): retry
+			// the SAME phase once on the fallback model before treating any of its
+			// output as a real outcome.
+			currentPhase.retried = true;
+			currentPhase.useFallback = true;
+			phaseQueue.unshift(currentPhase);
+			phasePending = false;
+			ctx.ui.notify(
+				`\n🔁 **Transient provider error** in ${currentPhase.label} — retrying once on the fallback model.`,
+				"warning",
+			);
+			sendNextGenericPhase(ctx);
+			return;
+		}
+
+		// BLOCKED (REPRODUCE cannot reproduce / VERIFY could not confirm): give the
+		// phase ONE second chance on the fallback model — a hasty BLOCKED is cheaper
+		// to re-check than to trust — then halt honestly. No fabricated success.
+		if (decision.action === "pause-blocked" && currentPhase) {
+			if (!currentPhase.blockedRetried) {
+				currentPhase.blockedRetried = true;
+				currentPhase.useFallback = true;
+				phaseQueue.unshift(currentPhase);
+				phasePending = false;
+				ctx.ui.notify(
+					`\n🔁 **${currentPhase.label} reported BLOCKED on the first attempt** — retrying once on the fallback model before halting. ${outcome.handoff || ""}`,
+					"warning",
+				);
+				sendNextGenericPhase(ctx);
+				return;
+			}
 			ctx.ui.notify(
-				`\n⏸️ **${currentPhase.label} reported BLOCKED.** ${outcome.handoff || "No reproducible/verifiable result."}`,
+				`\n⏸️ **${currentPhase.label} reported BLOCKED (confirmed on retry).** ${outcome.handoff || "No reproducible/verifiable result."}`,
 				"warning",
 			);
 			finishGenericOrchestration(ctx, `⏸️ **/${orchestrationMode} stopped: BLOCKED at ${currentPhase.label}.**`);

package/extensions/phi/providers/debug-build-commands.ts

@@ -59,7 +59,8 @@ ${failing}
    - If it PASSES → STOP. Write \`BLOCKED: cannot reproduce — passes on current code\` with the run pasted. Do not invent a bug.
    - If \`sandbox_run\` reports \`SANDBOX UNAVAILABLE\` → STOP. Write \`BLOCKED: no executable environment\`.
 4. Do NOT edit any source yet. This phase only observes.
-5. **Last action:** call \`phase_result\` — \`verdict: PASS\` if it reproduced (proceed to LOCALIZE), or \`verdict: BLOCKED\` with the reason if you stopped.` +
+5. **BLOCKED is a last resort, not a first reaction.** If a run fails for an infrastructure-looking reason (tool error, missing file you guessed wrong, transient failure), adjust and retry at least once — e.g. locate the real test paths, try an alternative reproduction — before concluding. Only report BLOCKED after a genuine attempt showed the state is not reproducible or not runnable.
+6. **Last action:** call \`phase_result\` — \`verdict: PASS\` if it reproduced (proceed to LOCALIZE), or \`verdict: BLOCKED\` with the reason if you stopped.` +
 			DEBUG_RULES,
 
 		localize: `You are the LOCALIZE agent (phase 2 of /debug). Drive from the REAL symptom the previous phase captured.
@@ -96,6 +97,7 @@ ${failing}
 3. Verdict (from what \`sandbox_run\` returned, not from inspection):
    - Both green → \`FIXED\`, and paste the before(fail)/after(pass) reproduction runs and the green suite as evidence.
    - Reproduction still fails, or the suite regresses → \`BLOCKED\` with the closest diagnostic. Do NOT ship the least-bad patch; a wrong fix is worse than an honest BLOCKED.
+   - **A TIMEOUT counts as a FAILURE.** If the reproduction or the suite TIMES OUT with the fix applied (\`sandbox_run\` verdict TIMEOUT), the fix has introduced a massive slowdown or an infinite loop — that IS a regression (measured: a fix that passed its repro but made the real test suite hang for 900s). Verdict \`BLOCKED\`, never \`FIXED\`. Compare rough durations before/after: a check that got dramatically slower is a red flag even below the timeout.
 4. Write the final verdict block, then call \`phase_result\` with \`verdict: PASS\` (FIXED) or \`verdict: BLOCKED\`, plus a one-line handoff:
 \`\`\`
 VERDICT: FIXED | BLOCKED

package/extensions/phi/providers/provider-bootstrap.ts

@@ -0,0 +1,98 @@
+/**
+ * Provider bootstrap — first-time, non-interactive provider configuration.
+ *
+ * `/keys set <id> <key>` used to refuse a provider that had no models.json
+ * entry yet ("run /setup first"), which made adding a known provider (e.g. the
+ * Alibaba Coding Plan) impossible outside the interactive wizard. This module
+ * closes that gap: for providers phi ships a config builder for, it produces a
+ * complete models.json entry (baseUrl + api + model list) from a single API
+ * key, with the provider's own key-format validation applied first.
+ *
+ * Pure (no fs, no network) so every branch is unit-tested; keys.ts is the only
+ * call site.
+ */
+
+import { ALIBABA_PROVIDERS, buildAlibabaProviderConfig, validateAlibabaApiKey } from "./alibaba.js";
+import {
+	buildOpenCodeGoAnthropicProviderConfig,
+	buildOpenCodeGoProviderConfig,
+	OPENCODE_GO_FALLBACK_MODELS,
+	type OpenCodeGoModel,
+	validateOpenCodeGoApiKey,
+} from "./opencode-go.js";
+
+export interface BootstrapModel {
+	id: string;
+	name: string;
+	reasoning: boolean;
+	input: readonly ("text" | "image")[];
+	contextWindow: number;
+	maxTokens: number;
+	compat?: Record<string, unknown>;
+}
+
+export interface BootstrapConfig {
+	baseUrl: string;
+	api: string;
+	apiKey: string;
+	models: BootstrapModel[];
+}
+
+export type BootstrapResult = { ok: true; config: BootstrapConfig; note: string } | { ok: false; error: string };
+
+/** Provider ids `/keys set` can fully configure from just an API key. */
+export const BOOTSTRAPPABLE_PROVIDERS = [
+	"alibaba-codingplan",
+	"alibaba-codingplan-anthropic",
+	"opencode-go",
+	"opencode-go-anthropic",
+] as const;
+
+export function isBootstrappableProvider(id: string): boolean {
+	return (BOOTSTRAPPABLE_PROVIDERS as readonly string[]).includes(id);
+}
+
+/**
+ * Build a complete first-time provider config from an API key. Validates the
+ * key FORMAT (prefix/length) per provider; liveness is `/keys test`'s job.
+ * The bundled model list seeds the entry — the session-start refresh and
+ * `/models refresh` replace it with the live catalog afterwards.
+ */
+export function bootstrapProviderConfig(id: string, apiKey: string): BootstrapResult {
+	const key = apiKey.trim();
+
+	switch (id) {
+		case "alibaba-codingplan":
+		case "alibaba-codingplan-anthropic": {
+			const invalid = validateAlibabaApiKey(key);
+			if (invalid) return { ok: false, error: invalid };
+			const variant = id === "alibaba-codingplan-anthropic" ? "anthropic" : "openai";
+			const config: BootstrapConfig = buildAlibabaProviderConfig(variant, key);
+			return {
+				ok: true,
+				config,
+				note: `${ALIBABA_PROVIDERS[variant].displayName} — ${config.models.length} bundled model(s); a live refresh follows on next session start (or run /models refresh ${id}).`,
+			};
+		}
+		case "opencode-go":
+		case "opencode-go-anthropic": {
+			const invalid = validateOpenCodeGoApiKey(key);
+			if (invalid) return { ok: false, error: invalid };
+			const models: OpenCodeGoModel[] = [...OPENCODE_GO_FALLBACK_MODELS];
+			const config: BootstrapConfig =
+				id === "opencode-go-anthropic"
+					? buildOpenCodeGoAnthropicProviderConfig(key, models)
+					: buildOpenCodeGoProviderConfig(key, models);
+			return {
+				ok: true,
+				config,
+				note: `OpenCode Go — ${config.models.length} bundled model(s); a live refresh follows on next session start (or run /models refresh ${id}).`,
+			};
+		}
+		default:
+			return {
+				ok: false,
+				error: `\`${id}\` has no bootstrap builder. Run \`/setup\` to configure it interactively, or add it to ~/.phi/agent/models.json. Bootstrappable ids: ${BOOTSTRAPPABLE_PROVIDERS.join(", ")}.`,
+			};
+	}
+}

package/package.json

@@ -1,6 +1,6 @@
 {
 	"name": "@phi-code-admin/phi-code",
-	"version": "0.90.0",
+	"version": "0.92.0",
 	"description": "Coding agent CLI with persistent memory, sub-agents, intelligent routing, and orchestration",
 	"type": "module",
 	"piConfig": {