fix(pi-claude-cli): unblock parameterless MCP tool calls in triage

Triage with claude-sonnet-4-6 via pi-claude-cli kept looping on
fn_review_spec calls that were rejected by pi's validator with
"root: must be object". Parameterless MCP tools (schema
{type:"object", properties:{}}) emit zero input_json_delta events,
so partialJson stayed "" and the catch fell through to
finalArgs = "" — a string, which TypeBox's Type.Object({}) rightly
refuses. Default empty partialJson to {} so the call lands.

Also:
- Add a 2-step reminder loop in triage before swapping to the
  fallback planning model — primary models that wrote PROMPT.md
  but forgot fn_review_spec recover from a nudge, no need to pay
  the cold-start tax of a new triage on a different model.
- Inject @runfusion/fusion's own pi extension into dashboard/
  daemon/serve sessions and propagate the path to createFnAgent
  via setHostExtensionPaths so fn_* tools register globally
  without requiring `pi install npm:@runfusion/fusion`.
- Drop the "historical" qualifier from replayed tool labels —
  Claude was reading "TOOL RESULT (historical Read):" as
  "previous session, ignore" and looping on verification.
- Remove subprocess-lifecycle stderr debug logs that landed for
  hang diagnosis — root cause is fixed, the noise can go.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

packages/engine/src/__tests__/restart.integration.test.ts

@@ -840,11 +840,20 @@ describe("Triage re-pick after restart", () => {
     const task = makeTask("FN-062", "triage");
     store.getTask.mockResolvedValue(makeTaskDetail("FN-062", "triage"));
 
-    // Slow agent to keep task in processing
+    // Slow agent to keep task in processing — only the first prompt() blocks;
+    // subsequent calls (e.g. the no-APPROVE reminder loop in triage) resolve
+    // immediately so cleanup can drain.
     let resolvePrompt: (() => void) | undefined;
+    let promptCallCount = 0;
     mockedCreateFnAgent.mockResolvedValue({
       session: {
-        prompt: vi.fn().mockImplementation(() => new Promise<void>((r) => { resolvePrompt = r; })),
+        prompt: vi.fn().mockImplementation(() => {
+          promptCallCount += 1;
+          if (promptCallCount === 1) {
+            return new Promise<void>((r) => { resolvePrompt = r; });
+          }
+          return Promise.resolve();
+        }),
         dispose: vi.fn(),
       },
     } as any);

packages/engine/src/index.ts

@@ -17,7 +17,7 @@ export { MissionAutopilot, type MissionAutopilotOptions } from "./mission-autopi
 export { MissionExecutionLoop, type MissionExecutionLoopOptions, type ValidationResult, loopLog } from "./mission-execution-loop.js";
 export { aiMergeTask, type MergerOptions } from "./merger.js";
 export { reviewStep, type ReviewType, type ReviewVerdict, type ReviewResult, type ReviewOptions } from "./reviewer.js";
-export { createFnAgent, promptWithFallback, describeModel, type AgentOptions, type AgentResult } from "./pi.js";
+export { createFnAgent, promptWithFallback, describeModel, setHostExtensionPaths, getHostExtensionPaths, type AgentOptions, type AgentResult } from "./pi.js";
 export {
   resolveSessionSkills,
   createSkillsOverrideFromSelection,

packages/engine/src/pi.ts

@@ -50,6 +50,24 @@ export interface AgentResult {
   sessionFile?: string;
 }
 
+/**
+ * Process-global list of extension paths to inject into every createFnAgent
+ * session. Set once at startup by the host (cli's dashboard/daemon/serve)
+ * before any sessions are created. The paths are passed to pi's
+ * `DefaultResourceLoader` as `additionalExtensionPaths` so the cli's own
+ * `@runfusion/fusion` extension (registering `fn_*` tools) is loaded inside
+ * every agent session — including chat sessions that pass no `customTools`.
+ */
+let hostExtensionPaths: string[] = [];
+
+export function setHostExtensionPaths(paths: readonly string[]): void {
+  hostExtensionPaths = [...paths];
+}
+
+export function getHostExtensionPaths(): readonly string[] {
+  return hostExtensionPaths;
+}
+
 export interface PromptableSession extends AgentSession {
   promptWithFallback: (prompt: string, options?: unknown) => Promise<void>;
 }
@@ -1066,6 +1084,10 @@ export async function createFnAgent(options: AgentOptions): Promise<AgentResult>
     settingsManager,
     systemPromptOverride: () => options.systemPrompt,
     appendSystemPromptOverride: () => [],
+    // Inject host-supplied extension paths (e.g. cli's own `@runfusion/fusion`
+    // extension that registers `fn_*` tools) so they're loaded inside every
+    // agent session, including chat sessions that don't pass `customTools`.
+    ...(hostExtensionPaths.length > 0 ? { additionalExtensionPaths: [...hostExtensionPaths] } : {}),
     ...(skillsOverrideFn ? { skillsOverride: skillsOverrideFn } : {}),
   });
   await resourceLoader.reload();

packages/engine/src/triage.ts

@@ -1043,6 +1043,44 @@ export class TriageProcessor {
             return;
           }
 
+          // Before swapping to the fallback model, give the primary one more
+          // shot with a pointed reminder. The model may have written PROMPT.md
+          // but stopped without calling fn_review_spec — that's recoverable
+          // with a nudge, no need to discard the session and pay the cold-start
+          // tax of a new triage on a different model.
+          const MAX_REVIEW_REMINDERS = 2;
+          let reviewReminders = 0;
+          while (
+            specReviewVerdictRef.current !== "APPROVE" &&
+            !this.pauseAborted.has(task.id) &&
+            !this.stuckAborted.has(task.id) &&
+            createdSubtasksRef.current.length === 0 &&
+            reviewReminders < MAX_REVIEW_REMINDERS
+          ) {
+            reviewReminders += 1;
+            const verdictDesc =
+              specReviewVerdictRef.current === null
+                ? "fn_review_spec was never called"
+                : `verdict was ${specReviewVerdictRef.current}`;
+            triageLog.warn(
+              `${task.id} primary planning model returned without APPROVE (${verdictDesc}) — reminder ${reviewReminders}/${MAX_REVIEW_REMINDERS}`,
+            );
+            await this.store.logEntry(
+              task.id,
+              `Primary planning model returned without APPROVE (${verdictDesc}) — reminder ${reviewReminders}/${MAX_REVIEW_REMINDERS}`,
+            );
+            const reminder =
+              specReviewVerdictRef.current === null
+                ? "You wrote the PROMPT.md but did not call `fn_review_spec()`. Call `fn_review_spec()` now to validate the spec. Do not stop until the verdict is APPROVE."
+                : `Spec review verdict was ${specReviewVerdictRef.current}. Address the feedback, rewrite the PROMPT.md as needed, and call \`fn_review_spec()\` again. Do not stop until the verdict is APPROVE.`;
+            stuckDetector?.recordActivity(task.id);
+            await promptWithFallback(session, reminder);
+            checkSessionError(session);
+            if (this.pauseAborted.has(task.id) || this.stuckAborted.has(task.id)) {
+              break;
+            }
+          }
+
           const planningFallbackProvider = settings.planningFallbackProvider;
           const planningFallbackModelId = settings.planningFallbackModelId;
           const canRetryWithPlanningFallback =