pi-gauntlet 7.18.0 → 7.18.1

package/CHANGELOG.md

@@ -1,5 +1,11 @@
 # Changelog
 
+## v7.18.1 - 2026-10-19
+
+### Removed
+
+- **`start implement` no longer warns about a missing `promptCache` lifetime.** The warning fired on every non-Anthropic model (pi's catalog declares `promptCache` only for direct `anthropic` Claude entries) and read as an instruction to edit `models.json`, which stalled auto-chaining into implement until the user typed "continue"; the per-call cache telemetry from #67 stays and is the real signal for cache hits.
+
 ## v7.18.0 - 2026-10-19
 
 ### Changed

package/extensions/phase-tracker.test.ts

@@ -69,7 +69,7 @@ const resumedBranch = (rest: Partial<Record<Phase, Status>>) => [
   phaseResult("complete", phases({ brainstorm: "skipped", ...rest })),
 ];
 
-type TestModel = { provider: string; id: string; promptCache?: { short?: number; long?: number } };
+type TestModel = { provider: string; id: string };
 
 function harness(options: { cwd?: string; branch?: unknown[]; idle?: boolean; beforeSettled?: (setIdle: (idle: boolean) => void) => void; sendThrows?: boolean; model?: TestModel; thinkingLevel?: string; registry?: Record<string, TestModel>; setModelResult?: boolean | Error } = {}) {
   const handlers = new Map<string, ((event: unknown, ctx: unknown) => unknown)[]>();
@@ -136,7 +136,7 @@ const startPhase = async (h: ReturnType<typeof harness>, phase: string) => {
   return { text: r.content.map((c) => c.text).join("\n"), status: r.details.phases[phase].status };
 };
 
-const M = (id: string, promptCache?: { short?: number; long?: number }) => ({ provider: "p", id, promptCache });
+const M = (id: string) => ({ provider: "p", id });
 
 const preparePhase = async (h: ReturnType<typeof harness>, phase = "plan") => {
   await settle(h);
@@ -223,46 +223,6 @@ test("phaseModels: resolver warnings appear only for their phase", async () => {
   assert.deepEqual(h.pi.thinkingCalls, []);
 });
 
-for (const row of [
-  { name: "missing short", phase: "implement", cache: undefined, retention: undefined, tier: "short" },
-  { name: "declared short", phase: "implement", cache: { short: 300 }, retention: undefined, tier: undefined },
-  { name: "missing long", phase: "implement", cache: { short: 300 }, retention: "long", tier: "long" },
-  { name: "plan ignores cache", phase: "plan", cache: undefined, retention: undefined, tier: undefined },
-]) {
-  test(`phaseModels: cache warning ${row.name}`, async () => {
-    const retention = process.env.PI_CACHE_RETENTION;
-    if (row.retention === undefined) delete process.env.PI_CACHE_RETENTION;
-    else process.env.PI_CACHE_RETENTION = row.retention;
-    try {
-      const h = harness({ cwd: tempCwd({ piGauntlet: { flowGuards: { enforce: false } } }), model: M("m", row.cache) });
-      await preparePhase(h, row.phase);
-      const r = await startPhase(h, row.phase);
-      if (row.tier) {
-        assert.ok(r.text.includes(`p/m declares no promptCache.${row.tier} lifetime, so pi's cache warmer skips it`));
-        assert.ok(r.text.includes("providers.p.modelOverrides.m.promptCache"));
-        assert.ok(r.text.includes("providers.p.models[].promptCache"));
-      } else assert.doesNotMatch(r.text, /cache warmer/);
-      assert.deepEqual(h.pi.setModelCalls, []);
-      assert.deepEqual(h.pi.thinkingCalls, []);
-      assert.equal(r.status, "in_progress");
-    } finally {
-      if (retention === undefined) delete process.env.PI_CACHE_RETENTION;
-      else process.env.PI_CACHE_RETENTION = retention;
-    }
-  });
-}
-
-test("phaseModels: cache warning checks the switched model", async () => {
-  const h = harness({ cwd: tempCwd({ piGauntlet: { flowGuards: { enforce: false }, phaseModels: { implement: "p/warm" } } }), model: M("old"), registry: { "p/warm": M("warm", { short: 300, long: 3600 }) } });
-  await preparePhase(h, "implement");
-  const r = await startPhase(h, "implement");
-  assert.equal(h.pi.setModelCalls.length, 1);
-  assert.deepEqual(h.pi.thinkingCalls, []);
-  assert.equal(h.ctx.model?.id, "warm");
-  assert.doesNotMatch(r.text, /cache warmer/);
-  assert.equal(r.status, "in_progress");
-});
-
 test("agent_settled nudges each exact edge with persisted details", async () => {
   for (const [state, edge, skill] of [
     [phases({ brainstorm: "complete", plan: "complete" }), "plan-implement", "/skill:subagent-driven-development"],

package/extensions/phase-tracker.ts

@@ -1031,17 +1031,6 @@ export default function (pi: ExtensionAPI) {
             for (const w of resolved.warning?.split("; ") ?? []) if (w.includes(`phaseModels.${phase} `)) startLines.push(`\u26a0\ufe0f ${w}`);
             const target = resolved.phaseModels[phase];
             if (target) startLines.push(...(await applyPhaseModel(pi, ctx, phase, target)));
-            if (phase === "implement") {
-              const tier = process.env.PI_CACHE_RETENTION === "long" ? "long" : "short";
-              const m = ctx.model;
-              if (m && m.promptCache?.[tier] === undefined) {
-                startLines.push(
-                  `\u26a0\ufe0f ${m.provider}/${m.id} declares no promptCache.${tier} lifetime, so pi's cache warmer skips it. ` +
-                    `Declare it in <agent-dir>/models.json (default ~/.pi/agent): providers.${m.provider}.modelOverrides.${m.id}.promptCache for a built-in model, ` +
-                    `or providers.${m.provider}.models[].promptCache for a custom one; the lifetime is required by the warmer but not sufficient - see doc/configuration.md#phase-models.`,
-                );
-              }
-            }
           }
           phases = { ...phases, [params.phase]: transitionPhaseState("in_progress") as PhaseState };
           // A rewind must not inherit the prior verify's conformance latch.

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "pi-gauntlet",
-  "version": "7.18.0",
+  "version": "7.18.1",
   "description": "Opinionated, gated workflow skills, subagent personas, and runtime extensions for the pi coding agent.",
   "author": "Jacek Juraszek",
   "type": "module",