pi-condense 2.14.0 → 2.15.0

package/CHANGELOG.md

@@ -7,6 +7,12 @@ Published to npm as [`pi-condense`](https://www.npmjs.com/package/pi-condense) (
 Pushing a `vX.Y.Z` tag triggers `.github/workflows/release.yml`, which runs the tests and
 publishes via OIDC trusted publishing. See `.agents/skills/release/SKILL.md`.
 
+## [2.15.0] - 2026-11-09
+
+### Changed
+
+- pi-condense treats sessions without a UI (`pi -p`, `--mode json`, an SDK host with no UI context) as single-prompt and skips the final `agent-message` flush: a single-prompt print child has no later call to read the pruned context. Multi-message print runs and headless SDK hosts still rely on budget, delta, and frontier-gap flushes at `turn_end` (`autoBudgetThreshold`, `budgetTurnDelta`, `frontierGapThresholdTokens`); pending work stays recoverable through the reload rearm. (#29)
+
 ## [2.14.0] - 2026-11-08
 
 ### Changed

package/PRUNING.md

@@ -975,7 +975,7 @@ Any other outcome - zero or multiple matches on either boundary, `finalAssistant
 - With K=3: the three most-recently-closed chains stay as-is; the fourth triggers compression of the oldest. Exactly K closed chains are kept raw (the open/live chain is never counted).
 - `/pruner compact` bypasses the window and compresses every eligible chain immediately (retroactive).
 
-**Closing-message threading.** In agent-message mode the flush runs from `message_end`, which pi emits to extensions *before* it persists the message to the session (`agent-session.js` runs `_emitExtensionEvent` ahead of `sessionManager.appendMessage`). So at flush time `getBranch()` is missing the just-closed final assistant, and the newest chain would read as open — over-retaining by one (effective K+1). `index.ts` threads the triggering `event.message` through `FlushOptions.closingMessage` into `withClosingMessage` so the chain closes and the window is exactly K.
+**Closing-message threading.** pi-condense treats `ctx.hasUI === false` sessions (`pi -p`, `--mode json`, an SDK host with no UI context) as single-prompt and skips the final agent-message flush: a single-prompt print child has no later call to read the pruned context. Multi-message print runs and headless SDK hosts still rely on the `turn_end` budget/delta/frontier-gap triggers (`autoBudgetThreshold`, `budgetTurnDelta`, `frontierGapThresholdTokens`) for pruning. In sessions with a UI, the agent-message flush runs from `message_end`, which pi emits to extensions *before* it persists the message to the session (`agent-session.js` runs `_emitExtensionEvent` ahead of `sessionManager.appendMessage`). So at flush time `getBranch()` is missing the just-closed final assistant, and the newest chain would read as open - over-retaining by one (effective K+1). `index.ts` threads the triggering `event.message` through `FlushOptions.closingMessage` into `withClosingMessage` so the chain closes and the window is exactly K.
 
 ### Synthetic message format
 

package/README.md

@@ -69,7 +69,7 @@ pi install npm:pi-condense
 | `agent-message` (default) | When the agent sends a final text-only reply | ~1 cache rewrite per task batch |
 | `on-demand` | Only when you run `/pruner now` | None until you ask |
 
-With the default `agent-message` trigger (and `autoBudgetThreshold`/`budgetTurnDelta` unset), a non-interactive (`pi -p`) session sees its first flush only at the final reply - set `autoBudgetThreshold` (e.g. `0.8`) so flushes also fire mid-run. This is a property of single-prompt sessions, not a defect in the default.
+pi-condense treats a session without a UI (`pi -p`, `--mode json`, an SDK host with no UI context) as single-prompt and skips the final `agent-message` flush there: for a single-prompt `-p` / `--mode json` child, nothing reads the pruned context afterwards. A multi-message print run or a headless SDK host that wants its final messages pruned still relies on the `turn_end` budget/delta/frontier-gap flushes: set `autoBudgetThreshold` (e.g. `0.8`), `budgetTurnDelta`, or `frontierGapThresholdTokens` to enable them. Pending work stays recoverable through the reload rearm if the session is resumed.
 
 Before any summarizer call, a pre-flush pipeline can drop or redirect a batch at zero LLM cost: protected tools/paths are never touched, content-hash duplicates are aliased to the original, batches too small to be worth summarizing are skipped outright, and oversized single results are spilled straight to a sidecar file. Closed tool-call chains older than a rolling window are additionally range-compressed. Full pipeline and each safeguard: [PRUNING.md § Pre-flush Pipeline & Safeguards](PRUNING.md#pre-flush-pipeline--safeguards), [§ Chain Compression](PRUNING.md#chain-compression).
 

package/index.ts

@@ -1021,9 +1021,13 @@ export default function (pi: ExtensionAPI) {
   // finished using the raw tool results. flushPending captures the SessionManager
   // before awaiting summarization so print-mode shutdown cannot invalidate the
   // persistence path while the summarizer model is running.
+  //
+  // No-UI sessions are treated as single-prompt to avoid a final prune print children never read.
+  // Multi-prompt print/SDK hosts rely on turn_end budget/delta/frontier-gap triggers instead.
   pi.on("message_end", async (event, ctx) => {
     if (!currentConfig.value.enabled) return;
     if (currentConfig.value.pruneOn !== "agent-message") return;
+    if (ctx.hasUI === false) return;
     if (!isFinalAssistantMessage(event.message)) return;
     await flushPending(ctx, { delivery: "session", closingMessage: event.message, trigger: "message-end" });
   });

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "pi-condense",
-  "version": "2.14.0",
+  "version": "2.15.0",
   "description": "Pi coding-agent extension that summarizes completed tool-call batches, replaces raw outputs with short stubs, compresses closed tool-call chains, and recovers any original on demand via context_tree_query.",
   "author": "Jacek Juraszek",
   "license": "MIT",

package/src/reload-rearm.integration.test.ts

@@ -1777,3 +1777,53 @@ describe("session-wide live turn index (#16)", () => {
     expect((fm[0].data as any).trigger).toBe("frontier-gap");
   });
 });
+
+describe("final agent-message flush in sessions without a UI (#29)", () => {
+  const finalReply = { message: { role: "assistant", content: [{ type: "text", text: "done" }] } };
+
+  it("skips the message-end flush when ctx.hasUI is false", async () => {
+    const branch: any[] = [];
+    const { handlers, ctx, appended } = await boot({ branch, autoBudgetThreshold: null, budgetTurnDelta: null });
+    ctx.hasUI = false;
+    ctx.getContextUsage = () => ({ tokens: 10, contextWindow: 1000000 });
+    await handlers.get("session_start")!({}, ctx);
+    const callsBefore = summarizerCalls;
+
+    await fireTurn(handlers, ctx, branch, "tc-p", "p".repeat(800), 0);
+    await handlers.get("message_end")!(finalReply, ctx);
+
+    expect(summarizerCalls).toBe(callsBefore);
+    expect(appended.some((e) => e.type === "context-prune-flush-metrics")).toBe(false);
+    expect(appended.some((e) => e.type === "context-prune-summary")).toBe(false);
+  });
+
+  it("still flushes mid-prompt on the turn_end budget trigger when ctx.hasUI is false", async () => {
+    const branch: any[] = [];
+    const { handlers, ctx, appended } = await boot({ branch });
+    ctx.hasUI = false;
+    await handlers.get("session_start")!({}, ctx);
+
+    await fireTurn(handlers, ctx, branch, "tc-b", "b".repeat(800), 0);
+
+    const fm = appended.filter((e) => e.type === "context-prune-flush-metrics");
+    expect(fm.length).toBe(1);
+    expect((fm[0].data as any).trigger).toBe("budget");
+    expect((fm[0].data as any).outcome).toBe("summarized");
+  });
+
+  it("flushes on the final assistant message when ctx.hasUI is true", async () => {
+    const branch: any[] = [];
+    const { handlers, ctx, appended } = await boot({ branch, autoBudgetThreshold: null, budgetTurnDelta: null });
+    ctx.hasUI = true;
+    ctx.getContextUsage = () => ({ tokens: 10, contextWindow: 1000000 });
+    await handlers.get("session_start")!({}, ctx);
+
+    await fireTurn(handlers, ctx, branch, "tc-u", "u".repeat(800), 0);
+    await handlers.get("message_end")!(finalReply, ctx);
+
+    const fm = appended.filter((e) => e.type === "context-prune-flush-metrics");
+    expect(fm.length).toBe(1);
+    expect((fm[0].data as any).trigger).toBe("message-end");
+    expect((fm[0].data as any).outcome).toBe("summarized");
+  });
+});