billion-context-pi 0.1.62 → 0.1.63-pr.352.144

package/dist/config.d.ts

@@ -1,5 +1,6 @@
 import { type Config, type Prompts } from "acp-kernel";
 import type { CompressReasoningConfig } from "./reasoning-drop.js";
+import type { DegenerationGuardConfig } from "./degeneration.js";
 import type { ThrottleRetryConfig } from "./throttle-retry.js";
 /** Per-role delegate defaults. Lets long-lived automation pin a cheaper or
  *  more capable model and a thinking level per delegate role, so the main
@@ -222,6 +223,15 @@ export interface AdapterConfig {
      *  warn=3, abort=5. Stops greedy small models looping on byte-identical
      *  tool calls (issue #308). */
     repetitionGuard?: boolean | RepetitionGuardConfig;
+    /** Character-level degenerate-repeat guard (see DegenerationGuardConfig).
+     *  Collapses long single-codepoint runs (e.g. 4655×「【」) in assistant
+     *  text/thinking of the outgoing view and injects a one-shot recovery notice
+     *  after a degenerated turn — breaking the abort loop where pi replays the
+     *  degenerated thinking back to the provider on every request (issue #351).
+     *  Distinct from `repetitionGuard`, which is tool-call level. Accepts a
+     *  boolean shorthand (`false` disables) or an object. Default: enabled,
+     *  minRun=200. */
+    degenerationGuard?: boolean | DegenerationGuardConfig;
     /** Legacy flat alias for `delegate.displayUsage`. Kept for backward
      *  compatibility with existing acp.json files. Prefer `delegate.displayUsage`. */
     displayUsage?: "merged" | "separate";

package/dist/degeneration.d.ts

@@ -0,0 +1,98 @@
+import type { SessionMessageEntry } from "@earendil-works/pi-coding-agent";
+type AgentMessage = SessionMessageEntry["message"];
+/** [#351] Character-level degenerate-repeat guard. Models occasionally
+ *  degenerate into long single-codepoint runs (observed in the wild: a
+ *  5968-char thinking block ending in 4655 consecutive 「【」, escalating over
+ *  turns until the turn aborts). This is distinct from `repetitionGuard`
+ *  (issue #308), which breaks byte-identical TOOL-CALL loops; here the
+ *  attractor is inside the generated text/thinking itself.
+ *
+ *  Why the adapter must act: pi replays prior assistant thinking back to the
+ *  provider on every subsequent request (openai-completions sends it as
+ *  `reasoning_content`, or as plain text when `requiresThinkingAsText`), and
+ *  an aborted turn's partial message persists in the session log. A
+ *  degenerated tail therefore rides along every later prompt, where the model
+ *  sees its own previous output ending in thousands of repeated characters —
+ *  a continuation bias that re-triggers the same degeneration, aborting the
+ *  next turn too. The session dies in an abort loop with no recovery path.
+ *
+ *  The pass below collapses runs >= minRun in assistant text/thinking of the
+ *  OUTGOING view (persisted history is never modified) and appends a one-shot
+ *  recovery notice while the degenerated message is the most recent assistant
+ *  turn. Position-based self-limiting: a fresh model turn makes the old
+ *  message non-last, so the notice stops appearing without any persistent
+ *  state (and cannot accumulate — #223 lesson). */
+export interface DegenerationGuardConfig {
+    /** Master switch. Default: true. `false` disables the pass entirely
+     *  (kill-switch). */
+    enabled?: boolean;
+    /** Minimum length of a single-codepoint run (counted in codepoints) before
+     *  it is treated as degeneration. Legitimate single-char runs in coding
+     *  sessions (markdown hrules, dotted leaders, comment banners) stay well
+     *  under this; observed pre-degeneration drift maxed at ~60 before the
+     *  catastrophic 4655×「【」 run. Default: 200. Values below 8 are raised to
+     *  8: the collapse marker must stay shorter than any detectable run, and a
+     *  sub-8 threshold would start matching ordinary dotted leaders/hrules. */
+    minRun?: number;
+}
+export declare const DEFAULT_DEGENERATION_GUARD: Required<DegenerationGuardConfig>;
+/** Resolve the guard config, handling the boolean shorthand (`false`
+ *  disables). Invalid minRun values (< 2 or non-numeric) fall back to the
+ *  default with a logged warning — they never fail the session. Valid values
+ *  below MIN_VALID_MIN_RUN are raised to it. */
+export declare function resolveDegenerationGuard(cfg?: boolean | DegenerationGuardConfig): Required<DegenerationGuardConfig>;
+/** One maximal run of a repeated codepoint. */
+export interface DegenerateRun {
+    /** The repeated codepoint (string of length 1 or 2 — surrogate pairs kept whole). */
+    char: string;
+    /** Run length in codepoints. */
+    count: number;
+    /** UTF-16 index of the run start in the original string. */
+    index: number;
+}
+/** Find maximal runs of a single repeated codepoint with length >= minRun.
+ *  Codepoint-safe: surrogate pairs count as one unit, so a run of astral
+ *  characters is detected like any other. Returns [] for empty input or
+ *  minRun < 2 (a "run" shorter than 2 carries no signal). */
+export declare function findDegenerateRuns(text: string, minRun: number): DegenerateRun[];
+/** Collapse every degenerate run in `text` into a short marker that names the
+ *  character and its original count. Pure, idempotent, fail-safe. Returns the
+ *  input unchanged when there is nothing to collapse. */
+export declare function collapseDegenerateRuns(text: string, minRun: number): string;
+/** Evidence of one rewritten message: which blocks changed and what was collapsed. */
+export interface CollapseEvidence {
+    /** Index of the rewritten message in the input array. */
+    msgIndex: number;
+    /** Block kinds rewritten ("content" for string content, else "text"/"thinking"). */
+    blocks: string[];
+    /** Runs collapsed across those blocks. */
+    runs: DegenerateRun[];
+}
+/** Request-time pass: collapse degenerate single-codepoint runs in ASSISTANT
+ *  messages' text/thinking blocks (string content included). Every position is
+ *  scanned — including the current turn's partial assistant message, which is
+ *  exactly the one pi will replay back to the provider on the next request.
+ *  Tool-call arguments are never touched (rewriting them would desync the
+ *  model's view from the call that actually executed). Pure: returns the same
+ *  array reference when nothing changed; idempotent; fail-safe (any error
+ *  returns the input unchanged). Persisted history is never modified. */
+export declare function collapseAssistantDegeneration(messages: AgentMessage[], cfg?: boolean | DegenerationGuardConfig): {
+    messages: AgentMessage[];
+    evidence: CollapseEvidence[];
+};
+/** Scan backward for the LAST assistant message and collect its degenerate
+ *  runs. Call it with the PERSISTED originals in session order (not the
+ *  outgoing view): thinking-only aborted turns never reach the outgoing view
+ *  (projectMessage drops them), yet they are still "the previous turn".
+ *  Returns null when absent or clean. Gates the recovery notice: because the
+ *  notice fires only while the degenerated message is the most recent
+ *  assistant turn, it self-limits — once the model produces a new turn the
+ *  old message is no longer last and the notice disappears on the next
+ *  rebuild (no persistent state needed). */
+export declare function lastAssistantRuns(messages: AgentMessage[], minRun: number): DegenerateRun[] | null;
+/** One-shot recovery notice appended while a degenerated assistant message is
+ *  the most recent turn: tells the model the repeated segment carries no
+ *  information and was truncated, and to resume from the last valid step
+ *  instead of continuing the attractor. */
+export declare function degenerationNotice(runs: DegenerateRun[]): AgentMessage;
+export {};

package/dist/index.js

@@ -3982,25 +3982,47 @@ function hasCompressCall(content) {
     return b2?.type === "toolCall" && b2.name === "compress";
   });
 }
+function compressCallIds(content) {
+  if (!Array.isArray(content)) return [];
+  return content.filter((p) => {
+    const b2 = p;
+    return b2?.type === "toolCall" && b2.name === "compress";
+  }).map((p) => p.id).filter((id) => typeof id === "string");
+}
+function resultIndexByCallId(messages) {
+  const map = /* @__PURE__ */ new Map();
+  for (let i = 0; i < messages.length; i++) {
+    const msg = messages[i];
+    if (msg?.role !== "toolResult" || typeof msg.toolCallId !== "string") continue;
+    if (!map.has(msg.toolCallId)) map.set(msg.toolCallId, i);
+  }
+  return map;
+}
 function reasoningLength(content) {
   if (!Array.isArray(content)) return 0;
   return content.reduce((n, p) => isThinking(p) ? n + p.thinking.length : n, 0);
 }
+function countThinkingChars(messages) {
+  return messages.reduce((n, m2) => n + reasoningLength(m2.content), 0);
+}
 function dropCompressReasoning(messages, cfg) {
   const { drop, threshold } = resolveReasoningDrop(cfg);
   if (!drop || messages.length === 0) return messages;
   try {
-    let lastUser = -1;
-    for (let i = 0; i < messages.length; i++) {
-      if (messages[i].role === "user") lastUser = i;
-    }
-    if (lastUser < 0) return messages;
+    const last = messages.length - 1;
+    const resultAt = resultIndexByCallId(messages);
     let changed = false;
     const out = messages.slice();
-    for (let i = 0; i < lastUser; i++) {
+    for (let i = 0; i <= last; i++) {
       const msg = messages[i];
       if (msg.role !== "assistant" || !Array.isArray(msg.content)) continue;
       if (!hasCompressCall(msg.content)) continue;
+      const ids = compressCallIds(msg.content);
+      const closed = ids.length > 0 && ids.every((id) => {
+        const ri = resultAt.get(id);
+        return ri !== void 0 && ri > i && ri < last;
+      });
+      if (!closed) continue;
       if (reasoningLength(msg.content) <= threshold) continue;
       out[i] = {
         ...msg,
@@ -4717,6 +4739,8 @@ var KNOWN = /* @__PURE__ */ new Set([
   "displayUsage",
   "throttleRetry",
   "outputHeadroomMaxPct",
+  "repetitionGuard",
+  "degenerationGuard",
   "prompts",
   "acknowledgePromptsRisk"
 ]);
@@ -16814,7 +16838,7 @@ async function statusReport(runtime, ctx) {
   const sentTokens = estimateTokens(coreMessages, coveredIds, imageTokens) + systemPromptTokens;
   const viewSentTokens = adjustedTokenCount(runtime.core, coreMessages, state, config, sentTokens, imageTokens, systemPromptTokens);
   const turn = runtime.core.processTurn({ messages: coreMessages, state, config, tokenCount: anchorStale ? viewSentTokens : Math.max(viewSentTokens, realUsage?.tokens ?? 0) });
-  const versionStr = "0.1.62" ? `billion-context-pi@${"0.1.62"}` : void 0;
+  const versionStr = "0.1.63" ? `billion-context-pi@${"0.1.63"}` : void 0;
   let text = buildStatusPanel({
     version: versionStr,
     tokenCount: sessionTokens,
@@ -16835,6 +16859,159 @@ async function statusReport(runtime, ctx) {
   return text;
 }
 
+// src/degeneration.ts
+var DEFAULT_DEGENERATION_GUARD = { enabled: true, minRun: 200 };
+var MIN_VALID_MIN_RUN = 8;
+function resolveDegenerationGuard(cfg) {
+  if (cfg === false) return { enabled: false, minRun: DEFAULT_DEGENERATION_GUARD.minRun };
+  const c = typeof cfg === "object" && cfg !== null ? cfg : {};
+  let minRun = DEFAULT_DEGENERATION_GUARD.minRun;
+  if (c.minRun !== void 0) {
+    const n = c.minRun;
+    if (typeof n === "number" && Number.isFinite(n) && n >= 2) {
+      minRun = Math.max(MIN_VALID_MIN_RUN, Math.floor(n));
+    } else {
+      logWarn("config", { event: "degeneration-guard-invalid", field: "minRun", value: n, fallback: DEFAULT_DEGENERATION_GUARD.minRun });
+    }
+  }
+  return { enabled: c.enabled !== false, minRun };
+}
+function findDegenerateRuns(text, minRun) {
+  const runs2 = [];
+  if (!text || !Number.isFinite(minRun) || minRun < 2) return runs2;
+  const chars = Array.from(text);
+  let utf16 = 0;
+  let k = 0;
+  while (k < chars.length) {
+    const ch = chars[k];
+    let m2 = k + 1;
+    while (m2 < chars.length && chars[m2] === ch) m2++;
+    const count = m2 - k;
+    if (count >= minRun) runs2.push({ char: ch, count, index: utf16 });
+    utf16 += count * ch.length;
+    k = m2;
+  }
+  return runs2;
+}
+function describeChar(ch) {
+  if (ch === " ") return "space";
+  if (ch === "\n") return "newline";
+  if (ch === "	") return "tab";
+  if (ch === "\r") return "carriage-return";
+  const cp = ch.codePointAt(0) ?? 0;
+  if (cp < 32 || cp === 127) return `U+${cp.toString(16).toUpperCase().padStart(4, "0")}`;
+  return JSON.stringify(ch);
+}
+function applyRuns(text, runs2, minRun) {
+  const keep = Math.max(1, Math.min(3, minRun - 1));
+  let out = "";
+  let last = 0;
+  for (const r of runs2) {
+    out += text.slice(last, r.index);
+    out += `${r.char.repeat(keep)}\u2026 [${r.count}\xD7 identical chars cut \u2014 degenerate repeat]`;
+    last = r.index + r.count * r.char.length;
+  }
+  out += text.slice(last);
+  return out;
+}
+function collapseAssistantDegeneration(messages, cfg) {
+  const { enabled, minRun } = resolveDegenerationGuard(cfg);
+  if (!enabled || messages.length === 0) return { messages, evidence: [] };
+  try {
+    const evidence = [];
+    let changed = false;
+    const out = messages.slice();
+    for (let i = 0; i < messages.length; i++) {
+      const msg = messages[i];
+      if (msg.role !== "assistant") continue;
+      const c = msg.content;
+      if (typeof c === "string") {
+        const runs3 = findDegenerateRuns(c, minRun);
+        if (runs3.length > 0) {
+          out[i] = { ...msg, content: applyRuns(c, runs3, minRun) };
+          evidence.push({ msgIndex: i, blocks: ["content"], runs: runs3 });
+          changed = true;
+        }
+        continue;
+      }
+      if (!Array.isArray(c)) continue;
+      const blocks = [];
+      const runs2 = [];
+      let blockChanged = false;
+      const nc = c.map((p) => {
+        const b2 = p;
+        if (b2?.type === "text" && typeof b2.text === "string") {
+          const r = findDegenerateRuns(b2.text, minRun);
+          if (r.length > 0) {
+            blockChanged = true;
+            blocks.push("text");
+            runs2.push(...r);
+            return { ...b2, text: applyRuns(b2.text, r, minRun) };
+          }
+          return p;
+        }
+        if (b2?.type === "thinking" && typeof b2.thinking === "string") {
+          const r = findDegenerateRuns(b2.thinking, minRun);
+          if (r.length > 0) {
+            blockChanged = true;
+            blocks.push("thinking");
+            runs2.push(...r);
+            return { ...b2, thinking: applyRuns(b2.thinking, r, minRun) };
+          }
+          return p;
+        }
+        return p;
+      });
+      if (blockChanged) {
+        out[i] = { ...msg, content: nc };
+        evidence.push({ msgIndex: i, blocks, runs: runs2 });
+        changed = true;
+      }
+    }
+    return { messages: changed ? out : messages, evidence };
+  } catch {
+    return { messages, evidence: [] };
+  }
+}
+function lastAssistantRuns(messages, minRun) {
+  try {
+    for (let i = messages.length - 1; i >= 0; i--) {
+      const msg = messages[i];
+      if (msg.role !== "assistant") continue;
+      const runs2 = [];
+      const c = msg.content;
+      if (typeof c === "string") {
+        runs2.push(...findDegenerateRuns(c, minRun));
+      } else if (Array.isArray(c)) {
+        for (const p of c) {
+          const b2 = p;
+          if (b2?.type === "text" && typeof b2.text === "string") runs2.push(...findDegenerateRuns(b2.text, minRun));
+          else if (b2?.type === "thinking" && typeof b2.thinking === "string") runs2.push(...findDegenerateRuns(b2.thinking, minRun));
+        }
+      }
+      return runs2.length > 0 ? runs2 : null;
+    }
+    return null;
+  } catch {
+    return null;
+  }
+}
+function degenerationNotice(runs2) {
+  const sorted = [...runs2].sort((a, b2) => b2.count - a.count);
+  const top = sorted[0];
+  const extra = sorted.length > 1 ? ` and ${sorted.length - 1} other repeated segment(s)` : "";
+  return {
+    role: "user",
+    content: [
+      {
+        type: "text",
+        text: `[ACP recovery notice] Your previous turn ended in degenerate generation: its output contained ${top.count} consecutive repetitions of ${describeChar(top.char)}${extra}. That repeated segment carries no information and has been truncated in the context above. Do not reproduce it or continue the pattern. Resume your task from your last valid step.`
+      }
+    ],
+    timestamp: Date.now()
+  };
+}
+
 // src/system-prompt.ts
 function buildAcpSystemPrompt(prompts) {
   return `
@@ -17348,7 +17525,7 @@ async function autoInstallLatest(latest, extDirOverride) {
       "--no-fund",
       "--no-save"
     ];
-    const prevVersion = (await readPackageJson(join11(extDir, "package.json")))?.version ?? "0.1.62";
+    const prevVersion = (await readPackageJson(join11(extDir, "package.json")))?.version ?? "0.1.63";
     const { code, stderr } = await runNpmImpl(installArgs(latest), { cwd: npmDir, timeout: 6e4 });
     if (code !== 0) {
       logWarn("update", {
@@ -17366,7 +17543,7 @@ async function autoInstallLatest(latest, extDirOverride) {
     }
     const verify = await verifyInstall(npmDir, latest);
     if (!verify.ok) {
-      const rollbackTo = SEMVER_RE.test(prevVersion) ? prevVersion : "0.1.62";
+      const rollbackTo = SEMVER_RE.test(prevVersion) ? prevVersion : "0.1.63";
       logWarn("update", { event: "auto-install-verify-failed", latest, reason: verify.reason, rollbackTo });
       const rb = await runNpmImpl(installArgs(rollbackTo), { cwd: npmDir, timeout: 6e4 });
       logInfo("update", { event: "rollback", from: latest, to: rollbackTo, ok: rb.code === 0 });
@@ -17441,7 +17618,7 @@ async function checkForUpdate(autoUpdate, notify) {
     }
     const latest = await fetchLatestVersion(tag);
     if (!latest) return;
-    const current = runtimeVersion ?? "0.1.62";
+    const current = runtimeVersion ?? "0.1.63";
     const hasUpdate = isVersionNewer(latest, current);
     debug.event("update-check", {
       current,
@@ -17619,7 +17796,7 @@ function wireSessionLifecycle(pi, runtime, standDownIfProxied) {
     setDelegatePolicy(DEFAULT_DELEGATE_POLICY);
     const sid = ctx.sessionManager.getSessionId();
     const modelInfo = ctx.model;
-    logInfo("session", { event: "start", sid, cwd: ctx.cwd, debug: runtime.adapter.debug ?? null, version: true ? "0.1.62" : null, model: modelInfo?.id ?? null, modelApi: modelInfo?.api ?? null, contextWindow: modelInfo?.contextWindow ?? null });
+    logInfo("session", { event: "start", sid, cwd: ctx.cwd, debug: runtime.adapter.debug ?? null, version: true ? "0.1.63" : null, model: modelInfo?.id ?? null, modelApi: modelInfo?.api ?? null, contextWindow: modelInfo?.contextWindow ?? null });
     try {
       await runtime.reloadConfig(ctx.cwd);
       const delegateCfg = resolveDelegate(runtime.adapter);
@@ -17662,6 +17839,7 @@ function wireSessionLifecycle(pi, runtime, standDownIfProxied) {
     closeLogStream();
   });
 }
+var lastDegNoticeKey = null;
 function wireContextTransform(pi, runtime, standDownIfProxied) {
   pi.on("context", async (event, ctx) => {
     if (runtime.refused) return;
@@ -17770,9 +17948,28 @@ function wireContextTransform(pi, runtime, standDownIfProxied) {
       const reasoningDrop = runtime.reasoningDropFor(ctx);
       const droppedThinking = dropCompressReasoning(rebuilt, reasoningDrop);
       if (droppedThinking !== rebuilt) {
-        debug.event("reasoning-drop", { sid, dropped: droppedThinking.length, drop: reasoningDrop.drop, threshold: reasoningDrop.threshold });
+        const droppedChars = countThinkingChars(rebuilt) - countThinkingChars(droppedThinking);
+        debug.event("reasoning-drop", { sid, droppedChars, drop: reasoningDrop.drop, threshold: reasoningDrop.threshold });
       }
       rebuilt = droppedThinking;
+      const degCfg = resolveDegenerationGuard(runtime.adapter.degenerationGuard);
+      const tailRuns = degCfg.enabled ? lastAssistantRuns([...originalById.values()], degCfg.minRun) : null;
+      const deg = collapseAssistantDegeneration(rebuilt, degCfg);
+      if (deg.messages !== rebuilt) {
+        rebuilt = deg.messages;
+        const maxRun = deg.evidence.reduce((m2, e) => e.runs.reduce((x2, r) => Math.max(x2, r.count), m2), 0);
+        logWarn("degeneration", { sid, event: "runs-collapsed", msgs: deg.evidence.length, maxRun, minRun: degCfg.minRun });
+        debug.event("degeneration-collapsed", { sid, msgs: deg.evidence.length, maxRun });
+      }
+      if (tailRuns) {
+        rebuilt.push(degenerationNotice(tailRuns));
+        const top = [...tailRuns].sort((a, b2) => b2.count - a.count)[0];
+        logInfo("degeneration", { sid, event: "recovery-notice", maxRun: top.count });
+        if (ctx.hasUI && lastDegNoticeKey !== `${sid}:${top.count}:${top.char.codePointAt(0)}`) {
+          lastDegNoticeKey = `${sid}:${top.count}:${top.char.codePointAt(0)}`;
+          ctx.ui.notify(`[ACP] previous turn ended in degenerate generation (${top.count}\xD7 repeat) \u2014 the repeated segment was truncated above and a recovery notice injected.`);
+        }
+      }
       const debugOn2 = debug.enabled;
       const turnKey = lastUserMessageId(entries) ?? sid;
       const compressOutcomes = collectCompressOutcomes(entries, turnStartIndex(entries));