v1.13.5: opencode truncate.ts port — full tool output retrievable via opaque id

- New services/truncate.ts. Tmpfs storage at /tmp/boocode-truncations/
  (BOOCODE_TRUNCATION_DIR env var overrides for tests). 12-char base32
  opaque ids (~60 bits entropy, "tr_<id>"). Three exports: storeTruncation,
  readTruncation, truncateIfNeeded (wrap-or-passthrough helper).
  cleanupTruncations does TTL-pass (7 days) + orphan-reap (parts query on
  payload->'output'->>'outputPath') in one shot.
- Wired four tools through truncateIfNeeded: view_file (raw full file),
  list_dir (full filtered+secret-filtered entries serialized one-per-line),
  web_fetch (textRaw pre-slice), codecontext_client (body.result pre-slice).
  Each returns the existing sliced view plus an optional outputPath field
  when truncation fires.
- New view_truncated_output ToolDef. Resolves opaque id → on-disk content
  internally; model never sees the truncation dir. Same start_line /
  end_line slicing semantics as view_file. Registered in ALL_TOOLS (alpha
  sort places it after view_file automatically) and READ_ONLY_TOOL_NAMES.
- cleanupTruncations piggybacks on the v1.13.3 stuck-row sweeper's 60s
  setInterval. No-op when truncation dir is empty.

Not wired (TODO follow-up): grep and find_files. file_ops returns post-cap
results to the tool execute path, so the "full content" isn't recoverable
without a refactor of fileOps.grep / fileOps.findFiles to expose the
uncapped result. web_search is silent-slice (no truncated flag); outside
scope. Five sites of seven covered; the remaining two are the only ones
needing a file_ops change.

Tests: 7 new in truncate.test.ts (roundtrip, unknown id, malformed id,
truncateIfNeeded false/true/over-cap/storage-failure paths). 186 total
(was 179). cleanupTruncations file-system half implicitly via TTL pass;
orphan-reap branch covered by the live container smoke.

Smoke verified end-to-end against the live container:
- view_file with start_line=1, end_line=3 on CLAUDE.md → tool_result part
  carried outputPath "tr_cdpn1o04k6ma" + truncated=true.
- /tmp/boocode-truncations/tr_cdpn1o04k6ma exists, 15876 bytes, mode 0o600,
  parent dir mode 0o700.
- Follow-up view_truncated_output(id, start_line=50, end_line=55) returned
  the actual lines 50-55 of CLAUDE.md (the 808notes/BooCode bullets).
- ALL_TOOLS count=20 (was 19); alpha sort places view_truncated_output
  between view_file and watch_changes.

Closes a v1.12 catalog row that was scoped but deferred. The v1.13 parts
table made outputPath ride on the existing tool_result payload with no
schema change beyond the storage helper itself.

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

apps/server/src/index.ts

@@ -21,6 +21,7 @@ import { createBroker } from './services/broker.js';
 import { listSkills } from './services/skills.js';
 import * as compaction from './services/compaction.js';
 import { configureModelContext } from './services/model-context.js';
+import { cleanupTruncations } from './services/truncate.js';
 
 async function main() {
   const config = loadConfig();
@@ -201,6 +202,52 @@ async function main() {
     app.log.info(`serving static frontend from ${webDist}`);
   }
 
+  // v1.13.3: periodic in-process sweeper for streaming rows orphaned by a
+  // mid-session crash. The boot sweep (above) only fires once at startup;
+  // this loop catches the in-flight case. 60s cadence + 5-min threshold
+  // matches the boot sweep so behavior is consistent. Publishes
+  // chat_status='idle' on the user channel so the UI dot drops without a
+  // refresh — same pattern as handleAbortOrError.
+  const SWEEP_INTERVAL_MS = 60_000;
+  const sweepStaleStreaming = async (): Promise<void> => {
+    try {
+      const rows = await sql<{ id: string; chat_id: string }[]>`
+        UPDATE messages
+        SET status = 'failed', finished_at = clock_timestamp()
+        WHERE status = 'streaming'
+          AND created_at < NOW() - INTERVAL '5 minutes'
+        RETURNING id, chat_id
+      `;
+      if (rows.length === 0) return;
+      app.log.warn(
+        { swept: rows.length, ids: rows.map((r) => r.id) },
+        'swept stale streaming rows',
+      );
+      const seenChats = new Set<string>();
+      const now = new Date().toISOString();
+      for (const row of rows) {
+        if (seenChats.has(row.chat_id)) continue;
+        seenChats.add(row.chat_id);
+        broker.publishUser('default', {
+          type: 'chat_status',
+          chat_id: row.chat_id,
+          status: 'idle',
+          at: now,
+        });
+      }
+    } catch (err) {
+      app.log.error({ err }, 'stuck-row sweeper failed');
+    }
+  };
+  // v1.13.5: truncation cleanup rides the same cadence — 60s tick reaps
+  // tmpfs files past the 7-day TTL plus any orphans whose owning part has
+  // been pruned (v1.13.4) or deleted. No-op when the dir is empty.
+  const sweepTimer = setInterval(() => {
+    void sweepStaleStreaming();
+    void cleanupTruncations({ sql, log: app.log });
+  }, SWEEP_INTERVAL_MS);
+  app.addHook('onClose', async () => { clearInterval(sweepTimer); });
+
   const shutdown = async (signal: string) => {
     app.log.info(`received ${signal}, shutting down`);
     try {

apps/server/src/schema.sql

@@ -1,3 +1,10 @@
+-- v1.13.3: statement_timeout is set at database level via:
+--   ALTER DATABASE boocode SET statement_timeout = '30s';
+-- ALTER DATABASE can't run inside a DO block, so this is an operational
+-- step rather than schema. Re-apply after a volume reset (the setting
+-- lives in pg_db which survives `docker compose up --build` but NOT a
+-- `docker volume rm boocode_pgdata`).
+
 CREATE TABLE IF NOT EXISTS projects (
   id UUID PRIMARY KEY DEFAULT gen_random_uuid(),
   name TEXT NOT NULL,
@@ -49,6 +56,24 @@ CREATE TABLE IF NOT EXISTS message_parts (
 );
 CREATE INDEX IF NOT EXISTS message_parts_msg_seq_idx ON message_parts (message_id, sequence);
 
+-- v1.13.4: prune support. hidden_at marks parts that have been pruned out
+-- of the model payload by the two-tier compaction prune (services/inference/
+-- prune.ts). Rows stay in the DB so frontend can still display them with a
+-- "hidden" indicator (out of scope this dispatch). messages_with_parts
+-- view filters these out — see below. Partial index speeds the common
+-- "visible parts only" filter.
+DO $$
+BEGIN
+  IF NOT EXISTS (
+    SELECT 1 FROM information_schema.columns
+    WHERE table_name = 'message_parts' AND column_name = 'hidden_at'
+  ) THEN
+    ALTER TABLE message_parts ADD COLUMN hidden_at timestamptz NULL;
+  END IF;
+END $$;
+CREATE INDEX IF NOT EXISTS message_parts_hidden_idx
+  ON message_parts (message_id) WHERE hidden_at IS NULL;
+
 -- v1.13.1-B: read-path view. Read sites SELECT FROM messages_with_parts
 -- instead of messages so tool_calls / tool_results / reasoning_parts come
 -- from the granular message_parts table. The COALESCE means pre-v1.13.0
@@ -66,23 +91,32 @@ SELECT
   m.last_seq, m.tokens_used, m.ctx_used, m.ctx_max,
   m.started_at, m.finished_at, m.created_at, m.metadata,
   m.summary, m.tail_start_id, m.compacted_at,
-  COALESCE(
+  -- v1.13.4: prune semantics need to distinguish "no parts row exists"
-    (SELECT jsonb_agg(p.payload ORDER BY p.sequence)
+  -- (pre-v1.13.0 fallback to legacy column) from "all parts hidden"
-       FROM message_parts p
+  -- (prune intended — return null/empty so the row drops from the model
-      WHERE p.message_id = m.id AND p.kind = 'tool_call'),
+  -- payload). A naive COALESCE would fall back to the legacy column when
-    m.tool_calls
+  -- every part is hidden, undoing the prune. CASE on EXISTS(any kind)
-  ) AS tool_calls,
+  -- splits the two cases.
-  COALESCE(
+  CASE
-    (SELECT p.payload
+    WHEN EXISTS (SELECT 1 FROM message_parts pp
-       FROM message_parts p
+                  WHERE pp.message_id = m.id AND pp.kind = 'tool_call')
-      WHERE p.message_id = m.id AND p.kind = 'tool_result'
+    THEN (SELECT jsonb_agg(p.payload ORDER BY p.sequence)
-      ORDER BY p.sequence
+            FROM message_parts p
-      LIMIT 1),
+           WHERE p.message_id = m.id AND p.kind = 'tool_call' AND p.hidden_at IS NULL)
-    m.tool_results
+    ELSE m.tool_calls
-  ) AS tool_results,
+  END AS tool_calls,
+  CASE
+    WHEN EXISTS (SELECT 1 FROM message_parts pp
+                  WHERE pp.message_id = m.id AND pp.kind = 'tool_result')
+    THEN (SELECT p.payload
+            FROM message_parts p
+           WHERE p.message_id = m.id AND p.kind = 'tool_result' AND p.hidden_at IS NULL
+           ORDER BY p.sequence LIMIT 1)
+    ELSE m.tool_results
+  END AS tool_results,
   (SELECT jsonb_agg(p.payload ORDER BY p.sequence)
      FROM message_parts p
-    WHERE p.message_id = m.id AND p.kind = 'reasoning') AS reasoning_parts
+    WHERE p.message_id = m.id AND p.kind = 'reasoning' AND p.hidden_at IS NULL) AS reasoning_parts
 FROM messages m;
 
 ALTER TABLE messages ADD COLUMN IF NOT EXISTS tokens_used INTEGER;

apps/server/src/services/__tests__/prune.test.ts

@@ -0,0 +1,96 @@
+import { describe, it, expect, beforeEach } from 'vitest';
+import {
+  selectPruneTargets,
+  PROTECTED_TOKENS,
+  PRUNE_TRIGGER_TOKENS,
+  type PartForPrune,
+} from '../inference/prune.js';
+
+// Test fixture: build a tool_result part whose payload size yields a known
+// token estimate (chars/4). The decision logic only cares about
+// JSON.stringify(payload).length, so a string payload of `4n` chars
+// produces exactly `n` tokens.
+let seq = 0;
+function part(tokens: number, createdAt: Date): PartForPrune {
+  seq += 1;
+  // JSON.stringify("xxx...") wraps in quotes (adds 2 chars), so subtract 2
+  // before multiplying. Math.ceil((len+2)/4) needs len ≈ 4*tokens - 2 so the
+  // total stringified length is 4*tokens. Approximate by padding 4 chars per
+  // token; the off-by-one from quotes is small and tests check totals, not
+  // exact per-part counts.
+  const text = 'x'.repeat(tokens * 4 - 2);
+  return { id: `p${seq}`, payload: text, created_at: createdAt };
+}
+
+const T_NOW = new Date('2026-05-22T12:00:00Z');
+function ago(secondsBack: number): Date {
+  return new Date(T_NOW.getTime() - secondsBack * 1000);
+}
+
+describe('selectPruneTargets', () => {
+  beforeEach(() => {
+    seq = 0;
+  });
+
+  it('returns nothing when there are no parts', () => {
+    expect(selectPruneTargets([], null)).toEqual({ ids: [], freedTokens: 0 });
+  });
+
+  it('returns nothing when total tokens are under the protection window', () => {
+    const parts: PartForPrune[] = [
+      part(10_000, ago(10)),
+      part(10_000, ago(20)),
+    ]; // 20k total, all protected
+    expect(selectPruneTargets(parts, null)).toEqual({ ids: [], freedTokens: 0 });
+  });
+
+  it('returns nothing when candidate total is below the prune trigger', () => {
+    // Protection fills with ~40k newest, candidates only ~5k. Below 20k trigger.
+    const parts: PartForPrune[] = [
+      part(20_000, ago(10)),
+      part(20_000, ago(20)),
+      // Past protection; total ~5k won't trigger.
+      part(5_000, ago(30)),
+    ];
+    const result = selectPruneTargets(parts, null);
+    expect(result.ids).toEqual([]);
+    expect(result.freedTokens).toBe(0);
+  });
+
+  it('hides candidates past protection when their total clears the trigger', () => {
+    // Newest 40k protected; older 30k cleanly above the 20k trigger.
+    const parts: PartForPrune[] = [
+      part(20_000, ago(10)),
+      part(20_000, ago(20)),
+      // Past protection, total ~30k freed.
+      part(15_000, ago(30)),
+      part(15_000, ago(40)),
+    ];
+    const result = selectPruneTargets(parts, null);
+    expect(result.ids).toEqual(['p3', 'p4']);
+    expect(result.freedTokens).toBeGreaterThanOrEqual(PRUNE_TRIGGER_TOKENS);
+  });
+
+  it('stops at the compaction summary boundary', () => {
+    // Newest 30k protected (just under PROTECTED_TOKENS=40k); then 30k of
+    // older parts. Boundary sits at ago(35), so the ago(40) part is
+    // beyond it and gets skipped.
+    const parts: PartForPrune[] = [
+      part(15_000, ago(10)),
+      part(15_000, ago(20)),
+      part(15_000, ago(30)), // crosses protection threshold; candidate
+      part(15_000, ago(40)), // beyond summary boundary; skipped
+    ];
+    const tailStart = ago(35);
+    const result = selectPruneTargets(parts, tailStart);
+    // ago(30) is the only candidate inside the window; 15k is below the
+    // 20k trigger so we expect no hides.
+    expect(result.ids).toEqual([]);
+  });
+
+  it('does not prune when only protected parts exist (no candidates)', () => {
+    // Exactly PROTECTED_TOKENS of newest parts; no older candidates.
+    const parts: PartForPrune[] = [part(PROTECTED_TOKENS, ago(10))];
+    expect(selectPruneTargets(parts, null)).toEqual({ ids: [], freedTokens: 0 });
+  });
+});

apps/server/src/services/__tests__/tools.test.ts

@@ -0,0 +1,14 @@
+import { describe, it, expect } from 'vitest';
+import { ALL_TOOLS } from '../tools.js';
+
+describe('ALL_TOOLS registry', () => {
+  // v1.13.3: tools must be alpha-sorted at module load. llama.cpp's prompt
+  // cache hits on byte-identical prefixes; the tool list lives near the
+  // top of the system prompt, so any order drift invalidates every cached
+  // turn. The registry sort is the single source of truth; downstream
+  // helpers (toolJsonSchemas, TOOLS_BY_NAME, buildAiTools) inherit it.
+  it('exports tools in alphabetical order by name', () => {
+    const names = ALL_TOOLS.map((t) => t.name);
+    expect(names).toEqual([...names].sort((a, b) => a.localeCompare(b)));
+  });
+});

apps/server/src/services/__tests__/truncate.test.ts

@@ -0,0 +1,104 @@
+// v1.13.5: truncate.ts unit coverage. Each test isolates TRUNCATION_DIR
+// under os.tmpdir() so concurrent vitest runs don't collide and the suite
+// stays self-cleaning. cleanupTruncations is covered by file-system half
+// only; the orphan-reap branch needs a real Postgres and is tested via the
+// smoke flow rather than vitest.
+import { afterEach, beforeAll, describe, expect, it, vi } from 'vitest';
+import { promises as fs } from 'fs';
+import path from 'path';
+import os from 'os';
+
+// Set the env var BEFORE importing the module so its module-load constant
+// reads the test directory rather than /tmp/boocode-truncations.
+const testDir = path.join(os.tmpdir(), `boocode-truncate-test-${process.pid}-${Date.now()}`);
+process.env.BOOCODE_TRUNCATION_DIR = testDir;
+
+const mod = await import('../truncate.js');
+const { storeTruncation, readTruncation, truncateIfNeeded, MAX_TRUNCATION_BYTES } = mod;
+
+beforeAll(async () => {
+  await fs.mkdir(testDir, { recursive: true });
+});
+
+afterEach(async () => {
+  // Drop every file between tests so id-collision asserts and orphan-style
+  // counts start from zero.
+  const entries = await fs.readdir(testDir).catch(() => [] as string[]);
+  await Promise.all(entries.map((n) => fs.unlink(path.join(testDir, n)).catch(() => {})));
+});
+
+describe('storeTruncation / readTruncation roundtrip', () => {
+  it('writes and reads identical content', async () => {
+    const original = 'hello\nworld\n' + 'x'.repeat(500);
+    const id = await storeTruncation(original);
+    expect(id).toMatch(/^tr_[0-9a-v]{12}$/);
+    const got = await readTruncation(id);
+    expect(got).toBe(original);
+  });
+
+  it('readTruncation returns null for unknown ids', async () => {
+    const got = await readTruncation('tr_000000000000');
+    expect(got).toBeNull();
+  });
+
+  it('readTruncation rejects malformed ids (returns null, never escapes dir)', async () => {
+    // Path traversal attempt; readTruncation should not even try to open.
+    const got = await readTruncation('../../etc/passwd');
+    expect(got).toBeNull();
+  });
+});
+
+describe('truncateIfNeeded', () => {
+  it('returns sliced content with no outputPath when wasTruncated=false', async () => {
+    const out = await truncateIfNeeded({
+      fullContent: 'irrelevant',
+      slicedContent: 'visible',
+      wasTruncated: false,
+    });
+    expect(out).toEqual({ content: 'visible', truncated: false });
+    expect('outputPath' in out).toBe(false);
+  });
+
+  it('stashes full content and returns outputPath when wasTruncated=true', async () => {
+    const full = 'line1\nline2\nline3\nline4\n';
+    const sliced = 'line1\nline2\n[truncated]';
+    const out = await truncateIfNeeded({
+      fullContent: full,
+      slicedContent: sliced,
+      wasTruncated: true,
+    });
+    expect(out.content).toBe(sliced);
+    expect(out.truncated).toBe(true);
+    expect(out.outputPath).toMatch(/^tr_[0-9a-v]{12}$/);
+    const stashed = await readTruncation(out.outputPath!);
+    expect(stashed).toBe(full);
+  });
+
+  it('skips storage but still reports truncated when fullContent exceeds the cap', async () => {
+    // Build content larger than MAX_TRUNCATION_BYTES. Use a Buffer to size
+    // it without holding a literal that triggers the gigantic-string lint.
+    const oversized = Buffer.alloc(MAX_TRUNCATION_BYTES + 1, 'x').toString('utf8');
+    const sliced = 'preview...';
+    const out = await truncateIfNeeded({
+      fullContent: oversized,
+      slicedContent: sliced,
+      wasTruncated: true,
+    });
+    expect(out).toEqual({ content: sliced, truncated: true });
+    expect('outputPath' in out).toBe(false);
+  });
+
+  it('storage failure surfaces as truncated without outputPath', async () => {
+    // Force writeFile to throw. Spy at the fs module level since truncate.ts
+    // imports { promises as fs } and storeTruncation calls fs.writeFile.
+    const spy = vi.spyOn(fs, 'writeFile').mockRejectedValueOnce(new Error('disk full'));
+    const out = await truncateIfNeeded({
+      fullContent: 'short',
+      slicedContent: 'sliced',
+      wasTruncated: true,
+    });
+    expect(out).toEqual({ content: 'sliced', truncated: true });
+    expect('outputPath' in out).toBe(false);
+    spy.mockRestore();
+  });
+});

apps/server/src/services/codecontext_client.ts

@@ -17,6 +17,7 @@
 //      which we re-surface with a hint to add the file to .codecontextignore.
 
 import { realpath } from 'node:fs/promises';
+import { truncateIfNeeded } from './truncate.js';
 
 export interface CodecontextRequest {
   toolName: string;
@@ -27,6 +28,9 @@ export interface CodecontextRequest {
 export interface CodecontextResponse {
   result: string;
   truncated: boolean;
+  // v1.13.5: optional opaque id pointing at the full pre-slice content on
+  // tmpfs. Set when truncated=true and storage succeeded.
+  outputPath?: string;
 }
 
 const CODECONTEXT_BASE_URL = process.env['CODECONTEXT_URL'] ?? 'http://codecontext:8080';
@@ -105,13 +109,22 @@ export async function callCodecontext(
 
   // Step 4: inline truncation. The model gets a clear hint about how to
   // narrow the next call rather than a silent cut. Mirrors web_fetch.ts.
+  // v1.13.5: stash the full body on tmpfs when truncating so the model can
+  // retrieve more via view_truncated_output(id).
   if (body.result.length > TRUNCATION_LIMIT) {
     const truncated = body.result.slice(0, TRUNCATION_LIMIT);
     const omitted = body.result.length - TRUNCATION_LIMIT;
+    const slicedWithMarker =
+      `${truncated}\n\n[truncated, ${omitted} chars omitted; narrow with file_path, file_type, or limit]`;
+    const wrapped = await truncateIfNeeded({
+      fullContent: body.result,
+      slicedContent: slicedWithMarker,
+      wasTruncated: true,
+    });
     return {
-      result:
+      result: wrapped.content,
-        `${truncated}\n\n[truncated, ${omitted} chars omitted; narrow with file_path, file_type, or limit]`,
+      truncated: wrapped.truncated,
-      truncated: true,
+      ...(wrapped.outputPath ? { outputPath: wrapped.outputPath } : {}),
     };
   }
   return { result: body.result, truncated: false };

apps/server/src/services/inference/payload.ts

@@ -8,6 +8,7 @@ import type {
 import * as compaction from '../compaction.js';
 import { buildSystemPrompt } from '../system-prompt.js';
 import { isAnySentinel } from './sentinels.js';
+import { PRUNE_TRIGGER_TOKENS, prune } from './prune.js';
 import type { InferenceContext } from './turn.js';
 
 export interface OpenAiMessage {
@@ -166,6 +167,26 @@ export async function maybeFlagForCompaction(
     contextLimit,
   );
   if (!overflow) return;
+
+  // v1.13.4: try the cheap prune first. If it freed at least the buffer
+  // worth of tokens (PRUNE_TRIGGER_TOKENS, identical to COMPACTION_BUFFER),
+  // we're below the threshold again — skip flagging summarize for the next
+  // turn. The next turn's overflow check will re-evaluate from scratch.
+  // Prune failures (DB errors etc.) propagate so the surrounding inference
+  // path sees them; the catch in finalizeCompletion / executeToolPhase
+  // doesn't shield this — by design, we want to know if prune is broken.
+  const pruned = await prune({ sql: ctx.sql, chatId });
+  if (pruned.hidden > 0) {
+    ctx.log.info(
+      { chatId, hidden: pruned.hidden, freedTokens: pruned.freedTokens },
+      'inference: prune freed context budget',
+    );
+  }
+  if (pruned.freedTokens >= PRUNE_TRIGGER_TOKENS) {
+    // Prune handled it; skip the (expensive) summarize path.
+    return;
+  }
+
   await ctx.sql`UPDATE chats SET needs_compaction = true WHERE id = ${chatId}`;
   ctx.log.info({ chatId, promptTokens, completionTokens, contextLimit }, 'inference: flagged for compaction');
 }

apps/server/src/services/inference/prune.ts

@@ -0,0 +1,127 @@
+import type { Sql } from '../../db.js';
+
+// v1.13.4: two-tier compaction prune. Opencode's prune half (the cheap one);
+// summarize half shipped in v1.11.0 as services/compaction.ts.
+//
+// Algorithm: scan tool_result parts newest-first. Protect the last
+// PROTECTED_TOKENS of content (the model recently saw these — pruning them
+// kills coherence). Older parts are candidates. Mark them hidden_at only
+// if the candidate pool would free at least PRUNE_TRIGGER_TOKENS — pruning
+// 3 small tool_results to recover 500 tokens isn't worth the loss of
+// fidelity for the model's next turn.
+//
+// Stops at the last compaction summary boundary (chats.tail_start_id). The
+// v1.11.0 summary already encodes everything before that point; pruning
+// across the boundary would double-erase.
+
+export const PROTECTED_TOKENS = 40_000;
+export const PRUNE_TRIGGER_TOKENS = 20_000;
+
+// Rough char-to-token estimate. Same heuristic compaction's usable() uses
+// implicitly via the buffer constant.
+function estimateTokens(text: string): number {
+  return Math.ceil(text.length / 4);
+}
+
+function payloadTokens(payload: unknown): number {
+  return estimateTokens(JSON.stringify(payload ?? ''));
+}
+
+export interface PruneResult {
+  hidden: number;
+  freedTokens: number;
+}
+
+// Pure algorithmic core, exported for unit-test access. Takes parts already
+// ordered newest-first, plus an optional cutoff (last compaction summary
+// boundary). Returns the part ids to hide and the total token estimate of
+// the candidates. Caller does the DB UPDATE.
+export interface PartForPrune {
+  id: string;
+  payload: unknown;
+  created_at: Date;
+}
+
+export function selectPruneTargets(
+  partsNewestFirst: ReadonlyArray<PartForPrune>,
+  tailStartCreatedAt: Date | null,
+): { ids: string[]; freedTokens: number } {
+  let protectedTokens = 0;
+  const candidates: { id: string; tokens: number }[] = [];
+  let crossedProtection = false;
+
+  for (const part of partsNewestFirst) {
+    if (tailStartCreatedAt && part.created_at < tailStartCreatedAt) {
+      // Past the last summary boundary; the v1.11.0 anchored summary already
+      // covers everything older. Bail rather than double-erase.
+      break;
+    }
+    const tokens = payloadTokens(part.payload);
+    if (!crossedProtection) {
+      protectedTokens += tokens;
+      if (protectedTokens >= PROTECTED_TOKENS) {
+        crossedProtection = true;
+      }
+      continue;
+    }
+    candidates.push({ id: part.id, tokens });
+  }
+
+  const candidateTokens = candidates.reduce((s, c) => s + c.tokens, 0);
+  if (candidates.length === 0 || candidateTokens < PRUNE_TRIGGER_TOKENS) {
+    return { ids: [], freedTokens: 0 };
+  }
+  return { ids: candidates.map((c) => c.id), freedTokens: candidateTokens };
+}
+
+export async function prune(args: {
+  sql: Sql;
+  chatId: string;
+}): Promise<PruneResult> {
+  const { sql, chatId } = args;
+
+  // Newest-first scan of visible tool_result parts in this chat. Pull
+  // chats.tail_start_id alongside so we know where the last summary boundary
+  // sits (don't prune across it).
+  const parts = await sql<{
+    id: string;
+    payload: unknown;
+    created_at: Date;
+    tail_start_id: string | null;
+  }[]>`
+    SELECT p.id, p.payload, m.created_at,
+      (SELECT c.tail_start_id FROM chats c WHERE c.id = ${chatId}) AS tail_start_id
+    FROM message_parts p
+    JOIN messages m ON m.id = p.message_id
+    WHERE m.chat_id = ${chatId}
+      AND p.kind = 'tool_result'
+      AND p.hidden_at IS NULL
+    ORDER BY m.created_at DESC, p.sequence DESC
+  `;
+
+  if (parts.length === 0) {
+    return { hidden: 0, freedTokens: 0 };
+  }
+
+  // Read the boundary cutoff timestamp once. Older messages are off-limits.
+  let tailStartCreatedAt: Date | null = null;
+  const firstTailId = parts[0]?.tail_start_id ?? null;
+  if (firstTailId) {
+    const tailRow = await sql<{ created_at: Date }[]>`
+      SELECT created_at FROM messages WHERE id = ${firstTailId}
+    `;
+    tailStartCreatedAt = tailRow[0]?.created_at ?? null;
+  }
+
+  const decision = selectPruneTargets(parts, tailStartCreatedAt);
+  if (decision.ids.length === 0) {
+    return { hidden: 0, freedTokens: 0 };
+  }
+
+  await sql`
+    UPDATE message_parts
+    SET hidden_at = clock_timestamp()
+    WHERE id = ANY(${decision.ids})
+  `;
+  return { hidden: decision.ids.length, freedTokens: decision.freedTokens };
+}

apps/server/src/services/inference/stream-phase.ts

@@ -19,7 +19,14 @@ import type {
   TurnArgs,
 } from './turn.js';
 import { upstreamModel } from './provider.js';
-import { jsonSchema, streamText, tool, type JSONValue, type ModelMessage } from 'ai';
+import {
+  jsonSchema,
+  streamText,
+  tool,
+  type JSONValue,
+  type ModelMessage,
+  type ToolCallRepairFunction,
+} from 'ai';
 
 interface StreamOptions {
   // null = omit tools entirely (compact phase); [] = caller stripped all tools
@@ -155,10 +162,36 @@ export async function streamCompletion(
   // Replaces the v1.13.1-A counter-only diagnostic.
   let reasoningAccumulated = '';
 
+  // v1.13.3: experimental_repairToolCall keeps the stream alive when the
+  // model emits a malformed tool call (bad JSON args, unknown name, etc.).
+  // Without a repair function streamText throws and the WHOLE stream dies;
+  // with one, the SDK invokes us and we route the bad call through normally.
+  // Strategy: pass through unmodified. executeToolPhase's existing error
+  // path (unknown tool name → "unknown tool: X" result; zod-reject → tool
+  // 'X' rejected — fieldname: required) already gives the model a clean
+  // recovery surface on the next turn. Logging gives us visibility into
+  // how often qwen3.6 actually emits broken calls.
+  const repairToolCall: ToolCallRepairFunction<NonNullable<typeof aiTools>> = async ({
+    toolCall,
+    error,
+  }) => {
+    ctx.log.warn(
+      {
+        toolCallId: toolCall.toolCallId,
+        toolName: toolCall.toolName,
+        error: error.message,
+      },
+      'malformed tool call surfaced via repairToolCall',
+    );
+    return toolCall;
+  };
+
   const result = streamText({
     model: upstreamModel(ctx.config.LLAMA_SWAP_URL, model),
     messages: aiMessages,
-    ...(aiTools ? { tools: aiTools, toolChoice: 'auto' as const } : {}),
+    ...(aiTools
+      ? { tools: aiTools, toolChoice: 'auto' as const, experimental_repairToolCall: repairToolCall }
+      : {}),
     ...(typeof opts.temperature === 'number' ? { temperature: opts.temperature } : {}),
     abortSignal: signal,
   });

apps/server/src/services/tools.ts

@@ -8,6 +8,7 @@ import { getGitMeta } from './git_meta.js';
 import { findSkills, getSkillBody, getSkillResource } from './skills.js';
 import { webSearch } from './web_search.js';
 import { webFetch } from './web_fetch.js';
+import { readTruncation, truncateIfNeeded } from './truncate.js';
 // v1.12 Track B.2: codecontext tools. 8 wrappers re-exported from
 // tools/codecontext/index.ts. Each calls into services/codecontext_client.ts
 // which talks to the codecontext sidecar at http://codecontext:8080.
@@ -109,12 +110,22 @@ export const viewFile: ToolDef<ViewFileInputT> = {
     const slice = lines.slice(start - 1, end);
     const content = slice.join('\n');
     const truncated = total > end || start > 1;
+    // v1.13.5: stash the full file on tmpfs so the model can retrieve more
+    // via view_truncated_output(id) without re-reading the file (which it
+    // may not have project-relative-path access to in future agent setups).
+    // raw is bounded by MAX_FILE_BYTES (5MB), within truncateIfNeeded's cap.
+    const wrapped = await truncateIfNeeded({
+      fullContent: raw,
+      slicedContent: content,
+      wasTruncated: truncated,
+    });
     return {
       path: relative(projectRoot, real) || basename(real),
-      content,
+      content: wrapped.content,
       total_lines: total,
       returned_lines: [start, end],
-      truncated,
+      truncated: wrapped.truncated,
+      ...(wrapped.outputPath ? { outputPath: wrapped.outputPath } : {}),
     };
   },
 };
@@ -157,41 +168,64 @@ export const listDir: ToolDef<ListDirInputT> = {
       ? entries
       : entries.filter((e) => !e.name.startsWith('.'));
     const total = filtered.length;
-    const slice = filtered.slice(0, MAX_DIR_ENTRIES);
+    const wasTruncated = total > MAX_DIR_ENTRIES;
-    const out = await Promise.all(
-      slice.map(async (e) => {
-        const child = resolve(real, e.name);
-        let size: number | undefined;
-        if (e.isFile()) {
-          try {
-            const cs = await stat(child);
-            size = cs.size;
-          } catch {
-            /* ignore */
-          }
-        }
-        return {
-          name: e.name,
-          type: e.isDirectory() ? ('dir' as const) : ('file' as const),
-          ...(size != null ? { size } : {}),
-        };
-      })
-    );
-    // v1.11.7: filter entries whose project-relative path matches a secret
-    // pattern. Each entry is tested using the project-rel dir + its name
-    // so the pattern's path/segment semantics work for nested dirs like
-    // `.aws/`. The count is surfaced via `pathguard_note` — we never list
-    // the hidden paths (defeats the purpose).
     const relDir = relative(projectRoot, real) || '.';
+    // v1.13.5: when we'd truncate, render the FULL list to tmpfs so
+    // view_truncated_output can serve it. Stat sizes for all entries when
+    // truncating so the stored view matches the visible shape; this is the
+    // one extra cost for big directories, bounded by total entries (which
+    // is itself bounded by filesystem behavior).
+    const processOne = async (e: typeof filtered[number]) => {
+      const child = resolve(real, e.name);
+      let size: number | undefined;
+      if (e.isFile()) {
+        try {
+          const cs = await stat(child);
+          size = cs.size;
+        } catch { /* ignore */ }
+      }
+      return {
+        name: e.name,
+        type: e.isDirectory() ? ('dir' as const) : ('file' as const),
+        ...(size != null ? { size } : {}),
+      };
+    };
+    const slice = filtered.slice(0, MAX_DIR_ENTRIES);
+    const out = await Promise.all(slice.map(processOne));
+    // v1.11.7: filter entries whose project-relative path matches a secret
+    // pattern. The same filter applies to the full-list snapshot below so
+    // the stashed file never holds entries the slice would have hidden.
     const secretFilter = filterSecretEntries(out, (e) =>
       relDir === '.' ? e.name : `${relDir}/${e.name}`,
     );
+    let outputPath: string | undefined;
+    if (wasTruncated) {
+      const fullProcessed = await Promise.all(filtered.map(processOne));
+      const fullFiltered = filterSecretEntries(fullProcessed, (e) =>
+        relDir === '.' ? e.name : `${relDir}/${e.name}`,
+      );
+      // One line per entry, view_truncated_output's line slicing semantics
+      // map cleanly. Format: "<type>\t<name>[\tsize=N]". Header documents
+      // the shape so the model can grep / regex without prior schema lookup.
+      const header = `# list_dir ${relDir} — ${fullFiltered.kept.length} entries`;
+      const lines = [header, ...fullFiltered.kept.map((e) => {
+        const sz = 'size' in e && e.size != null ? `\tsize=${e.size}` : '';
+        return `${e.type}\t${e.name}${sz}`;
+      })];
+      const wrapped = await truncateIfNeeded({
+        fullContent: lines.join('\n'),
+        slicedContent: '',
+        wasTruncated: true,
+      });
+      outputPath = wrapped.outputPath;
+    }
     return {
       path: relDir,
       entries: secretFilter.kept,
       total: secretFilter.kept.length,
-      truncated: total > MAX_DIR_ENTRIES,
+      truncated: wasTruncated,
       ...(secretFilter.note ? { pathguard_note: secretFilter.note } : {}),
+      ...(outputPath ? { outputPath } : {}),
     };
   },
 };
@@ -315,6 +349,71 @@ export const findFiles: ToolDef<FindFilesInputT> = {
   },
 };
 
+// v1.13.5: retrieves the full content of a previously-truncated tool output
+// via the opaque id stamped on the original tool_result. Line-based slicing
+// matches view_file's mental model so the model uses the same affordances.
+// Tmpfs-backed, 7-day TTL (see services/truncate.ts).
+const VIEW_TRUNCATED_DEFAULT_LINES = 200;
+
+const ViewTruncatedOutputInput = z.object({
+  id: z.string().regex(/^tr_[0-9a-v]{12}$/),
+  start_line: z.number().int().positive().optional(),
+  end_line: z.number().int().positive().optional(),
+});
+type ViewTruncatedOutputInputT = z.infer<typeof ViewTruncatedOutputInput>;
+
+export const viewTruncatedOutput: ToolDef<ViewTruncatedOutputInputT> = {
+  name: 'view_truncated_output',
+  description: `Retrieve the full content of a previously-truncated tool output by its outputPath id. When a tool returns { truncated: true, outputPath: "tr_..." }, call this to view the full content. Defaults to the first ${VIEW_TRUNCATED_DEFAULT_LINES} lines. Use start_line and end_line (1-indexed, inclusive) to slice. Stored for 7 days.`,
+  inputSchema: ViewTruncatedOutputInput,
+  jsonSchema: {
+    type: 'function',
+    function: {
+      name: 'view_truncated_output',
+      description: `Retrieve the full content of a previously-truncated tool output by its outputPath id. Returns the first ${VIEW_TRUNCATED_DEFAULT_LINES} lines by default; use start_line/end_line to slice. Stored for 7 days.`,
+      parameters: {
+        type: 'object',
+        properties: {
+          id: { type: 'string', description: 'The outputPath value from an earlier truncated tool result (e.g. "tr_abc123def456").' },
+          start_line: { type: 'integer', description: 'First line (1-indexed). Default 1.' },
+          end_line: { type: 'integer', description: `Last line (1-indexed, inclusive). Default ${VIEW_TRUNCATED_DEFAULT_LINES} lines past start.` },
+        },
+        required: ['id'],
+        additionalProperties: false,
+      },
+    },
+  },
+  async execute(input, _projectRoot) {
+    const content = await readTruncation(input.id);
+    if (content === null) {
+      return {
+        id: input.id,
+        content: '',
+        truncated: false,
+        error: `No truncation found for id "${input.id}". It may have been pruned (7-day TTL) or never existed.`,
+      };
+    }
+    const lines = content.split('\n');
+    const total = lines.length;
+    let start = input.start_line ?? 1;
+    let end = input.end_line ?? Math.min(total, start + VIEW_TRUNCATED_DEFAULT_LINES - 1);
+    if (start < 1) start = 1;
+    if (end > total) end = total;
+    if (end < start) end = start;
+    const slice = lines.slice(start - 1, end).join('\n');
+    // Re-slicing this view isn't truncation in the dual-write sense — the
+    // model already has the id; no point stashing the slice again.
+    const truncated = total > end || start > 1;
+    return {
+      id: input.id,
+      content: slice,
+      total_lines: total,
+      returned_lines: [start, end],
+      truncated,
+    };
+  },
+};
+
 // v1.8 Level 1 branch awareness: gives the model a read-only view of the
 // project's git state. No path input — operates on the inference-resolved
 // project root via getGitMeta. Subprocess runs with a 2s timeout (see git_meta).
@@ -527,8 +626,14 @@ export const askUserInput: ToolDef<AskUserInputInputT> = {
   },
 };
 
+// v1.13.3: alpha-sorted by tool.name at module load. llama.cpp's prompt
+// cache hits on byte-identical prefixes; the tool list lives near the top
+// of the system prompt, so any order drift would invalidate every cached
+// turn. Single source of truth for ordering lives here — toolJsonSchemas()
+// and TOOLS_BY_NAME inherit it.
 export const ALL_TOOLS: ReadonlyArray<ToolDef<unknown>> = [
   viewFile as ToolDef<unknown>,
+  viewTruncatedOutput as ToolDef<unknown>,
   listDir as ToolDef<unknown>,
   grep as ToolDef<unknown>,
   findFiles as ToolDef<unknown>,
@@ -553,7 +658,7 @@ export const ALL_TOOLS: ReadonlyArray<ToolDef<unknown>> = [
   watchChanges as ToolDef<unknown>,
   getSemanticNeighborhoods as ToolDef<unknown>,
   getFrameworkAnalysis as ToolDef<unknown>,
-];
+].sort((a, b) => a.name.localeCompare(b.name));
 
 // v1.8.2: forward-compatible read-only whitelist. An agent whose `tools` is
 // fully contained in this set gets a generous default tool budget (30);
@@ -565,6 +670,7 @@ export const ALL_TOOLS: ReadonlyArray<ToolDef<unknown>> = [
 // project state, so it belongs in the read-only set for budget purposes.
 export const READ_ONLY_TOOL_NAMES = [
   'view_file',
+  'view_truncated_output',
   'list_dir',
   'grep',
   'find_files',

apps/server/src/services/truncate.ts

@@ -0,0 +1,170 @@
+import { promises as fs } from 'fs';
+import { randomBytes } from 'crypto';
+import path from 'path';
+import type { Sql } from '../db.js';
+
+// v1.13.5: opencode-style truncation storage. When a tool slice would cut
+// content the model might still want, we store the full text on tmpfs and
+// hand the model an opaque id. view_truncated_output(id) retrieves it.
+//
+// Tmpfs path means full content vanishes on container restart; chats that
+// outlive a restart lose retrieval (acceptable — the user has usually moved
+// on or the data is stale). 7-day TTL + orphan reap bound disk growth via
+// the periodic sweeper in index.ts.
+
+export const TRUNCATION_DIR = process.env.BOOCODE_TRUNCATION_DIR ?? '/tmp/boocode-truncations';
+export const TRUNCATION_TTL_MS = 7 * 24 * 60 * 60 * 1000;
+// Matches view_file's MAX_FILE_BYTES — anything bigger was already refused
+// at the source tool's size check, so we never see it here.
+export const MAX_TRUNCATION_BYTES = 5 * 1024 * 1024;
+
+const ID_RE = /^tr_[0-9a-v]{12}$/;
+
+let dirEnsured = false;
+async function ensureDir(): Promise<void> {
+  if (dirEnsured) return;
+  await fs.mkdir(TRUNCATION_DIR, { recursive: true, mode: 0o700 });
+  dirEnsured = true;
+}
+
+// 12 base32 chars ≈ 60 bits of entropy. Collision probability across a
+// 7-day window with ~thousands of truncations is essentially zero.
+function newId(): string {
+  const buf = randomBytes(8);
+  const alphabet = '0123456789abcdefghijklmnopqrstuv';
+  let out = 'tr_';
+  for (const byte of buf) {
+    out += alphabet[byte & 0x1f];
+    out += alphabet[(byte >> 3) & 0x1f];
+  }
+  return out.slice(0, 15);
+}
+
+function idToPath(id: string): string {
+  // Defense-in-depth: the model never supplies a path component (only ids),
+  // but a malformed id from anywhere else shouldn't escape TRUNCATION_DIR.
+  if (!ID_RE.test(id)) {
+    throw new Error(`Invalid truncation id: ${id}`);
+  }
+  return path.join(TRUNCATION_DIR, id);
+}
+
+export async function storeTruncation(fullContent: string): Promise<string> {
+  const bytes = Buffer.byteLength(fullContent, 'utf8');
+  if (bytes > MAX_TRUNCATION_BYTES) {
+    throw new Error(`Truncation content ${bytes}B exceeds ${MAX_TRUNCATION_BYTES}B cap`);
+  }
+  await ensureDir();
+  const id = newId();
+  await fs.writeFile(idToPath(id), fullContent, { encoding: 'utf8', mode: 0o600 });
+  return id;
+}
+
+export async function readTruncation(id: string): Promise<string | null> {
+  if (!ID_RE.test(id)) return null;
+  try {
+    return await fs.readFile(idToPath(id), { encoding: 'utf8' });
+  } catch (err) {
+    if ((err as NodeJS.ErrnoException).code === 'ENOENT') return null;
+    throw err;
+  }
+}
+
+// Wrap a tool's output. If wasTruncated, stash the full content on tmpfs
+// and return its id alongside the sliced view the tool would have returned.
+// Storage failure (disk full, permission denied) is non-fatal — the sliced
+// view ships without an outputPath, which is exactly what the tool returned
+// before v1.13.5. Same goes for content over MAX_TRUNCATION_BYTES.
+export async function truncateIfNeeded(args: {
+  fullContent: string;
+  slicedContent: string;
+  wasTruncated: boolean;
+}): Promise<{ content: string; truncated: boolean; outputPath?: string }> {
+  if (!args.wasTruncated) {
+    return { content: args.slicedContent, truncated: false };
+  }
+  const bytes = Buffer.byteLength(args.fullContent, 'utf8');
+  if (bytes > MAX_TRUNCATION_BYTES) {
+    return { content: args.slicedContent, truncated: true };
+  }
+  try {
+    const outputPath = await storeTruncation(args.fullContent);
+    return { content: args.slicedContent, truncated: true, outputPath };
+  } catch {
+    return { content: args.slicedContent, truncated: true };
+  }
+}
+
+// Periodic cleanup. Called from index.ts's sweep interval (v1.13.3 cadence).
+// Pass 1: TTL — anything older than TRUNCATION_TTL_MS is gone.
+// Pass 2: orphans — files with no live message_parts.payload->'output'->>'outputPath'
+// reference. Catches the case where a part referencing an outputPath got
+// hidden by prune (v1.13.4) and the file is now unreachable.
+export async function cleanupTruncations(args: {
+  sql: Sql;
+  log: { warn: (obj: object, msg: string) => void; error: (obj: object, msg: string) => void };
+}): Promise<{ ttlReaped: number; orphanReaped: number }> {
+  await ensureDir();
+  const cutoff = Date.now() - TRUNCATION_TTL_MS;
+  let ttlReaped = 0;
+  let orphanReaped = 0;
+
+  let entries: string[];
+  try {
+    entries = await fs.readdir(TRUNCATION_DIR);
+  } catch (err) {
+    args.log.error({ err }, 'cleanupTruncations readdir failed');
+    return { ttlReaped, orphanReaped };
+  }
+  if (entries.length === 0) return { ttlReaped, orphanReaped };
+
+  const survivors: string[] = [];
+  for (const name of entries) {
+    if (!ID_RE.test(name)) continue;
+    const full = path.join(TRUNCATION_DIR, name);
+    try {
+      const stat = await fs.stat(full);
+      if (stat.mtimeMs < cutoff) {
+        await fs.unlink(full);
+        ttlReaped += 1;
+      } else {
+        survivors.push(name);
+      }
+    } catch {
+      // File vanished between readdir and stat — fine.
+    }
+  }
+
+  if (survivors.length === 0) {
+    if (ttlReaped > 0) {
+      args.log.warn({ ttlReaped, orphanReaped: 0 }, 'cleanupTruncations reaped files');
+    }
+    return { ttlReaped, orphanReaped: 0 };
+  }
+
+  // outputPath rides inside the tool_result part's payload.output object
+  // (see partsFromToolMessage in inference/parts.ts), so the json path is
+  // payload->'output'->>'outputPath' rather than top-level.
+  const referenced = await args.sql<{ output_path: string }[]>`
+    SELECT DISTINCT p.payload->'output'->>'outputPath' AS output_path
+    FROM message_parts p
+    WHERE p.kind = 'tool_result'
+      AND p.payload->'output' ? 'outputPath'
+      AND p.payload->'output'->>'outputPath' = ANY(${survivors})
+  `;
+  const live = new Set(referenced.map((r) => r.output_path));
+  for (const name of survivors) {
+    if (live.has(name)) continue;
+    try {
+      await fs.unlink(path.join(TRUNCATION_DIR, name));
+      orphanReaped += 1;
+    } catch {
+      // ignore
+    }
+  }
+
+  if (ttlReaped > 0 || orphanReaped > 0) {
+    args.log.warn({ ttlReaped, orphanReaped }, 'cleanupTruncations reaped files');
+  }
+  return { ttlReaped, orphanReaped };
+}

apps/server/src/services/web_fetch.ts

@@ -11,6 +11,7 @@
 import { z } from 'zod';
 import { isPublicUrl } from './url_guard.js';
 import type { ToolDef } from './tools.js';
+import { truncateIfNeeded } from './truncate.js';
 
 const WebFetchInput = z.object({
   url: z.string().min(1).max(2048),
@@ -230,15 +231,24 @@ export async function executeWebFetch(
   }
 
   const truncated = truncate(textRaw, maxChars);
+  // v1.13.5: stash the full pre-slice body when truncation fires so the
+  // model can pull more via view_truncated_output(id) without re-fetching.
+  // textRaw is already bounded by MAX_BYTES (5MB), within truncate.ts's cap.
+  const wrapped = await truncateIfNeeded({
+    fullContent: textRaw,
+    slicedContent: truncated.content,
+    wasTruncated: truncated.truncated,
+  });
   // Report the FINAL URL (post-redirects) so the LLM knows where the body
   // came from — useful for citations and for the model to reason about
   // domain trust.
   return {
     url: currentUrl,
     title,
-    content: truncated.content,
+    content: wrapped.content,
     content_type: contentType,
-    truncated: truncated.truncated,
+    truncated: wrapped.truncated,
+    ...(wrapped.outputPath ? { outputPath: wrapped.outputPath } : {}),
   };
 }