fix(hooks): differentiate burst and edit-ratio heuristics on tool type

The burst counter incremented on any tool call <30s apart regardless of
tool type, so a bulk read of many files produced the same "Rapid-fire"
alert as a rapid-fire editing sequence. The edit-ratio check reported
"possible stuck/spiral" for any session under 10% edits past 30 minutes,
which a read-heavy analysis session satisfies structurally whether or not
the work is productive. Both mechanisms are confirmed in
docs/BRIEF-vurdering-v2.md, verification points 1a and 1b.

tool-tracker.mjs now tracks whether the current burst run consists only
of read tools and suppresses the rapid-fire alert for such runs. A
read-dominant session (>=70% reads) reports its low edit ratio as
context rather than as a stuck/spiral claim, and never as the sole
reason for a warning. Bursts involving Edit/Write/Bash and
non-read-dominant sessions behave exactly as before.

No new data is recorded: the differentiation uses tool_name, which
events.jsonl already logs. The privacy design is untouched.

Tests first (Iron Law): 5 cases in tests/tool-tracker.test.mjs, 3 of
which failed against the previous implementation, 2 of which are
regression guards that passed before and still pass.

Verified: node --test tests/*.test.mjs -> 263 pass, 5 fail. All 5
failures are the perf wall-clock assertions, which fail identically on
HEAD without this change (measured by stashing and re-running) — they
are a pre-existing property of this machine, not a regression.

Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_011wMhJuPFUiWqKLSQjrzCXP
This commit is contained in:
Kjell Tore Guttormsen 2026-08-13 20:59:42 +02:00
commit 2c9e2de00a
5 changed files with 141 additions and 13 deletions

View file

@ -2,6 +2,24 @@
All notable changes to this project will be documented in this file.
## [Unreleased]
### Fixed
- **The burst and edit-ratio heuristics could not tell reading from editing**
(`docs/BRIEF-vurdering-v2.md` tiltak 1, verification points 1a/1b). A bulk
read of many files produced the same "Rapid-fire: N consecutive fast
interactions" alert as a rapid-fire editing sequence, and a read-heavy
analysis session was reported as "possible stuck/spiral" purely because its
edit ratio is structurally low. `tool-tracker.mjs` now tracks whether a
burst run consists only of read tools (`Read`/`Grep`/`Glob`/`NotebookRead`)
and suppresses the rapid-fire alert for such runs; a read-dominant session
(≥70% reads) reports its low edit ratio as context rather than as a
stuck/spiral claim, and never as the sole reason for a warning. Bursts
involving `Edit`/`Write`/`Bash` and non-read-dominant sessions are
unchanged. No new data is recorded — the differentiation uses `tool_name`,
which `events.jsonl` already logs.
## [1.2.2] — 2026-08-02
### Fixed

View file

@ -65,7 +65,7 @@ layer4: false # default off
## Testing
Automated test suite using `node:test` (258 cases, zero npm dependencies):
Automated test suite using `node:test` (263 cases, zero npm dependencies):
```bash
node --test tests/*.test.mjs
@ -75,7 +75,7 @@ node --test tests/*.test.mjs
|------|-------|----------|
| `tests/session-start.test.mjs` | 11 | State init, JSONL, tier-2 cross-session alert |
| `tests/prompt-analyzer.test.mjs` | 100 | All v1.x patterns × 2 + thresholds + valence + v1.2 pushback contract |
| `tests/tool-tracker.test.mjs` | 8 | Counting, burst, reminders |
| `tests/tool-tracker.test.mjs` | 13 | Counting, burst, reminders + read-tool calibration |
| `tests/session-end.test.mjs` | 7 | Finalize, duration, flags, v1.1.0 string + v1.2 array shapes |
| `tests/privacy.test.mjs` | 7 | Canary + matched-phrase × original + 5 v1.2 detector variants |
| `tests/skill-md.test.mjs` | 3 | Constitution citation + Score 5 + 11 guidance criteria |

View file

@ -133,6 +133,16 @@ export const THRESHOLD_SOFT_DEP_FLAGS = 2;
export const THRESHOLD_HARD_DEP_FLAGS = 5;
export const COOLDOWN_SOFT = 1800;
export const COOLDOWN_HARD = 3600;
// Read-only tools. A sequence of these is bulk reading (research, audit,
// bulk file review), not rapid-fire editing — the burst and edit-ratio
// heuristics must not treat the two as the same signal.
export const READ_TOOLS = Object.freeze(['Read', 'Grep', 'Glob', 'NotebookRead']);
export function isReadTool(tool) {
return READ_TOOLS.includes(tool);
}
// Share of read tools above which a session counts as read-dominant.
export const THRESHOLD_READ_DOMINANT_RATIO = 70;
// v1.1.0 — counting threshold; tier-reduction logic is v1.2 scope
export const THRESHOLD_PUSHBACK_FLAGS = 2;

View file

@ -10,6 +10,7 @@ import {
THRESHOLD_SOFT_SESSIONS, THRESHOLD_HARD_SESSIONS,
THRESHOLD_SOFT_BURST, THRESHOLD_HARD_BURST, THRESHOLD_BURST_INTERVAL,
THRESHOLD_LOW_EDIT_RATIO, THRESHOLD_LOW_EDIT_MIN_DURATION,
THRESHOLD_READ_DOMINANT_RATIO, isReadTool,
COOLDOWN_SOFT, COOLDOWN_HARD,
readState, sessionStateFile, writeState, appendJsonl, sessionsToday,
outputContinue, outputWithContext
@ -38,24 +39,37 @@ appendJsonl(EVENTS_LOG, { ts: nowIsoStr, session_id: sid, tool_name: tool });
let state = readState();
let toolCount = (Number(state.tool_count) || 0) + 1;
let editCount = Number(state.edit_count) || 0;
let readCount = Number(state.read_count) || 0;
const lastEvent = Number(state.last_event_epoch) || 0;
let burstCount = Number(state.burst_count) || 0;
// Absent in pre-calibration state files — an unseen run starts read-only.
let burstReadOnly = state.burst_read_only !== false;
const startEpoch = Number(state.start_epoch) || 0;
const lastWarning = Number(state.last_warning_epoch) || 0;
const toolIsRead = isReadTool(tool);
if (tool === 'Edit') editCount++;
if (toolIsRead) readCount++;
// Burst detection: rapid-fire if <30s since last event
if (lastEvent > 0) {
const interval = nowTs - lastEvent;
burstCount = interval < THRESHOLD_BURST_INTERVAL ? burstCount + 1 : 0;
if (interval < THRESHOLD_BURST_INTERVAL) {
burstCount++;
burstReadOnly = burstReadOnly && toolIsRead;
} else {
burstCount = 0;
burstReadOnly = toolIsRead;
}
}
// Write updated state
state.tool_count = toolCount;
state.edit_count = editCount;
state.read_count = readCount;
state.last_event_epoch = nowTs;
state.burst_count = burstCount;
state.burst_read_only = burstReadOnly;
writeState(state);
// Check thresholds every 25 calls or when burst threshold hit
@ -106,19 +120,33 @@ if (dayCount >= THRESHOLD_HARD_SESSIONS) {
messages.push(`${dayCount} sessions today.`);
}
// Burst
if (burstCount >= THRESHOLD_HARD_BURST) {
level = 'hard';
messages.push(`Rapid-fire: ${burstCount} consecutive fast interactions.`);
} else if (burstCount >= THRESHOLD_SOFT_BURST) {
if (!level) level = 'soft';
messages.push(`Rapid-fire: ${burstCount} consecutive fast interactions.`);
// Burst — a run of read-only tools is bulk reading, not rapid-fire work
if (!burstReadOnly) {
if (burstCount >= THRESHOLD_HARD_BURST) {
level = 'hard';
messages.push(`Rapid-fire: ${burstCount} consecutive fast interactions.`);
} else if (burstCount >= THRESHOLD_SOFT_BURST) {
if (!level) level = 'soft';
messages.push(`Rapid-fire: ${burstCount} consecutive fast interactions.`);
}
}
// Low edit ratio (only after minimum duration)
// Low edit ratio (only after minimum duration). A read-dominant session has
// a structurally low edit ratio whether or not the work is productive, so it
// is reported as context — never as a stuck/spiral claim, and never as the
// sole reason for a warning.
const readRatio = toolCount > 0 ? Math.floor(readCount * 100 / toolCount) : 0;
const readDominant = readRatio >= THRESHOLD_READ_DOMINANT_RATIO;
if (durationMin >= THRESHOLD_LOW_EDIT_MIN_DURATION && editRatio < THRESHOLD_LOW_EDIT_RATIO) {
if (!level) level = 'soft';
messages.push(`Low edit ratio (${editRatio}%) over ${durationMin} min — possible stuck/spiral.`);
if (readDominant) {
if (level) {
messages.push(`Low edit ratio (${editRatio}%) over ${durationMin} min, but ${readRatio}% of tool calls are reads — read-intensive work (research/audit) rather than a stall.`);
}
} else {
if (!level) level = 'soft';
messages.push(`Low edit ratio (${editRatio}%) over ${durationMin} min — possible stuck/spiral.`);
}
}
// Late night check

View file

@ -93,3 +93,75 @@ describe('tool-tracker', () => {
assert.equal(out.continue, true);
});
});
// Tiltak 1 (BRIEF-vurdering-v2.md): burst and edit-ratio heuristics must
// differentiate on tool type. A bulk-read sequence is structurally
// indistinguishable from a rapid-fire editing sequence today.
describe('tool-tracker — task-type calibration', () => {
it('does not raise a rapid-fire alert for a pure read burst', () => {
dir = setupTestDir();
// burst_count 9 + this call = THRESHOLD_HARD_BURST (10), all reads
createStateFile(dir, 'b1', freshState({
last_event_epoch: Math.floor(Date.now() / 1000) - 5,
burst_count: 9,
tool_count: 30,
read_count: 30,
}));
const out = runHook('tool-tracker.mjs', { session_id: 'b1', tool_name: 'Read' }, dir);
const ctx = out.hookSpecificOutput?.additionalContext || '';
assert.ok(!ctx.includes('Rapid-fire'), `expected no rapid-fire alert, got: ${ctx}`);
assert.equal(out.continue, true);
});
it('still raises a rapid-fire alert when the burst includes an edit', () => {
dir = setupTestDir();
createStateFile(dir, 'b2', freshState({
last_event_epoch: Math.floor(Date.now() / 1000) - 5,
burst_count: 9,
tool_count: 30,
read_count: 29,
}));
const out = runHook('tool-tracker.mjs', { session_id: 'b2', tool_name: 'Edit' }, dir);
const ctx = out.hookSpecificOutput?.additionalContext || '';
assert.ok(ctx.includes('Rapid-fire'), `expected rapid-fire alert, got: ${ctx}`);
});
it('does not call a read-dominant session stuck/spiral', () => {
dir = setupTestDir();
// 40 min, 50 tool calls, no edits, all reads — a research/audit session
createStateFile(dir, 'e1', freshState({
start_epoch: Math.floor(Date.now() / 1000) - 40 * 60,
tool_count: 49,
edit_count: 0,
read_count: 49,
}));
const out = runHook('tool-tracker.mjs', { session_id: 'e1', tool_name: 'Read' }, dir);
const ctx = out.hookSpecificOutput?.additionalContext || '';
assert.ok(!ctx.includes('stuck/spiral'), `expected no stuck/spiral claim, got: ${ctx}`);
});
it('still reports low edit ratio when the session is not read-dominant', () => {
dir = setupTestDir();
// Same duration and volume, but reads are a minority (5/50)
createStateFile(dir, 'e2', freshState({
start_epoch: Math.floor(Date.now() / 1000) - 40 * 60,
tool_count: 49,
edit_count: 2,
read_count: 5,
}));
const out = runHook('tool-tracker.mjs', { session_id: 'e2', tool_name: 'Bash' }, dir);
const ctx = out.hookSpecificOutput?.additionalContext || '';
assert.ok(ctx.includes('stuck/spiral'), `expected stuck/spiral claim, got: ${ctx}`);
});
it('counts read tools in read_count and leaves it alone for others', () => {
dir = setupTestDir();
createStateFile(dir, 'r1', freshState());
runHook('tool-tracker.mjs', { session_id: 'r1', tool_name: 'Grep' }, dir);
assert.equal(readState(dir, 'r1').read_count, 1);
runHook('tool-tracker.mjs', { session_id: 'r1', tool_name: 'Glob' }, dir);
assert.equal(readState(dir, 'r1').read_count, 2);
runHook('tool-tracker.mjs', { session_id: 'r1', tool_name: 'Write' }, dir);
assert.equal(readState(dir, 'r1').read_count, 2);
});
});