feat(agent-loop): expose compactionsDone + compactedReminder producer

Closes the loop on M2: when the compactor fires, the LLM needs to know
it's now seeing a <compact-summary> instead of raw turns so it
doesn't waste a turn asking about lost details or re-executing tools
whose responses are gone.

shared-ai:
  - LoopState grows `compactionsDone: number` (cap-1 by current loop
    policy, but shape kept as count for future multi-compact cycles).
  - runPlannerLoop populates it on each reminder-channel call. New
    loop test asserts [0, 1] sequence: round 1 before compaction,
    round 2 after.

mana-ai:
  - New producer `compactedReminder` — fires severity=info when
    compactionsDone >= 1, wrapped in a German one-liner ("frag nicht
    nach verlorenen Details").
  - Injected FIRST in buildReminderChannel so the LLM frames the rest
    of the round with "I'm looking at a summary" context. Metric
    surface stays `{producer='compacted', severity='info'}`.

4 new reminder tests (3 pure producer + 1 composition-ordering) +
1 loop-wiring test. 77 shared-ai, 20 reminders.test.ts — green.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
This commit is contained in:
Till JS 2026-04-23 15:36:21 +02:00
parent be8f5618c6
commit 72f7978ed4
4 changed files with 122 additions and 0 deletions

View file

@ -480,6 +480,50 @@ describe('runPlannerLoop — compactor', () => {
expect(compactSpy).not.toHaveBeenCalled();
});
it('surfaces compactionsDone in LoopState for reminder producers', async () => {
const llm = new MockLlmClient();
// Round 1: over threshold
(llm as unknown as { queue: unknown[] }).queue.push({
content: null,
toolCalls: [{ id: 'c1', name: 'list_things', arguments: {} }],
finishReason: 'tool_calls',
usage: { promptTokens: 950, completionTokens: 0, totalTokens: 950 },
});
// Round 2: stop so we end cleanly
llm.enqueueStop('done');
const compactionsDoneSeen: number[] = [];
await runPlannerLoop({
llm,
input: {
systemPrompt: 's',
userPrompt: 'u',
tools,
model: 'm',
compactor: {
maxContextTokens: 1000,
compact: async () => ({
messages: [
{ role: 'system', content: 's' },
{ role: 'user', content: 'u' },
{ role: 'assistant', content: '<compact>' },
],
compactedTurns: 2,
}),
},
reminderChannel: (state) => {
compactionsDoneSeen.push(state.compactionsDone);
return [];
},
},
onToolCall: async () => ({ success: true, message: 'ok' }),
});
// Round 1 channel call: before compaction fires, so 0
// Round 2 channel call: after compaction, so 1
expect(compactionsDoneSeen).toEqual([0, 1]);
});
it('skips when the compactor returns 0 compacted turns', async () => {
const llm = new MockLlmClient();
(llm as unknown as { queue: unknown[] }).queue.push({

View file

@ -100,6 +100,15 @@ export interface LoopState {
* tool), and similar. Empty in round 1; grows up to the cap.
*/
readonly recentCalls: readonly ExecutedCall[];
/**
* Number of times the compactor has folded the message history in
* this loop run. Capped at 1 by the loop itself (fire-once policy),
* but still exposed as a count rather than a boolean so future
* policies (e.g. multi-compact cycles) don't need a breaking API
* change. A producer can use this to inject a "just compacted"
* reminder on the round immediately after compaction.
*/
readonly compactionsDone: number;
}
/**
@ -276,6 +285,7 @@ export async function runPlannerLoop(opts: {
},
lastCall: executedCalls[executedCalls.length - 1],
recentCalls,
compactionsDone,
};
const reminders = input.reminderChannel(state);
if (reminders.length > 0) {

View file

@ -1,6 +1,7 @@
import { describe, expect, it } from 'bun:test';
import {
buildReminderChannel,
compactedReminder,
retryLoopReminder,
tokenBudgetReminder,
type ReminderContext,
@ -50,6 +51,7 @@ function makeState(overrides: Partial<LoopState> = {}): LoopState {
toolCallCount: 0,
usage: { promptTokens: 0, completionTokens: 0, totalTokens: 0 },
recentCalls: [],
compactionsDone: 0,
...overrides,
};
}
@ -188,6 +190,27 @@ describe('retryLoopReminder', () => {
});
});
// ─── compactedReminder ────────────────────────────────────────────
describe('compactedReminder', () => {
it('is silent when no compaction has happened', () => {
expect(compactedReminder({ compactionsDone: 0 })).toBeNull();
});
it('fires once compactionsDone >= 1 with severity=info', () => {
const r = compactedReminder({ compactionsDone: 1 });
expect(r).not.toBeNull();
expect(r!.severity).toBe('info');
expect(r!.producer).toBe('compacted');
expect(r!.text).toContain('compact-summary');
expect(r!.text).toContain('frag nicht');
});
it('fires for counts greater than 1 too (future multi-compact)', () => {
expect(compactedReminder({ compactionsDone: 3 })).not.toBeNull();
});
});
// ─── buildReminderChannel — composition ───────────────────────────
describe('buildReminderChannel', () => {
@ -229,6 +252,24 @@ describe('buildReminderChannel', () => {
expect(out[0]).toContain('fehlgeschlagen');
});
it('puts compacted reminder FIRST when it fires alongside budget warning', () => {
const channel = buildReminderChannel({
agent: makeAgent({ maxTokensPerDay: 10_000 }),
mission: makeMission(),
pretickUsage24h: 9_000, // triggers budget warn
});
const out = channel(
makeState({
round: 2,
compactionsDone: 1,
usage: { promptTokens: 500, completionTokens: 500, totalTokens: 1_000 },
})
);
expect(out).toHaveLength(2);
expect(out[0]).toContain('compact-summary'); // compacted first
expect(out[1]).toContain('Tagesbudget'); // budget second
});
it('can fire budget + retry together (composition)', () => {
const channel = buildReminderChannel({
agent: makeAgent({ maxTokensPerDay: 10_000 }),

View file

@ -101,6 +101,25 @@ export function tokenBudgetReminder(ctx: ReminderContext, roundUsage: number): R
* because a run that mixes failures and successes is not a true retry
* loop, it's just flaky tools.
*/
/**
* Fires the round immediately after the compactor folded older turns.
* Tells the LLM that it is now looking at a summary, not the raw log,
* so it doesn't burn a turn asking about "that error from earlier" or
* trying to re-execute a tool whose detailed result is gone.
*/
export function compactedReminder(state: { readonly compactionsDone: number }): Reminder | null {
if (state.compactionsDone < 1) return null;
return {
producer: 'compacted',
severity: 'info',
text:
`Ältere Turns wurden in ein <compact-summary> gefaltet, um den ` +
`Context-Window nicht zu sprengen. Die Summary (Goal / Decisions / ` +
`Tools Called / Current Progress) ist die autoritative Kurz-Historie ` +
`— frag nicht nach verlorenen Details, arbeite ab da weiter.`,
};
}
export function retryLoopReminder(state: {
readonly round: number;
readonly recentCalls: readonly { readonly result: { readonly success: boolean } }[];
@ -132,8 +151,16 @@ export function retryLoopReminder(state: {
export function buildReminderChannel(ctx: ReminderContext): ReminderChannel {
return (state) => {
const reminders: Reminder[] = [];
// Order matters — the compacted-info block goes first so the LLM
// frames the rest of the reminders (and the upcoming turn) with
// the knowledge that it's looking at a summary.
const compacted = compactedReminder({ compactionsDone: state.compactionsDone });
if (compacted) reminders.push(compacted);
const budget = tokenBudgetReminder(ctx, state.usage.totalTokens);
if (budget) reminders.push(budget);
const retry = retryLoopReminder({ round: state.round, recentCalls: state.recentCalls });
if (retry) reminders.push(retry);