fix: break infinite summary-retry loop (#1633) (#2072)

* Initial plan

* fix: break infinite summary-retry loop (#1633)

Three-part fix:
1. Parser coercion: When LLM returns <observation> tags instead of <summary>,
   coerce observation content into summary fields (root cause fix)
2. Stronger summary prompt: Add clearer tag requirements with warnings
3. Circuit breaker: Track consecutive summary failures per session,
   skip further attempts after 3 failures to prevent unbounded prompt growth

Agent-Logs-Url: https://github.com/thedotmack/claude-mem/sessions/e345e8ec-bc97-4eaa-94bd-6e951fda8f77

Co-authored-by: thedotmack <683968+thedotmack@users.noreply.github.com>

* refactor: extract shared constants for summary mode marker and failure threshold

Addresses code review feedback: SUMMARY_MODE_MARKER and
MAX_CONSECUTIVE_SUMMARY_FAILURES are now defined once in sdk/prompts.ts
and imported by ResponseProcessor and SessionManager.

Agent-Logs-Url: https://github.com/thedotmack/claude-mem/sessions/e345e8ec-bc97-4eaa-94bd-6e951fda8f77

Co-authored-by: thedotmack <683968+thedotmack@users.noreply.github.com>

* fix: guard summary failure counter on summaryExpected (Greptile P1)

The circuit breaker counter previously incremented on any response
containing <observation> or <summary> tags — which matches virtually
every normal observation response. After 3 observations the breaker
would open and permanently block summarization, reproducing the
data-loss scenario #1633 was meant to prevent.

Gate the increment block on summaryExpected (already computed for
parseSummary coercion) so the counter only tracks actual summary
attempts.

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

* test: cover circuit-breaker + apply review polish

- Use findLast / at(-1) for last-user-message lookup instead of
  filter + index (O(1) common case).
- Drop redundant `|| 0` fallback — field is required and initialized.
- Add comment noting counter is ephemeral by design.
- Add ResponseProcessor tests covering:
  * counter NOT incrementing on normal observation responses
    (regression guard for the Greptile P1)
  * counter incrementing when a summary was expected but missing
  * counter resetting to 0 on successful summary storage

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

* fix: iterate all observation blocks; don't count skip_summary as failure

Addresses CodeRabbit review on #2072:

- coerceObservationToSummary now iterates all <observation> blocks
  with a global regex and returns the first block that has title,
  narrative, or facts. Previously, an empty leading observation
  would short-circuit and discard populated follow-ups.

- Circuit-breaker counter now treats explicit <skip_summary/> as
  neutral — neither a failure nor a success — so a run that happens
  to end on a skip doesn't punish the session or mask a prior bad
  streak. Real failures (no summary, no skip) still increment.

- Tests added for both cases.

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

* test: reference SUMMARY_MODE_MARKER constant instead of hardcoded string

Addresses CodeRabbit nitpick: tests should pull the marker from the
canonical source so they don't silently drift when the constant is
renamed or edited.

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

* fix: also coerce observations when <summary> has empty sub-tags

When the LLM wraps an empty <summary></summary> around real observation
content, the #1360 empty-subtag guard rejects the summary and returns
null — which would lose the observation content and resurrect the
#1633 retry loop. Fall back to coerceObservationToSummary in that
branch too, mirroring the unmatched-<summary> path.

Adds a test covering the empty-summary-wraps-observation case and
a guard test for empty summary with no observation content.

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

---------

Co-authored-by: copilot-swe-agent[bot] <198982749+Copilot@users.noreply.github.com>
Co-authored-by: thedotmack <683968+thedotmack@users.noreply.github.com>
Co-authored-by: Alex Newman <thedotmack@gmail.com>
Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
This commit is contained in:
Copilot
2026-04-19 12:00:38 -07:00
committed by GitHub
parent beea7899b9
commit 8ec91e7ffa
7 changed files with 351 additions and 11 deletions
+15 -1
View File
@@ -16,6 +16,7 @@ import { PendingMessageStore } from '../sqlite/PendingMessageStore.js';
import { SessionQueueProcessor } from '../queue/SessionQueueProcessor.js';
import { getProcessBySession, ensureProcessExit } from './ProcessRegistry.js';
import { getSupervisor } from '../../supervisor/index.js';
import { MAX_CONSECUTIVE_SUMMARY_FAILURES } from '../../sdk/prompts.js';
/** Idle threshold before a stuck generator (zombie subprocess) is force-killed. */
export const MAX_GENERATOR_IDLE_MS = 5 * 60 * 1000; // 5 minutes
@@ -219,7 +220,8 @@ export class SessionManager {
currentProvider: null, // Will be set when generator starts
consecutiveRestarts: 0, // Track consecutive restart attempts to prevent infinite loops
processingMessageIds: [], // CLAIM-CONFIRM: Track message IDs for confirmProcessed()
lastGeneratorActivity: Date.now() // Initialize for stale detection (Issue #1099)
lastGeneratorActivity: Date.now(), // Initialize for stale detection (Issue #1099)
consecutiveSummaryFailures: 0 // Circuit breaker for summary retry loop (#1633)
};
logger.debug('SESSION', 'Creating new session object (memorySessionId cleared to prevent stale resume)', {
@@ -312,6 +314,18 @@ export class SessionManager {
session = this.initializeSession(sessionDbId);
}
// Circuit breaker: skip summarize if too many consecutive failures (#1633).
// This prevents the infinite loop where each failed summary spawns a new session
// with an ever-growing prompt. Counter is in-memory per ActiveSession — it resets
// on worker restart, which is acceptable because session state is already ephemeral.
if (session.consecutiveSummaryFailures >= MAX_CONSECUTIVE_SUMMARY_FAILURES) {
logger.warn('SESSION', `Circuit breaker OPEN: skipping summarize after ${session.consecutiveSummaryFailures} consecutive failures (#1633)`, {
sessionId: sessionDbId,
contentSessionId: session.contentSessionId
});
return;
}
// CRITICAL: Persist to database FIRST
const message: PendingMessage = {
type: 'summarize',