root/fusion
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

fix(engine): prevent auto-merge cooldown loop on unresolvable conflicts

Browse Source 
Tasks were getting stuck in `in-review` forever when auto-merge could not
resolve conflicts within MAX_AUTO_MERGE_RETRIES. The conflict-exhaustion
branch silently cleared `status` (no error, no log entry, no comment),
and the 30-min cooldown sweep would reset retries and re-attempt the
same impossible merge — looping silently with no user-facing surface.

Why:
- FN-2918 and FN-2903 both spent hours in this loop with no error/comment
  visible on the task. The only log evidence was repeated
  "Auto-merge retry cooldown elapsed (30m idle)" entries with no
  follow-up outcome.

How to apply:
- Every merge failure now writes a `<Manual|Auto>-merge failed: <msg>`
  entry to the task log so the dashboard surfaces the reason.
- Conflict-retry exhaustion now bounces the task back to `in-progress`
  with a comment + log entry so the executor re-rebases against main
  and retries — mirroring the verification-failure-bounce pattern.
- New `mergeConflictBounceCount` task field caps outer bounces
  (`MAX_MERGE_CONFLICT_BOUNCES = 2`); past the cap, the task is parked
  in `in-review` with `status="failed"` and a follow-up triage task is
  created so a human can resolve the conflict manually.
- Non-conflict and non-direct-strategy errors now also set
  `status="failed"` so the cooldown sweep can't re-pick them up.
- `canMergeTask` skips tasks with `status="failed"` so terminal
  failures (verification cap, bounce cap, non-conflict error) are no
  longer eligible for cooldown re-attempts.

Schema migration v52 adds the `mergeConflictBounceCount` column.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
This commit is contained in:
gsxdsm
2026-04-28 23:17:10 -07:00
parent d155b8964a
commit 15e4cba5e9
11 changed files with 242 additions and 45 deletions
Download Patch File Download Diff File Expand all files Collapse all files

26
packages/core/src/__tests__/db.test.ts
View File

@@ -131,7 +131,7 @@ describe("Database", () => {
});
it("seeds schema version", () => {
expect(db.getSchemaVersion()).toBe(51);
expect(db.getSchemaVersion()).toBe(52);
});
it("seeds lastModified", () => {
@@ -154,7 +154,7 @@ describe("Database", () => {
it("is idempotent - calling init() twice does not fail", () => {
expect(() => db.init()).not.toThrow();
expect(db.getSchemaVersion()).toBe(51);
expect(db.getSchemaVersion()).toBe(52);
});
it("does not overwrite existing config on re-init", () => {
@@ -761,7 +761,7 @@ describe("schema migrations", () => {
db.init();
// Verify version bumped to 29 (includes v1→v2 through v26→v29)
expect(db.getSchemaVersion()).toBe(51);
expect(db.getSchemaVersion()).toBe(52);
// Verify new columns exist and existing data is intact
const cols = db.prepare("PRAGMA table_info(tasks)").all() as Array<{ name: string }>;
@@ -786,11 +786,11 @@ describe("schema migrations", () => {
const db = new Database(fusionDir);
db.init();
expect(db.getSchemaVersion()).toBe(51);
expect(db.getSchemaVersion()).toBe(52);
// Re-init should not fail
db.init();
expect(db.getSchemaVersion()).toBe(51);
expect(db.getSchemaVersion()).toBe(52);
db.close();
});
@@ -825,7 +825,7 @@ describe("schema migrations", () => {
db.init();
expect(db.getSchemaVersion()).toBe(51);
expect(db.getSchemaVersion()).toBe(52);
const cols = db.prepare("PRAGMA table_info(tasks)").all() as Array<{ name: string }>;
expect(cols.map((col) => col.name)).toContain("priority");
@@ -866,7 +866,7 @@ describe("schema migrations", () => {
db.init();
expect(db.getSchemaVersion()).toBe(51);
expect(db.getSchemaVersion()).toBe(52);
const cols = db.prepare("PRAGMA table_info(tasks)").all() as Array<{ name: string }>;
const colNames = cols.map((col) => col.name);
@@ -935,7 +935,7 @@ describe("schema migrations", () => {
db.init();
expect(db.getSchemaVersion()).toBe(51);
expect(db.getSchemaVersion()).toBe(52);
const cols = db.prepare("PRAGMA table_info(tasks)").all() as Array<{ name: string }>;
const colNames = cols.map((col) => col.name);
@@ -994,7 +994,7 @@ describe("schema migrations", () => {
db.init();
expect(db.getSchemaVersion()).toBe(51);
expect(db.getSchemaVersion()).toBe(52);
const cols = db.prepare("PRAGMA table_info(chat_messages)").all() as Array<{ name: string }>;
expect(cols.map((col) => col.name)).toContain("attachments");
@@ -1016,7 +1016,7 @@ describe("schema migrations", () => {
db.init();
expect(db.getSchemaVersion()).toBe(51);
expect(db.getSchemaVersion()).toBe(52);
const tables = db.prepare("SELECT name FROM sqlite_master WHERE type='table' AND name = 'agentRatings'").all() as Array<{ name: string }>;
expect(tables).toEqual([{ name: "agentRatings" }]);
@@ -1040,7 +1040,7 @@ describe("schema migrations", () => {
db.init();
expect(db.getSchemaVersion()).toBe(51);
expect(db.getSchemaVersion()).toBe(52);
const tables = db.prepare("SELECT name FROM sqlite_master WHERE type='table' AND name = 'mission_events'").all() as Array<{ name: string }>;
expect(tables).toEqual([{ name: "mission_events" }]);
@@ -1144,7 +1144,7 @@ describe("schema migrations", () => {
db.init();
// Verify version bumped to 29
expect(db.getSchemaVersion()).toBe(51);
expect(db.getSchemaVersion()).toBe(52);
// Verify new columns exist and existing data is intact
const cols = db.prepare("PRAGMA table_info(tasks)").all() as Array<{ name: string }>;
@@ -1595,7 +1595,7 @@ describe("createDatabase factory", () => {
const db = createDatabase(fusionDir);
db.init();
expect(db.getSchemaVersion()).toBe(51);
expect(db.getSchemaVersion()).toBe(52);
expect(db.getLastModified()).toBeGreaterThan(0);
db.close();

8
packages/core/src/__tests__/insight-store.test.ts
View File

@@ -779,7 +779,7 @@ describe("Migration: pre-33 DB upgrade", () => {
// Step 1: Create a fresh database at v33 (runs all migrations up to 33)
const db1 = createDatabase(legacyDir);
db1.init();
expect(db1.getSchemaVersion()).toBe(51);
expect(db1.getSchemaVersion()).toBe(52);
db1.close();
// Step 2: Manually downgrade to version 32 and drop insight tables
@@ -814,7 +814,7 @@ describe("Migration: pre-33 DB upgrade", () => {
expect(tableNamesBefore).not.toContain("project_insight_runs");
// Now run init — this triggers the v32→v33 migration
db3.init();
expect(db3.getSchemaVersion()).toBe(51);
expect(db3.getSchemaVersion()).toBe(52);
// Step 4: Verify insight tables exist after migration
const tablesAfter = db3.prepare(
@@ -845,12 +845,12 @@ describe("Migration: pre-33 DB upgrade", () => {
try {
const db1 = createDatabase(testDir);
db1.init();
expect(db1.getSchemaVersion()).toBe(51);
expect(db1.getSchemaVersion()).toBe(52);
db1.close();
const db2 = createDatabase(testDir);
expect(() => db2.init()).not.toThrow();
expect(db2.getSchemaVersion()).toBe(51);
expect(db2.getSchemaVersion()).toBe(52);
db2.close();
} finally {
rmSync(testDir, { recursive: true, force: true });

2
packages/core/src/__tests__/mission-store.test.ts
View File

@@ -2629,7 +2629,7 @@ describe("MissionStore", () => {
describe("Loop State & Validator Run Schema (v31)", () => {
it("schema version is 40 after migration", () => {
expect(db.getSchemaVersion()).toBe(51);
expect(db.getSchemaVersion()).toBe(52);
});
it("mission_features table has loop state columns", () => {

2
packages/core/src/__tests__/roadmap-store.test.ts
View File

@@ -742,7 +742,7 @@ describe("RoadmapStore", () => {
describe("schema version", () => {
it("schema version is 40 after init", () => {
expect(db.getSchemaVersion()).toBe(51);
expect(db.getSchemaVersion()).toBe(52);
});
});

2
packages/core/src/__tests__/run-audit.test.ts
View File

@@ -465,7 +465,7 @@ describe("Run Audit", () => {
});
it("schema version is bumped to 40", () => {
expect(db.getSchemaVersion()).toBe(51);
expect(db.getSchemaVersion()).toBe(52);
});
});
});

2
packages/core/src/__tests__/task-documents.test.ts
View File

@@ -51,7 +51,7 @@ describe("TaskStore task documents", () => {
expect(tableNames.has("task_documents")).toBe(true);
expect(tableNames.has("task_document_revisions")).toBe(true);
expect(db.getSchemaVersion()).toBe(51);
expect(db.getSchemaVersion()).toBe(52);
const index = db
.prepare(

12
packages/core/src/db.ts
View File

@@ -86,7 +86,7 @@ export function probeFts5(db: DatabaseSync): boolean {
// ── Schema Definition ────────────────────────────────────────────────
const SCHEMA_VERSION = 51;
const SCHEMA_VERSION = 52;
function normalizeTaskComments(
steeringComments: SteeringComment[] | undefined,
@@ -1949,6 +1949,16 @@ export class Database {
});
}
// Outer auto-merge bounce counter so the cooldown sweep can't loop forever
// on a task whose conflicts can't be auto-resolved. Capped by
// MAX_MERGE_CONFLICT_BOUNCES in project-engine.ts; once reached, the task
// is parked in in-review with status="failed" and a follow-up is created.
if (version < 52) {
this.applyMigration(52, () => {
this.addColumnIfMissing("tasks", "mergeConflictBounceCount", "INTEGER DEFAULT 0");
});
}
}
/**

19
packages/core/src/store.ts
View File

@@ -54,6 +54,7 @@ interface TaskRow {
recoveryRetryCount: number | null;
taskDoneRetryCount: number | null;
verificationFailureCount: number | null;
mergeConflictBounceCount: number | null;
nextRecoveryAt: string | null;
error: string | null;
summary: string | null;
@@ -537,6 +538,7 @@ export class TaskStore extends EventEmitter<TaskStoreEvents> {
recoveryRetryCount: row.recoveryRetryCount ?? undefined,
taskDoneRetryCount: row.taskDoneRetryCount ?? undefined,
verificationFailureCount: row.verificationFailureCount ?? undefined,
mergeConflictBounceCount: row.mergeConflictBounceCount ?? undefined,
nextRecoveryAt: row.nextRecoveryAt || undefined,
error: row.error || undefined,
summary: row.summary || undefined,
@@ -834,7 +836,7 @@ export class TaskStore extends EventEmitter<TaskStoreEvents> {
"modelPresetId", "modelProvider", "modelId",
"validatorModelProvider", "validatorModelId",
"planningModelProvider", "planningModelId",
"mergeRetries", "workflowStepRetries", "stuckKillCount", "postReviewFixCount", "recoveryRetryCount", "taskDoneRetryCount", "verificationFailureCount", "nextRecoveryAt",
"mergeRetries", "workflowStepRetries", "stuckKillCount", "postReviewFixCount", "recoveryRetryCount", "taskDoneRetryCount", "verificationFailureCount", "mergeConflictBounceCount", "nextRecoveryAt",
"error", "summary", "thinkingLevel", "executionMode",
"tokenUsageInputTokens", "tokenUsageOutputTokens", "tokenUsageCachedTokens", "tokenUsageTotalTokens", "tokenUsageFirstUsedAt", "tokenUsageLastUsedAt",
"createdAt", "updatedAt", "columnMovedAt",
@@ -882,7 +884,7 @@ export class TaskStore extends EventEmitter<TaskStoreEvents> {
"modelPresetId", "modelProvider", "modelId",
"validatorModelProvider", "validatorModelId",
"planningModelProvider", "planningModelId",
"mergeRetries", "workflowStepRetries", "stuckKillCount", "postReviewFixCount", "recoveryRetryCount", "taskDoneRetryCount", "verificationFailureCount", "nextRecoveryAt",
"mergeRetries", "workflowStepRetries", "stuckKillCount", "postReviewFixCount", "recoveryRetryCount", "taskDoneRetryCount", "verificationFailureCount", "mergeConflictBounceCount", "nextRecoveryAt",
"error", "summary", "thinkingLevel", "executionMode",
"tokenUsageInputTokens", "tokenUsageOutputTokens", "tokenUsageCachedTokens", "tokenUsageTotalTokens", "tokenUsageFirstUsedAt", "tokenUsageLastUsedAt",
"createdAt", "updatedAt", "columnMovedAt",
@@ -924,7 +926,7 @@ export class TaskStore extends EventEmitter<TaskStoreEvents> {
id, title, description, priority, "column", status, size, reviewLevel, currentStep,
worktree, blockedBy, paused, baseBranch, branch, baseCommitSha, modelPresetId, modelProvider,
modelId, validatorModelProvider, validatorModelId, planningModelProvider, planningModelId, mergeRetries,
workflowStepRetries, stuckKillCount, postReviewFixCount, recoveryRetryCount, taskDoneRetryCount, verificationFailureCount, nextRecoveryAt, error,
workflowStepRetries, stuckKillCount, postReviewFixCount, recoveryRetryCount, taskDoneRetryCount, verificationFailureCount, mergeConflictBounceCount, nextRecoveryAt, error,
summary, thinkingLevel, executionMode, tokenUsageInputTokens, tokenUsageOutputTokens, tokenUsageCachedTokens,
tokenUsageTotalTokens, tokenUsageFirstUsedAt, tokenUsageLastUsedAt, createdAt, updatedAt, columnMovedAt,
dependencies, steps, log, attachments, steeringComments,
@@ -932,7 +934,7 @@ export class TaskStore extends EventEmitter<TaskStoreEvents> {
sourceIssueProvider, sourceIssueRepository, sourceIssueExternalIssueId, sourceIssueNumber, sourceIssueUrl,
mergeDetails, breakIntoSubtasks, enabledWorkflowSteps, modifiedFiles, missionId, sliceId, assignedAgentId, assigneeUserId, nodeId, effectiveNodeId, effectiveNodeSource, checkedOutBy, checkedOutAt
) VALUES (
?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?
?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?
)
ON CONFLICT(id) DO UPDATE SET
title = excluded.title,
@@ -963,6 +965,7 @@ export class TaskStore extends EventEmitter<TaskStoreEvents> {
recoveryRetryCount = excluded.recoveryRetryCount,
taskDoneRetryCount = excluded.taskDoneRetryCount,
verificationFailureCount = excluded.verificationFailureCount,
mergeConflictBounceCount = excluded.mergeConflictBounceCount,
nextRecoveryAt = excluded.nextRecoveryAt,
error = excluded.error,
summary = excluded.summary,
@@ -1034,6 +1037,7 @@ export class TaskStore extends EventEmitter<TaskStoreEvents> {
task.recoveryRetryCount ?? null,
task.taskDoneRetryCount ?? 0,
task.verificationFailureCount ?? 0,
task.mergeConflictBounceCount ?? 0,
task.nextRecoveryAt ?? null,
task.error ?? null,
task.summary ?? null,
@@ -2665,7 +2669,7 @@ export class TaskStore extends EventEmitter<TaskStoreEvents> {
async updateTask(
id: string,
updates: { title?: string; description?: string; priority?: TaskPriority | null; prompt?: string; worktree?: string | null; status?: string | null; dependencies?: string[]; steps?: import("./types.js").TaskStep[]; currentStep?: number; blockedBy?: string | null; assignedAgentId?: string | null; assigneeUserId?: string | null; nodeId?: string | null; effectiveNodeId?: string | null; effectiveNodeSource?: string | null; checkedOutBy?: string | null; checkedOutAt?: string | null; paused?: boolean; baseBranch?: string | null; branch?: string | null; baseCommitSha?: string | null; size?: "S" | "M" | "L"; reviewLevel?: number; executionMode?: import("./types.js").ExecutionMode | null; mergeRetries?: number; workflowStepRetries?: number; stuckKillCount?: number | null; postReviewFixCount?: number | null; recoveryRetryCount?: number | null; taskDoneRetryCount?: number | null; verificationFailureCount?: number | null; nextRecoveryAt?: string | null; enabledWorkflowSteps?: string[]; modelProvider?: string | null; modelId?: string | null; validatorModelProvider?: string | null; validatorModelId?: string | null; planningModelProvider?: string | null; planningModelId?: string | null; thinkingLevel?: string | null; error?: string | null; summary?: string | null; sessionFile?: string | null; workflowStepResults?: import("./types.js").WorkflowStepResult[] | null; mergeDetails?: import("./types.js").MergeDetails | null; sourceIssue?: import("./types.js").TaskSourceIssue | null; tokenUsage?: import("./types.js").TaskTokenUsage | null; modifiedFiles?: string[] | null; missionId?: string | null; sliceId?: string | null },
updates: { title?: string; description?: string; priority?: TaskPriority | null; prompt?: string; worktree?: string | null; status?: string | null; dependencies?: string[]; steps?: import("./types.js").TaskStep[]; currentStep?: number; blockedBy?: string | null; assignedAgentId?: string | null; assigneeUserId?: string | null; nodeId?: string | null; effectiveNodeId?: string | null; effectiveNodeSource?: string | null; checkedOutBy?: string | null; checkedOutAt?: string | null; paused?: boolean; baseBranch?: string | null; branch?: string | null; baseCommitSha?: string | null; size?: "S" | "M" | "L"; reviewLevel?: number; executionMode?: import("./types.js").ExecutionMode | null; mergeRetries?: number; workflowStepRetries?: number; stuckKillCount?: number | null; postReviewFixCount?: number | null; recoveryRetryCount?: number | null; taskDoneRetryCount?: number | null; verificationFailureCount?: number | null; mergeConflictBounceCount?: number | null; nextRecoveryAt?: string | null; enabledWorkflowSteps?: string[]; modelProvider?: string | null; modelId?: string | null; validatorModelProvider?: string | null; validatorModelId?: string | null; planningModelProvider?: string | null; planningModelId?: string | null; thinkingLevel?: string | null; error?: string | null; summary?: string | null; sessionFile?: string | null; workflowStepResults?: import("./types.js").WorkflowStepResult[] | null; mergeDetails?: import("./types.js").MergeDetails | null; sourceIssue?: import("./types.js").TaskSourceIssue | null; tokenUsage?: import("./types.js").TaskTokenUsage | null; modifiedFiles?: string[] | null; missionId?: string | null; sliceId?: string | null },
runContext?: RunMutationContext,
): Promise<Task> {
return this.withTaskLock(id, async () => {
@@ -2813,6 +2817,11 @@ export class TaskStore extends EventEmitter<TaskStoreEvents> {
} else if (updates.verificationFailureCount !== undefined) {
task.verificationFailureCount = updates.verificationFailureCount;
}
if (updates.mergeConflictBounceCount === null) {
task.mergeConflictBounceCount = undefined;
} else if (updates.mergeConflictBounceCount !== undefined) {
task.mergeConflictBounceCount = updates.mergeConflictBounceCount;
}
if (updates.nextRecoveryAt === null) {
task.nextRecoveryAt = undefined;
} else if (updates.nextRecoveryAt !== undefined) {

8
packages/core/src/types.ts
View File

@@ -914,6 +914,14 @@ export interface Task {
* follow-up triage task is created so a human / fresh agent can investigate
* rather than endlessly re-attempting the same fix. */
verificationFailureCount?: number;
/** Number of times this task has bounced from `in-review` back to `in-progress`
* due to auto-merge conflict-retry exhaustion. Incremented by the auto-merge
* error handler (project-engine.ts) when conflicts can't be auto-resolved
* within `MAX_AUTO_MERGE_RETRIES`. When this reaches
* `MAX_MERGE_CONFLICT_BOUNCES`, the task is parked in `in-review` with
* `status="failed"` and a follow-up triage task is created — preventing the
* cooldown sweep from re-attempting the same impossible merge forever. */
mergeConflictBounceCount?: number;
/** ISO-8601 timestamp indicating when the task becomes eligible for the next
* recovery retry. Scheduler and triage processor skip tasks whose
* `nextRecoveryAt` is still in the future. Cleared alongside `recoveryRetryCount`. */