mirror of
https://github.com/Kaelio/ktx.git
synced 2026-06-28 08:49:38 +02:00
fix(ingest): verify repair outcomes and reject dangling join targets (#292)
One ingest integration hiccup no longer discards a whole source: - Replace the duplicated gate-repair and textual-resolver loops with one shared constrained-repair loop whose success criterion is re-running the failed check (verify), not whether the agent edited files. Verify failures feed the retry prompt; maxAttempts is 2. - Let the resolver declare a conflicting patch redundant: a verified no-change resolution is accepted as subsumed instead of failing the source (duplicate wiki-page creation from parallel work units). - Carry per-source validation errors through validateWuTouchedSources into gate messages and work-unit failure reasons instead of discarding them. - Move join-neighbor expansion into the shared validation path so work-unit validation and integration gates check the same set. - Reject joins whose target resolves to no source, at sl_write time and in the gates, attributed to the declaring source. Resolution mirrors the Python engine exactly (case-sensitive name within the connection), with a case-mismatch hint for the writing agent.
This commit is contained in:
Andrey Avtomonov
GitHub
parent
00cdf2de90
commit
a278d2f7d0
17 changed files with 1119 additions and 705 deletions
|
|
@ -221,6 +221,7 @@ describe('integrateWorkUnitPatch', () => {
|
|||
touchedPaths: ['wiki/global/a.md'],
|
||||
});
|
||||
await writeFile(join(configDir, 'wiki/global/a.md'), 'accepted\nproposal\n', 'utf-8');
|
||||
await expect(context.verify(['wiki/global/a.md'])).resolves.toEqual({ ok: true });
|
||||
return {
|
||||
status: 'repaired' as const,
|
||||
attempts: 1,
|
||||
|
|
@ -336,6 +337,7 @@ describe('integrateWorkUnitPatch', () => {
|
|||
touchedPaths: ['wiki/global/a.md'],
|
||||
});
|
||||
await writeFile(join(configDir, 'wiki/global/a.md'), 'repaired semantic ref\n', 'utf-8');
|
||||
await expect(context.verify(['wiki/global/a.md'])).resolves.toEqual({ ok: true });
|
||||
return {
|
||||
status: 'repaired' as const,
|
||||
attempts: 1,
|
||||
|
|
@ -402,71 +404,56 @@ describe('integrateWorkUnitPatch', () => {
|
|||
await expect(readFile(join(configDir, 'wiki/global/a.md'), 'utf-8')).resolves.toBe('old\n');
|
||||
});
|
||||
|
||||
it('repairs a semantic gate failure after a textual conflict is resolved', async () => {
|
||||
const { homeDir, configDir, git } = await makeRepo();
|
||||
await mkdir(join(configDir, 'wiki/global'), { recursive: true });
|
||||
await writeFile(join(configDir, 'wiki/global/a.md'), 'base\n', 'utf-8');
|
||||
await git.commitFiles(['wiki/global/a.md'], 'base page', 'System User', 'system@example.com');
|
||||
const conflictBase = await git.revParseHead();
|
||||
it('accepts a redundant duplicate-creation patch as subsumed without committing', async () => {
|
||||
// Regression: two work units each emitted a creation patch for the same
|
||||
// wiki page. The second creation patch conflicts with the page already in
|
||||
// the tree; the resolver verifies a no-change resolution and the source
|
||||
// must not fail.
|
||||
const { homeDir, configDir, git, baseSha } = await makeRepo();
|
||||
await writeFile(join(configDir, 'wiki/global/b.md'), 'page from the first work unit\n', 'utf-8');
|
||||
await git.commitFiles(['wiki/global/b.md'], 'first creation', 'System User', 'system@example.com');
|
||||
const acceptedHead = await git.revParseHead();
|
||||
|
||||
await writeFile(join(configDir, 'wiki/global/a.md'), 'accepted\n', 'utf-8');
|
||||
await git.commitFiles(['wiki/global/a.md'], 'accepted edit', 'System User', 'system@example.com');
|
||||
|
||||
const childDir = join(homeDir, 'child-conflict-repair');
|
||||
await git.addWorktree(childDir, 'child-conflict-repair', conflictBase);
|
||||
const childDir = join(homeDir, 'child-duplicate');
|
||||
await git.addWorktree(childDir, 'child-duplicate', baseSha);
|
||||
const childGit = git.forWorktree(childDir);
|
||||
await writeFile(join(childDir, 'wiki/global/a.md'), 'proposal\n', 'utf-8');
|
||||
await childGit.commitFiles(['wiki/global/a.md'], 'proposal edit', 'System User', 'system@example.com');
|
||||
const patchPath = join(homeDir, 'proposal-repair.patch');
|
||||
await childGit.writeBinaryNoRenamePatch(conflictBase, 'HEAD', patchPath);
|
||||
await writeFile(join(childDir, 'wiki/global/b.md'), 'duplicate page from the second work unit\n', 'utf-8');
|
||||
await childGit.commitFiles(['wiki/global/b.md'], 'second creation', 'System User', 'system@example.com');
|
||||
const patchPath = join(homeDir, 'duplicate-creation.patch');
|
||||
await childGit.writeBinaryNoRenamePatch(baseSha, 'HEAD', patchPath);
|
||||
|
||||
const trace = new FileIngestTraceWriter({
|
||||
tracePath: join(homeDir, '.ktx/ingest-traces/job-resolver-repair/trace.jsonl'),
|
||||
jobId: 'job-resolver-repair',
|
||||
tracePath: join(homeDir, '.ktx/ingest-traces/job-subsumed/trace.jsonl'),
|
||||
jobId: 'job-subsumed',
|
||||
connectionId: 'warehouse',
|
||||
sourceKey: 'metabase',
|
||||
sourceKey: 'notion',
|
||||
level: 'trace',
|
||||
});
|
||||
|
||||
// Gate fails on the resolver's merged tree, then passes after the repair edit.
|
||||
const validateAppliedTree = vi
|
||||
.fn()
|
||||
.mockRejectedValueOnce(
|
||||
new Error('final artifact gates failed:\narr-definition: unknown sl_refs entity mart_arr_daily.arr_dollars'),
|
||||
)
|
||||
.mockResolvedValueOnce(undefined);
|
||||
|
||||
const repairGateFailure = vi.fn(async (context: { unitKey: string; touchedPaths: string[] }) => {
|
||||
expect(context).toMatchObject({ unitKey: 'wu-conflict-repair', touchedPaths: ['wiki/global/a.md'] });
|
||||
await writeFile(join(configDir, 'wiki/global/a.md'), 'accepted\nproposal repaired\n', 'utf-8');
|
||||
return { status: 'repaired' as const, attempts: 1, changedPaths: ['wiki/global/a.md'] };
|
||||
});
|
||||
|
||||
const result = await integrateWorkUnitPatch({
|
||||
unitKey: 'wu-conflict-repair',
|
||||
unitKey: 'wu-duplicate',
|
||||
patchPath,
|
||||
integrationGit: git,
|
||||
trace,
|
||||
author: { name: 'System User', email: 'system@example.com' },
|
||||
slDisallowed: false,
|
||||
allowedTargetConnectionIds: new Set(['warehouse']),
|
||||
validateAppliedTree,
|
||||
resolveTextualConflict: vi.fn(async () => {
|
||||
await writeFile(join(configDir, 'wiki/global/a.md'), 'accepted\nproposal\n', 'utf-8');
|
||||
return { status: 'repaired' as const, attempts: 1, changedPaths: ['wiki/global/a.md'] };
|
||||
validateAppliedTree: vi.fn(async () => {}),
|
||||
resolveTextualConflict: vi.fn(async (context) => {
|
||||
await expect(context.verify([])).resolves.toEqual({ ok: true });
|
||||
return { status: 'repaired' as const, attempts: 1, changedPaths: [] };
|
||||
}),
|
||||
repairGateFailure,
|
||||
});
|
||||
|
||||
expect(result).toMatchObject({
|
||||
status: 'accepted',
|
||||
touchedPaths: ['wiki/global/a.md'],
|
||||
textualResolution: { status: 'repaired' },
|
||||
gateRepair: { status: 'repaired', attempts: 1, changedPaths: ['wiki/global/a.md'] },
|
||||
touchedPaths: [],
|
||||
textualResolution: { status: 'repaired', attempts: 1, changedPaths: [] },
|
||||
});
|
||||
expect(validateAppliedTree).toHaveBeenCalledTimes(2);
|
||||
expect(repairGateFailure).toHaveBeenCalledOnce();
|
||||
await expect(readFile(join(configDir, 'wiki/global/a.md'), 'utf-8')).resolves.toBe('accepted\nproposal repaired\n');
|
||||
await expect(readFile(trace.tracePath, 'utf-8')).resolves.toContain('patch_accepted_after_textual_resolution');
|
||||
expect(await git.revParseHead()).toBe(acceptedHead);
|
||||
await expect(readFile(join(configDir, 'wiki/global/b.md'), 'utf-8')).resolves.toBe(
|
||||
'page from the first work unit\n',
|
||||
);
|
||||
await expect(readFile(trace.tracePath, 'utf-8')).resolves.toContain('patch_subsumed_after_textual_resolution');
|
||||
});
|
||||
});
|
||||
|
|
|
|||
|
|
@ -42,7 +42,7 @@ describe('resolveTextualConflict', () => {
|
|||
const { workdir, patchPath, trace } = await makeHarness();
|
||||
const agentRunner = {
|
||||
runLoop: vi.fn(async (params: any) => {
|
||||
const current = await params.toolSet.read_integration_file.execute({ path: 'wiki/global/account.md' });
|
||||
const current = await params.toolSet.read_repair_file.execute({ path: 'wiki/global/account.md' });
|
||||
expect(current.structured).toEqual({ path: 'wiki/global/account.md', exists: true });
|
||||
expect(current.markdown).toContain('accepted line');
|
||||
|
||||
|
|
@ -50,19 +50,20 @@ describe('resolveTextualConflict', () => {
|
|||
expect(patch.markdown).toContain('proposal line');
|
||||
|
||||
await expect(
|
||||
params.toolSet.write_integration_file.execute({
|
||||
params.toolSet.write_repair_file.execute({
|
||||
path: 'wiki/global/not-allowed.md',
|
||||
content: 'bad\n',
|
||||
}),
|
||||
).rejects.toThrow(/resolver path not allowed/);
|
||||
).rejects.toThrow(/repair path not allowed/);
|
||||
|
||||
await params.toolSet.write_integration_file.execute({
|
||||
await params.toolSet.write_repair_file.execute({
|
||||
path: 'wiki/global/account.md',
|
||||
content: 'accepted line\nproposal line\n',
|
||||
});
|
||||
return { stopReason: 'natural' as const };
|
||||
}),
|
||||
};
|
||||
const verify = vi.fn(async () => ({ ok: true as const }));
|
||||
|
||||
const result = await resolveTextualConflict({
|
||||
agentRunner,
|
||||
|
|
@ -72,6 +73,7 @@ describe('resolveTextualConflict', () => {
|
|||
touchedPaths: ['wiki/global/account.md'],
|
||||
trace,
|
||||
reason: 'patch failed: wiki/global/account.md',
|
||||
verify,
|
||||
maxAttempts: 1,
|
||||
stepBudget: 8,
|
||||
});
|
||||
|
|
@ -81,6 +83,7 @@ describe('resolveTextualConflict', () => {
|
|||
attempts: 1,
|
||||
changedPaths: ['wiki/global/account.md'],
|
||||
});
|
||||
expect(verify).toHaveBeenCalledWith(['wiki/global/account.md']);
|
||||
await expect(readFile(join(workdir, 'wiki/global/account.md'), 'utf-8')).resolves.toBe(
|
||||
'accepted line\nproposal line\n',
|
||||
);
|
||||
|
|
@ -97,8 +100,9 @@ describe('resolveTextualConflict', () => {
|
|||
);
|
||||
});
|
||||
|
||||
it('fails when the repair agent completes without editing any touched path', async () => {
|
||||
it('fails when the repair agent neither edits nor declares the patch redundant', async () => {
|
||||
const { workdir, patchPath, trace } = await makeHarness();
|
||||
const verify = vi.fn(async () => ({ ok: true as const }));
|
||||
const result = await resolveTextualConflict({
|
||||
agentRunner: { runLoop: vi.fn(async () => ({ stopReason: 'natural' as const })) },
|
||||
workdir,
|
||||
|
|
@ -107,6 +111,7 @@ describe('resolveTextualConflict', () => {
|
|||
touchedPaths: ['wiki/global/account.md'],
|
||||
trace,
|
||||
reason: 'patch failed: wiki/global/account.md',
|
||||
verify,
|
||||
maxAttempts: 1,
|
||||
stepBudget: 8,
|
||||
});
|
||||
|
|
@ -114,7 +119,112 @@ describe('resolveTextualConflict', () => {
|
|||
expect(result).toEqual({
|
||||
status: 'failed',
|
||||
attempts: 1,
|
||||
reason: 'resolver completed without editing an allowed path',
|
||||
reason: 'resolver completed without editing an allowed path or declaring the patch redundant',
|
||||
});
|
||||
expect(verify).not.toHaveBeenCalled();
|
||||
});
|
||||
|
||||
it('succeeds without edits when the agent declares the patch redundant and the gates verify', async () => {
|
||||
// Regression: two Notion pages produced creation patches for the same
|
||||
// wiki key. The second patch conflicts, the integration tree already
|
||||
// holds a complete page, and the correct resolution is no edit at all.
|
||||
const { workdir, patchPath, trace } = await makeHarness();
|
||||
const agentRunner = {
|
||||
runLoop: vi.fn(async (params: any) => {
|
||||
const declared = await params.toolSet.declare_patch_redundant.execute({
|
||||
reason: 'wiki/global/account.md already documents this page',
|
||||
});
|
||||
expect(declared.structured).toEqual({ reason: 'wiki/global/account.md already documents this page' });
|
||||
return { stopReason: 'natural' as const };
|
||||
}),
|
||||
};
|
||||
const verify = vi.fn(async () => ({ ok: true as const }));
|
||||
|
||||
const result = await resolveTextualConflict({
|
||||
agentRunner,
|
||||
workdir,
|
||||
unitKey: 'wu-duplicate',
|
||||
patchPath,
|
||||
touchedPaths: ['wiki/global/account.md'],
|
||||
trace,
|
||||
reason: 'patch failed: wiki/global/account.md',
|
||||
verify,
|
||||
maxAttempts: 1,
|
||||
stepBudget: 8,
|
||||
});
|
||||
|
||||
expect(result).toEqual({ status: 'repaired', attempts: 1, changedPaths: [] });
|
||||
expect(verify).toHaveBeenCalledWith([]);
|
||||
await expect(readFile(join(workdir, 'wiki/global/account.md'), 'utf-8')).resolves.toBe('accepted line\n');
|
||||
await expect(readFile(trace.tracePath, 'utf-8')).resolves.toContain('textual_conflict_resolver_repaired');
|
||||
});
|
||||
|
||||
it('retries with the gate failure when verification rejects the first resolution', async () => {
|
||||
const { workdir, patchPath, trace } = await makeHarness();
|
||||
const agentRunner = {
|
||||
runLoop: vi.fn(async (params: any) => {
|
||||
await params.toolSet.write_repair_file.execute({
|
||||
path: 'wiki/global/account.md',
|
||||
content: 'accepted line\nproposal line\n',
|
||||
});
|
||||
return { stopReason: 'natural' as const };
|
||||
}),
|
||||
};
|
||||
const verify = vi
|
||||
.fn()
|
||||
.mockResolvedValueOnce({ ok: false, reason: 'final artifact gates failed: stale sl_refs entry' })
|
||||
.mockResolvedValueOnce({ ok: true });
|
||||
|
||||
const result = await resolveTextualConflict({
|
||||
agentRunner,
|
||||
workdir,
|
||||
unitKey: 'wu-retry',
|
||||
patchPath,
|
||||
touchedPaths: ['wiki/global/account.md'],
|
||||
trace,
|
||||
reason: 'patch failed: wiki/global/account.md',
|
||||
verify,
|
||||
maxAttempts: 2,
|
||||
stepBudget: 8,
|
||||
});
|
||||
|
||||
expect(result).toEqual({
|
||||
status: 'repaired',
|
||||
attempts: 2,
|
||||
changedPaths: ['wiki/global/account.md'],
|
||||
});
|
||||
expect(agentRunner.runLoop).toHaveBeenCalledTimes(2);
|
||||
const secondPrompt = agentRunner.runLoop.mock.calls[1][0].userPrompt as string;
|
||||
expect(secondPrompt).toContain('final artifact gates failed: stale sl_refs entry');
|
||||
});
|
||||
|
||||
it('fails when edits never pass verification', async () => {
|
||||
const { workdir, patchPath, trace } = await makeHarness();
|
||||
const agentRunner = {
|
||||
runLoop: vi.fn(async (params: any) => {
|
||||
await params.toolSet.write_repair_file.execute({
|
||||
path: 'wiki/global/account.md',
|
||||
content: 'still wrong\n',
|
||||
});
|
||||
return { stopReason: 'natural' as const };
|
||||
}),
|
||||
};
|
||||
const verify = vi.fn(async () => ({ ok: false as const, reason: 'final artifact gates failed' }));
|
||||
|
||||
const result = await resolveTextualConflict({
|
||||
agentRunner,
|
||||
workdir,
|
||||
unitKey: 'wu-never-passes',
|
||||
patchPath,
|
||||
touchedPaths: ['wiki/global/account.md'],
|
||||
trace,
|
||||
reason: 'patch failed: wiki/global/account.md',
|
||||
verify,
|
||||
maxAttempts: 2,
|
||||
stepBudget: 8,
|
||||
});
|
||||
|
||||
expect(result).toEqual({ status: 'failed', attempts: 2, reason: 'final artifact gates failed' });
|
||||
expect(verify).toHaveBeenCalledTimes(2);
|
||||
});
|
||||
});
|
||||
|
|
|
|||
Loading…
Add table
Add a link
Reference in a new issue