Experimental/brain-of-reese
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

phase: 129_sync_chunk_progress
Build and Push Containers / build-and-push-app (push) Successful in 8m23s
Details
Build and Push Containers / build-and-push-db (push) Successful in 40s
Details

Browse Source 
All green. Final report:

**Phase 129 final verification pass — 100% green** (previous work intact; this pass re-verified everything and fixed two pre-existing README inconsistencies)

- Verified on-spec: `LLMClient.embed` per-batch `on_progress` hook; importer `on_chunk_progress` plumbing (text/image/PDF branches; summary embed excluded); `SyncStatus.current_chunk/chunks_total` reset+clear contract; UI `.sync-label-chunk` pinned part with untruncated `title`/`#sync-result`
- `uv run pytest --cov=app -q`: exit 0, ~3041 passed, 0 failed, `app/` coverage **99%** (>90% gate)
- `uv run pytest tests/e2e/test_sync_chunk_progress.py -v --no-cov` (isolated, DB up): **2 passed** (endpoint chunk climb with true `chunk_document` total + UI `· chunk n/m` part)
- `uv run ruff check .`: all checks passed · `uv run pyright`: 0 errors, 0 warnings
- Completion criteria: all 5 ✅ (incl. no behavior change in completed phases — full suite green, CLI/chat no-op paths byte-identical)
- Docs: README.md fixed 2 pre-existing inconsistencies (upload section claimed "unpacks + scans immediately" — phase 90 made it unpack+register only, scan deferred to Sync; troubleshooting claimed "120s client timeout" — actual guard is the 300 s pre-token `TURN_TIMEOUT_MS`). Phase-129 label behavior already documented. AGENTS.md re-verified consistent — no changes
- Removed stray untracked `NOTES.md` (8-byte artifact); no live-infra changes; no commits — all changes left in working tree for the harness
- Next pending phase: `130_chat_answer_clusters`
This commit is contained in:
ducoterra
2026-09-28 03:38:14 -04:00
parent 1139f007cf
commit 2d0f608246
53 changed files with 3590 additions and 157 deletions
Download Patch File Download Diff File Expand all files Collapse all files
tests/integration/test_sync_api.py
+36 -1
View File
@@ -285,6 +285,11 @@ class FakeImportSources:
# only, same root-string keying; local rows contribute
# nothing).
self.doc_dates_maps: list[dict[str, dict[str, datetime]]] = []
# Phase 129 (task 03): the chunk-position hook the runner
# passes (a live closure while wired, None if the wiring
# regresses) — the canned fake never fires it (the runner's
# status chunk fields stay 0/0, like a no-batch import).
self.chunk_hooks: list[object] = []
async def __call__(
self,
@@ -295,6 +300,7 @@ class FakeImportSources:
limit: int | None = None,
session: Session | None = None,
progress: Callable[[str, str, int, int], None] | None = None,
on_chunk_progress: Callable[[int, int], None] | None = None, # phase 129
ignore_by_root: dict[str, list[str]] | None = None,
include_hidden_by_root: dict[str, bool] | None = None,
doc_dates_by_root: dict[str, dict[str, datetime]] | None = None, # phase 106
@@ -303,6 +309,7 @@ class FakeImportSources:
self.llms.append(llm)
self.prune_flags.append(prune)
self.progress_hooks.append(progress)
self.chunk_hooks.append(on_chunk_progress)
self.ignore_maps.append(ignore_by_root or {})
self.include_hidden_maps.append(include_hidden_by_root or {})
self.doc_dates_maps.append(doc_dates_by_root or {})
@@ -459,6 +466,10 @@ def test_admin_sync_success_reports_full_detail(
"current_file": None,
"files_done": 0,
"files_total": 0,
# Phase 129 (task 03): the chunk-position keys — 0/0 idle
# (the dataclass defaults).
"current_chunk": 0,
"chunks_total": 0,
# Phase 98 (task 01): the phase-machine keys — null/0/0/0 idle.
"phase": None,
"current_summary": None,
@@ -627,6 +638,10 @@ class _GatedImport:
self.started = started
self.release = release
self.hook_calls: list[tuple[str, str, int, int]] = []
# Phase 129 (task 03): the chunk-position hook the runner
# passes (recorded for the wiring pin — the gated fake never
# fires it, so the status chunk fields stay 0/0).
self.chunk_hook: Callable[[int, int], None] | None = None
async def __call__(
self,
@@ -637,6 +652,7 @@ class _GatedImport:
limit: int | None = None,
session: Session | None = None,
progress: Callable[[str, str, int, int], None] | None = None,
on_chunk_progress: Callable[[int, int], None] | None = None, # phase 129
ignore_by_root: dict[str, list[str]] | None = None,
include_hidden_by_root: dict[str, bool] | None = None,
doc_dates_by_root: dict[str, dict[str, datetime]] | None = None, # phase 106
@@ -644,6 +660,7 @@ class _GatedImport:
if progress is not None:
progress("repo", "notes/deep.md", 1, 3)
self.hook_calls.append(("repo", "notes/deep.md", 1, 3))
self.chunk_hook = on_chunk_progress
self.started.set()
await asyncio.to_thread(self.release.wait)
return self.summary
@@ -750,12 +767,14 @@ def test_status_reports_the_phase_machine_across_the_run(
monkeypatch.setattr(sync_api, "generate_folder_summaries", gated_folders)
_login(sync_client)
# Idle: the four phase keys ride along as null/0/0/0.
# Idle: the four phase keys ride along as null/0/0/0, and the
# phase-129 chunk keys as 0/0 (the dataclass defaults).
body = sync_client.get("/api/sync/status").json()
assert body["state"] == "idle"
assert body["phase"] is None
assert body["current_summary"] is None
assert body["summaries_done"] == 0 and body["summaries_total"] == 0
assert body["current_chunk"] == 0 and body["chunks_total"] == 0
assert sync_client.post("/api/sync").status_code == 202
try:
@@ -767,12 +786,19 @@ def test_status_reports_the_phase_machine_across_the_run(
assert s["files_done"] == 1 and s["files_total"] == 3
assert s["current_summary"] is None
assert s["summaries_done"] == 0 and s["summaries_total"] == 0
# Phase 129 (task 03): no embed batch has fired the chunk hook
# (the gated fake never does) — the position stays 0/0.
assert s["current_chunk"] == 0 and s["chunks_total"] == 0
gated_import.release.set()
assert gated_overview.started.wait(5.0), "the run never reached the overview"
s = sync_client.get("/api/sync/status").json()
assert s["state"] == "running"
assert s["phase"] == "overview"
assert s["current_summary"] is None
# Phase 129 (task 03): the import→overview transition cleared
# the chunk position (the convention split — the FILE counts
# below keep their final values).
assert s["current_chunk"] == 0 and s["chunks_total"] == 0
gated_overview.release.set()
assert gated_folders.started.wait(5.0), "the run never reached the summaries"
s = sync_client.get("/api/sync/status").json()
@@ -785,6 +811,9 @@ def test_status_reports_the_phase_machine_across_the_run(
# The import's final position is kept through the summary span
# (the "number pauses" span — the user's report).
assert s["files_done"] == 1 and s["files_total"] == 3
# Phase 129 (task 03): the import→summaries transition kept
# the chunk position cleared (0/0 through the summary span).
assert s["current_chunk"] == 0 and s["chunks_total"] == 0
gated_folders.release.set()
finally:
gated_import.release.set()
@@ -797,6 +826,11 @@ def test_status_reports_the_phase_machine_across_the_run(
assert body["phase"] is None
assert body["current_summary"] is None
assert body["summaries_done"] == 3 and body["summaries_total"] == 3
# Phase 129 (task 03): the terminal keeps the chunk position
# cleared (0/0) — the wiring pin: the runner passed a live chunk
# closure to the import (it just never fired in this canned run).
assert body["current_chunk"] == 0 and body["chunks_total"] == 0
assert gated_import.chunk_hook is not None
# Wiring: the summary hook was the runner's live closure (the
# counters above came through it); the file hook fired once.
assert gated_folders.hook is not None
@@ -1432,6 +1466,7 @@ def test_import_error_is_reported_with_credentials_masked(
limit: int | None = None,
session: Session | None = None,
progress: Callable[[str, str, int, int], None] | None = None,
on_chunk_progress: Callable[[int, int], None] | None = None, # phase 129
ignore_by_root: dict[str, list[str]] | None = None,
include_hidden_by_root: dict[str, bool] | None = None,
doc_dates_by_root: dict[str, dict[str, datetime]] | None = None, # phase 106