CoolBoy/submmit
1
0
Fork 0
Code Issues Pull Requests Actions Projects Releases Wiki Activity

feat: compact durable logs and refine framework routing

Browse Source
This commit is contained in:
CoolBoy
2026-09-04 10:30:21 +08:00
parent 5b1ec4d3eb
commit ff73768537
13 changed files with 621 additions and 44 deletions
Download Patch File Download Diff File Expand all files Collapse all files

60
modelhub_submmit_api/outcome_tracker.py
View File

@@ -31,7 +31,7 @@ DEFAULT_OUTCOME_CHECKPOINT_PATH = Path(".modelhub_state/outcome_checkpoint.json"
DEFAULT_RECENT_OUTCOMES_PATH = Path(".modelhub_state/recent_outcomes.jsonl")
DEFAULT_ARCHIVE_PENDING_DIR = Path(".modelhub_state/archive_pending/outcomes")
OUTCOME_CHECKPOINT_VERSION = 1
DEFAULT_OUTCOME_COMPACT_THRESHOLD = 2000
DEFAULT_OUTCOME_COMPACT_THRESHOLD = 1000
DEFAULT_RECENT_OUTCOME_LIMIT = 1000
FAILURE_ENRICHMENT_LIMIT = 40
FAILURE_ENRICHMENT_WORKERS = 4
@@ -215,6 +215,25 @@ class OutcomeTracker:
}
return contexts
def merge_task_contexts(self, contexts: dict[str, dict[str, Any]] | None) -> int:
"""Repair framework/profile fields omitted by the platform history API."""
if not isinstance(contexts, dict):
return 0
changed = 0
for task_id, context in contexts.items():
record = self._by_task_id.get(str(task_id))
if record is None or not isinstance(context, dict):
continue
before = json.dumps(record, ensure_ascii=False, sort_keys=True)
self._merge_record_metadata(record, self._enrich_history_task({}, context))
if json.dumps(record, ensure_ascii=False, sort_keys=True) != before:
changed += 1
if changed:
write_jsonl(self.recent_path, self._recent_records)
self._rebuild_indexes()
self.save()
return changed
def get_strategy_history_records(self) -> list[dict[str, Any]]:
"""Expose only successes and evidence-attributable failures for GPU ranking."""
records: list[dict[str, Any]] = []
@@ -331,7 +350,12 @@ class OutcomeTracker:
self._rebuild_failed_index()
return marked
def sync_from_api(self, client: ModelHubClient | ModelHubClientPool) -> int:
def sync_from_api(
self,
client: ModelHubClient | ModelHubClientPool,
*,
task_contexts: dict[str, dict[str, Any]] | None = None,
) -> int:
try:
begin = self._last_sync_time
end = utc_now()
@@ -350,13 +374,32 @@ class OutcomeTracker:
if not task_id:
continue
task = self._enrich_history_task(task, (task_contexts or {}).get(task_id))
existing = self._by_task_id.get(task_id)
if existing is not None:
metadata_before = (
existing.get("modelId"),
existing.get("targetGpu"),
existing.get("framework"),
existing.get("taskType"),
existing.get("modelProfile"),
)
self._merge_record_metadata(existing, task)
metadata_changed = metadata_before != (
existing.get("modelId"),
existing.get("targetGpu"),
existing.get("framework"),
existing.get("taskType"),
existing.get("modelProfile"),
)
if existing.get("outcome") in {"pending", "policy_cancelled"}:
self._update_record_from_task(existing, task)
if existing.get("outcome") == "failed" and existing.get("logCosUrl"):
enrichment_candidates.append(existing)
updated_count += 1
elif metadata_changed:
updated_count += 1
else:
status = str(task.get("status") or "").lower()
if status in TERMINAL_TASK_STATUSES:
@@ -393,6 +436,7 @@ class OutcomeTracker:
if updated_count or enrichment_attempts:
self._last_sync_time = end
self._rebuild_failed_index()
write_jsonl(self.recent_path, self._recent_records)
self.save()
return updated_count
@@ -630,6 +674,18 @@ class OutcomeTracker:
now = now or utc_now()
return failed_at >= now - timedelta(hours=max(0, int(cooldown_hours)))
def has_non_transformers_failure(self, model_id: str) -> bool:
"""Return platform evidence that unlocks prerequisite-gated transformers."""
for record in [*self._recent_records, *self._records]:
if str(record.get("modelId") or "") != str(model_id):
continue
if record.get("outcome") != "failed":
continue
framework = str(record.get("framework") or "").strip().casefold()
if framework and framework != "transformers":
return True
return False
def get_stats_report(self) -> dict[str, Any]:
now_datetime = utc_now()
now = now_datetime.isoformat()