feat: 完善模型用量趋势与全局手账卡片并补齐阶段验收

backend/app/services/transcription_service.py

@@ -82,8 +82,9 @@ async def create_transcription(attachment_id, language=None, *, diarization=Fals
     actual = source if source.is_file() else attachment_path(f"{attachment_id}.txt")
     if not actual.is_file():
         raise ApiError(404, "ATTACHMENT_NOT_FOUND", "Attachment was not found.")
-    if not 0 < actual.stat().st_size <= 25 * 1024 * 1024:
-        raise ApiError(413, "ATTACHMENT_TOO_LARGE", "Attachment must be between 1 byte and 25 MiB.")
+    from app.providers.routing import MAX_LOCAL_MEDIA_BYTES, MAX_MEDIA_BYTES
+    if not 0 < actual.stat().st_size <= (MAX_LOCAL_MEDIA_BYTES if local_only else MAX_MEDIA_BYTES):
+        raise ApiError(413, "ATTACHMENT_TOO_LARGE", "仅本地处理最大支持 128 MiB；超过 25 MiB 的录音请启用仅本地处理。")
     digest = await asyncio.to_thread(lambda: hashlib.sha256(actual.read_bytes()).hexdigest())
     from app.container import container
     from app.local_models.runtime import configuration
@@ -160,6 +161,7 @@ async def _execute(job_id, request, routing=None):
             result = await (routing or container.model_routing).transcribe(source, request.language, local_only=request.local_only)
             job.text, job.source, job.fallback_reason = result.text, result.source, result.fallback_reason
             job.segments = getattr(result, "segments", []) or []
+            job.warnings.extend(getattr(result, "warnings", []) or [])
         if not job.text or not job.text.strip():
             raise ApiError(422, "TRANSCRIPT_EMPTY", "Transcript is empty.")
         if request.diarization:

backend/app/services/usage_service.py

@@ -6,7 +6,7 @@ import logging
 import math
 from contextlib import closing
 from contextvars import ContextVar
-from datetime import datetime, timezone
+from datetime import datetime, timezone, timedelta
 from uuid import uuid4
 
 from app.database.db import connect
@@ -107,8 +107,8 @@ class UsageAttempt:
             logger.warning("Usage persistence failed; model response remains available")
 
 
-def aggregate(start, end, provider_id=None, model=None, source=None):
-    query = "SELECT counters_json,completed,capability FROM model_usage WHERE started_at>=? AND started_at<?"
+def aggregate(start, end, provider_id=None, model=None, source=None, timezone_offset=0):
+    query = "SELECT counters_json,completed,capability,started_at,source FROM model_usage WHERE started_at>=? AND started_at<?"
     args = [start.astimezone(timezone.utc).isoformat(), end.astimezone(timezone.utc).isoformat()]
     for column, value in (("provider_id", provider_id), ("model", model), ("source", source)):
         if value:
@@ -117,6 +117,18 @@ def aggregate(start, end, provider_id=None, model=None, source=None):
     with closing(connection()) as conn:
         rows = conn.execute(query, args).fetchall()
         options = conn.execute("SELECT DISTINCT provider_id,model,source FROM model_usage ORDER BY provider_id,model").fetchall()
+    # Calendar buckets use the caller's UTC offset; absent counters remain null.
+    zone = timezone(timedelta(minutes=timezone_offset))
+    first = start.astimezone(zone).date()
+    last = (end - timedelta(microseconds=1)).astimezone(zone).date()
+    days = (last - first).days + 1
+    step = max(1, (days + 89) // 90)
+    series = []
+    for offset in range(0, days, step):
+        date = first + timedelta(days=offset)
+        series.append({"date": date.isoformat(), "end_date": (first + timedelta(days=min(days-1, offset+step-1))).isoformat(),
+                       "local": {"requests": 0, "totals": {key: None for key in METRICS}, "coverage": {key: 0 for key in METRICS}},
+                       "api": {"requests": 0, "totals": {key: None for key in METRICS}, "coverage": {key: 0 for key in METRICS}}})
     totals = {key: None for key in METRICS}
     coverage = {key: 0 for key in METRICS}
     hits, eligible_input, cache_requests = 0, 0, 0
@@ -125,6 +137,13 @@ def aggregate(start, end, provider_id=None, model=None, source=None):
         if row[2] in {"transcription", "speaker_matching"}:
             audio_requests += 1
         counts = json.loads(row[0])
+        date = datetime.fromisoformat(row[3]).astimezone(zone).date()
+        bucket = series[(date - first).days // step][row[4]]
+        bucket['requests'] += 1
+        for key in METRICS:
+            if counts.get(key) is not None:
+                bucket['totals'][key] = (bucket['totals'][key] or 0) + counts[key]
+                bucket['coverage'][key] += 1
         if counts.get("audio_seconds") is not None:
             audio_covered += 1
             audio_seconds = (audio_seconds or 0) + counts["audio_seconds"]
@@ -140,4 +159,4 @@ def aggregate(start, end, provider_id=None, model=None, source=None):
             "complete_requests": sum(row[1] for row in rows), "cache_covered_requests": cache_requests,
             "cache_hit_rate": hits / eligible_input if eligible_input else None,
             "options": [dict(row) for row in options], "start": start, "end": end,
-            "scope": "application_observed_usage"}
+            "scope": "application_observed_usage", "series": series, "timezone_offset": timezone_offset}