Track token in/out per prompt on PromptMetric (#18)

Closes #15

## Summary
- Add nullable `tokens_in` / `tokens_out` `IntegerField`s to `PromptMetric` to record real prompt/completion token counts per turn.
- New `extract_token_usage()` helper parses provider usage payloads (LangChain `usage_metadata`, OpenAI-style `prompt_tokens`/`completion_tokens`, Ollama `prompt_eval_count`/`eval_count`). When a provider reports no usage, the fields stay **null** — counts are never estimated/fabricated.
- `create_prompt_metric` / `finish_prompt_metric` in both `consumers.py` and `consumers_graph.py` accept and persist optional `tokens_in` / `tokens_out` (added to `update_fields` only when present).
- Admin panel (this ticket's deliverable):
  - `PromptMetricAdmin` lists `tokens_in` / `tokens_out` and adds `event` / `model_name` / `has_file` filters.
  - `ConversationAdmin` shows summed `tokens_in` / `tokens_out` / `tokens_total` per conversation.
- Migration `0023_promptmetric_tokens_in_promptmetric_tokens_out` (existing rows remain valid — null).

## Note on live capture
The streaming chat path uses LangChain `StrOutputParser`, which yields plain string chunks with no usage metadata, so live turns currently persist `null` tokens (honest, per acceptance criteria — no fabricated counts). The plumbing + helper are in place so wiring real provider usage is a drop-in once the services expose it.

## Follow-ups
- #16 — Show token in/out in chat web app UI (FE + API exposure)
- #17 — Token-based billing, quotas, and enforcement

## Test plan
- [x] `uv run python manage.py test` — full suite green (266 tests, 6 skipped)
- [x] Model: token fields default null + persist when set
- [x] `extract_token_usage`: LangChain / OpenAI / Ollama key variants, attribute sources, bool/float handling, missing usage → (None, None)
- [x] Metric lifecycle: tokens persist when provided, stay null when absent (both consumers)
- [x] Admin: conversation token totals sum across metrics and ignore other conversationsReviewed-on: #18

llm_be/chat_backend/consumers_graph.py

@@ -114,11 +114,12 @@ def save_generated_message(conversation_id, message):
         print(serializer.errors)
 
 @database_sync_to_async
-def create_prompt_metric(prompt_id, prompt, has_file, file_type, model_name, conversation_id):
+def create_prompt_metric(prompt_id, prompt, has_file, file_type, model_name, conversation_id, tokens_in=None):
     prompt_metric = PromptMetric.objects.create(
         prompt_id=prompt_id,
         start_time=timezone.now(),
         prompt_length=len(prompt),
+        tokens_in=tokens_in,
         has_file=has_file,
         file_type=file_type,
         model_name=model_name,
@@ -127,11 +128,18 @@ def create_prompt_metric(prompt_id, prompt, has_file, file_type, model_name, con
     return prompt_metric
 
 @database_sync_to_async
-def finish_prompt_metric(prompt_metric, response_length):
+def finish_prompt_metric(prompt_metric, response_length, tokens_in=None, tokens_out=None):
     prompt_metric.end_time = timezone.now()
     prompt_metric.reponse_length = response_length
     prompt_metric.event = "FINISHED"
-    prompt_metric.save(update_fields=["end_time", "reponse_length", "event"])
+    update_fields = ["end_time", "reponse_length", "event"]
+    if tokens_in is not None:
+        prompt_metric.tokens_in = tokens_in
+        update_fields.append("tokens_in")
+    if tokens_out is not None:
+        prompt_metric.tokens_out = tokens_out
+        update_fields.append("tokens_out")
+    prompt_metric.save(update_fields=update_fields)
 
 async def get_conversation_file_async(conversation_id):
     try: