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/admin.py

@@ -1,4 +1,5 @@
 from django.contrib import admin
+from django.db.models import Sum
 from .models import (
     CustomUser,
     Announcement,
@@ -60,10 +61,35 @@ class PromptInline(admin.TabularInline):
 
 class ConversationAdmin(admin.ModelAdmin):
     model = Conversation
-    list_display = ("title", "get_user_email", "deleted")
+    list_display = (
+        "title",
+        "get_user_email",
+        "deleted",
+        "tokens_in",
+        "tokens_out",
+        "tokens_total",
+    )
     search_fields = ("title",)
     inlines = [PromptInline,]
 
+    def _token_sum(self, conversation, field):
+        total = PromptMetric.objects.filter(
+            conversation_id=conversation.id
+        ).aggregate(total=Sum(field))["total"]
+        return total or 0
+
+    @admin.display(description="Tokens in")
+    def tokens_in(self, conversation):
+        return self._token_sum(conversation, "tokens_in")
+
+    @admin.display(description="Tokens out")
+    def tokens_out(self, conversation):
+        return self._token_sum(conversation, "tokens_out")
+
+    @admin.display(description="Tokens total")
+    def tokens_total(self, conversation):
+        return self.tokens_in(conversation) + self.tokens_out(conversation)
+
 
 class PromptAdmin(admin.ModelAdmin):
     model = Prompt
@@ -79,11 +105,14 @@ class PromptMetricAdmin(admin.ModelAdmin):
         "model_name",
         "prompt_length",
         "reponse_length",
+        "tokens_in",
+        "tokens_out",
         "has_file",
         "file_type",
         "get_duration",
         "created"
     )
+    list_filter = ("event", "model_name", "has_file")
 
 
 class DocumentWorkspaceAdmin(admin.ModelAdmin):