westfarn cc45ae5808 Persist Ollama token usage from streamed LLM responses (#16) (#38) ...

## Summary
- Fixes token tracking for [#16](#16): streaming chat never persisted `PromptMetric.tokens_in` / `tokens_out` (admin + account usage showed `—`).
- Drop `StrOutputParser` on async LLM/RAG/data-analysis chains so Ollama `generation_info` (`prompt_eval_count` / `eval_count`) survives; collect usage while streaming via `TokenUsageCollector`.
- Stop calling `self.close()` in `disconnect` (fixes Grafana `Unexpected ASGI message 'websocket.close'`).

## Test plan
- [x] Unit tests: `test_utils`, consumers, LLM/RAG/data-analysis services, finance quotas
- [ ] Deploy / local: send a chat prompt, confirm admin Prompt Metrics shows Tokens In/Out
- [ ] Reload Account usage card — in/out no longer `—` for new turns
- [ ] Confirm WS disconnect no longer raises double-close in logsReviewed-on: #38

2026-07-31 10:46:57 -07:00

..

migrations

Add Google/Microsoft SSO OAuth for register and sign-in (#24) (#29)

2026-07-27 05:13:32 -07:00

services

Persist Ollama token usage from streamed LLM responses (#16) (#38)

2026-07-31 10:46:57 -07:00

templates/emails

Fix password reset flow (#1) (#27)

2026-07-27 05:07:42 -07:00

tests

Persist Ollama token usage from streamed LLM responses (#16) (#38)

2026-07-31 10:46:57 -07:00

__init__.py

temp checkin

2025-03-07 12:23:00 -06:00

admin.py

Add Google/Microsoft SSO OAuth for register and sign-in (#24) (#29)

2026-07-27 05:13:32 -07:00

apps.py

Dockerize chat_backend + Ollama LAN + DB file storage (#6) (#7)

2026-07-25 05:23:33 -07:00

client.py

Dockerize chat_backend + Ollama LAN + DB file storage (#6) (#7)

2026-07-25 05:23:33 -07:00

consumers_graph.py

Persist Ollama token usage from streamed LLM responses (#16) (#38)

2026-07-31 10:46:57 -07:00

consumers.py

Persist Ollama token usage from streamed LLM responses (#16) (#38)

2026-07-31 10:46:57 -07:00

email_tasks.py

Fix password reset flow (#1) (#27)

2026-07-27 05:07:42 -07:00

models.py

Add Google/Microsoft SSO OAuth for register and sign-in (#24) (#29)

2026-07-27 05:13:32 -07:00

oauth.py

Multi-plan subscriptions, quotas, and token usage APIs (#16 #17 #36) (#37)

2026-07-31 04:24:20 -07:00

ollama_config.py

Dockerize chat_backend + Ollama LAN + DB file storage (#6) (#7)

2026-07-25 05:23:33 -07:00

renderers.py

RAG implementation, content moderation, prompt classification, new LLM chain, document storage

2025-05-14 03:27:38 -05:00

routing.py

updates

2025-12-07 06:31:06 -06:00

serializers.py

Multi-plan subscriptions, quotas, and token usage APIs (#16 #17 #36) (#37)

2026-07-31 04:24:20 -07:00

signals.py

Dockerize chat_backend + Ollama LAN + DB file storage (#6) (#7)

2026-07-25 05:23:33 -07:00

storage.py

Add offline unit test suite for chat_backend (#12)

2026-07-26 05:00:17 -07:00

urls.py

Add Google/Microsoft SSO OAuth for register and sign-in (#24) (#29)

2026-07-27 05:13:32 -07:00

utils.py

Persist Ollama token usage from streamed LLM responses (#16) (#38)

2026-07-31 10:46:57 -07:00

views_oauth.py

Multi-plan subscriptions, quotas, and token usage APIs (#16 #17 #36) (#37)

2026-07-31 04:24:20 -07:00

views.py

Multi-plan subscriptions, quotas, and token usage APIs (#16 #17 #36) (#37)

2026-07-31 04:24:20 -07:00