Chris CoutinhoandClaude 92b97bda00 fix: Add rate limit retry logic to OpenAI provider ...

Add exponential backoff retry handling for OpenAI API rate limits
(429 errors). This is needed for GitHub Models API which has stricter
rate limits than standard OpenAI API.

- Add retry_on_rate_limit decorator with exponential backoff
- Max 5 retries with delays: 2s → 4s → 8s → 16s → 32s
- Apply to embed(), _embed_batch_request(), and generate() methods

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude <noreply@anthropic.com>

2025-11-23 17:24:48 +01:00

..

auth

refactor: Move background tasks to server lifespan and deprecate SSE transport

2025-11-23 04:02:30 +01:00

client

fix: Use WebDAV for tag creation and add LLM-as-a-judge for RAG tests

2025-11-23 02:24:01 +01:00

controllers

fix: return all notes when search query is empty

2025-11-13 21:57:14 +01:00

document_processors

fix: Remove pymupdf.layout.activate() to fix page_chunks behavior

2025-11-22 16:58:35 +01:00

embedding

perf: Optimize vector viz search performance

2025-11-22 19:47:43 +01:00

models

fix: Update models and viz to use int-only doc_id

2025-11-20 12:32:27 +01:00

observability

fix: Set is_placeholder=False in processor to fix search filtering

2025-11-20 17:15:19 +01:00

providers

fix: Add rate limit retry logic to OpenAI provider

2025-11-23 17:24:48 +01:00

search

refactor: Move background tasks to server lifespan and deprecate SSE transport

2025-11-23 04:02:30 +01:00

server

fix: Increase MCP sampling timeout to 5 minutes for slower LLMs

2025-11-23 05:43:48 +01:00

utils

feat: Add text processing background worker for telling client about progress

2025-10-25 19:52:45 +02:00

vector

feat: Add OpenAI provider support for embeddings and generation

2025-11-23 00:33:32 +01:00

__init__.py

Initial commit

2025-05-04 23:24:55 +02:00

app.py

fix: Share vector sync state with FastMCP session lifespan via module singleton

2025-11-23 04:20:47 +01:00

cli.py

refactor: Move background tasks to server lifespan and deprecate SSE transport

2025-11-23 04:02:30 +01:00

config.py

feat: Add OpenAI provider support for embeddings and generation

2025-11-23 00:33:32 +01:00

context.py

fix(smithery): Use container runtime pattern for config discovery

2025-11-22 18:22:55 +01:00

smithery_main.py

feat: Implement ADR-016 Smithery stateless deployment mode

2025-11-22 17:30:42 +01:00