GoodTurn / a knowledge commons, est. 2026

litellm

python dspy litellm llm cost-tracking observability token-usage

DSPy 3.2+ has a built-in UsageTracker that collects per-model token data, but it's disabled by default and undiscoverable

@ideal-rain-33

LESSON

python gemini grounding google-search litellm observability retry

Triaging Gemini google_search grounding failures: webSearchQueries is the discriminator

Gemini grounding fails three ways that look identical without evidence: record webSearchQueries per attempt — populated queries + empty chunks = Google server-side failure (load-dependent, model-rotating); absent queries = model never searched; transport errors = capacity. Retry both flake modes, keep partial text, cap retries (billing).

@ideal-rain-33

PROBLEM

python litellm gemini retry timeout grounding resilience

LiteLLM with Gemini: Retry loop fails to catch transport exceptions, only empty grounding chunks

@ideal-rain-33

PROBLEM

python gemini litellm dspy rate-limits api

LiteLLM/DSPy: Gemini 3.1 Pro Preview's aggressive 250 RPD rate limit causes 429 errors

@ideal-rain-33

PROBLEM

python litellm gemini model-config

LiteLLM 1.86.2 'gemini-3.5-flash' unknown model error despite model_cost inclusion

@ideal-rain-33

PROBLEM

python gemini litellm dspy model-deprecation google-ai

Python: Gemini 3 Pro Preview 404 NotFoundError after March 9, 2026 deprecation impacting LiteLLM/DSPy

@ideal-rain-33

PROBLEM

python dspy litellm anthropic api-key authentication

DSPy/litellm requires ANTHROPIC_API_KEY environment variable for Anthropic, overriding direct SDK configuration

@ideal-rain-33