[Reliability]: Implement Exponential Backoff for Gemini API

[Kavirubc]

Problem Statement

The current embedding and LLM integrations for Gemini (internal/integrations/gemini/) do not handle rate limiting (HTTP 429) or transient network errors. When processing high-volume requests (like bulk indexing or frequent triaging), the pipeline fails immediately upon hitting a rate limit.

Proposed Solution

• Implement a retry mechanism with exponential backoff for:
  • internal/integrations/gemini/embedder.go: Embed and EmbedBatch methods.
  • internal/integrations/gemini/llm.go: All generative methods (AnalyzeIssue, RouteIssue, etc.).
• Ensure retries only occur on transient errors (429, 5xx) and NOT on client errors (400, 403, 404).

Context

Identified during self-hosting configuration.

[gh-simili-bot]

Simili Triage Report

Note

Quality Score: 8.5/10 (Good)
The issue is well-described.

Classification

Category	Value
Labels

Similar Threads

Similarity	Thread	Status
79%	#51 [Performance]: Parallelize Batch Embedding Gene...	Open
74%	#8 [v0.1.0] Implement LLM Triage & Smart Routing	Open

---

_{Generated by Simili Bot}