airkjw/claude-mem
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

fix(gemini): add conversation history truncation to prevent O(N²) token cost growth

Browse Source 
GeminiAgent sends the full conversation history with every API call,
causing quadratic token growth per session. A 100-observation session
sends ~30M cumulative input tokens. This ports the proven truncateHistory()
sliding window from OpenRouterAgent to GeminiAgent.

- Add CLAUDE_MEM_GEMINI_MAX_CONTEXT_MESSAGES (default: 20) and
  CLAUDE_MEM_GEMINI_MAX_TOKENS (default: 100000) settings
- Add truncateHistory() to GeminiAgent using shared estimateTokens()
- Always preserve at least the newest message to avoid empty API requests
- Add settings validation in SettingsRoutes (1-100 messages, 1K-1M tokens)
- Add regression tests for truncation and oversized single-prompt edge case

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
This commit is contained in:
vnz
2026-03-17 08:00:29 +01:00
parent e2a230286d
commit df1fb8bb89
8 changed files with 503 additions and 338 deletions
Download Patch File Download Diff File Expand all files Collapse all files
src/shared/SettingsDefaultsManager.ts
+4
View File
@@ -23,6 +23,8 @@ export interface SettingsDefaults {
CLAUDE_MEM_GEMINI_API_KEY: string;
CLAUDE_MEM_GEMINI_MODEL: string; // 'gemini-2.5-flash-lite' | 'gemini-2.5-flash' | 'gemini-3-flash-preview'
CLAUDE_MEM_GEMINI_RATE_LIMITING_ENABLED: string; // 'true' | 'false' - enable rate limiting for free tier
CLAUDE_MEM_GEMINI_MAX_CONTEXT_MESSAGES: string; // Max messages in Gemini context window (prevents O(N²) cost growth)
CLAUDE_MEM_GEMINI_MAX_TOKENS: string; // Max estimated tokens for Gemini context (~100k safety limit)
CLAUDE_MEM_OPENROUTER_API_KEY: string;
CLAUDE_MEM_OPENROUTER_MODEL: string;
CLAUDE_MEM_OPENROUTER_SITE_URL: string;
@@ -82,6 +84,8 @@ export class SettingsDefaultsManager {
CLAUDE_MEM_GEMINI_API_KEY: '', // Empty by default, can be set via UI or env
CLAUDE_MEM_GEMINI_MODEL: 'gemini-2.5-flash-lite', // Default Gemini model (highest free tier RPM)
CLAUDE_MEM_GEMINI_RATE_LIMITING_ENABLED: 'true', // Rate limiting ON by default for free tier users
CLAUDE_MEM_GEMINI_MAX_CONTEXT_MESSAGES: '20', // Max messages in Gemini context window
CLAUDE_MEM_GEMINI_MAX_TOKENS: '100000', // Max estimated tokens (~100k safety limit)
CLAUDE_MEM_OPENROUTER_API_KEY: '', // Empty by default, can be set via UI or env
CLAUDE_MEM_OPENROUTER_MODEL: 'xiaomi/mimo-v2-flash:free', // Default OpenRouter model (free tier)
CLAUDE_MEM_OPENROUTER_SITE_URL: '', // Optional: for OpenRouter analytics