picoclaw

mirror of https://github.com/sipeed/picoclaw.git synced 2026-06-12 18:08:54 +00:00

Files

T

xiaoen 9c82b0baa2 refactor(agent): context boundary detection, proactive budget check, and safe compression

Separate context_window from max_tokens — they serve different purposes
(input capacity vs output generation limit). The previous conflation caused
premature summarization or missed compression triggers.

Changes:
- Add context_window field to AgentDefaults config (default: 4x max_tokens)
- Extract boundary-safe truncation helpers (isSafeBoundary, findSafeBoundary)
  into context_budget.go — pure functions with no AgentLoop dependency
- forceCompression: align split to safe boundary so tool-call sequences
  (assistant+ToolCalls → tool results) are never torn apart
- summarizeSession: use findSafeBoundary instead of hardcoded keep-last-4
- estimateTokens: count ToolCalls arguments and ToolCallID metadata,
  not just Content — fixes systematic undercounting in tool-heavy sessions
- Add proactive context budget check before LLM call in runAgentLoop,
  preventing 400 context-length errors instead of reacting to them
- Add estimateToolDefsTokens for tool definition token cost

Closes #556, closes #665
Ref #1439

2026-03-16 14:48:32 +08:00

config_test.go

add model command to set default model (#1250 )

2026-03-13 14:10:11 +08:00

config.go

refactor(agent): context boundary detection, proactive budget check, and safe compression

2026-03-16 14:48:32 +08:00

defaults.go

feat(agent): steering (#1517 )

2026-03-16 00:08:16 +08:00

migration_test.go

feat(provider): add ModelScope as OpenAI-compatible provider (#1486 )