11 Commits

Author SHA1 Message Date
YeonGyu-Kim
d786691260 fix: read anthropic 1m flag from live model cache state 2026-02-17 10:51:01 +09:00
YeonGyu-Kim
b444899153 fix: use model cache context flag for runtime context limits 2026-02-17 10:51:01 +09:00
YeonGyu-Kim
d672eb1c12 fix: recognize google-vertex-anthropic as Claude provider (#1700) 2026-02-17 01:28:27 +09:00
YeonGyu-Kim
158ca3f22b refactor: remove unused params/imports/types from lsp-tools, task-tools, delegate-task, skill-loader, context-window-monitor, plugin-config 2026-02-16 22:12:21 +09:00
popododo0720
eb56701996 fix: reduce session.messages() calls with event-based caching to prevent memory leaks
- Replace session.messages() fetch in context-window-monitor with message.updated event cache
- Replace session.messages() fetch in preemptive-compaction with message.updated event cache
- Add per-session transcript cache (5min TTL) to avoid full rebuild per tool call
- Remove session.messages() from background-agent polling (use event-based progress)
- Add TTL pruning to todo-continuation-enforcer session state Map
- Add setInterval.unref() to tool-input-cache cleanup timer

Fixes #1222
2026-02-12 11:38:11 +09:00
justsisyphus
c7ca608b38 refactor: unify system directive prefix for keyword-detector filtering
- Add shared/system-directive.ts with SYSTEM_DIRECTIVE_PREFIX constant
- Unify all system message prefixes to [SYSTEM DIRECTIVE: OH-MY-OPENCODE - ...]
- Add isSystemDirective() filter to keyword-detector to skip system messages
- Update prometheus-md-only tests to use new prefix constants
2026-01-16 11:35:37 +09:00
Steven Vo
99c7df5640
fix: respect ANTHROPIC_1M_CONTEXT and VERTEX_ANTHROPIC_1M_CONTEXT env vars (#450)
- Update preemptive-compaction hook to use 1M limit when env vars set
- Update dynamic-truncator to use 1M limit for output truncation
- Update context-window-monitor to use 1M limit for usage tracking

Previously hardcoded 200k limits caused compaction at 140k tokens even
with 1M context enabled. Now respects env vars consistently with base
opencode implementation.

Fixes compaction triggering too early with Claude Sonnet 4.5 1M context.

Related to anomalyco/opencode#6660
2026-01-03 21:06:06 +09:00
YeonGyu-Kim
3d273ff853 fix(hooks): use last assistant message tokens instead of cumulative sum
Previously, token calculation accumulated ALL assistant messages' tokens,
causing incorrect usage display (e.g., 524.9%) after compaction.
Now uses only the last message's input tokens, which reflects the actual
current context window usage.

🤖 GENERATED WITH ASSISTANCE OF [OhMyOpenCode](https://github.com/code-yeongyu/oh-my-opencode)
2025-12-13 01:02:21 +09:00
YeonGyu-Kim
adabace02d improve(hooks): refine context window reminder message for better clarity and guidance 2025-12-10 15:45:45 +09:00
YeonGyu-Kim
b397dd6655 feat(hook): block grep tool and guide to safe-grep 2025-12-04 18:20:01 +09:00
YeonGyu-Kim
9a11901590 feat(hook): add context window monitor for Anthropic token usage tracking 2025-12-04 16:19:12 +09:00