33d39597ae
- 1208→1243 TS files (+35), 143k→155k LOC (+12k) - Update all agent models: Sisyphus, Hephaestus, Oracle, Librarian, Atlas, Metis, Momus - Add 6 new hook directories (39→45 dirs): beast-mode-system, hashline-edit-diff-enhancer, anthropic-image-context, task-reminder, compaction-todo-preserver, runtime-fallback - Update category models: visual-engineering/artistry gemini-3-pro→gemini-3.1-pro - Add 2 config schema files: fallback-models.ts, runtime-fallback.ts - Timestamp: 2026-03-02 | Commit: 1c2caa09 🤖 Generated with assistance of [OhMyOpenCode](https://github.com/code-yeongyu/oh-my-opencode)
2.1 KiB
2.1 KiB
src/hooks/anthropic-context-window-limit-recovery/ — Multi-Strategy Context Recovery
Generated: 2026-03-02
OVERVIEW
31 files (~2232 LOC). Most complex hook. Recovers from context window limit errors via multiple strategies applied in sequence.
RECOVERY STRATEGIES (in priority order)
| Strategy | File | Mechanism |
|---|---|---|
| Empty content recovery | empty-content-recovery.ts |
Handle empty/null content blocks in messages |
| Deduplication | deduplication-recovery.ts |
Remove duplicate tool results from context |
| Target-token truncation | target-token-truncation.ts |
Truncate largest tool outputs to fit target ratio |
| Aggressive truncation | aggressive-truncation-strategy.ts |
Last-resort truncation with minimal output preservation |
| Summarize retry | summarize-retry-strategy.ts |
Compaction + summarization then retry |
KEY FILES
| File | Purpose |
|---|---|
recovery-hook.ts |
Main hook entry — session.error handler, strategy orchestration |
executor.ts |
Execute recovery strategies in sequence |
parser.ts |
Parse Anthropic token limit error messages |
state.ts |
AutoCompactState — per-session retry/truncation tracking |
types.ts |
ParsedTokenLimitError, RetryState, TruncateState, config constants |
storage.ts |
Persist tool results for later truncation |
tool-result-storage.ts |
Store/retrieve individual tool call results |
message-builder.ts |
Build retry messages after recovery |
RETRY CONFIG
- Max attempts: 2
- Initial delay: 2s, backoff ×2, max 30s
- Max truncation attempts: 20
- Target token ratio: 0.5 (truncate to 50% of limit)
- Chars per token estimate: 4
PRUNING SYSTEM
pruning-*.ts files handle intelligent output pruning:
pruning-deduplication.ts— Remove duplicate content across tool resultspruning-tool-output-truncation.ts— Truncate oversized tool outputspruning-types.ts— Pruning-specific type definitions
SDK VARIANTS
empty-content-recovery-sdk.ts and tool-result-storage-sdk.ts provide SDK-based implementations for OpenCode client interactions.