Commit Graph

10 Commits

Author SHA1 Message Date
YeonGyu-Kim
b64b3f96e6 fix(recovery): correct prompt_async API path parameter from sessionID to id
The prompt_async method expects path parameter named 'id' (not 'sessionID').
This bug prevented the 'Continue' message from being sent after compaction,
causing the recovery process to fail silently due to silent error swallowing
in the empty catch block.

Fixes:
- Type definition: changed path: { sessionID: string } to path: { id: string }
- Implementation: changed path: { sessionID } to path: { id: sessionID } at 2 locations (lines 411, 509)

🤖 GENERATED WITH ASSISTANCE OF [OhMyOpenCode](https://github.com/code-yeongyu/oh-my-opencode)
2026-01-02 21:16:23 +09:00
YeonGyu-Kim
7a896fd2b9 fix(token-limit-recovery): exclude thinking block errors from token limit detection
- Removed 'invalid_request_error' from TOKEN_LIMIT_KEYWORDS (too broad)
- Added THINKING_BLOCK_ERROR_PATTERNS to explicitly detect thinking block structure errors
- Added isThinkingBlockError() function to filter these out before token limit checks
- Prevents 'thinking block order' errors from triggering compaction instead of session-recovery

🤖 Generated with assistance of OhMyOpenCode (https://github.com/code-yeongyu/oh-my-opencode)
2026-01-02 20:28:37 +09:00
YeonGyu-Kim
dc057e9910 fix(recovery): restore compaction pipeline sufficient check and conservative charsPerToken
Fixes critical v2.10.0 compaction regression where truncation ALWAYS returned early
without checking if it was sufficient, causing PHASE 3 (Summarize) to be skipped.
This led to "history disappears" symptom where all context was lost after compaction.

Changes:
- Restored aggressiveResult.sufficient check before early return in executor
- Only return from Truncate phase if truncation successfully reduced tokens below limit
- Otherwise fall through to Summarize phase when truncation is insufficient
- Restored conservative charsPerToken=4 (was changed to 2, too aggressive)
- Added 2 regression tests:
  * Test 1: Verify Summarize is called when truncation is insufficient
  * Test 2: Verify Summarize is skipped when truncation is sufficient

Regression details:
- v2.10.0 changed charsPerToken from 4 to 2, making truncation too aggressive
- Early return removed sufficient check, skipping fallback to Summarize
- Users reported complete loss of conversation history after compaction

🤖 Generated with assistance of OhMyOpenCode (https://github.com/code-yeongyu/oh-my-opencode)
2026-01-02 11:34:33 +09:00
YeonGyu-Kim
d4787c477a fix(recovery): implement early exit in tool output truncation
🤖 GENERATED WITH ASSISTANCE OF [OhMyOpenCode](https://github.com/code-yeongyu/oh-my-opencode)
2026-01-02 11:14:28 +09:00
YeonGyu-Kim
b30c17ac77 fix(recovery): more aggressive truncation, remove revert fallback
- Change charsPerToken from 4 to 2 for more aggressive truncation calculation
- Remove revert fallback (PHASE 2.5)
- Always try Continue after truncation if anything was truncated

🤖 Generated with assistance of OhMyOpenCode (https://github.com/code-yeongyu/oh-my-opencode)
2026-01-01 21:03:27 +09:00
YeonGyu-Kim
a5983f1678 fix(anthropic-context-window-limit-recovery): add revert fallback when truncation insufficient
When over token limit after truncation, use session.revert to remove last message instead of attempting summarize (which would also fail). Skip summarize entirely when still over limit to prevent infinite loop.

🤖 Generated with assistance of [OhMyOpenCode](https://github.com/code-yeongyu/oh-my-opencode)
2026-01-01 21:03:27 +09:00
YeonGyu-Kim
2948d94a3c Change recovery phase ordering to DCP → Truncate → Summarize
When session hits token limit (e.g. 207k > 200k), the summarize API also fails
because it needs to process the full 207k tokens. By truncating FIRST, we reduce
token count before attempting summarize.

Changes:
- PHASE 1: DCP (Dynamic Context Pruning) - prune duplicate tool calls first
- PHASE 2: Aggressive Truncation - always try when over limit
- PHASE 3: Summarize - last resort after DCP and truncation

🤖 Generated with assistance of [OhMyOpenCode](https://github.com/code-yeongyu/oh-my-opencode)
2026-01-01 21:03:27 +09:00
YeonGyu-Kim
d49c221cb1 fix(anthropic-context-window-limit-recovery): remove emergency fallback message revert logic
Remove the FallbackState interface and related fallback recovery mechanism that deleted message pairs when all other compaction attempts failed. This simplifies the recovery strategy by eliminating the last-resort fallback approach.

Changes:
- Removed FallbackState interface and FALLBACK_CONFIG from types.ts
- Removed fallbackStateBySession from AutoCompactState
- Removed getOrCreateFallbackState and getLastMessagePair functions
- Removed emergency revert block that deleted user+assistant message pairs
- Updated clearSessionState and timeout reset logic
- Removed related test cases

🤖 GENERATED WITH ASSISTANCE OF [OhMyOpenCode](https://github.com/code-yeongyu/oh-my-opencode)
2025-12-31 13:14:59 +09:00
YeonGyu-Kim
ec61350664 refactor(dcp-for-compaction): migrate from experimental config to hook system
- Add 'dcp-for-compaction' to HookNameSchema
- Remove dcp_for_compaction from ExperimentalConfigSchema
- Update executor.ts to use dcpForCompaction parameter
- Enable DCP by default (can be disabled via disabled_hooks)
- Update all 4 README files (EN, KO, JA, ZH-CN)

🤖 GENERATED WITH ASSISTANCE OF [OhMyOpenCode](https://github.com/code-yeongyu/oh-my-opencode)
2025-12-30 19:09:16 +09:00
YeonGyu-Kim
f7696a1fbb refactor: rename anthropic-auto-compact to anthropic-context-window-limit-recovery
The old name 'auto-compact' was misleading - the hook does much more than
just compaction. It's a full recovery pipeline for context window limit
errors including:
- DCP (Dynamic Context Pruning)
- Aggressive/single truncation
- Summarize with retry
- Emergency message revert

The new name accurately describes its purpose: recovering from Anthropic
context window limit exceeded errors.

🤖 GENERATED WITH ASSISTANCE OF [OhMyOpenCode](https://github.com/code-yeongyu/oh-my-opencode)
2025-12-30 12:00:02 +09:00