NCBM/plyngent
1
0
Fork 0
mirror of https://github.com/NCBM/plyngent.git synced 2026-07-25 08:04:57 +08:00
Code Issues Packages Projects Releases Wiki Activity

core/agent: keep more recent tool results in soft-compact

Browse Source 
Raise DEFAULT_RECENT_TOOL_RESULTS from 4 to 12 so near-term tool
payloads stay full-size longer when trimming older dumps for context.
This commit is contained in:
worldmozara
2026-07-20 17:34:01 +08:00
parent 879e28ea4c
commit 71b9f91e14
2 changed files with 3 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files
CLAUDE.md
+1 -1
View File
@@ -69,7 +69,7 @@ Async SQLAlchemy + aiosqlite. `MemoryStore`: schema init (+ lightweight SQLite `
- **`@tool` / `ToolRegistry`**: decorator infers JSON Schema from type hints; execute tools by name. - **`@tool` / `ToolRegistry`**: decorator infers JSON Schema from type hints; execute tools by name.
- **`run_chat_loop`**: multi-round tool loop; default **streaming** text deltas + stream tool-call merge; parallel tools; tool-result char budget; soft context compact on request (**API-calibrated** after first usage when available); cooperative cancel points; optional `on_limit`. - **`run_chat_loop`**: multi-round tool loop; default **streaming** text deltas + stream tool-call merge; parallel tools; tool-result char budget; soft context compact on request (**API-calibrated** after first usage when available); cooperative cancel points; optional `on_limit`.
- **`ChatAgent`**: optional `MemoryStore` (user message persisted immediately; **completed tool batches checkpointed** mid-turn; unfinished assistant suffix rolled back on failure); `stream`; system prompt; `retry()` continues incomplete turns (user-only **or** after committed tools — does not re-run those tools). - **`ChatAgent`**: optional `MemoryStore` (user message persisted immediately; **completed tool batches checkpointed** mid-turn; unfinished assistant suffix rolled back on failure); `stream`; system prompt; `retry()` continues incomplete turns (user-only **or** after committed tools — does not re-run those tools).
- **`/compact`**: soft-compact tool dumps → model summary (no tools) → **new** session seeded with summary message. - **`/compact`**: soft-compact tool dumps → model summary (no tools) → **new** session seeded with summary message. Soft-compact keeps the last **12** tool results full-size by default (`DEFAULT_RECENT_TOOL_RESULTS`); older tool payloads shrink first.
- Events: text_delta, **reasoning_delta**, assistant_message, tool_call/result, max_rounds, **error** (`retryable`/`source`), **cancelled** (`reason`), **usage** (`TokenUsage`). - Events: text_delta, **reasoning_delta**, assistant_message, tool_call/result, max_rounds, **error** (`retryable`/`source`), **cancelled** (`reason`), **usage** (`TokenUsage`).
- Usage: API `usage` from completions (stream with `include_usage`); **char≈token fallback** (~4 chars/token) when omitted; **context size** = last request ``prompt_tokens`` (API preferred); `last_turn_usage` / `session_usage` are **billed sums** (tool rounds re-send history); CLI end-of-turn + `/status`. - Usage: API `usage` from completions (stream with `include_usage`); **char≈token fallback** (~4 chars/token) when omitted; **context size** = last request ``prompt_tokens`` (API preferred); `last_turn_usage` / `session_usage` are **billed sums** (tool rounds re-send history); CLI end-of-turn + `/status`.
- Config ``[agent]``: `system_prompt`, `max_tool_result_chars`, `parallel_tools`, `confirm_destructive`, `path_denylist`, `max_context_tokens` (default 200k est. tokens). - Config ``[agent]``: `system_prompt`, `max_tool_result_chars`, `parallel_tools`, `confirm_destructive`, `path_denylist`, `max_context_tokens` (default 200k est. tokens).
src/plyngent/agent/budget.py
+2 -1
View File
@@ -21,7 +21,8 @@ DEFAULT_TOOL_RESULT_MAX_CHARS = 32_000
# Soft context budget in tokens (API-calibrated when possible; else ~4 chars/token). # Soft context budget in tokens (API-calibrated when possible; else ~4 chars/token).
DEFAULT_CONTEXT_MAX_TOKENS = 200_000 DEFAULT_CONTEXT_MAX_TOKENS = 200_000
DEFAULT_OLD_TOOL_RESULT_CHARS = 800 DEFAULT_OLD_TOOL_RESULT_CHARS = 800
DEFAULT_RECENT_TOOL_RESULTS = 4 # Soft-compact: leave this many most-recent tool results at full size.
DEFAULT_RECENT_TOOL_RESULTS = 12
# Backward-compat alias (older code/docs may still import this name). # Backward-compat alias (older code/docs may still import this name).
DEFAULT_CONTEXT_MAX_CHARS = DEFAULT_CONTEXT_MAX_TOKENS * 4 DEFAULT_CONTEXT_MAX_CHARS = DEFAULT_CONTEXT_MAX_TOKENS * 4