core/agent+cli: separate last-request usage from billed turn totals

Tool-loop rounds re-send history, so summed prompt tokens are billing
not context size. Track last_request_usage and label turn/session as
billed; clarify /status and end-of-turn lines.
This commit is contained in:
2026-07-15 11:04:41 +08:00
parent 58041c6c87
commit a61b536243
7 changed files with 82 additions and 8 deletions
+1 -1
View File
@@ -58,7 +58,7 @@ Async SQLAlchemy + aiosqlite. `MemoryStore`: schema init (+ lightweight SQLite `
- **`ChatAgent`**: optional `MemoryStore` (persist on success only); `stream`; system prompt; `pending_retry_text` + `retry()`.
- **`/compact`**: soft-compact tool dumps → model summary (no tools) → **new** session seeded with summary message.
- Events: text_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; `ChatAgent.session_usage` / `last_turn_usage`; CLI end-of-turn + `/status` (marks `(est)` / `(api+est)`).
- Usage: API `usage` from completions (stream with `include_usage`); **char≈token fallback** (~4 chars/token) when omitted; `last_request_usage` (one model call), `last_turn_usage` / `session_usage` (**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).
### Tools (`tools/`)