Handoff-style /model switch command and per-turn thinking level (#64)

Co-authored-by: Claude Fable 5 <noreply@anthropic.com>
This commit is contained in:
Yaowei ZhengandClaude Fable 5 authored and GitHub committed 2026-07-26 16:31:51 +08:00
1 parent 816a823b75
commit 1e23452f48
58 files changed
+1064 -336

No files matched your search

+1 -2
View File
@@ -38,7 +38,6 @@ interface SessionMetaPayload {
model_context_window: number | string;
system_prompt: string; // fully assembled, placeholders substituted
tools: ToolDefinition[]; // the complete tool schema sent to the model
thinking_level: string; // "default" when unconfigured
agent_state: string; // absolute path of the Agent State
workspace: string; // absolute path of the Workspace
source?: "subagent" | "schedule"; // session origin; absent = user-created
@@ -51,7 +50,7 @@ interface ToolDefinition {
}
```
On resume, the engine takes this Trace line as the runtime config — the model, system prompt and Workspace are immutable for the Session's lifetime. See [Sessions & Traces](/sessions-and-traces).
session_meta holds **per-session invariants only** — the model, system prompt and Workspace are immutable for the Session's lifetime; on resume, the engine takes this Trace line as the runtime config. See [Sessions & Traces](/sessions-and-traces). The thinking level is a per-turn parameter (sent with each Task) and is not recorded here; legacy Traces may still carry a `thinking_level` field in their meta, which resume keeps honoring for back-compat.
## model_msg: complete payloads