smashimo/oh-my-pi
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

fix(coding-agent/eval): remove per-call model override from agent() (#6438)

Browse Source 
Completes the maintainer's removal of per-call model selection from
subagent spawns (9f8aa87dbf removed it from the task tool and the
model-facing agent() docs/prompt, but the eval agent() runtime and all
four preludes still accepted and forwarded a per-call model).

Subagents now always resolve through the selected agent's frontmatter
model and settings, so an explicit model: "default" can no longer
silently route children onto the parent session model.

- agent-bridge: drops "model?" from agentArgsSchema and the request
  forward; adds "+": "delete" so a legacy model argument is stripped
  (same contract as the task wire schemas).
- JS/Python/Ruby/Julia preludes: remove the model parameter from
  agent(); completion()'s tier selector is unchanged.
- docs (tools/eval.md, python-repl.md) updated to the removed surface.

Refs #6438
This commit is contained in:
Slava Zavadsky
2026-08-04 08:35:01 -04:00
parent 003bb5548c
commit b8779dae63
10 changed files with 31 additions and 24 deletions
Download Patch File Download Diff File Expand all files Collapse all files
docs/tools/eval.md
+2 -2
View File
@@ -149,9 +149,9 @@ A stateless, tool-free one-shot model call:
Runs one subagent through `runStructuredSubagent(...)`:
- JS supports the preferred `await agent(prompt, { agent?, model?, label?, schema?, schemaMode?, isolated?, apply?, merge?, handle? })`; legacy positional slots are still implemented.
- JS supports the preferred `await agent(prompt, { agent?, label?, schema?, schemaMode?, isolated?, apply?, merge?, handle? })`; legacy positional slots are still implemented.
- Python/Ruby/Julia use keyword arguments (`schema_mode` outside JS).
- `agent` defaults from the current spawn policy. `model` may pin a selector/fallback chain. `schema` overrides agent/session schemas; `schemaMode`/`schema_mode` chooses `permissive` or `strict`.
- `agent` defaults from the current spawn policy; the selected agent's frontmatter model and settings always apply (there is no per-call model override — `model` is not accepted). `schema` overrides agent/session schemas; `schemaMode`/`schema_mode` chooses `permissive` or `strict`.
- `isolated` requests isolation. `apply` controls whether captured changes are integrated; `merge=false` selects patch mode while the normal setting controls branch mode.
- `handle=true` returns `{ text, output, handle, id, agent }`, optional parsed `data`, and isolation metadata instead of only output/data.
- Eval subagents are one-shot (`keepAlive=false`), are unregistered/disposed after completion, and **do not share the caller's eval executor** (`shareEvalSession=false`). Their code mutations therefore do not appear in the caller's retained VM/kernel.