docs: state that the model is chosen once per run - #18
Merged
Conversation
The skill showed `--model` once in its command block but never said the choice is run-level, while step 3 spoke of preserving "every explicit model" and step 5 offered one to three workers. A reader combining those infers one model per worker and writes `--model` twice, which the CLI rejects before anything runs. The rejection is correct: `Request.Model` is a single string that `run.Controller` hands to every worker. Step 3 now states the scope and names the consequence a caller has to plan around, that two models mean two runs and that two runs declaring writes cannot overlap in one workspace. The concurrency rule itself is not repeated; it already stands under Boundaries.
Merged
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
The bundled skill showed
--modelonce in its command block but never said thechoice is run-level, while step 3 spoke of preserving "every explicit model" and
step 5 offered one to three workers. A reader combining those infers one model
per worker and writes
--modeltwice, which the CLI rejects before anythingruns. The rejection is correct:
Request.Modelis a single string thatrun.Controllerhands to every worker. Showing the rule in an example is notstating it.
Step 3 now states the scope and names the consequence a caller has to plan
around: two models mean two runs, and two runs that both declare writes cannot
overlap in one workspace. The concurrency rule itself is not repeated; it
already stands under
## Boundaries.One line changed. The file stays at 52 lines, no numeric exit code was
introduced, and
npm run verifypasses.