Repository navigation
Launch opencode workers via mini so --model is accepted - #17
Merged
Merged
Conversation
OpenCode 2.0.12 rejects --model on the root CLI (Unrecognized flag: --model); mini accepts --model/-m as provider/model plus --prompt. The model flag, permission-allow config, and prompt encoding are unchanged, as are the busy-state plugin path (verified loading under mini) and all harness routing. mini honors OPENCODE_CONFIG_CONTENT permission allow: a live probe ran a file write plus a shell command with zero prompts.
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
2 participants
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
OpenCode 2.0.12 rejects --model on the root CLI (Unrecognized flag: --model), which killed every model-pinned opencode worker launch at a shell. This switches the opencode launch template to opencode mini, which accepts --model/-m as provider/model plus --prompt.
Unchanged: model-flag threading, OPENCODE_CONFIG_CONTENT permission-allow config, prompt encoding via operational input, busy-state plugin path (verified loading under mini), and all harness routing. The muse template is untouched.
Approval-freedom: mini has no --auto flag, so this relies on the existing OPENCODE_CONFIG_CONTENT permission-allow config. Verified live on mini v2.0.12 with model opencode-go/muse-spark-1.3-contributor: a probe launch ran a file write plus a shell command with zero permission prompts.
Validation: bash -n, shellcheck, tests/fm-spawn-dispatch-profile.test.sh (assertion updated to the mini launch shape), tests/fm-busy-adapter-wiring.test.sh — all pass. Direct-PR delivery, no no-mistakes run.