anomalyco/opencode
1
0
Fork 0
mirror of https://github.com/anomalyco/opencode.git synced 2026-07-22 02:05:26 -04:00
Code Issues 5.9k Packages Projects Releases 19 Wiki Activity

[PR #13783] fix: --prompt submitting the first message before recent model has been loaded #14813

New Issue
Open
opened 2026-02-16 18:19:34 -05:00 by yindo · 0 comments
yindo commented 2026-02-16 18:19:34 -05:00
Owner
Copy Link
Copy Source

Original Pull Request: https://github.com/anomalyco/opencode/pull/13783

State: open
Merged: No

What does this PR do?

Fixes #8551

Issue

Running opencode normally starts the session with the most recent model.
Running opencode with --prompt starts the session with a random(ish) fallback model. Im my case Gemini3.

This happens because the prompt arg is submitted as a message before the model is ready and has loaded the recent model.
The onMount already uses once to make it idempotent. Adding an additional check that the model is "ready" (has loaded recent models, etc.) ensures that the prompt is submitted with the most recent model like when opencode is opened normally.

How did you verify your code works?

Using the latest commit from the dev branch:

  1. Run opencode and pick a model. Send a "hello" message
  2. Run opencode --prompt hello. The model is different than the one selected in step 1
  3. Run bun dev and verify that the model from step 1 is selected
  4. Run bun dev --prompt hello The model is different than step 1 and the same as step 2

Using this fix branch:

  1. Run bun dev and verify that the model from step 1 is selected
  2. Run bun dev --prompt hello The model from step 1 should be selected
**Original Pull Request:** https://github.com/anomalyco/opencode/pull/13783 **State:** open **Merged:** No --- ### What does this PR do? Fixes #8551 #### Issue Running opencode normally starts the session with the most recent model. Running opencode with `--prompt` starts the session with a random(ish) fallback model. Im my case Gemini3. This happens because the prompt arg is submitted as a message before the model is ready and has loaded the recent model. The `onMount` already uses `once` to make it idempotent. Adding an additional check that the model is "ready" (has loaded recent models, etc.) ensures that the prompt is submitted with the most recent model like when opencode is opened normally. ### How did you verify your code works? Using the latest commit from the dev branch: 1. Run `opencode` and pick a model. Send a "hello" message 2. Run `opencode --prompt hello`. The model is different than the one selected in step 1 3. Run `bun dev` and verify that the model from step 1 is selected 4. Run `bun dev --prompt hello` The model is different than step 1 and the same as step 2 Using this fix branch: 1. Run `bun dev` and verify that the model from step 1 is selected 2. Run `bun dev --prompt hello` The model from step 1 should be selected
yindo added the pull-request label 2026-02-16 18:19:34 -05:00
Sign in to join this conversation.
No Branch/Tag Specified
Branches Tags
Labels
Clear labels
acp
bad
bug
discussion
docs
documentation
enhancement
extension
good first issue
growth
help-wanted
mcp
model-problem
needs:compliance
nix
opentui
perf
pull-request
Mirrored from GitHub Pull Request
 tui
web
windows
zen
No Label pull-request
Milestone
No items
No Milestone
Projects
Clear projects
No project
Assignees
Clear assignees
yindo
No Assignees
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: anomalyco/opencode#14813
Delete Branch "%!s()"

Deleting a branch is permanent. Although the deleted branch may continue to exist for a short time before it actually gets removed, it CANNOT be undone in most cases. Continue?