Repository navigation
Allow per-task coding model and reasoning settings - #629
Merged
Merged
Conversation
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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Coding tasks previously inherited the worker model and local CLI reasoning setting, so a user could not select them reliably for one task. Native tasks now preserve optional
requested_modelandrequested_reasoning_effortthrough create, update and read APIs. The worker resolves each independently, defaults to Astra/medium, passes both explicitly to Codex, and records the selected values and their sources in run evidence and result messages. Invalid settings are reported, and the existing Sol restriction applies to task overrides.Validation: 142 focused tests passed across task persistence, MCP/REST propagation, actor-bound continuation, retry behaviour, worker/inbox launches and rejection without a model call. The final worker/inbox check passed all 38 tests after the startup default adjustment; Python compilation and diff checks passed. No paid model evaluation campaign.
This ships repository support. The DGX operator defaults have separately been set to Astra/medium; the already completed composer task ran Astra/high. Activation of the new task fields in the running Von server and worker requires their normal rollout. No production web deployment is included.
Jira JVNAUTOSCI-2745