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

Reasoning Effort Levels Not Reflected for OpenAI Models (GPT-5.2-Codex Extra Level Missing) #7228

New Issue
Closed
opened 2026-02-16 18:06:31 -05:00 by yindo · 1 comment
yindo commented 2026-02-16 18:06:31 -05:00
Owner
Copy Link
Copy Source

Originally created by @murtazaairesearcher on GitHub (Jan 22, 2026).

Originally assigned to: @thdxr on GitHub.

Question

GitHub Copilot recently introduced configurable reasoning-effort levels for OpenAI models. In OpenCode, I can see similar options—Low, Medium, and High—but it’s unclear whether these settings are actually applied, as they appear to have existed prior to Copilot’s recent update.

Additionally, GPT-5.2-Codex supports an extra reasoning-effort level beyond the standard Low/Medium/High options. Currently, this additional level does not appear to be exposed or configurable in OpenCode.

Questions

Are the existing reasoning-effort options (Low / Medium / High) in OpenCode actively mapped to the underlying OpenAI model parameters?

If so, how can this be verified or observed in practice?

Is it possible to expose and support the additional reasoning-effort level that GPT-5.2-Codex provides?

Originally created by @murtazaairesearcher on GitHub (Jan 22, 2026). Originally assigned to: @thdxr on GitHub. ### Question GitHub Copilot recently introduced configurable reasoning-effort levels for OpenAI models. In OpenCode, I can see similar options—Low, Medium, and High—but it’s unclear whether these settings are actually applied, as they appear to have existed prior to Copilot’s recent update. Additionally, GPT-5.2-Codex supports an extra reasoning-effort level beyond the standard Low/Medium/High options. Currently, this additional level does not appear to be exposed or configurable in OpenCode. Questions Are the existing reasoning-effort options (Low / Medium / High) in OpenCode actively mapped to the underlying OpenAI model parameters? If so, how can this be verified or observed in practice? Is it possible to expose and support the additional reasoning-effort level that GPT-5.2-Codex provides?
yindo added the zen label 2026-02-16 18:06:31 -05:00
yindo closed this issue 2026-02-16 18:06:31 -05:00
yindo commented 2026-02-16 18:06:31 -05:00
Author
Owner
Copy Link
Copy Source

@github-actions[bot] commented on GitHub (Jan 22, 2026):

This issue might be a duplicate of existing issues. Please check:

  • #450: Support for reasoning_effort parameter in UI - Early feature request for reasoning_effort implementation in UI for supported models
  • #9818: xhigh not available for GPT-5.2 or GPT-5.2-Codex via Github CoPilot - Reports missing 'xhigh' reasoning level for these models
  • #8123: I can't set the effort when configuring a sub-agent! - Addresses the inability to configure reasoning effort/variants for sub-agents
  • #6864: No reasoning at all through Github Copilot provider - Reports that reasoning/thinking configuration doesn't seem to work with Github Copilot

Feel free to ignore if your specific case addresses something different from these existing issues.

@github-actions[bot] commented on GitHub (Jan 22, 2026): This issue might be a duplicate of existing issues. Please check: - #450: Support for reasoning_effort parameter in UI - Early feature request for reasoning_effort implementation in UI for supported models - #9818: xhigh not available for GPT-5.2 or GPT-5.2-Codex via Github CoPilot - Reports missing 'xhigh' reasoning level for these models - #8123: I can't set the effort when configuring a sub-agent! - Addresses the inability to configure reasoning effort/variants for sub-agents - #6864: No reasoning at all through Github Copilot provider - Reports that reasoning/thinking configuration doesn't seem to work with Github Copilot Feel free to ignore if your specific case addresses something different from these existing issues.
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 zen
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#7228
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?