feat(opencode): add gpt-5.5 with xhigh reasoning variant#12
Merged
Jose-Sabater merged 1 commit intomainfrom May 7, 2026
Merged
feat(opencode): add gpt-5.5 with xhigh reasoning variant#12Jose-Sabater merged 1 commit intomainfrom
Jose-Sabater merged 1 commit intomainfrom
Conversation
GPT-5.5 supports a fifth reasoning_effort tier ("xhigh") that opencode's
built-in dropdown (default | low | medium | high) doesn't expose. Adding
the model with `reasoning: true` plus a `variants: { xhigh }` block makes
all five tiers selectable out of the box for fresh installs, instead of
each user having to discover and add the variant locally.
Pricing/context taken from data/models/openai.yaml (input $5 / output $30
per Mtok, 1.05M context, 128k output) so the picker matches Opper's
authoritative values.
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Summary
gpt-5.5to the opencode provider template (data/opencode.json).reasoning: trueso opencode's reasoning-effort picker is enabled.variants: { xhigh }block — opencode's built-in picker only exposesdefault | low | medium | high, so without this users can't reach gpt-5.5's fifth tier without editing~/.config/opencode/opencode.jsonthemselves.Why now
Customer hit this through opencode while exploring gpt-5.5: the picker showed four tiers, the model docs (and Opper's YAML) list five. xhigh is the right tier for the hardest async/eval workloads on gpt-5.5. Shipping it in the template is one less hand-edit for everyone.
Numbers
Pricing and context limits taken from
task-api/data/models/openai.yaml(the authoritative source) — input $5 / output $30 per Mtok, 1.05M context, 128k output.Test plan
npx vitest run— all 317 tests passpython3 -c "import json; json.load(...)")default | low | medium | high | xhigh