fix: bump coder/fantasy for gpt-5.6 Responses routing (#27132) - #27134
Conversation
gpt-5.6 models were unusable with agents: fantasy's Responses allowlist did not include the new family, so `IsResponsesModel` returned false and chatd fell back to the Chat Completions path (no reasoning params, no encrypted reasoning continuity). ## Changes - Bump the `charm.land/fantasy` replace pin to coder/fantasy `6da0c3b10237` (coder_2_33), pulling in: - coder/fantasy#46: route `gpt-5.6-sol`, `gpt-5.6-terra`, `gpt-5.6-luna` through the OpenAI Responses API as reasoning models. - coder/fantasy#41: surface Anthropic refusal stop_reason as content-filter (already on coder_2_33, rides along with the bump). - Update the fork changelog comment in go.mod. ## Verification - Probed all three gpt-5.6 models through the ai-gateway: `/v1/responses` with `reasoning.effort`, `include: ["reasoning.encrypted_content"]`, and `store: false` completes for each. - `go build ./coderd/...` and `go test ./coderd/x/chatd/chatopenai/ ./coderd/x/chatd/chatprovider/` pass against the new pin. > This PR was authored by Mux on Mike's behalf. (cherry picked from commit f84801e)
|
👋 Hey @ibetitsmike! This PR is targeting the Only bug fixes should be cherry-picked to release branches. If this is a bug fix, please update the PR title to match the conventional commit format: If this is not a bug fix, it likely should not target a release branch. |
There was a problem hiding this comment.
💡 Codex Review
Here are some automated review suggestions for this pull request.
Reviewed commit: b40412b7a0
ℹ️ About Codex in GitHub
Your team has set up Codex to review pull requests in this repo. Reviews are triggered when you
- Open a pull request for review
- Mark a draft as ready
- Comment "@codex review".
If Codex has suggestions, it will comment; otherwise it will react with 👍.
Codex can also answer questions or update the PR. Try commenting "@codex address that feedback".
| // 16) coder/fantasy#46, route the gpt-5.6 family (sol, terra, luna) | ||
| // through the OpenAI Responses API. | ||
| // See: https://github.com/coder/fantasy/commits/6da0c3b10237 | ||
| replace charm.land/fantasy => github.com/coder/fantasy v0.0.0-20260709180403-6da0c3b10237 |
There was a problem hiding this comment.
Add the GPT-5.6 Sol alias to the Responses pin
When admins configure the documented OpenAI alias gpt-5.6 for Sol, this bump still leaves that model off fantasy's exact-match Responses allowlist. chatopenai.UsesResponsesOptions delegates routing to fantasyopenai.IsResponsesModel(model.Model()), and the pinned fantasy commit adds only gpt-5.6-sol, gpt-5.6-terra, and gpt-5.6-luna, so the alias continues to take the Chat Completions path and loses reasoning/encrypted-continuity, which is the regression this backport is meant to fix.
Useful? React with 👍 / 👎.
Cherry-pick of #27132 (
f84801ee) ontorelease/2.35.gpt-5.6 models were unusable with agents: fantasy's Responses allowlist did not include the new family, so
IsResponsesModelreturned false and chatd fell back to the Chat Completions path (no reasoning params, no encrypted reasoning continuity).Changes
charm.land/fantasyreplace pin from2e3ddbca75ddto coder/fantasy6da0c3b10237(coder_2_33), pulling in:gpt-5.6-sol,gpt-5.6-terra,gpt-5.6-lunathrough the OpenAI Responses API as reasoning models.Backport safety
go build ./coderd/...andgo test ./coderd/x/chatd/{chatopenai,chatprovider,chatprompt,chatloop}/pass on this branch;go mod tidyis a no-op.