anomalyco/opencode
1
0
Fork 0
mirror of https://github.com/anomalyco/opencode.git synced 2026-07-22 18:25:32 -04:00
Code Issues 5.9k Packages Projects Releases 19 Wiki Activity

Opus 4.5 selection serves Sonnet 4 instead - subscription routing bug #3392

New Issue
Closed
opened 2026-02-16 17:39:55 -05:00 by yindo · 10 comments
yindo commented 2026-02-16 17:39:55 -05:00
Owner
Copy Link
Copy Source

Originally created by @simmonsgoku337-wq on GitHub (Dec 8, 2025).

Description

OpenCode is serving the wrong Claude model for subscription users.
When claude-opus-4-5-20251101 is selected, the system serves claude-sonnet-4-20250514 instead.

Evidence:

  1. Model selection confirms Opus 4.5:
    // ~/.local/state/opencode/model.json
    {recent:[{providerID:anthropic,modelID:claude-opus-4-5-20251101}]}

  2. Model identifies as Sonnet 4:
    I'm Claude Sonnet 4 (claude-sonnet-4-20250514)

  3. Knowledge cutoff confirms wrong model:

    • Expected (Opus 4.5): January 2025
    • Actual: April 2024 (Sonnet 3.5/3.6 range)

Related: Issue #3063 was similar but dismissed as "models lying." Knowledge cutoffs are factual and cannot be misrepresented.

OpenCode version

1.0.134

Steps to reproduce

  1. Select claude-opus-4-5-20251101
  2. Ask: "What model are you?" and "What is your knowledge cutoff date?"
  3. Model reports as Sonnet with April 2024 cutoff

Environment:

  • OpenCode: 1.0.134
  • Provider: Anthropic subscription
  • OS: Linux

Screenshot and/or share link

No response

Operating System

Ubuntu 24.04.3 LTS

Terminal

VS Code integrated terminal

Originally created by @simmonsgoku337-wq on GitHub (Dec 8, 2025). ### Description OpenCode is serving the wrong Claude model for subscription users. When claude-opus-4-5-20251101 is selected, the system serves claude-sonnet-4-20250514 instead. Evidence: 1. Model selection confirms Opus 4.5: // ~/.local/state/opencode/model.json {recent:[{providerID:anthropic,modelID:claude-opus-4-5-20251101}]} 2. Model identifies as Sonnet 4: I'm Claude Sonnet 4 (claude-sonnet-4-20250514) 3. Knowledge cutoff confirms wrong model: - Expected (Opus 4.5): January 2025 - Actual: April 2024 (Sonnet 3.5/3.6 range) Related: Issue #3063 was similar but dismissed as "models lying." Knowledge cutoffs are factual and cannot be misrepresented. ### OpenCode version 1.0.134 ### Steps to reproduce 1. Select claude-opus-4-5-20251101 2. Ask: "What model are you?" and "What is your knowledge cutoff date?" 3. Model reports as Sonnet with April 2024 cutoff Environment: - OpenCode: 1.0.134 - Provider: Anthropic subscription - OS: Linux ### Screenshot and/or share link _No response_ ### Operating System Ubuntu 24.04.3 LTS ### Terminal VS Code integrated terminal
yindo added the bug label 2026-02-16 17:39:55 -05:00
yindo closed this issue 2026-02-16 17:39:55 -05:00
yindo commented 2026-02-16 17:39:55 -05:00
Author
Owner
Copy Link
Copy Source

@github-actions[bot] commented on GitHub (Dec 8, 2025):

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

  • #3063: Model identity incorrectly reported - Claude/OAuth issue (similar issue where Sonnet was reported instead of the selected model, with discussion of OAuth workflow mismatch)

Feel free to ignore if this doesn't address your specific case.

@github-actions[bot] commented on GitHub (Dec 8, 2025): This issue might be a duplicate of existing issues. Please check: - #3063: Model identity incorrectly reported - Claude/OAuth issue (similar issue where Sonnet was reported instead of the selected model, with discussion of OAuth workflow mismatch) Feel free to ignore if this doesn't address your specific case.
yindo commented 2026-02-16 17:39:55 -05:00
Author
Owner
Copy Link
Copy Source

@rekram1-node commented on GitHub (Dec 8, 2025):

Knowledge cutoffs are factual and cannot be misrepresented.

This is not accurate from my testing

@rekram1-node commented on GitHub (Dec 8, 2025): > Knowledge cutoffs are factual and cannot be misrepresented. This is not accurate from my testing
yindo commented 2026-02-16 17:39:55 -05:00
Author
Owner
Copy Link
Copy Source

@rekram1-node commented on GitHub (Dec 8, 2025):

Yup just tested, this is indeed the model lying

@rekram1-node commented on GitHub (Dec 8, 2025): Yup just tested, this is indeed the model lying
yindo commented 2026-02-16 17:39:55 -05:00
Author
Owner
Copy Link
Copy Source

@rekram1-node commented on GitHub (Dec 8, 2025):

Use mitm proxy to validate correct model is being picked:

Image

Replicated the model lying
Image

@rekram1-node commented on GitHub (Dec 8, 2025): Use mitm proxy to validate correct model is being picked: <img width="1025" height="477" alt="Image" src="https://github.com/user-attachments/assets/42c9801c-3eb9-43a7-81ac-c3f666617339" /> Replicated the model lying <img width="1158" height="453" alt="Image" src="https://github.com/user-attachments/assets/16cc6136-cfb1-44ce-bc7d-b8271a01e17c" />
yindo commented 2026-02-16 17:39:55 -05:00
Author
Owner
Copy Link
Copy Source

@rekram1-node commented on GitHub (Dec 8, 2025):

claude code puts in their system prompt:

"You are "
"Your knowledge cutoff is "

We don't have that and maybe we should add it because people keep asking this

@rekram1-node commented on GitHub (Dec 8, 2025): claude code puts in their system prompt: "You are <model>" "Your knowledge cutoff is <date>" We don't have that and maybe we should add it because people keep asking this
yindo commented 2026-02-16 17:39:55 -05:00
Author
Owner
Copy Link
Copy Source

@rekram1-node commented on GitHub (Dec 8, 2025):

But I just validated this is indeed not an issue, it is just model lying

@rekram1-node commented on GitHub (Dec 8, 2025): But I just validated this is indeed not an issue, it is just model lying
yindo commented 2026-02-16 17:39:55 -05:00
Author
Owner
Copy Link
Copy Source

@simmonsgoku337-wq commented on GitHub (Dec 8, 2025):

That is indeed strange haha. Thanks for checking it out @rekram1-node
Perhaps its better to put a 'knowledge cutoff' in there. Its extremely confusing otherwise, and would prevent further issues.
Thanks again!

@simmonsgoku337-wq commented on GitHub (Dec 8, 2025): That is indeed strange haha. Thanks for checking it out @rekram1-node Perhaps its better to put a 'knowledge cutoff' in there. Its extremely confusing otherwise, and would prevent further issues. Thanks again!
yindo commented 2026-02-16 17:39:55 -05:00
Author
Owner
Copy Link
Copy Source

@abdullah-orangevest commented on GitHub (Dec 13, 2025):

still not working on latest version

@abdullah-orangevest commented on GitHub (Dec 13, 2025): still not working on latest version
yindo commented 2026-02-16 17:39:55 -05:00
Author
Owner
Copy Link
Copy Source

@rekram1-node commented on GitHub (Dec 13, 2025):

@abdullah-orangevest please explain? Did you read the previous messages in this thread, a model cannot be counted on to say what it is they lie!

@rekram1-node commented on GitHub (Dec 13, 2025): @abdullah-orangevest please explain? Did you read the previous messages in this thread, a model cannot be counted on to say what it is they lie!
yindo commented 2026-02-16 17:39:55 -05:00
Author
Owner
Copy Link
Copy Source

@abdullah-orangevest commented on GitHub (Dec 17, 2025):

@rekram1-node i chose Opus 4.5 it said sonnet. i started using it and it was hitting my sonnet usage on my Claude usage tracker.

@abdullah-orangevest commented on GitHub (Dec 17, 2025): @rekram1-node i chose Opus 4.5 it said sonnet. i started using it and it was hitting my sonnet usage on my Claude usage tracker.
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 bug
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#3392
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?