anomalyco/opencode
1
0
Fork 0
mirror of https://github.com/anomalyco/opencode.git synced 2026-07-23 02:36:57 -04:00
Code Issues 5.9k Packages Projects Releases 19 Wiki Activity

claude sonnet "thinking"? #784

New Issue
Open
opened 2026-02-16 17:28:18 -05:00 by yindo · 13 comments
yindo commented 2026-02-16 17:28:18 -05:00
Owner
Copy Link
Copy Source

Originally created by @jubishop on GitHub (Jul 17, 2025).

Originally assigned to: @thdxr on GitHub.

im not sure how to make open code use the claude sonnet thinking model with my claude pro plan? im using sonnet fine, but unclear how to make it "thinking".?

Originally created by @jubishop on GitHub (Jul 17, 2025). Originally assigned to: @thdxr on GitHub. im not sure how to make open code use the claude sonnet thinking model with my claude pro plan? im using sonnet fine, but unclear how to make it "thinking".?
yindo commented 2026-02-16 17:28:18 -05:00
Author
Owner
Copy Link
Copy Source

@almirsarajcic commented on GitHub (Jul 18, 2025):

Have you tried using the word "think" in your prompt?

Ask Claude to make a plan for how to approach a specific problem. We recommend using the word "think" to trigger extended thinking mode, which gives Claude additional computation time to evaluate alternatives more thoroughly. These specific phrases are mapped directly to increasing levels of thinking budget in the system: "think" < "think hard" < "think harder" < "ultrathink." Each level allocates progressively more thinking budget for Claude to use.

https://www.anthropic.com/engineering/claude-code-best-practices

Here's an example: https://opencode.ai/s/BT8v9iuG (in the middle, I ask it to think hard).

But yeah, it's not clear when it's using the thinking mode.
In Claude Code there's an indicator * Thinking. Maybe opencode should show thinking... instead of working... in that case.

@almirsarajcic commented on GitHub (Jul 18, 2025): Have you tried using the word "think" in your prompt? > Ask Claude to make a plan for how to approach a specific problem. We recommend using the word "think" to trigger extended thinking mode, which gives Claude additional computation time to evaluate alternatives more thoroughly. These specific phrases are mapped directly to increasing levels of thinking budget in the system: "think" < "think hard" < "think harder" < "ultrathink." Each level allocates progressively more thinking budget for Claude to use. https://www.anthropic.com/engineering/claude-code-best-practices Here's an example: https://opencode.ai/s/BT8v9iuG (in the middle, I ask it to think hard). But yeah, it's not clear when it's using the thinking mode. In Claude Code there's an indicator `* Thinking`. Maybe opencode should show `thinking...` instead of `working...` in that case.
yindo commented 2026-02-16 17:28:18 -05:00
Author
Owner
Copy Link
Copy Source

@jubishop commented on GitHub (Jul 18, 2025):

thanks for the info!

@jubishop commented on GitHub (Jul 18, 2025): thanks for the info!
yindo commented 2026-02-16 17:28:18 -05:00
Author
Owner
Copy Link
Copy Source

@thdxr commented on GitHub (Jul 18, 2025):

we don't support this yet but we're talking about how to implement it

@thdxr commented on GitHub (Jul 18, 2025): we don't support this yet but we're talking about how to implement it
yindo commented 2026-02-16 17:28:19 -05:00
Author
Owner
Copy Link
Copy Source

@nerdo commented on GitHub (Jul 30, 2025):

@thdxr To clarify, do you mean that extended thinking modes do not yet work, or is it opencode exposing Claude's thought process a-la * Thinking in Claude Code that isn't working... or both?

I'd love the extended thinking feedback, but I kind of rely on extended thinking for a lot of my work so I need to understand whether or not it's actually working or if I should wait until there is some basic support for extended thinking modes.

@nerdo commented on GitHub (Jul 30, 2025): @thdxr To clarify, do you mean that extended thinking modes do not yet work, or is it opencode exposing Claude's thought process a-la `* Thinking` in Claude Code that isn't working... or both? I'd love the extended thinking feedback, but I kind of rely on extended thinking for a lot of my work so I need to understand whether or not it's actually working or if I should wait until there is some basic support for extended thinking modes.
yindo commented 2026-02-16 17:28:19 -05:00
Author
Owner
Copy Link
Copy Source

@IV2KBMoFxYIA commented on GitHub (Aug 21, 2025):

@thdxr To clarify, do you mean that extended thinking modes do not yet work, or is it opencode exposing Claude's thought process a-la * Thinking in Claude Code that isn't working... or both?

I'd love the extended thinking feedback, but I kind of rely on extended thinking for a lot of my work so I need to understand whether or not it's actually working or if I should wait until there is some basic support for extended thinking modes.

@thdxr any reply on this? it's a pretty important distinction.

@IV2KBMoFxYIA commented on GitHub (Aug 21, 2025): > [@thdxr](https://github.com/thdxr) To clarify, do you mean that extended thinking modes do not yet work, or is it opencode exposing Claude's thought process a-la `* Thinking` in Claude Code that isn't working... or both? > > I'd love the extended thinking feedback, but I kind of rely on extended thinking for a lot of my work so I need to understand whether or not it's actually working or if I should wait until there is some basic support for extended thinking modes. @thdxr any reply on this? it's a pretty important distinction.
yindo commented 2026-02-16 17:28:19 -05:00
Author
Owner
Copy Link
Copy Source

@rekram1-node commented on GitHub (Aug 21, 2025):

We now have thinking blocks @IV2KBMoFxYIA, we need better documentation but w/ anthropic models we do not have thinking enabled by default, I will comment a config here of how to do it and then I will probably update docs too

/thinking will make thinking blocks show

they look like:

Image
@rekram1-node commented on GitHub (Aug 21, 2025): We now have thinking blocks @IV2KBMoFxYIA, we need better documentation but w/ anthropic models we do not have thinking enabled by default, I will comment a config here of how to do it and then I will probably update docs too /thinking will make thinking blocks show they look like: <img width="1020" height="424" alt="Image" src="https://github.com/user-attachments/assets/dca0a949-4a6b-4281-a0dd-6f489bf280da" />
yindo commented 2026-02-16 17:28:19 -05:00
Author
Owner
Copy Link
Copy Source

@nerdo commented on GitHub (Aug 22, 2025):

Please do so! I've been waiting for this! Better yet, just update the docs and link it here.

@nerdo commented on GitHub (Aug 22, 2025): Please do so! I've been waiting for this! Better yet, just update the docs and link it here.
yindo commented 2026-02-16 17:28:19 -05:00
Author
Owner
Copy Link
Copy Source

@rekram1-node commented on GitHub (Aug 25, 2025):

@nerdo here is how you can set it in your opencode.json for anthropic:

"provider": {
    "anthropic": {
      "name": "Anthropic",
      "models": {
        "claude-sonnet-4-20250514": {
          "options": {
            "thinking": {
              "type": "enabled",
              "budgetTokens": 16000
            }
          }
        }
      }
    }
  }
@rekram1-node commented on GitHub (Aug 25, 2025): @nerdo here is how you can set it in your opencode.json for anthropic: ``` "provider": { "anthropic": { "name": "Anthropic", "models": { "claude-sonnet-4-20250514": { "options": { "thinking": { "type": "enabled", "budgetTokens": 16000 } } } } } } ```
yindo commented 2026-02-16 17:28:19 -05:00
Author
Owner
Copy Link
Copy Source

@nerdo commented on GitHub (Aug 26, 2025):

So it's permanently on all the time?

On Mon, Aug 25, 2025 at 11:00 AM Aiden Cline @.***>
wrote:

rekram1-node left a comment (sst/opencode#1106)
https://github.com/sst/opencode/issues/1106#issuecomment-3220642796

@nerdo https://github.com/nerdo here is how you can set it in your
opencode.json for anthropic:

"provider": {
"anthropic": {
"name": "Anthropic",
"models": {
"claude-sonnet-4-20250514": {
"options": {
"thinking": {
"type": "enabled",
"budgetTokens": 16000
}
}
}
}
}
}

—
Reply to this email directly, view it on GitHub
https://github.com/sst/opencode/issues/1106#issuecomment-3220642796, or
unsubscribe
https://github.com/notifications/unsubscribe-auth/AAH32TSNKLJ6G5VBITLS5VL3PMQH7AVCNFSM6AAAAACBZC2RVGVHI2DSMVQWIX3LMV43OSLTON2WKQ3PNVWWK3TUHMZTEMRQGY2DENZZGY
.
You are receiving this because you were mentioned.Message ID:
@.***>

@nerdo commented on GitHub (Aug 26, 2025): So it's permanently on all the time? On Mon, Aug 25, 2025 at 11:00 AM Aiden Cline ***@***.***> wrote: > *rekram1-node* left a comment (sst/opencode#1106) > <https://github.com/sst/opencode/issues/1106#issuecomment-3220642796> > > @nerdo <https://github.com/nerdo> here is how you can set it in your > opencode.json for anthropic: > > "provider": { > "anthropic": { > "name": "Anthropic", > "models": { > "claude-sonnet-4-20250514": { > "options": { > "thinking": { > "type": "enabled", > "budgetTokens": 16000 > } > } > } > } > } > } > > — > Reply to this email directly, view it on GitHub > <https://github.com/sst/opencode/issues/1106#issuecomment-3220642796>, or > unsubscribe > <https://github.com/notifications/unsubscribe-auth/AAH32TSNKLJ6G5VBITLS5VL3PMQH7AVCNFSM6AAAAACBZC2RVGVHI2DSMVQWIX3LMV43OSLTON2WKQ3PNVWWK3TUHMZTEMRQGY2DENZZGY> > . > You are receiving this because you were mentioned.Message ID: > ***@***.***> >
yindo commented 2026-02-16 17:28:19 -05:00
Author
Owner
Copy Link
Copy Source

@rekram1-node commented on GitHub (Aug 26, 2025):

I recall Dax mentioning wanting to add a better DX for doing it dynamically but rn it is by config only

@rekram1-node commented on GitHub (Aug 26, 2025): I recall Dax mentioning wanting to add a better DX for doing it dynamically but rn it is by config only
yindo commented 2026-02-16 17:28:19 -05:00
Author
Owner
Copy Link
Copy Source

@iamhenry commented on GitHub (Nov 5, 2025):

@rekram1-node is the thinking block missing from the new v1.0+?

@iamhenry commented on GitHub (Nov 5, 2025): @rekram1-node is the thinking block missing from the new `v1.0+`?
yindo commented 2026-02-16 17:28:19 -05:00
Author
Owner
Copy Link
Copy Source

@rekram1-node commented on GitHub (Nov 5, 2025):

@iamhenry there is one:

Image

One may argue it is non obvious if it is an assistant message vs reasoning one.

Here is share link too: https://opencode.ai/s/z6QQSSh9

@rekram1-node commented on GitHub (Nov 5, 2025): @iamhenry there is one: <img width="769" height="332" alt="Image" src="https://github.com/user-attachments/assets/a9dff45c-0cd0-4d9d-8226-20e888bd762c" /> One may argue it is non obvious if it is an assistant message vs reasoning one. Here is share link too: https://opencode.ai/s/z6QQSSh9
yindo commented 2026-02-16 17:28:19 -05:00
Author
Owner
Copy Link
Copy Source

@iamhenry commented on GitHub (Nov 5, 2025):

Here is share link too: https://opencode.ai/s/z6QQSSh9

Ah, yes. It just wasn't clear I guess. Thanks!

@iamhenry commented on GitHub (Nov 5, 2025): > Here is share link too: https://opencode.ai/s/z6QQSSh9 Ah, yes. It just wasn't clear I guess. Thanks!
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
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#784
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?