You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
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".?
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.
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.
Reacted by Justin Bishop, Tyler C Laprade, CFA and Divanshu Chauhan
@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.
Reacted by Alexandr, Andy Yao, Nathan Luk and Alexander RGF2aWxh==
@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.
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
Activity
almirsarajcic commentedon Jul 18, 2025
Have you tried using the word "think" in your prompt?
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 showthinking...instead ofworking...in that case.jubishop commentedon Jul 18, 2025
thanks for the info!
thdxr commentedon Jul 18, 2025
we don't support this yet but we're talking about how to implement it
nerdo commentedon 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
* Thinkingin 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.
IV2KBMoFxYIA commentedon Aug 21, 2025
@thdxr any reply on this? it's a pretty important distinction.
rekram1-node commentedon 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:
nerdo commentedon Aug 22, 2025
Please do so! I've been waiting for this! Better yet, just update the docs and link it here.
rekram1-node commentedon Aug 25, 2025
@nerdo here is how you can set it in your opencode.json for anthropic:
nerdo commentedon Aug 26, 2025
rekram1-node commentedon Aug 26, 2025
I recall Dax mentioning wanting to add a better DX for doing it dynamically but rn it is by config only
iamhenry commentedon Nov 5, 2025
@rekram1-node is the thinking block missing from the new
v1.0+?rekram1-node commentedon Nov 5, 2025
@iamhenry there is one:
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
iamhenry commentedon Nov 5, 2025
Ah, yes. It just wasn't clear I guess. Thanks!
fix(settings): align authorized folders dark mode (anomalyco#1106)