Problem
I'm using Opus 4.6 via Amazon Bedrock in OpenCode. Auto-compaction is not happening, resulting in broken sessions.
Claude suggests this is an issue with models.dev reporting the Anthropic token limit rather than the Bedrock one.
In a session, at the top of the sidebar I see "200,084 tokens" and "20% used", indicating a 1M token limit.
But at this point the session has the error undefined: The model returned the following errors: prompt is too long: 200148 tokens > 200000 maximum.
If I try to manually /compact, that fails too: undefined: The model returned the following errors: messages.5.content.6: thinkingorredacted_thinking blocks in the latest assistant message cannot be modified. These blocks must remain as they were in the original response.
The only thing I can do is abandon the session.
Expected Behavior
OpenCode should use the correct 200k token limit that Bedrock uses (maybe by fixing what models.dev reports).
Workaround
Override the limit in ~/.config/opencode/opencode.json:
{
"provider": {
"amazon-bedrock": {
"models": {
"us.anthropic.claude-opus-4-6-v1": {
"limit": {
"context": 200000,
"output": 32000
}
}
}
}
}
}
With this, in a new session I see 20k tokens and "10% used".
Plugins
None
OpenCode version
1.2.20
Steps to reproduce
- Use Claude Opus 4.6 via Amazon Bedrock
- Continue session until 200k tokens are used
Screenshot and/or share link
Operating System
MacOS Tahoe 26.3
Terminal
iTerm2 3.6.8
Problem
I'm using Opus 4.6 via Amazon Bedrock in OpenCode. Auto-compaction is not happening, resulting in broken sessions.
Claude suggests this is an issue with models.dev reporting the Anthropic token limit rather than the Bedrock one.
In a session, at the top of the sidebar I see "200,084 tokens" and "20% used", indicating a 1M token limit.
But at this point the session has the error
undefined: The model returned the following errors: prompt is too long: 200148 tokens > 200000 maximum.If I try to manually
/compact, that fails too:undefined: The model returned the following errors: messages.5.content.6:thinkingorredacted_thinkingblocks in the latest assistant message cannot be modified. These blocks must remain as they were in the original response.The only thing I can do is abandon the session.
Expected Behavior
OpenCode should use the correct 200k token limit that Bedrock uses (maybe by fixing what models.dev reports).
Workaround
Override the limit in
~/.config/opencode/opencode.json:{ "provider": { "amazon-bedrock": { "models": { "us.anthropic.claude-opus-4-6-v1": { "limit": { "context": 200000, "output": 32000 } } } } } }With this, in a new session I see 20k tokens and "10% used".
Plugins
None
OpenCode version
1.2.20
Steps to reproduce
Screenshot and/or share link
Operating System
MacOS Tahoe 26.3
Terminal
iTerm2 3.6.8