prompt is too long unrecoverable

[benceferdinandy-signifyd]

Description

Opencode with Opus 4.5 often gives me prompt is too long: 209549 tokens > 200000 maximum. This is completely unrecoverable, short of rolling back the session or forking and you then need to compact or something.

Note I'm only at: 121,480 61% ($5.62)

OpenCode version

1.0.119

Steps to reproduce

Use Antropic api key with Opus 4.5, trigger a huge search for example in the primary agent.

Screenshot and/or share link

No response

Operating System

macos

Terminal

ghostty

[github-actions]

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

• AI_APICallError: prompt is too long #1092: AI_APICallError: prompt is too long - Nearly identical error with Opus model causing unrecoverable session state
• AI_APICallError: prompt is too long &  AI_APICallError: OAuth token has been revoked. Please obtain a new token. #164: AI_APICallError: prompt is too long & OAuth error - Exact same token overflow error (201082 > 200000) with Anthropic Opus
• [v0.1.162] [Anthropic: Claude Sonnet 4]: AI_APICallError: input length and 'max_tokens' exceed context limit: 140740 + 64000 > 200000, decrease input length or 'max_tokens and try again #491: input length and 'max_tokens' exceed context limit - Same context window calculation issue with Anthropic models
• AT_APICallError: prompt token count of 130389 exceeds the limit of 128000 #2464: AT_APICallError: prompt token count exceeds limit - Similar token overflow blocking work (130389 > 128000)
• bufio.Scanner: token too long #3409: Opencode stuck after token too long - Token overflow causing stuck/unrecoverable state
• Fetched documentation exeeds context window limit - Automatic truncation possible? #1212: Fetched documentation exceeds context window limit - Context window overflow from tool outputs
• [Question] Is automatic tool calling output truncation supported? #4826: Is automatic tool calling output truncation supported? - Root cause discussion about tools generating huge outputs

All these issues share the same core problem: context window overflow leading to unrecoverable sessions. Feel free to ignore if your case has specific differences!

[menoatree]

I had this happen today aswell when the main agent tried to webfetch the openrouter model list

% WebFetch https://openrouter.ai/api/v1/models
prompt is too long: 206917 tokens > 200000 maximum

[Nindaleth]

@menoatree That URL returns over 450 kB of data for me, that must be around 100,000 tokens of context.

[ben-vargas]

Yeah, see that #5360 issue where i added comments, there are tool calls like webfetch and mcp tools that are not truncated and if the source being webfetched or mcp tool scraped with something like firecrawl, it can easily cause the context window to be exceeded which results in this error with opus 4.5.