Sessions fail after viewing more than 5 files with Bedrock provider

[cjohnhanson]

Describe the bug
Goose sessions using Bedrock fail after viewing more than 5 files. This happens because Bedrock's API has a hard limit of 5 document attachments per request.

To Reproduce

1. Use Goose with Bedrock provider
2. View files using the text_editor view command
3. Try to view more than 5 files in the same session
4. The session fails with:

{
  "message": "You can't include more than 5 documents in a request.
Reduce the number of documents and retry your request.",
  "code": "ValidationException",
  "aws_request_id": "XXXX-XXXX-XXXX-XXXX"
}

Expected behavior
Session should be able to maintain functionality and context while viewing multiple files, working within or around Bedrock's document limit.

Please provide following information:

• OS & Arch: MacOS (affects all platforms)
• Interface: CLI
• Version: 1.0.5+
• Extensions enabled: developer
• Provider & Model: AWS Bedrock, anthropic.claude-3-5-sonnet-20241022-v2:0 (but would occur with any Bedrock model)

Additional context
Looking at the Bedrock API docs, this appears to bea core limitation of their API:

"You can include up to five documents. Each document's size must be no more than 4.5 MB."

The issue seems to be in:

• crates/goose-mcp/src/developer/mod.rs - text_editor_view function
• crates/goose/src/providers/formats/bedrock.rs - document handling

Currently I manage this in my goosehints by prompting to cat files via the shell tool when looking at more than 5 files. This isn't very robust. When I inevitably hit the issue again, I just open up the session file and manually clean up the history, then prompt to usecat moving forward.

I can think of a couple approaches but I'm not sure which would be best:

1. Just use regular text content instead of documents for Bedrock
2. Track document count and clean up old ones or switch to plain text content after 5 documents

Not sure how this works for other providers besides Bedrock and I'm also not totally sure yet what the token usage/cost implications would be of using regular text content vs. document blocks for this.

Happy to attempt a PR with one of the above approaches as well, but very new to this codebase so interested to hear alternative approaches or reasons why either of these proposed solutions are infeasible.

[lily-de]

Is the session erroring out? What would be the downside of failing gracefully to avoid a session breaking error?

Actually perhaps I don't understand the mechanism of failure -- is it 5+ files all at once in a single request to Bedrock? Or 5+ files throughout the course of a session using Bedrock? We use AWS Bedrock ourselves at Block, so I am surprised haven't heard of this issue before from other users at the company

[VasilijP]

Same issue with claude 3.7 and Bedrock, goose 1.0.9, running on Ubuntu.

2025-02-26T19:16:46.423927Z ERROR goose::agents::truncate: Error: Server error: Failed to call Bedrock: ValidationException(ValidationException { message: Some("You can’t include more than 5 documents in a request. Reduce the number of documents and retry your request."), meta: ErrorMetadata { code: Some("ValidationException"), message: Some("You can’t include more than 5 documents in a request. Reduce the number of documents and retry your request."), extras: Some({"aws_request_id": "..."}) } })
    at crates/goose/src/agents/truncate.rs:279

Ran into this error: Server error: Failed to call Bedrock: ValidationException(ValidationException { message: Some("You can’t include more than 5 documents in a request. Reduce the number of do
cuments and retry your request."), meta: ErrorMetadata { code: Some("ValidationException"), message: Some("You can’t include more than 5 documents in a request. Reduce the number of documents a
nd retry your request."), extras: Some({"aws_request_id": "..."}) } }).

This error appeared after another context related one (same setup):

 2025-02-26T19:15:19.378027Z ERROR goose::agents::truncate: Error: Execution error: content was missing: content was not specified but it is required when building ToolResultBlock
    at crates/goose/src/agents/truncate.rs:279

Ran into this error: Execution error: content was missing: content was not specified but it is required when building ToolResultBlock.

Another related problem: adding of unsupported file type (shell script in this case) is also causing the error at the same source location:

 2025-02-26T21:50:09.799646Z ERROR goose::agents::truncate: Error: Server error: Failed to call Bedrock: ValidationException(ValidationException { message: Some("Unsupported MIME type: application/x-sh. Retry your request with a supported file type: xlsx, txt, pdf, csv, md, doc, html, xls, docx"), meta: ErrorMetadata { code: Some("ValidationException"), message: Some("Unsupported MIME type: application/x-sh. Retry your request with a supported file type: xlsx, txt, pdf, csv, md, doc, html, xls, docx"), extras: Some({"aws_request_id": "..."}) } })
    at crates/goose/src/agents/truncate.rs:279

Ran into this error: Server error: Failed to call Bedrock: ValidationException(ValidationException { message: Some("Unsupported MIME type: application/x-sh. Retry your request with a supported
file type: xlsx, txt, pdf, csv, md, doc, html, xls, docx"), meta: ErrorMetadata { code: Some("ValidationException"), message: Some("Unsupported MIME type: application/x-sh. Retry your request w
ith a supported file type: xlsx, txt, pdf, csv, md, doc, html, xls, docx"), extras: Some({"aws_request_id": "..."}) } }).

This is not a transient problem, it reoccurs after resuming the session.