cli(ux): Show active context length in CLI #2315
Merged
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
dbraduan
changed the title
dbraduan
commented
Apr 23, 2025
crates/goose-cli/src/session/mod.rs
Outdated
|
|
||
| // Calculate system prompt tokens (approximate using a simpler system prompt) | ||
| // Since we can't directly access the built system prompt | ||
| let system_prompt = "You are an AI assistant."; |
Contributor
Author
There was a problem hiding this comment.
This is a hack to get it working for now, we should probably load context prompt similar to how we do it truncate.rs
crates/goose-cli/src/session/mod.rs
Outdated
| .provider() | ||
| .get_model_config() | ||
| .context_limit | ||
| .unwrap_or(32000); // Default to 32k if not specified |
Contributor
Author
There was a problem hiding this comment.
Similar to truncate.rs, perhaps there could be one place where this is exposed, but don't have that much of knowledge about the codebase yet to tell where that should be.
dbraduan
changed the title
dbraduan
commented
May 1, 2025
crates/goose/src/model.rs
Outdated
Comment on lines
81
to
85
| name if name.contains("gpt-4.1") | ||
| || name.contains("gpt-4-1") | ||
| || name.contains("gpt-41") => | ||
| { | ||
| Some(1_000_000) |
Contributor
Author
There was a problem hiding this comment.
This might be just a thing for our internal proxies, let me know if that's not a good addition, can remove.
baxen
reviewed
May 5, 2025
crates/goose-cli/src/session/mod.rs
Outdated
| all_tools.extend(toolshim_tools.iter().cloned()); | ||
|
|
||
| // Create a token counter using the same tokenizer as the model | ||
| let token_counter = TokenCounter::new(model_config.tokenizer_name()); |
Collaborator
There was a problem hiding this comment.
the token counting i think can be somewhat slow and inaccurate (the anthropic ones are proprietary and we've seen our estimates be off by as much as 30%). Instead i think we can save the current token usage from the most recent model inference? that way we know more exactly and don't spend any extra time on it during the iteration loop
dbraduan
changed the title
salman1993
approved these changes
May 28, 2025
Collaborator
|
hey @dbraduan - couple of merge conflicts to address |
Contributor
Author
|
should be good to go, @angiejones ? |
katzdave
added a commit
to katzdave/goose
that referenced
this pull request
Jun 3, 2025
* upstream/main: Feat: Refined the documentation for Goose (block#2751) mcp(developer): add fallback on .gitignore if no .gooseignore is present (block#2661) cli(ux): Show active context length in CLI (block#2315) cli(config): Add GOOSE_CONTEXT_STRATEGY setting (block#2666) fix: new models have different messages for context length exceeded (block#2763)
lifeizhou-ap
added a commit
that referenced
this pull request
Jun 4, 2025
* main: fix: pr comment build cli workflow (#2774) hotfix: don't always run prompt (#2773) Lifei/test workflow (#2772) chore: use hermit to install node, rust and protoc (#2766) Feat: Refined the documentation for Goose (#2751) mcp(developer): add fallback on .gitignore if no .gooseignore is present (#2661) cli(ux): Show active context length in CLI (#2315) cli(config): Add GOOSE_CONTEXT_STRATEGY setting (#2666) fix: new models have different messages for context length exceeded (#2763) fix: increase limit for direct to disk for performance (#2762) Revert "chore: use hermit in goose" (#2759) alexhancock/remove-settings-v1 (#2744) blog: Democratizing Detection Engineering at Block with Goose and Panther MCP (#2746)
michaelneale
added a commit
that referenced
this pull request
Jun 5, 2025
* main: (82 commits) feat: lead/worker model (#2719) fix: pass ref in pr comment workflow (#2777) feat: goose web for local terminal alternative (#2718) chore: run CI on merge_group (#2786) fix: Don't break from consuming subprocess output in shell tool until both streams are done (#2771) Add retries w/ exponential backoff for databricks provider (#2764) Fix paths in google drive mcp documentation (#2775) testing windows build (#2770) docs: Add Context7 YouTube Video (#2779) cli(command): Add `export` command to CLI for markdown export of sessions (#2533) fix(copilot): gh copilot auth token conflicts w/ gh mcp env var (#2743) feat(providers): Add support for Gemini 2.5 Flash Preview and Pro Preview models (#2780) fix: pr comment build cli workflow (#2774) hotfix: don't always run prompt (#2773) Lifei/test workflow (#2772) chore: use hermit to install node, rust and protoc (#2766) Feat: Refined the documentation for Goose (#2751) mcp(developer): add fallback on .gitignore if no .gooseignore is present (#2661) cli(ux): Show active context length in CLI (#2315) cli(config): Add GOOSE_CONTEXT_STRATEGY setting (#2666) ...
iandouglas
pushed a commit
that referenced
this pull request
Jun 5, 2025
Co-authored-by: Angie Jones <jones.angie@gmail.com>
cbruyndoncx
pushed a commit
to cbruyndoncx/goose
that referenced
this pull request
Jul 20, 2025
Co-authored-by: Angie Jones <jones.angie@gmail.com>
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
4 participants
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Exposing # of tokens used in a last message(total_tokens = input_tokens + output_tokens) to the end user for UX improvement.
How this looks like:
