Do not derive model context from prompt and output token limits
Nobody has claimed this yet.
Assessment
- Difficulty
- 2/5
- Estimated time
- 1-3 hours
- Newbie friendliness
- 75/100
Research direction
Start at the CLI model details display and trace how synthetic model metadata is formatted. Reproduce with max_prompt_tokens 100000, max_output_tokens 20000, and max_context_window_tokens 100000; done means the display reports the declared 100000-token context window while keeping prompt and output limits independent.
Written by the indexing model from the issue text.
Description
Describe the bug
The model details display can overstate total context if it derives context by adding max_prompt_tokens and max_output_tokens. These are independent maxima and their sum may exceed max_context_window_tokens.
Affected version
1.0.81
Steps to reproduce the behavior
- Return synthetic model metadata with
max_prompt_tokens: 100000,max_output_tokens: 20000, andmax_context_window_tokens: 100000. - Open the CLI model details display.
- Check whether it reports 120,000 tokens instead of the declared 100,000-token context window.
Expected behavior
Display max_context_window_tokens as the total context window. Treat prompt and output limits as independent maxima rather than values whose sum defines context.
Additional context
The Copilot SDK/runtime preserves the independent context value, so this appears limited to CLI presentation.
- Dominant language
- Shell
- Stars
- 11.2k
- Forks
- 1.9k
- Avg merge
- 14h 16m
- Merged PRs (30d)
- 6
Contributor guide
First steps
- Read the whole issue, then the project's contributing guide.
- Comment on the issue to say you are picking it up — it saves two people doing the same work.
- Fork the repository and make your change on a branch.
- Open a pull request that references the issue number.
More from github/copilot-cli
-
triage
Difficulty 2/5 1-3 hours Newbie friendliness 72/100
github/copilot-cli#4848 ·
-
area:agents area:mcp
Difficulty 2/5 1-3 hours Newbie friendliness 72/100
github/copilot-cli#4729 ·
-
area:sessions
Difficulty 2/5 1-3 hours Newbie friendliness 72/100
github/copilot-cli#4712 ·
-
Expose large_output_file_path on TaskShellProgress so clients can read complete shell-task output Openarea:tools
Difficulty 2/5 1-3 hours Newbie friendliness 78/100
github/copilot-cli#4630 · 1 comment ·
-
Clarify startup message "No copilot-instructions.md found" to specify it means the repo-scoped file Openarea:context-memory
Difficulty 1/5 1-3 hours Newbie friendliness 72/100
github/copilot-cli#4475 ·
All issues in github/copilot-cli
Similar issues
-
docs(agents): strengthen the no-backslash-escaped-backticks rule with an issue-creation example Open
Difficulty 1/5 Under an hour Newbie friendliness 92/100
-
package-update
Difficulty 2/5 1-3 hours Newbie friendliness 76/100
oSoWoSo/vOid_Community_repOsitory#148 · 1 comment ·
-
chore
Difficulty 1/5 Under an hour Newbie friendliness 91/100
alunduil/alunduil-chezmoi#792 ·
-
area: compat bug
Difficulty 2/5 1-3 hours Newbie friendliness 72/100
-
zenhub-dev
Difficulty 2/5 1-3 hours Newbie friendliness 68/100
OpenLiberty/ci.docker#747 ·