Describe the bug
The CLI accepts contextTier: "long_context" in ~/.copilot/settings.json, but new/default sessions launched non-interactively do not reliably start with the long context tier. The session starts with the smaller/default context even when settings specify model, effortLevel, and contextTier.
Selecting the same model interactively through /model switches the session from gpt-5.5 (xhigh) to gpt-5.5 (xhigh) (1.1M context), which suggests the context tier is recognized by the model picker but not applied during startup/model resolution.
This blocks autonomous or automatically launched sessions that start with an initial prompt, because those sessions cannot interactively choose the long-context tier after launch.
Affected version
GitHub Copilot CLI 1.0.52-4
Observed installed package: 1.0.52-4 on Windows.
Steps to reproduce the behavior
-
Configure ~/.copilot/settings.json with:
{
"model": "gpt-5.5",
"effortLevel": "xhigh",
"contextTier": "long_context"
}
-
Start a new default Copilot CLI session, or launch an automated session with an initial prompt.
-
Run /context or inspect the displayed model/context information.
-
Observe that the session uses the smaller/default context rather than the long-context tier.
-
In an interactive session, run /model and select the same model/tier. The display changes to the long-context variant, for example gpt-5.5 (xhigh) (1.1M context).
Expected behavior
A new session should honor contextTier: "long_context" from settings.json during startup/model resolution. For automation, there should also be a launch flag such as:
copilot --model gpt-5.5 --reasoning-effort xhigh --context-tier long_context
or equivalent.
Additional context
I inspected the installed 1.0.52-4 bundle locally and found:
contextTier is schema-recognized with values "default" and "long_context".
- The interactive model picker has a
context_tier phase and writes contextTier when selecting the long-context tier.
- The documented CLI flags include
--model and --reasoning-effort, but not a context-tier flag.
- The startup/model-resolution path appears to read
model and effortLevel, while the UI path applies context-tier capability overrides later.
- The plain
/model <id> command path appears to clear contextTier, while the picker path can write it.
Operating system: Windows 11 / Windows Terminal / PowerShell.
Describe the bug
The CLI accepts
contextTier: "long_context"in~/.copilot/settings.json, but new/default sessions launched non-interactively do not reliably start with the long context tier. The session starts with the smaller/default context even when settings specifymodel,effortLevel, andcontextTier.Selecting the same model interactively through
/modelswitches the session fromgpt-5.5 (xhigh)togpt-5.5 (xhigh) (1.1M context), which suggests the context tier is recognized by the model picker but not applied during startup/model resolution.This blocks autonomous or automatically launched sessions that start with an initial prompt, because those sessions cannot interactively choose the long-context tier after launch.
Affected version
GitHub Copilot CLI 1.0.52-4
Observed installed package:
1.0.52-4on Windows.Steps to reproduce the behavior
Configure
~/.copilot/settings.jsonwith:{ "model": "gpt-5.5", "effortLevel": "xhigh", "contextTier": "long_context" }Start a new default Copilot CLI session, or launch an automated session with an initial prompt.
Run
/contextor inspect the displayed model/context information.Observe that the session uses the smaller/default context rather than the long-context tier.
In an interactive session, run
/modeland select the same model/tier. The display changes to the long-context variant, for examplegpt-5.5 (xhigh) (1.1M context).Expected behavior
A new session should honor
contextTier: "long_context"fromsettings.jsonduring startup/model resolution. For automation, there should also be a launch flag such as:or equivalent.
Additional context
I inspected the installed 1.0.52-4 bundle locally and found:
contextTieris schema-recognized with values"default"and"long_context".context_tierphase and writescontextTierwhen selecting the long-context tier.--modeland--reasoning-effort, but not a context-tier flag.modelandeffortLevel, while the UI path applies context-tier capability overrides later./model <id>command path appears to clearcontextTier, while the picker path can write it.Operating system: Windows 11 / Windows Terminal / PowerShell.