This reverts commit 7eee3e0878.
Middle-out truncation is a really great feature and it should still be
implemented, however it unnecessarily interferes with #1365 because it
hooked into the low-level chunk management that comes directly from VSCE
shell integration.
The best place to hook OutputBuilder is as follows depending on the
state of terminal interaction:
1. Foreground terminals:
Cline.ts:
executeCommandTool(...) {
process.on("line", (line) => {
lines.push(line)
...
}
}
2. For background terminals: hook in at the point that getUnretrievedOutput is consumed for active or
inactive terminals in Cline.ts:getEnvironmentDetails()
Please note:
The Terminal classes are very sensitive to change, partially because of
the complicated way that shell integration works with VSCE, and
partially because of the way that Cline interacts with the Terminal*
class abstractions that make VSCE shell integration easier to work with.
At the point that PR#1365 is merged, it is unlikely that any Terminal*
classes will need to be modified substantially. Generally speaking, we
should think of this is a stable interface and minimize changes.
Reverts: #1390
This commit adds a new setting to allow users to disable custom mode creation,
which can help reduce token usage in Roo's prompts.
Key changes:
Add enableCustomModeCreation setting to global state
Conditionally include custom modes documentation in prompt only when enabled
Add UI toggle in PromptsView with explanatory text
Default the setting to enabled (true) for backward compatibility
Update necessary interfaces and message handlers for the new setting
The setting is placed in PromptsView rather than SettingsView since it directly
relates to the modes functionality managed in that component.
- Update DeepSeekHandler to support prompt caching
- Add cache token tracking in usage metrics
- Update DeepSeek model configurations with cache-related pricing
- Enhance test coverage for cache and usage metric handling
- Add support for prompt caching in DeepSeek models
- Update model configurations to reflect caching capabilities
- Implement detailed usage metrics tracking cache write and read tokens
- Extend test coverage for new usage metrics and model parameters
- Update pricing information for DeepSeek models to include cache-related costs
