smashimo/oh-my-pi
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

feat(coding-agent): added /extended-context slash command and pass settings to model registry

Browse Source 
- Add the `/extended-context` builtin slash command to toggle premium long-context windows.
- Update `ModelRegistry` to accept settings and apply context-window caps using the finalized configuration.
- Add tests covering extended context toggle behavior and session context window capping.
This commit is contained in:
can1357
2026-08-20 08:00:23 +02:00
parent ce94be2b93
commit 57305b99cd
8 changed files with 143 additions and 24 deletions
Download Patch File Download Diff File Expand all files Collapse all files
packages/coding-agent/CHANGELOG.md
+1
View File
@@ -11,6 +11,7 @@
- Backgroundable Python — `eval` cells can run async and auto-background like `bash`, with configurable thresholds.
- Local Claude token counting — Anthropic-family tokens now count via a native local tokenizer, and every counter (session maintenance, advisor, stats, context tools) uses the active model's own tokenizer.
- `extendedContext` setting — pick whether models with premium long-context pricing (272K/1M tiers on Codex-class models) use the extended window or compact early and stay on standard pricing.
- `/extended-context` — toggle premium long-context windows without leaving the session.
- Speculative compaction — with `compaction.asyncEnabled`, all compaction modes compact in parallel while the session continues, then splice the result in instantly.
- `tokenizer` property on custom models and `modelOverrides` to pin the tokenizer family for proxy models.
- `qwenTemplateReasoningEffort` in `models.yml` `compat` to disable the Qwen 3.8+ reasoning-effort template parameter for strict local servers.