@bastani/atomic 0.8.31-alpha.2 → 0.8.31-alpha.3

package/CHANGELOG.md

@@ -4,7 +4,7 @@
 
 ### Added
 
-- Added configurable context-window support for models that declare `contextWindowOptions`, including explicit `--context-window` CLI/settings control, a GitHub Copilot CLI-style `/model`-flow picker (numbered `Default`/`Long context` tiers with token counts), session replay, SDK/runtime/RPC APIs, and docs while preserving each model's scalar default context window. For GitHub Copilot, context windows are measured in **input (prompt) tokens** (consistent with every other provider) and derived **dynamically from GitHub's live CAPI model catalog** (`GET /models`) instead of a hardcoded model list: Atomic resolves each model's input budget as `max_prompt_tokens || max_context_window_tokens || 128_000` and, for tiered models, exposes the per-tier input budgets (`token_prices.<tier>.context_max`) as a selectable default/long window — gated on the user actually having the GitHub Copilot provider and cached on disk for 30 minutes (for example `github-copilot/gpt-5.5` resolves to `272k` default / `922k` long, and the Claude/Gemini long-context models to `200k` default / `936k` long). Atomic raises the local budget and sends `X-GitHub-Api-Version: 2026-06-01`, while GitHub applies the long-context billing tier server-side by prompt token count. Long-context Copilot requests consume more AI credits and require Copilot long-context/usage-based billing entitlement; offline, unauthenticated, or non-Copilot sessions leave the built-in window untouched and show no picker; custom providers and explicit model overrides can still expose their own selectable windows ([#1409](https://github.com/bastani-inc/atomic/issues/1409)).
+- Added configurable context-window support for models that declare `contextWindowOptions`, including explicit `--context-window` CLI/settings control, a GitHub Copilot CLI-style `/model`-flow picker (numbered `Default`/`Long context` tiers with token counts), session replay, SDK/runtime/RPC APIs, and docs while preserving each model's scalar default context window. For GitHub Copilot, context windows are measured in **input (prompt) tokens** (consistent with every other provider) and derived **dynamically from GitHub's live CAPI model catalog** (`GET /models`) instead of a hardcoded model list: Atomic resolves each model's input budget as `max_prompt_tokens || max_context_window_tokens || 128_000` and, for tiered models, exposes a selectable default window (`token_prices.default.context_max`) plus a long window set to the model's full `max_context_window_tokens` (retaining `max_prompt_tokens` as the internal effective compaction/overflow budget) — gated on the user actually having the GitHub Copilot provider and cached on disk for 30 minutes (for example `github-copilot/gpt-5.5` exposes `272k` default / `1.05m` long, and the Claude/Gemini long-context models `200k` default / `1m` long). Atomic raises the local budget and sends `X-GitHub-Api-Version: 2026-06-01`, while GitHub applies the long-context billing tier server-side by prompt token count. Long-context Copilot requests consume more AI credits and require Copilot long-context/usage-based billing entitlement; offline, unauthenticated, or non-Copilot sessions leave the built-in window untouched and show no picker; custom providers and explicit model overrides can still expose their own selectable windows ([#1409](https://github.com/bastani-inc/atomic/issues/1409)).
 - Exported context-window helper functions and types from the package root, including parser/formatter/normalizer/selection utilities and the `Model<Api>` augmentation for `contextWindowOptions`/`defaultContextWindow`, so SDK consumers can use the public API without importing internal source paths ([#1409](https://github.com/bastani-inc/atomic/issues/1409)).
 - Added RPC mode runtime context-window commands so headless clients can read supported token budgets with `get_available_context_windows` and select the active runtime budget with `set_context_window` without persisting context-window settings ([#1409](https://github.com/bastani-inc/atomic/issues/1409)).
 - Added upstream pi v0.79.7 automatic theme mode support so `/settings` can choose separate light and dark themes and follow terminal color-scheme changes.
@@ -12,7 +12,8 @@
 
 ### Changed
 
-- Changed built-in GitHub Copilot context windows to be measured in **input (prompt) tokens** (matching every other provider) and derived from GitHub's live CAPI model catalog (`GET /models`, cached 30 minutes, gated on the Copilot provider) instead of a hardcoded long-context model list, so newly added/removed Copilot models and retiered windows are reflected automatically without shipping a stale snapshot. Each model's window now resolves to `max_prompt_tokens || max_context_window_tokens || 128_000`, and tiered models expose their per-tier input budgets (`token_prices.<tier>.context_max`) as the selectable default/long windows (e.g. `gpt-5.5` 272k/922k, Claude/Gemini 200k/936k) — replacing the previous input+output totals — while preserving custom provider entries and explicit `models.json` overrides and relying on GitHub's API-version header and server-side tier selection rather than payload fields or model-id variants ([#1409](https://github.com/bastani-inc/atomic/issues/1409)).
+- Changed the GitHub Copilot **long-context tier to advertise the model's full context window** (`max_context_window_tokens`, for example `github-copilot/gpt-5.5` `1.05m`, and `github-copilot/claude-opus-4.8`/`github-copilot/gemini-3.1-pro-preview` `1m`) instead of GitHub's prompt-token cap, so Copilot models report and display the same window as the native `openai/*` and `anthropic/*` providers (the chat footer denominator now shows the full window). GitHub's lower server-side input cap (`max_prompt_tokens`, e.g. `922k`/`936k`, which equals `max_context_window_tokens − max_output_tokens`) is now parsed and carried as an internal effective input budget (`Model.maxInputTokens`, exposed via the new `getEffectiveInputBudget()` helper): auto-compaction thresholds and the Copilot overflow-recovery guard run against that budget while the picker/footer show the full window. As a result, a prompt that reaches the real prompt cap is now compacted-and-retried automatically (previously the long window equalled the cap), and the friendly “enable long-context/usage-based billing / server-cap” hint fires only when GitHub rejects a prompt *below* the cap (a genuine entitlement/tier drop) rather than at the cap. Sparse catalog payloads without `max_context_window_tokens` still fall back to the long-context prompt threshold, and the on-disk Copilot catalog cache schema version was bumped so existing caches refetch the new windows ([#1409](https://github.com/bastani-inc/atomic/issues/1409)).
+- Changed built-in GitHub Copilot context windows to be measured in **input (prompt) tokens** (matching every other provider) and derived from GitHub's live CAPI model catalog (`GET /models`, cached 30 minutes, gated on the Copilot provider) instead of a hardcoded long-context model list, so newly added/removed Copilot models and retiered windows are reflected automatically without shipping a stale snapshot. Each model's window now resolves to `max_prompt_tokens || max_context_window_tokens || 128_000`, and tiered models expose a selectable default window (`token_prices.default.context_max`) plus a long window set to the model's full `max_context_window_tokens` (e.g. `gpt-5.5` 272k/1.05m, Claude/Gemini 200k/1m), with `max_prompt_tokens` retained as the internal effective compaction/overflow budget — while preserving custom provider entries and explicit `models.json` overrides and relying on GitHub's API-version header and server-side tier selection rather than payload fields or model-id variants ([#1409](https://github.com/bastani-inc/atomic/issues/1409)).
 - Bumped the bundled upstream pi runtime libraries `@earendil-works/pi-agent-core`, `@earendil-works/pi-ai`, and `@earendil-works/pi-tui` from `^0.79.4` to `^0.79.6` so Atomic's installed pi runtime packages pick up upstream v0.79.5/v0.79.6 provider, model, thinking-payload, and shared TUI compatibility fixes; no Atomic coding-agent source changes were made for upstream coding-agent-only marked export or fetch-override behavior in this dependency sync ([#1413](https://github.com/bastani-inc/atomic/issues/1413)).
 - Synced Atomic's coding-agent fork with upstream pi v0.79.7, including the new self-only default for bare `atomic update` (`atomic update --all` restores the previous all-packages behavior), automatic light/dark theme settings, configured project config directory labels, extension example updates, model-search parity, tree navigator horizontal panning, and the latest user-facing docs.
 - Bumped the bundled upstream pi runtime libraries `@earendil-works/pi-agent-core`, `@earendil-works/pi-ai`, and `@earendil-works/pi-tui` from `^0.79.6` to `^0.79.7` so Atomic inherits upstream v0.79.7 TUI color-scheme, Warp image, generated model catalog, and agent-core fixes.
@@ -25,7 +26,7 @@
 - Fixed RPC unknown-command errors to include the request id so RPC clients do not hang waiting for a response.
 - Fixed `/model` autocomplete and model-selection searches to match provider/model queries regardless of whether the provider or model token is typed first.
 - Fixed the tree navigator to horizontally pan deep entries so the selected item remains readable.
-- Fixed long-context selection for GitHub Copilot's rounded 1M model names: requesting `1m` for tiered Copilot models now resolves to the largest advertised long-context input budget at or below the request (for example `936k` for `github-copilot/claude-opus-4.8`) instead of falling back to the short `200k` tier. Interactive/context-picker persistence now writes the effective selected budget to per-model `defaultContextWindows["provider/modelId"]` settings instead of the global `defaultContextWindow` fallback, so Copilot-specific prompt caps such as `936k`/`922k` do not leak into Anthropic, Cursor, or other providers on restart. Legacy/stale global `defaultContextWindow` values from earlier builds are now treated as optional fallbacks and ignored without warning when unsupported by the active model.
+- Fixed long-context selection for GitHub Copilot's rounded 1M model names: requesting `1m` now selects the advertised full context window when the catalog exposes it, and otherwise resolves to the largest advertised long-context window at or below the request (for example `936k` for sparse catalog payloads) instead of falling back to the short `200k` tier. Interactive/context-picker persistence now writes the effective selected budget to per-model `defaultContextWindows["provider/modelId"]` settings instead of the global `defaultContextWindow` fallback, so Copilot-specific prompt caps such as `936k`/`922k` do not leak into Anthropic, Cursor, or other providers on restart. Legacy/stale global `defaultContextWindow` values from earlier builds are now treated as optional fallbacks and ignored without warning when unsupported by the active model.
 - Fixed a GitHub Copilot context-window warning on restart: after selecting a long-context window (e.g. `claude-opus-4.8` → `936k`) and reopening Atomic, startup validated the persisted selection before the (async, auth-gated) Copilot catalog loaded, so the model still looked limited to its default window and Atomic warned “Context window 936k is not supported… Supported values: 200k” and reset the choice. The model registry now seeds the Copilot context-window catalog synchronously from its on-disk cache at construction (ignoring the refresh TTL, gated on a `github-copilot` credential), so a returning user's selection is recognized immediately while the live refresh still runs in the background ([#1409](https://github.com/bastani-inc/atomic/issues/1409)).
 - Fixed context-window startup, session-switch, settings, and RPC edge cases: unknown provider fallback models no longer inherit selectable context-window options from provider defaults, fatal startup diagnostics no longer persist context-window settings, `AgentSession.setModel()` preserves an incoming target model's explicit selected context window, model-switch paths that change effective context windows now notify listeners via `context_window_changed`, the interactive context-window picker keys selection on raw token counts so colliding formatted labels never change which window is selected, RPC `set_model` returns the effective post-switch session model, and explicit startup `contextWindow` selections are journaled even when they equal the model scalar default ([#1409](https://github.com/bastani-inc/atomic/issues/1409)).
 - Fixed `AgentSession.setContextWindow()` so bare SDK/runtime calls update the active session, append `context_window_change`, and emit `context_window_changed` without persisting settings; callers must pass `{ persistDefault: true }` to update the active model's `defaultContextWindows["provider/modelId"]` setting ([#1409](https://github.com/bastani-inc/atomic/issues/1409)).

package/dist/builtin/cursor/CHANGELOG.md

@@ -4,7 +4,7 @@
 
 ### Changed
 
-- Published a synchronized Atomic 0.8.31-alpha.2 prerelease; no functional Cursor provider changes were made after 0.8.30.
+- Published a synchronized Atomic 0.8.31-alpha.3 prerelease; no functional Cursor provider changes were made after 0.8.30.
 
 ## [0.8.30] - 2026-06-17
 

package/dist/builtin/cursor/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@bastani/cursor",
-  "version": "0.8.31-alpha.2",
+  "version": "0.8.31-alpha.3",
   "private": true,
   "description": "Experimental first-party Atomic extension for Cursor OAuth, model discovery, and streaming provider registration.",
   "contributors": [
@@ -40,7 +40,7 @@
     }
   },
   "dependencies": {
-    "@bastani/atomic-natives": "0.8.31-alpha.2",
+    "@bastani/atomic-natives": "0.8.31-alpha.3",
     "@bufbuild/protobuf": "^2.0.0"
   }
 }

package/dist/builtin/intercom/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@bastani/intercom",
-  "version": "0.8.31-alpha.2",
+  "version": "0.8.31-alpha.3",
   "private": true,
   "description": "Atomic extension providing a private coordination channel between parent and child agent sessions. Fork of: https://github.com/nicobailon/pi-intercom",
   "contributors": [

package/dist/builtin/mcp/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@bastani/mcp",
-  "version": "0.8.31-alpha.2",
+  "version": "0.8.31-alpha.3",
   "private": true,
   "description": "Atomic extension that adapts MCP (Model Context Protocol) servers into the coding agent. Fork of: https://github.com/nicobailon/pi-mcp-adapter",
   "contributors": [

package/dist/builtin/subagents/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@bastani/subagents",
-  "version": "0.8.31-alpha.2",
+  "version": "0.8.31-alpha.3",
   "private": true,
   "description": "Atomic extension for delegating tasks to subagents with chains, parallel execution, and TUI clarification. Fork of: https://github.com/nicobailon/pi-subagents",
   "contributors": [

package/dist/builtin/web-access/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@bastani/web-access",
-  "version": "0.8.31-alpha.2",
+  "version": "0.8.31-alpha.3",
   "private": true,
   "description": "Atomic extension for web search, URL fetching, GitHub repo cloning, PDF/video extraction. Fork of: https://github.com/nicobailon/pi-web-access",
   "contributors": [

package/dist/builtin/workflows/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@bastani/workflows",
-  "version": "0.8.31-alpha.2",
+  "version": "0.8.31-alpha.3",
   "private": true,
   "description": "Atomic extension for multi-stage workflow authoring and execution.",
   "contributors": [