@diegopetrucci/pi-extensions 0.1.73 → 0.1.76

package/extensions/dynamic-context-pruning/package.json

@@ -1,6 +1,6 @@
 {
   "name": "pi-dynamic-context-pruning",
-  "version": "0.1.11",
+  "version": "0.1.12",
   "type": "module",
   "description": "A pi extension that dynamically prunes stale context to keep sessions lean.",
   "keywords": [

package/extensions/fast/README.md

@@ -1,6 +1,6 @@
 # fast
 
-A pi extension that provides one `/fast` toggle for supported direct OpenAI API, OpenAI Codex, and Anthropic Claude models. It selects the provider-specific Fast-mode request shape from the currently selected model.
+A pi extension that provides `/fast` and `/ultrafast` toggles for supported direct OpenAI API, OpenAI Codex, and Anthropic Claude models. It selects the provider-specific Fast-mode request shape from the currently selected model.
 
 For eligible direct OpenAI API models it injects:
 
@@ -44,27 +44,62 @@ Direct OpenAI API Fast mode requires all of the following:
 
 The direct OpenAI route stays on OpenAI's direct API contract for both API-key
 auth and Pi's `openai` ChatGPT OAuth. Acceptance of `service_tier: "fast"` by
-Pi's `openai` ChatGPT OAuth sign-in endpoint has not been live-verified and
-remains deferred to manual gate `pel-71t6`. This direct route is never forwarded
-to legacy `openai-codex` or its subscription-usage endpoint. The documented
-request shape is support evidence, not live certification; this change was
-validated only with mocked eligibility and request payloads, not live or paid
-provider calls.
+Pi's `openai` ChatGPT OAuth sign-in endpoint has not been live-verified.
+This direct route is never forwarded to legacy `openai-codex` or its
+subscription-usage endpoint. The documented request shape is support evidence,
+not live certification; this change was validated only with mocked eligibility
+and request payloads, not live or paid provider calls.
+
+### Ultrafast support (initial, fail-closed)
+
+Ultrafast is intentionally narrower than ordinary Fast mode. It requires all of
+the following on every activation and provider request:
+
+- Provider `openai`.
+- API `openai-responses`.
+- Model `gpt-6-astra`.
+- Direct API-key auth, not Codex OAuth or direct OpenAI OAuth.
+- Base URL exactly `https://api.openai.com/v1` (a single trailing slash is also accepted).
+
+It does not support Chat Completions, preview models, regional or proxy endpoints,
+or Anthropic Ultrafast. Eligible payloads receive the requested
+`service_tier: "ultrafast"` only when they do not already contain a
+`service_tier` field. Existing values and mismatched/malformed payloads are left
+untouched. The extension reports a requested tier; it does not claim that OpenAI
+accepted or applied it, and it never silently falls back to ordinary Fast.
+
+OpenAI documents this request shape in the [Ultrafast API guide](https://developers.openai.com/api/docs/guides/ultrafast-mode)
+and lists the account/model pricing in its [API pricing](https://developers.openai.com/api/docs/pricing).
+Actual Ultrafast API pricing is **6x Standard**, while Pi's current cost display
+omits that premium. Treat the activation warning as a deliberate paid-usage
+warning.
 
 OpenAI Codex Fast mode requires all of the following:
 
 - Provider `openai-codex`.
 - API `openai-codex-responses`.
-- Model `gpt-5.5`, `gpt-5.6-sol`, `gpt-5.6-terra`, or `gpt-5.6-luna`.
+- Model `gpt-5.5`, `gpt-5.6-sol`, `gpt-5.6-terra`, `gpt-5.6-luna`, `gpt-6-astra`, `gpt-6.1-sol`, `gpt-6-sol`, or `gpt-6-luna`.
 - ChatGPT OAuth/subscription auth, not API-key auth.
 - No existing `service_tier` field in the request payload.
 
-GPT-6.1 Sol is intentionally unsupported on this legacy Codex route. The
-Codex speed documentation lists GPT-6.1 Sol Fast with `service_tier: "fast"`,
-but Pi's legacy Codex service-tier cost handling currently accounts for
-`priority` and `flex`, not `fast`. The direct OpenAI API's `priority` alias is
-not evidence for the legacy Codex endpoint, so this extension leaves the route
-fail-closed without patching upstream pricing.
+Codex evidence, 2026-10-03: the [maintainer's PR #103 review](https://github.com/diegopetrucci/pi-extensions/pull/103)
+reports that the Codex model list advertises Fast as `priority` for `gpt-6-astra`,
+`gpt-6.1-sol`, `gpt-6-sol`, and `gpt-6-luna`. The official Codex CLI
+[sends Fast as `priority`](https://github.com/openai/codex/blob/b741e480e203f037ca726bc2a76d99a8e8668e66/codex-rs/protocol/src/config_types.rs#L539-L553).
+The maintainer's live check through Pi 1.0.0 on that date returned HTTP 200 and
+completed normally for `gpt-6-astra` and `gpt-6.1-sol`; `gpt-6-sol` and
+`gpt-6-luna` are enabled based on the model list only. In that check,
+`response.completed` always reported `service_tier: "default"`, with or without
+`priority`, so the response cannot confirm Fast was applied.
+
+Pi trusts the requested tier and applies a 2× multiplier to its displayed cost
+estimate for `priority`; this does not measure included subscription allowance
+consumption or confirm Fast was applied. [OpenAI's Codex speed documentation](https://developers.openai.com/codex/speed),
+checked on 2026-10-03, lists `gpt-6-sol` and `gpt-6-luna` among supported Fast
+models where available. It specifies 2.5× the Standard rate for included
+subscription limits and 2× for purchased credits and Enterprise pay-as-you-go
+billing. Treating Pi's 2× estimate as a subscription-limit multiplier would
+understate the documented allowance consumption.
 
 Anthropic Fast mode requires all of the following:
 
@@ -79,11 +114,26 @@ Anthropic Fast mode supports both API-key and Claude Code OAuth access when the
 
 ```text
 /fast
+/ultrafast
+/fast ultrafast
 ```
 
-Run `/fast` to toggle Fast mode for the current session/runtime. The enabled state follows model changes: switching between eligible OpenAI and Anthropic models automatically changes the request format without resetting the toggle. The footer shows `fast` only while the selected model is eligible and Fast mode is enabled.
+Run `/fast` to toggle ordinary Fast mode for the current session/runtime. The
+enabled state follows model changes: switching between eligible OpenAI and
+Anthropic models automatically changes the request format without resetting the
+toggle. The footer shows `fast` only while the selected model is eligible and
+Fast mode is enabled.
+
+`/ultrafast` and `/fast ultrafast` are equivalent toggles for the session-only
+Ultrafast override. Ultrafast defaults off, is never enabled by global or project
+configuration, and can be undone with either command. Running ordinary `/fast`
+while Ultrafast is selected turns Ultrafast off rather than silently switching to
+another paid tier. Switching to an unsupported model or endpoint disables
+Ultrafast and does not re-enable it when `gpt-6-astra` is selected again. The
+footer uses `ultrafast` while an eligible request is selected; status text says
+that the tier is requested, not remotely applied.
 
-The extension defaults to off so installing the full collection does not accidentally spend Fast-mode credits.
+The extension defaults to off so installing the full collection does not accidentally spend Fast-mode credits. Ultrafast verification is mocked-only: tests use local eligibility checks, fake payloads, and a fake fetch through Pi's `openai-responses` `streamSimple`; they make no live or paid provider requests.
 
 ## Config
 
@@ -111,7 +161,7 @@ Here `<pi-config-dir>` is Pi's runtime config directory name (`CONFIG_DIR_NAME`;
 - `enabled`: default Fast-mode state when there is no session override.
 - `showStatus`: show a compact `fast` status when Fast mode is active for the selected model.
 
-The unified extension intentionally does not read `openai-fast.json` or `claude-fast.json`; those files belong to the provider-specific standalone packages and may contain conflicting defaults.
+The unified extension reads only `fast.json`. It does not read `openai-fast.json` or `claude-fast.json`.
 
 ## Install
 
@@ -141,16 +191,16 @@ Then reload pi:
 
 ## Legacy provider-specific packages
 
-The collection package loads this unified extension instead of `openai-fast` and `claude-fast`. Both provider-specific packages remain available as standalone alternatives. Do not load them together with this extension: independent Fast-mode state and duplicate `/fast` registrations can produce conflicting behavior.
+The collection package loads this unified extension only (`extensions/fast/index.ts`). `openai-fast` and `claude-fast` remain published as deprecated standalone leftovers. On session start they warn, clear their leftover footer status, and remove `fast-mode-2026-02-01` from the current model header. They do not read config, register commands, or inject Fast fields into requests.
 
 ## Notes
 
 - Anthropic Fast mode has separate rate limits, costs more than standard speed, and does not share prompt-cache prefixes with standard-speed requests.
 - Direct OpenAI Fast mode is limited to the confirmed GPT-6 API models above; Fast pricing, availability, and rate limits remain provider- and account-dependent.
 - Authoritative support evidence: [OpenAI Fast mode](https://developers.openai.com/api/docs/guides/fast-mode) explicitly uses `gpt-6.1-sol` with `service_tier: "fast"` and documents `priority` as an equivalent alias for supported API models; the [GPT-6.1 Sol model page](https://developers.openai.com/api/docs/models/gpt-6.1-sol) documents the model itself.
-- The [Codex speed guide](https://developers.openai.com/codex/speed/) documents GPT-6.1 Sol Fast for ChatGPT-signed-in Codex, but legacy Codex support remains pending separate wire and cost validation; this ticket makes no live-certification claim.
+- Codex Fast availability depends on plan, client, workspace settings, and rollout. Local eligibility is not live-provider certification.
 - Pi's provider catalog remains the source of reported model pricing, including any tiered pricing; this extension does not apply guessed discounts or rewrite cost metadata.
-- OpenAI Codex Fast mode intentionally does not affect API-key models, and GPT-6.1 Sol remains blocked on the legacy Codex route.
-- The retired `openai-fast` and `claude-fast` packages remain legacy standalone boundaries; new provider/auth behavior belongs only to this unified extension.
+- OpenAI Codex Fast mode intentionally does not affect API-key models.
+- Deprecated `openai-fast` and `claude-fast` packages no longer implement Fast mode. New provider/auth behavior belongs only to this unified extension.
 - Existing `speed` and `service_tier` fields are never overwritten.
 - Pi's model catalog may not include a Fast-mode premium. Cost accounting depends on the provider reporting the effective tier in its streamed response, and this extension does not patch usage totals.