@oai404iao/pi-codex-minimal-tools 1.4.1-alpha.0 → 2.0.0

package/README.md

@@ -3,7 +3,7 @@
 Codex-specific Responses support for Pi, driven by an exact per-model JSON
 catalog instead of model-name heuristics.
 
-Peer floor: Pi 0.84.2; tested against 0.84.2 and 0.85.1.
+Peer floor: Pi 0.85.1; tested against 0.85.1.
 
 > npm identity stays `@oai404iao/pi-codex-minimal-tools`. This checkout composes
 > core, web-search and imagegen through a shared runtime. The four new packages
@@ -113,6 +113,7 @@ Without `PI_CODING_AGENT_DIR`, Pi normally uses `~/.config/pi/agent` or
   "glyphStyle": "unicode",
   "autoEnable": true,
   "fastMode": false,
+  "imageGeneration": true,
   "imageOutputDir": ".pi/openai-codex-images",
   "imageModel": "gpt-image-2",
   "directImageApiFallback": false,
@@ -127,6 +128,7 @@ Without `PI_CODING_AGENT_DIR`, Pi normally uses `~/.config/pi/agent` or
 | `glyphStyle` | Use `unicode` or `ascii` UI glyphs. |
 | `autoEnable` | Add supported package tools automatically. |
 | `fastMode` | Global user toggle; only profiles with `fast` are affected. |
+| `imageGeneration` | Global master switch. Set `false` to omit image tools, `/image-gen`, presentation, hosted injection, standalone requests, and direct fallback without changing other model behavior. |
 | `imageOutputDir` | Generated-image output directory. Relative paths resolve from the workspace root. |
 | `imageModel` | Image model used by standalone/hosted image requests and direct fallback. |
 | `directImageApiFallback` | Permit the separate `OPENAI_API_KEY` Images API fallback. |
@@ -134,7 +136,8 @@ Without `PI_CODING_AGENT_DIR`, Pi normally uses `~/.config/pi/agent` or
 | `deferApplyPatchRendering` | Use Pi's fallback renderer instead of the streaming patch preview. |
 
 The older model-level keys remain readable for one migration version, but are
-deprecated. See [Legacy migration](#legacy-migration).
+deprecated. `imageGeneration` is the exception: it remains the supported global
+master switch. See [Legacy migration](#legacy-migration).
 
 ### Per-Model Catalog
 
@@ -297,10 +300,12 @@ Important constraints:
 ## Built-In Profiles
 
 The bundled catalog is based on local Codex commit
-`eb9dceba1a2e658142a456c5898836774835616b` from August 12, 2026.
+`eb9dceba1a2e658142a456c5898836774835616b` from August 12, 2026, with the
+Astra profile updated from `ddea03ad049142943bdbf13e937b1d67e8c1ba0c`.
 
 | Models | Responses | Web | Image | Patch | Compaction |
 | --- | --- | --- | --- | --- | --- |
+| `openai-codex/gpt-6-astra` | Lite, auto WS/SSE | standalone text+image | standalone | custom | responses |
 | `gpt-5.6-sol`, `gpt-5.6-terra`, `gpt-5.6-luna` | Lite, auto WS/SSE | standalone text+image | standalone | custom | responses |
 | `gpt-5.5`, `gpt-5.4` | Standard, auto WS/SSE | hosted text+image | standalone | custom | responses |
 | `gpt-5.4-mini`, `codex-auto-review` | Standard, auto WS/SSE | hosted text+image | standalone | custom | responses |
@@ -309,8 +314,19 @@ The bundled catalog is based on local Codex commit
 | `gpt-4.1` | Standard SSE | off | hosted | off | Pi |
 | `o4-mini` | Standard SSE | off | off | off | Pi |
 
-Equivalent `openai/...` and `openai-codex/...` IDs are included; the latter
-switch only the endpoint/auth shape to `codex`.
+The pre-Astra entries include equivalent `openai/...` and
+`openai-codex/...` IDs; the latter switch only the endpoint/auth shape to
+`codex`. Astra is bundled only for `openai-codex`, matching the analyzed
+ChatGPT subscription route. A public-API or proxy Astra deployment requires an
+explicit user profile for that endpoint.
+
+Pi 0.85.1 provides the Astra model descriptor; it is now the package peer
+floor. The extension composes its stream shim over that provider and does not
+replace authentication, streams, or the model catalog.
+The descriptor keeps the production default at 272,000 context tokens and
+128,000 output tokens. A backend-authorized larger context must be selected
+explicitly through Pi's provider `modelOverrides`; the extension does not infer
+that entitlement from the Astra slug.
 
 These entries are defaults, not claims that every proxy with the same model
 slug supports the protocol. Override or disable a profile for the endpoint
@@ -335,6 +351,10 @@ raw result text.
 
 ## Image Generation
 
+Set global `config.json.imageGeneration` to `false` to disable the entire
+generation capability. Per-model `tools.imageGeneration:false` disables only
+that profile. Neither setting disables image input or historical image replay.
+
 `tools.imageGeneration` supports:
 
 - `hosted`: Responses `image_generation`.
@@ -407,14 +427,15 @@ model override for compatibility:
 | `requestProfile.systemPromptPlacement` | `responses.systemPromptPlacement` |
 | `requestProfile.patchTransport` | `tools.applyPatch` |
 | `apiKeyMode` | `responses.endpoint` |
-| `imageGeneration` | `tools.imageGeneration` |
 | `webSearchEnabled` | `tools.webSearch` |
 | `viewImage` | `tools.viewImage` |
 | `applyPatchEnabled` | `tools.applyPatch` |
 | `additionalModelIds` | one exact user catalog entry per model |
 
 Move these values to extension `models.json`; legacy projection is intended
-only as a transition path.
+only as a transition path. `imageGeneration` is no longer a legacy projection:
+it is the supported global gate, while per-model selection stays in
+`tools.imageGeneration`.
 
 ## Protocol Reference
 

package/THIRD_PARTY_NOTICES.md

@@ -8,7 +8,7 @@ forwards or verified asset mirrors. Their adaptations now live in
 `@oai404iao/pi-codex-runtime/src/reserved-tools/`. Those packages retain the
 original modification notices, Apache snapshots and provenance. Search/image
 clients live in their respective capability packages. No upstream revision or
-reviewed fingerprint changed during this move.
+reviewed reserved-tool fingerprint changed during this move.
 
 ## OpenAI Codex
 
@@ -59,6 +59,16 @@ The repository's `reference/` directory contains protocol analysis based on
 both Codex revisions above. It is development documentation and is excluded
 from the npm tarball.
 
+### GPT-6 Astra profile
+
+The Astra profile is derived from Codex model/request metadata at revision
+[`ddea03ad049142943bdbf13e937b1d67e8c1ba0c`](https://github.com/openai/codex/commit/ddea03ad049142943bdbf13e937b1d67e8c1ba0c)
+and cross-checked against the MIT-licensed
+`@earendil-works/pi-ai@0.85.1` generated catalog. The Codex file/blob hashes
+and locked npm tarball identity are recorded in
+`provenance/openai-codex-ddea03ad-astra.json`. This delta does not repin or
+modify the reserved namespace-tool and apply-patch grammar fingerprints.
+
 ### Modified namespace-tool compatibility serialization
 
 `src/codex-reserved-tools.ts` is a modified TypeScript compatibility

package/config.schema.json

@@ -109,8 +109,7 @@
     },
     "imageGeneration": {
       "type": "boolean",
-      "description": "Deprecated compatibility override. Move per-model image-generation support to extension models.json.",
-      "deprecated": true,
+      "description": "Global image-generation master switch. false disables image tools, commands, presentation, hosted injection, standalone endpoints, and direct fallback without changing other model-profile behavior.",
       "default": true
     },
     "webSearchEnabled": {

package/index.ts

@@ -0,0 +1,2 @@
+export { default } from "./src/index.js";
+export * from "./src/index.js";

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@oai404iao/pi-codex-minimal-tools",
-  "version": "1.4.1-alpha.0",
+  "version": "2.0.0",
   "description": "Model-profiled Codex Responses tools for Pi: WebSocket, Lite, web search, images, compaction, and apply_patch",
   "repository": {
     "type": "git",
@@ -33,20 +33,20 @@
   },
   "pi": {
     "extensions": [
-      "./src/index.ts"
+      "./index.ts"
     ]
   },
   "peerDependencies": {
-    "@earendil-works/pi-ai": ">=0.84.2",
-    "@earendil-works/pi-coding-agent": ">=0.84.2",
-    "@earendil-works/pi-tui": ">=0.84.2",
+    "@earendil-works/pi-ai": ">=0.85.1",
+    "@earendil-works/pi-coding-agent": ">=0.85.1",
+    "@earendil-works/pi-tui": ">=0.85.1",
     "typebox": "*"
   },
   "dependencies": {
-    "@oai404iao/pi-codex-runtime": "0.1.0-alpha.1",
-    "@oai404iao/pi-codex-core": "0.1.0-alpha.1",
-    "@oai404iao/pi-codex-web-search": "0.1.0-alpha.1",
-    "@oai404iao/pi-codex-imagegen": "0.1.0-alpha.1"
+    "@oai404iao/pi-codex-runtime": "0.1.0",
+    "@oai404iao/pi-codex-core": "0.1.0",
+    "@oai404iao/pi-codex-web-search": "0.1.0",
+    "@oai404iao/pi-codex-imagegen": "0.1.0"
   },
   "devDependencies": {
     "@earendil-works/pi-ai": "0.85.1",
@@ -63,6 +63,7 @@
     "check": "npm run typecheck && npm test"
   },
   "files": [
+    "index.ts",
     "src/",
     "provenance/",
     "README.md",
@@ -87,5 +88,5 @@
       "optional": true
     }
   },
-  "gitHead": "53026bf9e3f6a1d16a9c990e6034b49041928eab"
+  "gitHead": "88cb6f56447d88b71232cd764ca5b29251341d23"
 }

package/provenance/openai-codex-ddea03ad-astra.json

@@ -0,0 +1,54 @@
+{
+  "schemaVersion": 1,
+  "upstream": {
+    "repository": "https://github.com/openai/codex",
+    "revision": "ddea03ad049142943bdbf13e937b1d67e8c1ba0c",
+    "commitUrl": "https://github.com/openai/codex/commit/ddea03ad049142943bdbf13e937b1d67e8c1ba0c",
+    "license": "Apache-2.0"
+  },
+  "files": {
+    "LICENSE": {
+      "role": "upstream Apache-2.0 license",
+      "gitBlobSha": "4606e72e042564097e8780d66c1d4dcb611869bd",
+      "sha256": "d17f227e4df5da1600391338865ce0f3055211760a36688f816941d58232d8dc",
+      "rawUrl": "https://raw.githubusercontent.com/openai/codex/ddea03ad049142943bdbf13e937b1d67e8c1ba0c/LICENSE"
+    },
+    "NOTICE": {
+      "role": "upstream NOTICE",
+      "gitBlobSha": "2805899d56d0332d175cfc613c67d45d6f006db7",
+      "sha256": "9d71575ecfd9a843fc1677b0efb08053c6ba9fd686a0de1a6f5382fd3c220915",
+      "rawUrl": "https://raw.githubusercontent.com/openai/codex/ddea03ad049142943bdbf13e937b1d67e8c1ba0c/NOTICE"
+    },
+    "codex-rs/models-manager/models.json": {
+      "role": "GPT-6 Astra capabilities and defaults",
+      "gitBlobSha": "1b5ce2c515986f84147abe5f4fb6e9b0deab0470",
+      "sha256": "897614e513a591b362f76c34e4b4d31af5809a2b52f8c0ab57f2990c5bf4ab3d",
+      "rawUrl": "https://raw.githubusercontent.com/openai/codex/ddea03ad049142943bdbf13e937b1d67e8c1ba0c/codex-rs/models-manager/models.json"
+    },
+    "codex-rs/models-manager/src/model_info.rs": {
+      "role": "model metadata representation and context-window limits",
+      "gitBlobSha": "ca1006993137d66de19137ff136f7ac8d36f9da3",
+      "sha256": "919883a4a15f6f3cace2ec78388aa7f9f8e042f74f553877843552ed55bf15bf",
+      "rawUrl": "https://raw.githubusercontent.com/openai/codex/ddea03ad049142943bdbf13e937b1d67e8c1ba0c/codex-rs/models-manager/src/model_info.rs"
+    },
+    "codex-rs/core/src/client.rs": {
+      "role": "Responses Lite and WebSocket request behavior",
+      "gitBlobSha": "8d2db30d7bb942cd030cb8d511eaafba8cbe46dd",
+      "sha256": "6a9b3d5d60293ca694e1642c905b574c2c12da490cff1c165e485f35a81f6edb",
+      "rawUrl": "https://raw.githubusercontent.com/openai/codex/ddea03ad049142943bdbf13e937b1d67e8c1ba0c/codex-rs/core/src/client.rs"
+    }
+  },
+  "catalogReference": {
+    "package": "@earendil-works/pi-ai",
+    "version": "0.85.1",
+    "license": "MIT",
+    "repository": "https://github.com/earendil-works/pi",
+    "tarballIntegrity": "sha512-+VgVIJDkDO2efYJKEEqvPTH4zmnIaXdAppGbO+vKFA9qy5PdhFiAenuFAkU+oiCSfOC4dMHDyrjdQeL4ZoC5CQ==",
+    "path": "dist/providers/data/openai-codex.json",
+    "sha256": "a10bfcfd34db6bcb98d8ee46175e154cab30530a137dbf31ac1434020ed3ffdd"
+  },
+  "localImplementations": [
+    "pi-codex-runtime/src/model-catalog/default-models.json",
+    "pi-codex-minimal-tools/src/model-catalog/default-models.json"
+  ]
+}

package/src/model-catalog/default-models.json

@@ -150,6 +150,14 @@
         "endpoint": "codex"
       }
     },
+    {
+      "id": "openai-codex/gpt-6-astra",
+      "extends": "openai/gpt-5.6-sol",
+      "responses": {
+        "endpoint": "codex",
+        "reasoningSummary": "none"
+      }
+    },
     {
       "id": "openai-codex/gpt-5.6-terra",
       "extends": "openai/gpt-5.6-terra",