pi-openai-codex-compat 0.0.10-alpha.7 → 0.0.10-alpha.8
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
package/CHANGELOG.md
CHANGED
|
@@ -4,6 +4,9 @@
|
|
|
4
4
|
|
|
5
5
|
### Added
|
|
6
6
|
|
|
7
|
+
- Support `gpt-6-astra` for opt-in Responses Lite requests and `pro` reasoning
|
|
8
|
+
mode, without changing either setting's default.
|
|
9
|
+
|
|
7
10
|
- Add configurable Codex `exec_command` + `write_stdin` and `shell_command`
|
|
8
11
|
command surfaces, defaulting to persistent unified exec and replacing only
|
|
9
12
|
an active Pi `bash` tool. Command output follows Pi's 2,000-line/50-KiB tail
|
package/README.md
CHANGED
|
@@ -13,7 +13,7 @@ OpenAI Codex compatibility for [Pi](https://github.com/earendil-works/pi-mono),
|
|
|
13
13
|
- **Standalone web search**: exposes Pi's dotted `web.run` tool as a native Responses namespace and executes search and browsing through Codex `alpha/search`.
|
|
14
14
|
- **Dedicated Codex tool UI**: renders command tools, `apply_patch`, `image_gen.imagegen`, and `web.run` on a shared configurable surface with compact summaries and `Ctrl+O` expansion.
|
|
15
15
|
- **Hosted web-search fallback**: injects native `web_search` only when `web.run` is inactive, with cached, indexed, or live modes.
|
|
16
|
-
- **Native request controls**: configures Responses API text verbosity, reasoning summaries, and
|
|
16
|
+
- **Native request controls**: configures Responses API text verbosity, reasoning summaries, and standard/pro reasoning mode on supported models.
|
|
17
17
|
- **Session-local settings pane**: `/codex-settings` changes every compatibility setting for the current session; `Enter` persists and closes, `Escape` discards unsaved changes and closes, and `Ctrl+S` persists without closing.
|
|
18
18
|
- **Session-aware footer**: shows the current Pi session ID on the first line and appends non-default Codex request modes to the model side of Pi's normal second line.
|
|
19
19
|
|
|
@@ -37,21 +37,21 @@ The compatibility baseline is official Codex CLI `0.149.1`, released August 24,
|
|
|
37
37
|
|
|
38
38
|
### Configurable defaults that differ from Codex
|
|
39
39
|
|
|
40
|
-
| Area | This package by default
|
|
41
|
-
| --------------------------------------------- |
|
|
42
|
-
| Generated-image detail sent back to the model | Sends image tool-result content with `input_image.detail: "auto"`. On GPT-5.6, `auto` uses original-size image accounting.
|
|
43
|
-
| Image-generation tool | Enabled whenever an `openai-codex` model is selected. Backend capability and account failures surface when the tool executes.
|
|
44
|
-
| Standalone `web.run` | Disabled by default; when enabled, preferred over hosted `web_search` and sent with the complete reserved schema and description.
|
|
45
|
-
| Hosted web search | Disabled by default; when enabled, injected only for ordinary Responses while `web.run` is inactive. Responses Lite omits hosted tools.
|
|
46
|
-
| Coding mutation tools | Enables `apply_patch` and suppresses Pi's active `edit` and `write` tools.
|
|
47
|
-
| Command tools | Replaces an active Pi `bash` tool with `exec_command` and `write_stdin`.
|
|
48
|
-
| `apply_patch` debug output | Disabled; collapsed results show the normal visual summary and instruction rows.
|
|
49
|
-
| `apply_patch` diagnostics capture | Disabled; no separate request or filesystem snapshot artifacts are retained.
|
|
50
|
-
| Codex tool background | Uses a subtle theme-derived surface for extension-owned Codex tools.
|
|
51
|
-
| Auto-compaction trigger | Relies on Pi's reserve-token threshold unless a percentage is configured.
|
|
52
|
-
| Fast mode | Uses the normal tier.
|
|
53
|
-
| Responses Lite | Disabled; supported
|
|
54
|
-
| Text and reasoning request controls | Sends low text verbosity and automatic reasoning summaries; omits the default
|
|
40
|
+
| Area | This package by default | Official Codex | Configuration |
|
|
41
|
+
| --------------------------------------------- | ----------------------------------------------------------------------------------------------------------------------------------------- | --------------------------------------------------------------------------------------------------------------------------------------------- | --------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
|
|
42
|
+
| Generated-image detail sent back to the model | Sends image tool-result content with `input_image.detail: "auto"`. On GPT-5.6, `auto` uses original-size image accounting. | Uses `high`. | `imageDetail`: `auto`, `low`, `high`, or `original`. |
|
|
43
|
+
| Image-generation tool | Enabled whenever an `openai-codex` model is selected. Backend capability and account failures surface when the tool executes. | Stable and enabled by default, but additionally gated by plan, model, provider, authentication, image-generation, and namespace capabilities. | `imageGeneration`: boolean. |
|
|
44
|
+
| Standalone `web.run` | Disabled by default; when enabled, preferred over hosted `web_search` and sent with the complete reserved schema and description. | Enabled by default for `gpt-5.6-sol` through Responses Lite; otherwise subject to standalone-search feature and runtime gates. | `webRun`: boolean. |
|
|
45
|
+
| Hosted web search | Disabled by default; when enabled, injected only for ordinary Responses while `web.run` is inactive. Responses Lite omits hosted tools. | Omitted for `gpt-5.6-sol` while standalone `web.run` is available; otherwise defaults to cached mode when hosted search is supported. | `webRun` and `webSearch`: `disabled`, `cached`, `indexed`, or `live`. |
|
|
46
|
+
| Coding mutation tools | Enables `apply_patch` and suppresses Pi's active `edit` and `write` tools. | Chooses its tool surface from model metadata and runtime capabilities; there are no Pi `edit` or `write` tools to suppress. | `applyPatch`: boolean. |
|
|
47
|
+
| Command tools | Replaces an active Pi `bash` tool with `exec_command` and `write_stdin`. | Chooses unified exec or legacy shell from model metadata, platform, execution environment, and runtime capabilities. | `shellTool`: `unified_exec` or `shell_command`. |
|
|
48
|
+
| `apply_patch` debug output | Disabled; collapsed results show the normal visual summary and instruction rows. | Not applicable to Pi's tool-result renderer. | `applyPatchDebug`: boolean. |
|
|
49
|
+
| `apply_patch` diagnostics capture | Disabled; no separate request or filesystem snapshot artifacts are retained. | Codex owns its rollout diagnostics rather than writing this package's artifact format. | `applyPatchDiagnostics`: boolean. |
|
|
50
|
+
| Codex tool background | Uses a subtle theme-derived surface for extension-owned Codex tools. | Uses Codex's own TUI activity cells rather than Pi tool rows. | `toolBackground`: `subtle`, `status`, or `none`. |
|
|
51
|
+
| Auto-compaction trigger | Relies on Pi's reserve-token threshold unless a percentage is configured. | Tracks Codex's model/token-budget state before and between sampling steps. | `autoCompactAtPercent`: percentage or unset. Mid-response percentage boundaries use Pi's bounded compact-and-continue lifecycle, so Pi auto-compaction must remain enabled. |
|
|
52
|
+
| Fast mode | Uses the normal tier. | Uses the configured Codex service tier. | `fastMode`: boolean; `true` requests the priority tier. |
|
|
53
|
+
| Responses Lite | Disabled; supported models use ordinary Responses. | Enabled according to Codex model metadata. | `responsesLite`: boolean; `true` enables Responses Lite. |
|
|
54
|
+
| Text and reasoning request controls | Sends low text verbosity and automatic reasoning summaries; omits the default standard mode and sends `reasoning.mode` only for pro mode. | Resolves these controls through Codex configuration, model metadata, and turn state. | `textVerbosity`, `reasoningSummary`, and `reasoningMode`. |
|
|
55
55
|
|
|
56
56
|
`web.run` is a reserved GPT-5.6 tool name. Its declaration therefore reproduces the complete current Codex post-normalization `SearchCommands` schema and official tool description instead of using Pi's normal compact tool schema. This intentionally omits generated annotations such as `format` and `minimum` that Codex removes before sending the declaration to Responses.
|
|
57
57
|
|
|
@@ -198,7 +198,7 @@ Defaults:
|
|
|
198
198
|
| Setting | Values | Default | Behavior |
|
|
199
199
|
| ----------------------- | ---------------------------------------------------- | -------------- | ----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
|
|
200
200
|
| `fastMode` | boolean | `false` | Adds `service_tier: "priority"` to requests while retaining the current `openai-codex` provider and model. |
|
|
201
|
-
| `responsesLite` | boolean | `false` | Uses Codex's Responses Lite input envelope on supported
|
|
201
|
+
| `responsesLite` | boolean | `false` | Uses Codex's Responses Lite input envelope on supported models when enabled. By default, those models use ordinary Responses instructions and tools. |
|
|
202
202
|
| `toolBackground` | `subtle`, `status`, `none` | `subtle` | Controls the shared self-rendered background for command tools, `apply_patch`, `image_gen.imagegen`, and `web.run`. `status` uses Pi's pending/success/error backgrounds; `none` keeps the custom layout transparent. |
|
|
203
203
|
| `shellTool` | `unified_exec`, `shell_command` | `unified_exec` | Selects the command surface on `openai-codex` models. The selected Codex command surface replaces Pi `bash` only when `bash` was active. |
|
|
204
204
|
| `applyPatch` | boolean | `true` | On selected `openai-codex` models, uses the extension's `apply_patch` tool instead of Pi's active `edit` and `write` tools. Other providers always use their normal Pi tool set. |
|
|
@@ -211,7 +211,12 @@ Defaults:
|
|
|
211
211
|
| `webSearch` | `disabled`, `cached`, `indexed`, `live` | `disabled` | Controls hosted search and standalone-search external access. `disabled` removes hosted search but leaves an independently enabled `web.run` in cached-only mode; `indexed` prefers indexed content; `live` permits live external access. |
|
|
212
212
|
| `textVerbosity` | `low`, `medium`, `high` | `low` | Sets Responses API `text.verbosity`. |
|
|
213
213
|
| `reasoningSummary` | `auto`, `concise`, `detailed`, `off` | `auto` | Sets `reasoning.summary` when reasoning is enabled; `off` omits the summary parameter. |
|
|
214
|
-
| `reasoningMode` | `standard`, `pro` | `standard` | Controls
|
|
214
|
+
| `reasoningMode` | `standard`, `pro` | `standard` | Controls supported models' execution mode independently of Pi's reasoning-effort control. The default omits `reasoning.mode`; `pro` sends `reasoning.mode: "pro"`. |
|
|
215
|
+
|
|
216
|
+
Responses Lite supports exactly `gpt-5.6-sol`, `gpt-5.6-terra`, `gpt-5.6-luna`,
|
|
217
|
+
and `gpt-6-astra`. Pro reasoning mode supports `gpt-5.6`, `gpt-5.6-*`, and
|
|
218
|
+
exactly `gpt-6-astra`. Both controls remain opt-in; other GPT-6 model IDs are
|
|
219
|
+
not included.
|
|
215
220
|
|
|
216
221
|
Invalid JSON setting values are ignored and invalid JSON does not prevent Pi from starting. The settings pane never writes on ordinary changes, refuses to overwrite invalid JSON when `Enter` or `Ctrl+S` attempts to save, and retains unknown keys when saving. Project configuration is read only when the project is trusted.
|
|
217
222
|
|
|
@@ -306,6 +311,12 @@ permissions.
|
|
|
306
311
|
|
|
307
312
|
## Native compaction
|
|
308
313
|
|
|
314
|
+
See the [Codex compaction approach review](CODEX_COMPACTION_APPROACH_REVIEW.md)
|
|
315
|
+
for a focused `0.153.4` source review, including experimental notes/history
|
|
316
|
+
recovery and unsummarized context resets, implementation options, and trade-offs.
|
|
317
|
+
That proposal does not change this package's runtime or its package-wide
|
|
318
|
+
compatibility baseline.
|
|
319
|
+
|
|
309
320
|
The extension handles native compaction for `openai-codex`. It follows the Codex v2 flow:
|
|
310
321
|
|
|
311
322
|
1. Send normal Responses history followed by `{ "type": "compaction_trigger" }`.
|
|
@@ -313,7 +324,7 @@ The extension handles native compaction for `openai-codex`. It follows the Codex
|
|
|
313
324
|
3. Retain approximately 64,000 tokens of recent user, developer, and system context.
|
|
314
325
|
4. Persist the opaque checkpoint in the Pi session and replay it on later requests.
|
|
315
326
|
|
|
316
|
-
Ordinary responses and compaction use the same extension-managed SSE/WebSocket transport. Before the first WebSocket turn for a session and model, the provider performs a best-effort v2 `generate: false` prewarm of the static instruction/tool prefix, then generates the dynamic conversation input from its continuation. With `responsesLite: false`, supported
|
|
327
|
+
Ordinary responses and compaction use the same extension-managed SSE/WebSocket transport. Before the first WebSocket turn for a session and model, the provider performs a best-effort v2 `generate: false` prewarm of the static instruction/tool prefix, then generates the dynamic conversation input from its continuation. With `responsesLite: false`, supported models use the ordinary Responses envelope and receive their own ordinary-prefix prewarm.
|
|
317
328
|
|
|
318
329
|
Healthy session WebSockets remain available until the server closes them or Pi tears down the session. Retryable WebSocket failures before model-visible output receive up to five fresh-connection retries before the session switches to sticky SSE. Retryable SSE HTTP failures and dropped streams receive up to five same-request resampling attempts before model-visible output. Both transports use Codex-style exponential backoff with ±10% jitter and preserve the same prompt-cache, session, account, installation, and window identities. Server metadata is not considered model-visible output, so a routing-state-only response can still be retried safely. Transport failures after model-visible output fail closed rather than risk duplicate text or tool calls. Explicit retryable `response.failed`/`response.incomplete` protocol terminals instead return to the provider-owned sampling loop, which preserves completed output items as the next request's history.
|
|
319
330
|
|
|
@@ -20,7 +20,7 @@ export function isCodexModel(model: Model<Api> | undefined): model is Model<type
|
|
|
20
20
|
}
|
|
21
21
|
|
|
22
22
|
export function supportsReasoningMode(modelId: string): boolean {
|
|
23
|
-
return /^gpt-5\.6(?:-|$)/.test(modelId);
|
|
23
|
+
return modelId === "gpt-6-astra" || /^gpt-5\.6(?:-|$)/.test(modelId);
|
|
24
24
|
}
|
|
25
25
|
|
|
26
26
|
function isWebSearchTool(value: unknown): boolean {
|
package/package.json
CHANGED