@bastani/pi-ai 0.9.25-alpha.4 → 0.9.25
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 +4,32 @@ This package is a Bastani fork of `@earendil-works/pi-ai`. Upstream history at t
|
|
|
4
4
|
|
|
5
5
|
## [Unreleased]
|
|
6
6
|
|
|
7
|
+
## [0.9.25] - 2026-10-01
|
|
8
|
+
|
|
9
|
+
### Added
|
|
10
|
+
|
|
11
|
+
- Added Anthropic workload identity federation from the Anthropic SDK environment variables `ANTHROPIC_FEDERATION_RULE_ID`, `ANTHROPIC_ORGANIZATION_ID`, and `ANTHROPIC_IDENTITY_TOKEN_FILE` (plus optional `ANTHROPIC_SERVICE_ACCOUNT_ID` and `ANTHROPIC_WORKSPACE_ID`). API keys and `ANTHROPIC_AUTH_TOKEN` take precedence ([#10177](https://github.com/earendil-works/pi/issues/10177), [#10242](https://github.com/earendil-works/pi/pull/10242) by [@philfreo](https://github.com/philfreo)).
|
|
12
|
+
- Anthropic subscription login now offers a copy-code method for remote or headless machines, alongside the default browser callback method ([#10194](https://github.com/earendil-works/pi/pull/10194) by [@lucasmeijer](https://github.com/lucasmeijer)).
|
|
13
|
+
- Added GPT-6.1 Sol for OpenAI and Codex with supported reasoning efforts, prompt-cache and tool capabilities, and long-context pricing metadata.
|
|
14
|
+
- Added GPT-6.1 Sol to the GitHub Copilot catalog with Copilot's Responses endpoint, supported reasoning efforts, and provider-published context and output limits. Availability remains subject to the account's model policy.
|
|
15
|
+
- Added **Sign in with ChatGPT** for the OpenAI Responses API alongside API-key authentication, separate from Codex subscription login.
|
|
16
|
+
- Added Jev classifiers on Vercel AI Gateway and OpenCode Zen, and provider-reported classifier usage and costs, including billed responses with invalid answers.
|
|
17
|
+
- Added the lightweight `@bastani/pi-ai/models` entry point for model catalog consumers.
|
|
18
|
+
- Added `Model.serviceTiers` and `getServiceTierCost()` for the Fast and Ultrafast tiers a model advertises and their published rates. The OpenAI catalog follows OpenAI's Fast and Ultrafast pricing tables. The Codex catalog follows Codex's per-model tiers: Fast for every model except GPT-5.3 Codex Spark, and Ultrafast for GPT-6 Astra.
|
|
19
|
+
- The OpenAI Responses adapter can send GPT-6 Astra's `ultrafast` tier.
|
|
20
|
+
|
|
21
|
+
### Changed
|
|
22
|
+
|
|
23
|
+
- The Codex Responses adapter sends `service_tier` only when the model advertises it, following Codex: `flex` always passes through, `default` sends no tier, and an unadvertised tier is left out instead of failing.
|
|
24
|
+
- The OpenAI Responses adapter leaves out a Fast or Ultrafast tier the model doesn't advertise. It sends other tiers as requested.
|
|
25
|
+
- Fast and Ultrafast usage is priced at the served tier's published rates. A model without tier metadata keeps the previous Fast multiplier.
|
|
26
|
+
|
|
27
|
+
### Fixed
|
|
28
|
+
|
|
29
|
+
- Fixed context overflow detection for Z.AI CN endpoint `Prompt exceeds max length` errors ([#10208](https://github.com/earendil-works/pi/issues/10208)).
|
|
30
|
+
- Anthropic `strict: "prefer"` tools now fall back to non-strict mode for unsupported string formats and additional array/object constraints instead of rejecting the request. Supported string length and pattern constraints remain strict ([#9953](https://github.com/earendil-works/pi/issues/9953)).
|
|
31
|
+
- Provider retries now use exponential backoff when `Retry-After` or `retry-after-ms` cannot be parsed as a finite delay ([#9571](https://github.com/earendil-works/pi/issues/9571)).
|
|
32
|
+
|
|
7
33
|
## [0.9.25-alpha.3] - 2026-09-30
|
|
8
34
|
|
|
9
35
|
### Added
|
|
@@ -1 +1 @@
|
|
|
1
|
-
{"schemaVersion":6,"generatedAt":"2026-10-
|
|
1
|
+
{"schemaVersion":6,"generatedAt":"2026-10-01T15:22:35.819Z","structureHash":"013f6e15be3a5cc2ce1033d8612d08eeeff85f84bfd529371b11882af9e00b39","files":{"amazon-bedrock.json":"d1e91cffcaa338ce0574ecfae1a52271c4c4944b3e8e7581c5d7bc4154a396bb","ant-ling.json":"628feab3ef6c7d80ce96f75999804e1d9f05fec3851e5302e30fff3b69db90f6","anthropic.json":"c436c0f1f984e0a04f9d472533c20ce38c8da101d23484d6d7fe7892cdaa6830","azure-openai-responses.json":"bddff8380252746bbf6ee9901d6299e00ec0cc38facb6013b46b43c6ef231fdd","baseten.json":"b04d1423d6958bec857ffccc36726f091ec1a8f3a09cf0836b64cc94b0ee697d","cerebras.json":"3eccb58c5de3d0dc7ba49dc6e477ba29f00cb3150ce0a35cc90d59e6b5ab368e","cloudflare-ai-gateway.json":"5f9dbc3e5f4ef2ea7aa659f3fa28d77b5127e309305906bae47b25638931ba73","cloudflare-workers-ai.json":"b9f76cc83756a05920a8a7046c515919a1de918331b860a211f309bb716c4bb0","deepseek.json":"10a296fb3e898f7715c80890c8af0af4f5fd58f22dbcd6612fdc5d762157ccdc","fireworks.json":"d6144ba451bd7a0617669527bec1898f97a633f7d7ea5035d8e03234550340c0","github-copilot.json":"2362c7f129b6fca87ac45e06463ddb0f080477f820fd4eba55c150b0aeb99cba","google-vertex.json":"40090c680538bc867f2624d986a449f361be4dfa6ba96d7a27402050f036e009","google.json":"c0f5a633e5e5a5044432db3e537f4bc674d4de18df09325c6349547fcc13cabe","groq.json":"910952ad9dad07856983459d63fce0148dba1203edd7b10d801a77c5824f3405","huggingface.json":"1b8604bd31a5e05fe43a40ec1ec6dfc1a51a28b0b020151ef057fab43f57c923","kimi-coding.json":"582250b920454d98940da3e7e99d30b807edbea28f2eb8ac15f658d2ef41e8fc","meta.json":"0c7e9a370a7005c5a89dc94f0f93bc67b8935c3f802de324f11af6ff56fff429","minimax-cn.json":"f962c20ee6a6a342820f778e9dc363a18a524bf11998f6e2c57f2989915d62e5","minimax.json":"17a432f80d0ea6dd26eade80a4314250d3a855678601728a5f70dd8fa0d21dd2","mistral.json":"10f33bff9adf1248f7e6848e5890c265399f1f94e5b42cfdc28c109d547af98d","moonshotai-cn.json":"79c9585dc84ee525ebaebbc78b3c55f3d369ec884d4f943488f1e0b14e3587f5","moonshotai.json":"1da2c4e34f22aef17a07c974d85bdee8e1b68b6dc712e3769c935b3f1e7dadca","nvidia.json":"3b4e7b799bf3eaacd1af0491eef77fe33147ea7f72a3a9fa54d77af0e7eacf4c","openai-codex.json":"0c6c33c094d3175641a64a13215aa3b8c229964bb2c896e04cac1e2d2edf4a63","openai.json":"31e704f9e0ce46d0c2265eacd51a8d80e64ac52d5f3ca9679880fc0e0d79e057","opencode-go.json":"d05b3eb87b81c6e5a94801484e668e660fe60c68f06a972b716d581c3bbd7c25","opencode.json":"7996b45788b8c3892d474194661a70dc63a4f59470ea50b00cbd902859a262b5","openrouter.json":"35c8352b26532de10ee1b312cf998f00bc5d2454a689dd5c16335d631cad1a67","qwen-token-plan-cn.json":"2469a4091c474ec3db0a49a9962d8d2726c074ad9065b96bc4e0c87861c4c6c5","qwen-token-plan-individual.json":"0fb7cf64faf39d1a3b0a884210a86c87084b805eda15644f5f39293287b959dd","qwen-token-plan.json":"eff10620cb577142de4ec02698d5961a71fda2fe4f6ae7ea9432bad9d6844176","radius.json":"d9158329af6688b83afb5bdf3916dc91115af2a85f97bfffa72449a29450a52f","together.json":"94ec3839972061405885d64f5fdbde48eb1f29a159be5e607e9770befd54e28e","typesafe.json":"a4429a2f696d5cc5273969af61a7310bda07d6bdcd27bf9ac9c76c534cc43716","vercel-ai-gateway.json":"1790cf122b681d418c01f1f4c6a6f0f9ad741502c032727b31dad43c84f96e7d","xai.json":"879c49b78b663a52a220ac4ee013e726b10c4f50aaa03bc58ee53a4b54c76928","xiaomi-token-plan-ams.json":"ca65178f4525d9705bc8d085ed136cecbe149c4080e857ea6a64ae643d2ac00a","xiaomi-token-plan-cn.json":"b065326926681c2262084e59c1c19ebdaf146c07107b5242c76b456becf74db0","xiaomi-token-plan-sgp.json":"92c3d6d707f81fd9cd2b6d1fb57dc431d90ba51e10fe49d97bc8806035c23492","xiaomi.json":"b81d01a374f7b558728c78d81f4168efa9c8996e6e2b5618409a8094b083c759","zai-coding-cn.json":"ee5ee705fb6e413a6088db5e3616c27fce802a8ece6c355f1db35490d787f610","zai.json":"58e6642fdfb736f0b9a4a277c760c536a3cea66a030abbfb2615f7b2851d5c6f"}}
|