pi-better-web-search 0.1.9 → 0.1.11
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 +14 -0
- package/README.md +15 -6
- package/docs/README.zh-CN.md +10 -4
- package/docs/providers.md +14 -2
- package/docs/publishing.md +6 -6
- package/lib/providers/openai.ts +9 -1
- package/lib/search.ts +1 -1
- package/package.json +3 -3
package/CHANGELOG.md
CHANGED
|
@@ -1,5 +1,19 @@
|
|
|
1
1
|
# Changelog
|
|
2
2
|
|
|
3
|
+
## 0.1.11
|
|
4
|
+
|
|
5
|
+
- Increase the default timeout to 120 seconds per search and URL fetch attempt
|
|
6
|
+
for all providers. Provider errors still trigger fallback immediately, and
|
|
7
|
+
`PI_BETTER_WEB_SEARCH_TIMEOUT_MS` can override the default.
|
|
8
|
+
|
|
9
|
+
## 0.1.10
|
|
10
|
+
|
|
11
|
+
- Verify against Pi 1.5.2 and document support for the OpenAI ChatGPT OAuth
|
|
12
|
+
login as well as OpenAI API keys and legacy Codex OAuth.
|
|
13
|
+
- Use the lowest model-supported reasoning effort for OpenAI Responses search,
|
|
14
|
+
independently of the conversation's thinking level, as in pi-web-search.
|
|
15
|
+
- Document that Pi virtual models are not directly supported.
|
|
16
|
+
|
|
3
17
|
## 0.1.9
|
|
4
18
|
|
|
5
19
|
- Preserve provider diversity and apply cooldowns before limiting actual search
|
package/README.md
CHANGED
|
@@ -10,7 +10,7 @@ and returns provider data as-is.
|
|
|
10
10
|
[](https://github.com/zhexusun10/pi-better-web-search/actions/workflows/ci.yml)
|
|
11
11
|
[](https://www.npmjs.com/package/pi-better-web-search)
|
|
12
12
|
[](LICENSE)
|
|
13
|
-
[](https://pi.dev)
|
|
14
14
|
[](https://nodejs.org)
|
|
15
15
|
|
|
16
16
|
[简体中文](docs/README.zh-CN.md) · [Architecture](docs/architecture.md) · [Providers](docs/providers.md) · [Testing](docs/testing.md) · [Source](extensions/index.ts)
|
|
@@ -29,14 +29,14 @@ Then start a new pi process, or run `/reload` in an existing session.
|
|
|
29
29
|
GitHub and local installations also work:
|
|
30
30
|
|
|
31
31
|
```bash
|
|
32
|
-
pi install git:github.com/zhexusun10/pi-better-web-search@v0.1.
|
|
32
|
+
pi install git:github.com/zhexusun10/pi-better-web-search@v0.1.11
|
|
33
33
|
pi install ./path/to/pi-better-web-search
|
|
34
34
|
```
|
|
35
35
|
|
|
36
36
|
> Do not load this package together with `pi-web-search`. Both register a tool
|
|
37
37
|
> named `web_search`, and the second registration replaces the first.
|
|
38
38
|
|
|
39
|
-
Requirements: **pi 1.3+** and **Node.js 22.19+**.
|
|
39
|
+
Requirements: **pi 1.3+** and **Node.js 22.19+**. Tested with **pi 1.5.2**.
|
|
40
40
|
|
|
41
41
|
## What it fixes
|
|
42
42
|
|
|
@@ -120,6 +120,12 @@ invalid URLs alongside valid work are reported in the `fetched` entries.
|
|
|
120
120
|
| 10 | **xAI (Grok)** | Yes | No | Grok dialect Responses API (`web_search_call.action.sources`) |
|
|
121
121
|
| * | **Anthropic Messages** | Yes | No | Messages API `web_search_20260209` tool & Claude Code OAuth |
|
|
122
122
|
|
|
123
|
+
OpenAI search supports both Pi's **OpenAI (ChatGPT subscription) / Sign in with
|
|
124
|
+
ChatGPT** OAuth login and an OpenAI API key, as well as the separate legacy
|
|
125
|
+
**OpenAI Codex** OAuth login. Model and web search availability still depend
|
|
126
|
+
on the account and service. Pi virtual models (`pi-virtual`) are not directly
|
|
127
|
+
supported; automatic fallback can still use an authenticated concrete model.
|
|
128
|
+
|
|
123
129
|
URL analysis is only exposed when at least one usable interface supports it.
|
|
124
130
|
For example, a current OpenAI model with only OpenAI credentials gets a
|
|
125
131
|
query-only schema, while the same session with DeepSeek, Ollama Cloud, or Google
|
|
@@ -173,9 +179,12 @@ remembered compatible provider immediately on later calls.
|
|
|
173
179
|
|
|
174
180
|
If a provider errors, the extension records the attempt and moves to the next
|
|
175
181
|
interface. An overlong query rejected by DeepSeek instead returns immediately
|
|
176
|
-
without trying another provider or updating its health state. Aborts stop
|
|
177
|
-
|
|
178
|
-
|
|
182
|
+
without trying another provider or updating its health state. Aborts stop
|
|
183
|
+
immediately. Each search or URL fetch attempt times out after 120 seconds by
|
|
184
|
+
default; explicit provider errors trigger fallback immediately without waiting
|
|
185
|
+
for the timeout. Set `PI_BETTER_WEB_SEARCH_TIMEOUT_MS` to override the per-attempt
|
|
186
|
+
timeout. If every attempt fails, the tool returns an error whose message contains
|
|
187
|
+
the provider errors.
|
|
179
188
|
Provider/model routing remains in `details.attempts`. For a URL-only call, the
|
|
180
189
|
error also reports the per-URL failures. Provider error bodies and model-facing
|
|
181
190
|
error text are bounded to prevent an oversized error from filling the context.
|
package/docs/README.zh-CN.md
CHANGED
|
@@ -22,14 +22,14 @@ pi install npm:pi-better-web-search
|
|
|
22
22
|
也可以从 GitHub 或本地安装:
|
|
23
23
|
|
|
24
24
|
```bash
|
|
25
|
-
pi install git:github.com/zhexusun10/pi-better-web-search@v0.1.
|
|
25
|
+
pi install git:github.com/zhexusun10/pi-better-web-search@v0.1.11
|
|
26
26
|
pi install ./path/to/pi-better-web-search
|
|
27
27
|
```
|
|
28
28
|
|
|
29
29
|
> 不要和 `pi-web-search` 同时加载。两者都注册 `web_search`,后注册的会覆盖
|
|
30
30
|
> 先注册的。
|
|
31
31
|
|
|
32
|
-
要求:**pi 1.3+**,**Node.js 22.19
|
|
32
|
+
要求:**pi 1.3+**,**Node.js 22.19+**。已通过 **pi 1.5.2** 依赖测试。
|
|
33
33
|
|
|
34
34
|
## 它解决什么问题
|
|
35
35
|
|
|
@@ -101,6 +101,11 @@ provider 都失败时,工具返回错误(`isError: true`),不会静默
|
|
|
101
101
|
| 10 | **xAI (Grok)** | 是 | 否 | 原生 Grok 方言 Responses API(`web_search_call.action.sources`) |
|
|
102
102
|
| * | **Anthropic Messages** | 是 | 否 | Messages API `web_search_20260209` 工具及 Claude Code OAuth 凭据 |
|
|
103
103
|
|
|
104
|
+
OpenAI 搜索支持 Pi 的 **OpenAI(ChatGPT 订阅)/ Sign in with ChatGPT**
|
|
105
|
+
OAuth 登录、OpenAI API Key,以及独立的旧版 **OpenAI Codex** OAuth 登录。
|
|
106
|
+
模型和搜索工具能否使用仍取决于账号及服务。Pi 虚拟模型(`pi-virtual`)
|
|
107
|
+
暂不直接支持,但可自动回退到其他已认证的具体模型。
|
|
108
|
+
|
|
104
109
|
只有至少一个可用接口支持 URL 分析时,`urls` 才会暴露。例如:当前模型是
|
|
105
110
|
OpenAI 且只有 OpenAI 凭据时,schema 只有 `query`;同一会话只要还有
|
|
106
111
|
DeepSeek、Google Gemini、Antigravity 或 Ollama Cloud 凭据,就会出现 `urls`。
|
|
@@ -142,8 +147,9 @@ Provider 识别顺序:
|
|
|
142
147
|
的兼容 provider。
|
|
143
148
|
|
|
144
149
|
Provider 报错时记录 attempt 并继续下一个接口。DeepSeek 查询超长则直接返回错误,
|
|
145
|
-
不继续尝试其他 provider,也不记录为 provider
|
|
146
|
-
|
|
150
|
+
不继续尝试其他 provider,也不记录为 provider 健康故障。取消会立即停止。搜索和 URL
|
|
151
|
+
抓取的每次尝试默认超时 120 秒;provider 直接报错时立即 fallback,不等待超时。
|
|
152
|
+
`PI_BETTER_WEB_SEARCH_TIMEOUT_MS` 可覆盖默认值。所有尝试都失败时,
|
|
147
153
|
工具返回错误,消息中包含 provider 返回的错误;provider/model 路由信息保留在
|
|
148
154
|
`details.attempts` 中。URL-only 调用还会报告每个 URL 的失败原因。provider 错误
|
|
149
155
|
响应体与发给模型的错误文本都有大小限制,避免错误内容占满上下文。
|
package/docs/providers.md
CHANGED
|
@@ -24,6 +24,9 @@ served by the native DeepSeek provider or Ollama Cloud. In particular, the
|
|
|
24
24
|
built-in `opencode-go` DeepSeek models use `openai-completions`; brand ranking
|
|
25
25
|
does not make them Responses-compatible or expose them as search candidates.
|
|
26
26
|
A local Ollama daemon is not supported; Ollama Cloud uses the hosted REST API.
|
|
27
|
+
Pi virtual models (`pi-virtual`) are not directly supported: their routed
|
|
28
|
+
concrete model is not known to this extension. The normal fallback can still
|
|
29
|
+
select another authenticated concrete model.
|
|
27
30
|
|
|
28
31
|
## DeepSeek
|
|
29
32
|
|
|
@@ -150,9 +153,18 @@ Supported APIs:
|
|
|
150
153
|
- `azure-openai-responses`
|
|
151
154
|
- `openai-codex-responses`
|
|
152
155
|
|
|
156
|
+
The `openai` provider uses the Responses API with either pi's **Sign in with
|
|
157
|
+
ChatGPT** OAuth credentials or an OpenAI API key (`OPENAI_API_KEY` or pi's
|
|
158
|
+
registry). Pi resolves and refreshes OAuth credentials; the resulting access
|
|
159
|
+
token is sent as a Bearer token. `openai-codex` uses a separate legacy ChatGPT
|
|
160
|
+
OAuth flow and Codex endpoint. Search availability depends on the account,
|
|
161
|
+
subscription, model and OpenAI service.
|
|
162
|
+
|
|
153
163
|
The request uses `tools: [{ "type": "web_search" }]`, `stream: true`, and
|
|
154
|
-
`store: false`.
|
|
155
|
-
|
|
164
|
+
`store: false`. For reasoning models, the request uses the lowest effort
|
|
165
|
+
supported by the model metadata, independently of the conversation's thinking
|
|
166
|
+
level; native xAI does not send this setting. Endpoint resolution appends
|
|
167
|
+
`/responses`, or `/codex/responses` for Codex models. Codex requests add the account id header,
|
|
156
168
|
`originator: codex_cli_rs`, instructions, low verbosity, required tool choice,
|
|
157
169
|
and parallel tool calls.
|
|
158
170
|
|
package/docs/publishing.md
CHANGED
|
@@ -30,7 +30,7 @@ local `pi-web-search` reference checkout, `.env` files, and `DESIGN.md`.
|
|
|
30
30
|
npm run build
|
|
31
31
|
```
|
|
32
32
|
|
|
33
|
-
This produces `dist/pi-better-web-search-0.1.
|
|
33
|
+
This produces `dist/pi-better-web-search-0.1.11.tgz`. The tarball is not
|
|
34
34
|
committed.
|
|
35
35
|
|
|
36
36
|
## Publish
|
|
@@ -42,7 +42,7 @@ npm publish --access public
|
|
|
42
42
|
Alternatively, publish the verified tarball directly:
|
|
43
43
|
|
|
44
44
|
```bash
|
|
45
|
-
npm publish dist/pi-better-web-search-0.1.
|
|
45
|
+
npm publish dist/pi-better-web-search-0.1.11.tgz --access public
|
|
46
46
|
```
|
|
47
47
|
|
|
48
48
|
`prepublishOnly` reruns the checks, tests, and package verification. npm may
|
|
@@ -51,10 +51,10 @@ require browser or OTP authentication.
|
|
|
51
51
|
## Tag and release
|
|
52
52
|
|
|
53
53
|
```bash
|
|
54
|
-
git tag -a v0.1.
|
|
55
|
-
git push origin v0.1.
|
|
56
|
-
gh release create v0.1.
|
|
57
|
-
--title "v0.1.
|
|
54
|
+
git tag -a v0.1.11 -m "v0.1.11"
|
|
55
|
+
git push origin v0.1.11
|
|
56
|
+
gh release create v0.1.11 dist/pi-better-web-search-0.1.11.tgz \
|
|
57
|
+
--title "v0.1.11" \
|
|
58
58
|
--notes-file /path/to/release-notes.md
|
|
59
59
|
```
|
|
60
60
|
|
package/lib/providers/openai.ts
CHANGED
|
@@ -1,5 +1,5 @@
|
|
|
1
1
|
import type { ExtensionContext } from "@earendil-works/pi-coding-agent";
|
|
2
|
-
import type
|
|
2
|
+
import { clampThinkingLevel, type Api, type Model } from "@earendil-works/pi-ai";
|
|
3
3
|
import {
|
|
4
4
|
buildRequestHeaders,
|
|
5
5
|
getHeader,
|
|
@@ -152,6 +152,14 @@ async function searchResponses(
|
|
|
152
152
|
stream: true,
|
|
153
153
|
store: false,
|
|
154
154
|
};
|
|
155
|
+
// Search is independent of the conversation's thinking setting. Use the
|
|
156
|
+
// lowest supported effort to avoid unnecessary latency and token usage.
|
|
157
|
+
// Native xAI does not accept the same reasoning controls.
|
|
158
|
+
if (family !== "xai" && model.reasoning) {
|
|
159
|
+
const level = clampThinkingLevel(model, "off");
|
|
160
|
+
const mapped = model.thinkingLevelMap?.[level];
|
|
161
|
+
if (mapped !== null) body.reasoning = { effort: mapped ?? (level === "off" ? "none" : level) };
|
|
162
|
+
}
|
|
155
163
|
if (isCodex) {
|
|
156
164
|
body.instructions = "Answer the user's request using web search when needed.";
|
|
157
165
|
body.text = { verbosity: "low" };
|
package/lib/search.ts
CHANGED
|
@@ -31,7 +31,7 @@ import {
|
|
|
31
31
|
import { QueryLengthError } from "./providers/types.ts";
|
|
32
32
|
import { MAX_URLS } from "./schema.ts";
|
|
33
33
|
|
|
34
|
-
export const DEFAULT_ATTEMPT_TIMEOUT_MS =
|
|
34
|
+
export const DEFAULT_ATTEMPT_TIMEOUT_MS = 120_000;
|
|
35
35
|
|
|
36
36
|
export interface UrlValidationError {
|
|
37
37
|
url: string;
|
package/package.json
CHANGED
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
{
|
|
2
2
|
"name": "pi-better-web-search",
|
|
3
|
-
"version": "0.1.
|
|
3
|
+
"version": "0.1.11",
|
|
4
4
|
"description": "A better provider-native web_search tool for pi: raw results, automatic provider fallback, URL analysis, and native DeepSeek Search/Fetch.",
|
|
5
5
|
"type": "module",
|
|
6
6
|
"license": "MIT",
|
|
@@ -58,8 +58,8 @@
|
|
|
58
58
|
"typebox": "*"
|
|
59
59
|
},
|
|
60
60
|
"devDependencies": {
|
|
61
|
-
"@earendil-works/pi-ai": "1.
|
|
62
|
-
"@earendil-works/pi-coding-agent": "1.
|
|
61
|
+
"@earendil-works/pi-ai": "1.5.2",
|
|
62
|
+
"@earendil-works/pi-coding-agent": "1.5.2",
|
|
63
63
|
"@types/node": "22.19.19",
|
|
64
64
|
"typebox": "1.3.27",
|
|
65
65
|
"typescript": "5.9.3"
|