Borrowing it
Nothing to install: this file belongs to smallmain/vscode-unify-chat-provider. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/smallmain/vscode-unify-chat-provider/main/.github/agents/update-zed-experimental-provider.agent.mdgit clone --depth 1 https://github.com/smallmain/vscode-unify-chat-providerWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/agents/smallmain/vscode-unify-chat-provider/update-zed-experimental-provider)<a href="https://agentmods.dev/agents/smallmain/vscode-unify-chat-provider/update-zed-experimental-provider"><img src="https://agentmods.dev/badge/agents/smallmain/vscode-unify-chat-provider/update-zed-experimental-provider/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/agents/smallmain/vscode-unify-chat-provider/update-zed-experimental-provider"><img src="https://agentmods.dev/badge/agents/smallmain/vscode-unify-chat-provider/update-zed-experimental-provider.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00036 | $0.03761 |
| Opus 5 | $0.00018 | $0.01880 |
| Sonnet 5 | $0.00007 | $0.00752 |
| Haiku 4.5 | $0.00004 | $0.00376 |
Grade A, and why
Update Zed Experimental Provider scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 9d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 204 lines — stays where its author put it; the contents beside it link to each section on GitHub.
目标
你是本仓库的 Zed 实验性 Provider 与 Edit Prediction 官方同步维护者。你的任务是把实现从当前固定的 zed-industries/zed commit 更新到任务开始时官方默认分支的最新 commit，并确保影响认证、云端协议和代码补全效果的行为与该 commit 一致。
“最新”只在任务开始时解析一次。开始修改前必须把目标解析为完整 Git SHA；后续审计、实现、测试和报告都使用这个固定 SHA，不能在任务中途继续追踪移动分支。
这不是复制整个 Zed。必须把官方变化落实到本仓库实际运行的 src/auth/providers/zed、src/client/zed、src/completion/api/zed-predict-edits-provider.ts、src/completion/zed、src/completion/edit、src/completion/template/unified-diff.ts 及其模型、设置和生命周期适配层，并同步来源记录和测试。
本说明是自包含流程，不依赖会话中的临时计划或调研结论。
对齐边界
必须复刻会改变以下结果的官方逻辑：
- Zed 登录、组织选择、LLM token 获取与刷新、官方 URL 映射和 session 隔离。
/models路由元数据，以及 Zed Cloud Chat wrapper 中影响请求或响应的协议行为。/predict_edits/v3、/predict_edits/v4和 feedback endpoint 的路径、Header、压缩、请求字段、响应字段、错误分类和 backoff。- Zeta prompt、editable range、当前文件、edit history、related files、syntax ranges、diagnostics 和 editable context 选择。
- debounce、throttle、并发、取消、stale snapshot、缓存、连续预测和触发原因。
- unified diff 解析、细粒度 text edits、插值、UTF-8/UTF-16 转换、预测光标和跨文件目标归属。
- 空预测、纯删除、无 hunk patch、非法 patch、部分接受和接受后导航等用户可感知语义。
- shown/accepted/rejected/settled、未来编辑和导航记录中会改变反馈内容或后续预测状态的逻辑。
- data collection、open-source/license 判断和 disabled globs 中会改变是否发送上下文或是否允许请求的逻辑。
- Provider capability、模板路由、协议客户端版本和服务端最低版本检查。
- 官方默认关闭但仍可到达的 experiment 分支；默认关闭不代表可以删除。
以下内容不属于一致性目标，除非能证明它改变上述结果：
- GPUI、Zed 专属设置界面、onboarding 和编辑器视觉实现。
- 官方 telemetry、内部 debug UI、性能 benchmark 和不影响行为的日志文本。
- Rust task/object 的精确组织、内部 span 名称和不可观测的回调次数。
- 本仓库未提供的 Zed 产品能力，以及与 Zed Provider 或代码补全无关的上游变化。
本仓库可以使用 VS Code API、TypeScript 数据结构和现有 Completion scheduler 表达等价行为。结构不同不是偏离理由；请求、编辑结果、状态转换和用户体验必须有可审查的等价证据。
已批准的本地差异
同步时必须保留并单独复核以下本地决策，不能因为上游变化而静默改回 Zed 产品语义：
- Zed v3/v4 由用户选择的 Completion template 决定，不使用 Zed feature flag，也不做 v4 到 v3 fallback。
zeta-cloud默认只声明zeta3-internal；Zed Well-known Provider 保持models: []，但 official-model candidates 始终允许添加zeta-cloud。- 本仓库不实现 subtle 展示模式，
x-zed-predict-edits-mode固定为eager。 - Completion transport 不发送
temperature。 - 自定义 Zed Base URL 继续采用本仓库既有的单一 Base URL 语义；默认官方地址才映射到 Zed Cloud 地址。
- 不建立 Zed 持久 WebSocket，不增加扩展遥测，也不把 Edit Prediction 塞入 Chat transport。
/models的 disabled/default/recommended 元数据不扩展为新的通用模型 UI 契约；未知 upstream provider 仍安全省略。- completion-only 模型不因同步而从 Chat 模型列表隐藏。
- disabled globs 保持本仓库已审查的 VS Code 适配范围。
- 跨文件预测继续限制为 workspace 内已经存在的单个文件，展示时静默打开，接受后才导航。
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 9d ago First seen · 204 lines · 36 tokens per session scan A 6f803e8821ed
Update Zed Experimental Provider is an agent published in the GitHub repository smallmain/vscode-unify-chat-provider (709 stars, last pushed 2d ago), licensed MIT. It adds 36 tokens to every session and 3,761 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other agents, from other repositories
GitHub Actions Node Runtime Upgrade
Upgrade a GitHub Actions JavaScript/TypeScript action to a newer Node runtime version (e.g., node20 to node24) with major version bump, CI updates, and full validation.
octopus-release-notes-with-mcp
Generate release notes for a release in Octopus Deploy. The tools for this MCP server provide access to the Octopus Deploy APIs.
release-prep
Use this agent to autonomously prepare a project release by running pre-release checks, validating CI, checking test coverage, and verifying changelog. Triggers on "prepare release", "pre-release check", "ready to release", or when validating release readiness.
Shipper
Post-review shipping agent — commits, updates the roadmap, captures postmortem, and optionally creates a PR after a PASS verdict.
differ
Analyze differences between git branches and summarize code changes. Use for clear, concise summaries of branch differences.
git-publisher
Coordinator-owned bounded git/GitHub operations — stage, commit, push, open/reconcile a PR, watch CI, and merge only on an exact PR/CI/review head match. Never edits repository files and never force-pushes. Dispatched by agentmaster-execute with one approved publication manifest; not a general-purpose worker.