Evidence for Context

Context knowledge records, for every section, which source files and line ranges it was written from, each pinned to a commit. Source Graph can read any registered repository at any eligible commit. Together they let an Agent go from an answer to the exact code behind it without cloning anything: read the knowledge page, receive its recorded sources alongside the text, then read those sources at their recorded commits.

flowchart LR
  ws["Knowledge workspace repo<br/>knowledge/ + structure.yaml<br/>+ context-evidence plugin"] -->|registered in| sg["Source Graph"]
  code["Source code repos<br/>at recorded commits"] -->|registered in| sg
  agent["Agent with<br/>context-inspect-search"] -->|read knowledge page| sg
  sg -->|text + references| agent
  agent -->|read cited range at its commit| sg

Two pieces make this work: a WebAssembly plugin that Context places in the knowledge workspace repository, and the query Skill's access policy for using Source Graph.

The evidence plugin

Source Graph lets a repository ship plugins named <name>.sourcegraph.wasm. When it serves a read or read_many, it discovers plugins in that repository at the same commit being read and runs them after the ordinary read has succeeded; their output is appended to the returned text. Plugins have no network, filesystem or process access — the host binds every file they read to the same repository, commit and readable scope.

Context's plugin is context-evidence.sourcegraph.wasm. For each returned file under knowledge/ that ends in .md, it:

1. Reads the full article at that commit only to locate its <!-- context:section --> markers, then selects the sections that overlap the lines actually returned.
2. Looks up those sections in knowledge/structure.yaml, the approved structure that records each section's references.
3. Appends a YAML references: list for the item, deduplicated. Repository references with a full commit and a supported remote become commit-pinned web URLs with line anchors; other references keep their structured fields.

If anything fails, the ordinary text is still returned and the plugin adds diagnostics instead of references. A reference is recorded metadata, not proof that the source was reread during this query.

Getting the plugin into the repository

context init writes the plugin when the workspace is the repository root, or when it has no enclosing Git repository. For an existing workspace run:

context evidence install --format json

A workspace nested inside a larger repository needs an explicit choice: --repository-root <git-root> when Source Graph hosts the whole repository, or --plugin-root <registered-content-root> when it hosts only a registered path; the workspace directory relative to that root is then passed to the plugin as workspace_root. The installer upgrades only files it recognizes as earlier versions of the plugin, preserves unknown or modified files with the same name, and never commits or pushes — commit the file and let Source Graph synchronize before relying on it remotely.

How the query Skill uses Source Graph

The context-inspect-search Skill reads Source Graph through a read-only MCP server the host names context-sourcegraph. CONTEXT_QUERY_ACCESS_MODE decides when:

Mode	Behavior
auto (default)	Reuse suitable local material first, then prefer the authorized read-only service before local retrieval
remote	Read knowledge and original code only through the service; never clone automatically, and on failure use only material that already carries a version
local	Local retrieval only; no MCP required

For remote knowledge, the Skill resolves a branch once and pins the returned full commit for every knowledge read in that answer. It searches within knowledge/**, reads the matching sections, and consumes the references the plugin already attached rather than rereading to request them; when a host does not enable plugins by default it asks for plugins: [{"name":"context-evidence"}] once.

Reading the cited code

For code, the Skill passes the exact repository from the source registration, the recorded full commit as the revision, and a repository-root-relative path that already includes any registered subpath. It reads directly when the file is known and searches that repository and commit when it is not, without a discovery pass before every query. It never replaces a missing baseline with the default branch.

Each piece of evidence keeps four things together: the repository, the returned full commit, the path and the returned line range. Multi-step reads stay on the same commit, follow the continuation range the service returns, and treat Partial, Truncated and coverage as limits rather than proof of absence. With read_many, every item's content and error are checked separately.

Related pages

• Reading Code Evidence Remotely — turning this on for an Agent.
• Evidence Chains and Index First — why every section records its sources.
• Pinned Search and Reads — how Source Graph resolves commits and bounds reads.

与 Context 协同

Context 知识为每个章节记录了它依据哪些源文件和行范围写成，且每条都固定到一个提交。Source Graph 可以在任何符合条件的提交上读取任何已登记的仓库。两者结合后，Agent 无需克隆任何内容，就能从一个答案追溯到其背后的确切代码：读取知识页面，随正文一起拿到其记录的来源，再在记录的提交上读取这些来源。

flowchart LR
  ws["知识工作区仓库<br/>knowledge/ + structure.yaml<br/>+ context-evidence 插件"] -->|"登记到"| sg["Source Graph"]
  code["源代码仓库<br/>位于记录的提交"] -->|"登记到"| sg
  agent["带有<br/>context-inspect-search 的 Agent"] -->|"读取知识页面"| sg
  sg -->|"正文 + 引用"| agent
  agent -->|"在对应提交上读取被引用的范围"| sg

实现这一点需要两部分：Context 放在知识工作区仓库中的 WebAssembly 插件，以及查询 Skill 使用 Source Graph 的访问策略。

证据插件

Source Graph 允许仓库附带名为 <name>.sourcegraph.wasm 的插件。在处理 read 或 read_many 时，它会在被读取的同一提交上发现该仓库中的插件，并在普通读取成功后运行它们；插件的输出会追加到返回的文本中。插件没有网络、文件系统或进程访问权限——宿主会把插件读取的每个文件都限定在同一仓库、同一提交和同一可读范围内。

Context 的插件是 context-evidence.sourcegraph.wasm。对于返回结果中每个位于 knowledge/ 下、以 .md 结尾的文件，它会：

1. 读取该提交上的完整文章，仅用于定位其中的 <!-- context:section --> 标记，然后选出与实际返回行有重叠的章节。
2. 在 knowledge/structure.yaml（记录每个章节引用的已批准结构）中查找这些章节。
3. 为该项追加一个去重后的 YAML references: 列表。带有完整提交且远端受支持的仓库引用，会变成固定到提交、带行锚点的网页 URL；其他引用保留其结构化字段。

如果任何一步失败，普通文本仍会照常返回，插件会附加诊断信息而不是引用。引用是记录下来的元数据，并不证明本次查询中重新读取过该来源。

把插件放进仓库

当知识工作区就是仓库根目录，或者它不在任何 Git 仓库之内时，context init 会写入插件。对于已有的知识工作区，运行：

context evidence install --format json

嵌套在更大仓库中的知识工作区需要显式选择：Source Graph 托管整个仓库时使用 --repository-root <git-root>，只托管某个已登记路径时使用 --plugin-root <registered-content-root>；知识工作区目录相对于该根目录的路径随后作为 workspace_root 传给插件。安装器只升级它识别为旧版本插件的文件，保留同名的未知文件或已修改文件，并且从不提交或推送——请自行提交该文件，并等 Source Graph 完成同步后再依赖它进行远程读取。

查询 Skill 如何使用 Source Graph

context-inspect-search Skill 通过宿主命名为 context-sourcegraph 的只读 MCP 服务器读取 Source Graph。由 CONTEXT_QUERY_ACCESS_MODE 决定何时使用：

模式	行为
auto（默认）	先复用合适的本地材料，然后在本地检索之前优先使用已授权的只读服务
remote	只通过该服务读取知识和原始代码；从不自动克隆，失败时只使用已带有版本信息的材料
local	仅本地检索；不需要 MCP

对于远程知识，该 Skill 只解析一次分支，并在这次回答的所有知识读取中固定使用返回的完整提交。它在 knowledge/** 范围内搜索，读取匹配的章节，并直接使用插件已附加的引用，而不是为了获取引用再读一遍；如果宿主默认未启用插件，它会请求一次 plugins: [{"name":"context-evidence"}]。

读取被引用的代码

对于代码，该 Skill 传入来源登记信息中的确切仓库、作为版本参数的已记录完整提交，以及一个相对于仓库根目录、已包含任何已登记子路径的路径。文件已知时直接读取，未知时在该仓库和提交上搜索，不会在每次查询前都先做一轮发现。它从不用默认分支替代缺失的基线。

每条证据都把四项信息放在一起：仓库、返回的完整提交、路径和返回的行范围。多步读取始终停留在同一提交上，遵循服务返回的续读范围，并把 Partial、Truncated 和覆盖范围视为限制，而不是不存在的证明。使用 read_many 时，每一项的内容和错误都会分别检查。

相关页面

• 远程读取代码证据——为 Agent 开启此功能。
• 证据链与索引优先——为什么每个章节都要记录其来源。
• 固定版本的搜索与阅读——Source Graph 如何解析提交并限制读取。