# Evidence for Context



<a id="section-goal"></a>

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.

```mermaid
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.


<a id="section-plugin"></a>

## 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.


<a id="section-install"></a>

## 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:

```bash
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.


<a id="section-query"></a>

## 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.


<a id="section-code"></a>

## 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.


<a id="section-next"></a>

## Related pages

- [Reading Code Evidence Remotely](</context/llms/pages/4c3472783cd20f6e615aab817f44126d.txt>) — turning this on for an Agent.
- [Evidence Chains and Index First](</context/llms/pages/d2f41bdf9360d05ff944e1b475267498.txt>) — why every section records its sources.
- [Pinned Search and Reads](</context/llms/pages/9b8f7c105b990cf29a3a7936dc0ff462.txt>) — how Source Graph resolves commits and bounds reads.

---

## Sources

- [context/packages/context-evidence-wasm/README.md L1–L5 · 3b0ce0a](<https://github.com/context4ai/context/blob/3b0ce0a0a1761f5fceb3bb48fb9dc29b54c0786b/packages/context-evidence-wasm/README.md#L1-L5>)
- [sourcegraph/docs/ref/repository-plugins.md L1–L15 · 4e5c555](<https://github.com/context4ai/sourcegraph/blob/4e5c5552394f4c16e050ae3185aad585fb07785d/docs/ref/repository-plugins.md#L1-L15>)
- [sourcegraph/internal/service/plugins.go L70–L116 · 4e5c555](<https://github.com/context4ai/sourcegraph/blob/4e5c5552394f4c16e050ae3185aad585fb07785d/internal/service/plugins.go#L70-L116>)
- [context/packages/context-evidence-wasm/src/lib.rs L144–L235 · 3b0ce0a](<https://github.com/context4ai/context/blob/3b0ce0a0a1761f5fceb3bb48fb9dc29b54c0786b/packages/context-evidence-wasm/src/lib.rs#L144-L235>)
- [context/packages/context-evidence-wasm/README.md L60–L96 · 3b0ce0a](<https://github.com/context4ai/context/blob/3b0ce0a0a1761f5fceb3bb48fb9dc29b54c0786b/packages/context-evidence-wasm/README.md#L60-L96>)
- [context/packages/context-cli/README.md L1–L12 · 3b0ce0a](<https://github.com/context4ai/context/blob/3b0ce0a0a1761f5fceb3bb48fb9dc29b54c0786b/packages/context-cli/README.md#L1-L12>)
- [context/packages/context-cli/src/project/evidencePlugin.ts L70–L92 · 3b0ce0a](<https://github.com/context4ai/context/blob/3b0ce0a0a1761f5fceb3bb48fb9dc29b54c0786b/packages/context-cli/src/project/evidencePlugin.ts#L70-L92>)
- [context/plugins/context/skills/context-inspect-search/SKILL.md L47–L56 · 3b0ce0a](<https://github.com/context4ai/context/blob/3b0ce0a0a1761f5fceb3bb48fb9dc29b54c0786b/plugins/context/skills/context-inspect-search/SKILL.md#L47-L56>)
- [context/plugins/context/skills/context-inspect-search/SKILL.md L158–L190 · 3b0ce0a](<https://github.com/context4ai/context/blob/3b0ce0a0a1761f5fceb3bb48fb9dc29b54c0786b/plugins/context/skills/context-inspect-search/SKILL.md#L158-L190>)
- [context/plugins/context/skills/context-inspect-search/SKILL.md L266–L276 · 3b0ce0a](<https://github.com/context4ai/context/blob/3b0ce0a0a1761f5fceb3bb48fb9dc29b54c0786b/plugins/context/skills/context-inspect-search/SKILL.md#L266-L276>)
- [context/plugins/context/skills/context-inspect-search/SKILL.md L302–L321 · 3b0ce0a](<https://github.com/context4ai/context/blob/3b0ce0a0a1761f5fceb3bb48fb9dc29b54c0786b/plugins/context/skills/context-inspect-search/SKILL.md#L302-L321>)
- [context/plugins/context/skills/context-inspect-search/SKILL.md L158–L166 · 3b0ce0a](<https://github.com/context4ai/context/blob/3b0ce0a0a1761f5fceb3bb48fb9dc29b54c0786b/plugins/context/skills/context-inspect-search/SKILL.md#L158-L166>)