Wiki

Wiki is an experimental feature and is not enabled by default. Functionality may be incomplete and breaking changes may ship in non-major releases. To enable it for your deployment, contact us.

Sourcebot writes and maintains a wiki for the repositories you choose. Each wiki is architecture documentation that an LLM generates from the repository’s code. It explains how the repository’s systems fit together, the contracts between them, and why they work the way they do.

A wiki is an engineer’s handbook, not an encyclopedia. It favors a few dense documents over covering every feature.

Your team reads a repository’s wiki in its Wiki tab, and agents in Ask Sourcebot and MCP search it alongside the code. Scheduled scans keep each wiki up to date as the code changes.

Reading the wiki

When your license includes Wiki, every repository has a Wiki tab next to its Code tab. The wiki opens on its README.md overview and lists every document by system. A citation of the repository’s own files links to the cited lines in its Code tab.

If a repository doesn’t have a wiki yet, its Wiki tab says why. Owners get a button that takes them to the right place in Settings → Wiki.

If your license doesn’t include Wiki, only repositories that already have a wiki show the Wiki tab.

Each document shows when a scan last checked it against the code, the commit it checked, and which model checked it. A check doesn’t always change the document.

As in the Code tab, switch a document between Preview, Code and Blame, and open History at the bottom of the page to see when and how it changed.

A repository’s wiki is visible to exactly the people who can see the repository.

Linking from a developer portal

Each repository’s wiki has a stable address, so you can link to it from other tools, such as Backstage or another developer portal. Link to the wiki’s home page rather than a single document. A document’s address follows its path, and later scans can merge or remove documents.

Not every repository has a wiki. To show a link only when there’s one, call GET /api/wiki with the repository’s name, authenticated with an API key:

curl "https://sourcebot.example.com/api/wiki?repo=github.com/acme/app" \
  -H "X-Sourcebot-Api-Key: $SOURCEBOT_API_KEY"

When the repository has a wiki, the response includes its address:

{
  "exists": true,
  "url": "https://sourcebot.example.com/browse/github.com/acme/app/-/wiki/",
  "docCount": 9,
  "lastUpdatedAt": "2026-11-10T18:42:07.000Z",
  "lastUpdatedCommit": "9f3c2a1e7d4b8c6a5f0e2d1c3b4a596877869a54"
}

Field	Description
exists	true once the wiki has at least one document.
url	The address of the wiki’s home page. Present when exists is true.
docCount	How many documents the wiki has, including its README.md overview. 0 when it has none.
lastUpdatedAt	When a scan last updated the wiki, in ISO 8601. A scan updates each document it checks against the code, even when the text stays the same. Present once a scan has updated a document.
lastUpdatedCommit	The SHA of the repository’s commit that the wiki was last updated against. Present with lastUpdatedAt.

Show the link when exists is true, and point it at url.

• The API key acts as the user who created it. A repository that user can’t see returns 404, the same as a repository that doesn’t exist. Use a key from an account that can see every repository your portal lists.
• Each request counts toward your API rate limit.

How agents use it

Generated docs appear as a knowledge-base/ folder inside each repository in search and agent tools. The folder’s README.md gives you an overview and an index of the generated documents. In the web app, the docs appear in the repository’s Wiki tab instead of its file tree.

Sourcebot indexes the docs like any other repository. Agents find them with the existing grep, read_file, and list_tree tools in Ask Sourcebot and MCP.

The docs cite a repository and file together, so an agent can verify a claim with one read_file call. Citations use @file:{repo::path} syntax.

Searches scoped to a repository include its generated docs. When a search covers both knowledge documents and ordinary code, knowledge documents receive a large ranking boost so they appear first.

This is a strong preference, not a strict guarantee. The streaming web search UI displays results as they arrive from the search backend, so a knowledge document from a slower shard can appear after earlier code results. Non-streaming search surfaces (such as agent tools and the API) sort all results before returning, so knowledge documents rank first reliably.

Enabling Wiki

Wiki requires all of the following:

• Your license includes the knowledge-base entitlement.
• Your config file’s top-level models array contains at least one entry.
• An owner turns on Enabled on Settings → Wiki.
• An owner then chooses repositories with Edit repositories on the same page.

Sourcebot does not scan any repository until Wiki is on and an owner chooses repositories. Only owners can open Settings → Wiki. Everyone else reads the wiki in each repository’s Wiki tab.

Turning Wiki off pauses all scans. Docs that Sourcebot already generated stay searchable. Use a repository’s Remove wiki action to remove them. While Wiki is off, you can’t change repositories or select Generate now.

If your license no longer includes the knowledge-base entitlement, generated docs stay searchable, but Sourcebot stops updating them.

Choosing repositories

Owners choose repositories on Settings → Wiki. The page also shows the status of each repository’s scans.

Select Edit repositories, tick the repositories that should have a wiki, and select Save. Sourcebot scans a newly selected repository as soon as it is indexed. It does not wait for the first scheduled refresh.

Select Generate now to scan every selected repository immediately.

Each repository shows what is happening right now, with a detail line underneath:

Status	Meaning
Waiting for index	The repository has not finished its first code index. Generation starts after it does.
Setting up	Sourcebot is creating the repository’s knowledge repository.
Queued	A scan is waiting to run. The detail shows its position in the queue.
Generating	A scan is running. The detail shows the current stage, such as Writing docs 7/23.
Retrying	A scan attempt failed and will run again. Open the icon to see the error.
Indexing for search	The docs are written. Search picks them up once indexing finishes.
Up to date	The latest scan succeeded. The detail shows the number of docs.
Not generated	No scan has run yet. The detail shows when the next scheduled scan runs.
Failed, Setup failed	The latest scan or setup failed. Open the icon to see the error and logs.

Expand a repository to see the current or latest run, its token usage by model, and how much of the Token budget per scan it used. Select View logs to see the run’s logs.

If a repository already has a real root entry named knowledge-base, the repository shows a warning and generation pauses for it. While the conflict stands, the repository’s Wiki tab says its wiki couldn’t be written, and GET /api/wiki reports no wiki. Sourcebot keeps the generated docs. Rename or remove the entry, then select Generate now to bring the wiki back.

To remove a repository’s wiki, select Remove wiki from the repository’s menu. Sourcebot deletes the repository’s knowledge repository, clone, and shards, and stops generating its wiki. To bring the wiki back, select the repository again in Edit repositories.

Configuration

Owners tune generation on Settings → Wiki → Configuration. Sourcebot stores these settings in its database, so you don’t edit your config file to change them.

Setting	Default	Description
Scan mode	Delta	Chooses between Delta and Full scans. See Scan modes.
Refresh interval	24 hours	Sets how often Sourcebot checks each repository for changes.
Model (per stage)	The first entry in your models array	Selects the model for a stage. See Per-stage models and reasoning effort.
Reasoning effort (per stage)	High	Sets the reasoning effort for a stage. See Per-stage models and reasoning effort.
Token budget per scan	50,000,000	Sets the maximum number of tokens that one repository scan newly processes. Prompt-cache reads do not count against this budget.
Parallel tasks per scan	4	Sets how many scouts, surveyors, or document agents run concurrently in one scan.

Models and their credentials stay in your config file. The configuration page lists the entries in your top-level models array.

The settings.maxKnowledgeScanJobConcurrency config setting controls how many repositories scan concurrently. Its default is 1. Increasing it multiplies your possible per-job spend by the number of concurrent jobs.

Per-stage models and reasoning effort

Generation runs in four stages, described in How docs are generated. You can choose a model and reasoning effort for each one:

• Discovery runs territory scouts and the system reconciler.
• Survey surveys each canonical system and merges the work list.
• Document generation writes each knowledge document.
• Overview writes the README overview.

A stage without a chosen model uses the first entry in your models array, the same default that Ask Sourcebot uses. To change that default, reorder your models array.

Discovery and Overview use the Survey model unless you choose a model for them. Document generation does not inherit a model from another stage.

Each stage has its own reasoning effort. No stage inherits effort from another. A stage without a chosen effort works as follows:

• If its model supports reasoning effort, the stage uses high.
• If its model is OpenAI-compatible, the stage shows Model default and Sourcebot sends no effort. Some OpenAI-compatible servers reject an effort for models that do not reason. Choose an effort to send one, or choose Model default to stop sending it.
• If its model does not support reasoning effort, the stage shows Not supported.

Stage efforts replace the model’s own effort or thinking settings from your config file, such as reasoningEffort or thinkingBudget, during scans. Ask Sourcebot still uses those settings.

Providers map effort values as follows:

Provider	Supported values	Mapping
Anthropic	low, medium, high, xhigh, max	Uses the value directly with adaptive thinking.
OpenAI and Azure	low, medium, high, xhigh	Uses the value directly. max clamps to xhigh and logs a warning.
Google (google-generative-ai) and Google Vertex (google-vertex), Gemini 3 and later	low, medium, high	Uses the value as the thinking level. xhigh and max clamp to high and log a warning.
OpenAI-compatible	low, medium, high, xhigh	Passes the value through. max clamps to xhigh and logs a warning.
Amazon Bedrock, Claude 4.6 and later	low, medium, high, xhigh, max	Uses the value directly with adaptive thinking. Claude Opus 4.6 and Claude Sonnet 4.6 clamp xhigh to high and log a warning.
Amazon Bedrock, OpenAI models	low, medium, high, xhigh	Uses the value directly. gpt-oss models clamp xhigh and max to high. Other OpenAI models clamp max to xhigh. Both log a warning.
All other providers and models	None	Sends no effort. A chosen effort rejects the scan before it starts. This includes Amazon Bedrock models older than Claude 4.6, application inference profiles, and Gemini 2.5 and earlier, which use the thinkingBudget from your config file.

Sourcebot resolves all stage settings before it starts the scan. A missing model, unsupported provider, or model setup failure stops the whole scan before it spends tokens.

Anthropic models without adaptive thinking log a warning and run without the effort. They keep their existing thinking behavior.

Usage rows appear separately for each model. Each generated document records the model that wrote it. README.md records the readme model.

Scan modes

The Delta mode is the default. It updates only documents whose cited files changed. It falls back to a full scan for a large diff, missing history, or a last full scan older than 7 days.

The Full mode re-verifies every document during each scan cycle. A repository’s first scan is always a full scan.

If a full scan fails after its retries, scheduled delta scans back off before they try a full scan again:

• The wait starts at 1 day and doubles with each further failed full scan, up to 7 days.
• During the wait, a scan that is only due for its periodic full scan runs as a delta scan instead, as long as the repository has a previous successful scan.
• A scan that needs a full scan for any other reason is skipped until the wait ends. The scan status keeps showing the last scan that ran.
• A successful full scan ends the backoff. Generate now and the Full mode always run as requested.

Repositories that cite busy shared dependencies re-scan whenever those dependencies change. The Delta mode keeps that work cheap.

Scheduling and cost

Scheduled scans refresh according to the Refresh interval setting. The default interval is 24 hours. Sourcebot uses the citation index to skip repositories with no relevant changes.

Every job records input, output, cache-read, and cache-write tokens for each model. You can see this usage on Settings → Wiki. The Token budget per scan setting bounds the tokens that your job newly processes. Prompt-cache reads do not count against this budget.

Sourcebot caches the agent conversation with supported providers so your long scans re-read context from cache. If your scan exhausts its budget, encounters a structural failure, or an agent’s response is cut off at the model’s output token limit, it fails immediately without a retry.

Your scan model calls use a 45 minute transport timeout. Reconciliation and other single-step generations can legitimately exceed typical HTTP header timeouts.

How docs are generated

A background, offline scan reads each selected repository with an LLM. It writes Markdown documents into a managed knowledge repository for that repository. Sourcebot indexes the knowledge repository and serves its documents as the repository’s wiki.

A full scan organizes documentation around discovered systems:

1. Sourcebot carves the repository’s pinned tree into deterministic, weight-budgeted territories.
2. Territory scouts explore in parallel and identify a few load-bearing systems with code evidence.
3. A system reconciler fuses duplicates, folds satellite candidates into parent systems, and rejects low-value groupings.
4. Per-system surveyors prioritize architectural invariants, cross-cutting flows, tricky contracts, and why-decisions.
5. A taxonomist merge agent curates the final work list. Document agents write it, then the README fan-in builds the overview.

Three hard caps protect your scan budget. A scan accepts at most 24 systems, 6 proposed documents per system, and 120 create items in its final work list. These caps are backstops, not content targets. Existing documents can still be kept, merged, or deleted without counting toward the create cap.

A document agent must call finish_doc successfully for its own path. If it stops without finishing, Sourcebot nudges it to submit before treating that item as failed. Other document items continue running when one item fails.

A delta scan skips territory scouting and reconciliation. It groups affected documents by their existing system folder and runs only the relevant surveyors. Changed repository files that no document cites are sent to every active delta surveyor for adjudication.

Document naming contract

Every newly planned document uses exactly system-slug/concept-slug.md. Both segments use lowercase kebab-case with at most 64 characters. The folder names the canonical system, and the file names a specific concept.

The concept name cannot repeat its system folder. Sourcebot also refuses these generic concept names after ignoring case and punctuation: overview, readme, index, doc, docs, documentation, about, misc, general, summary, notes, info, main, other, todo, claude, and agents.

Existing documents at legacy paths remain editable, finishable, and deletable. The stricter naming contract applies only when surveyors or the merge agent propose a new path.

Notes

• Sourcebot must index a repository before it can generate the repository’s wiki.
• Generated documents go live as soon as Sourcebot commits them. There is no review queue.
• Use the per-repository Remove wiki action as your escape hatch.
• Cloud-licensed deployments receive the entitlement from the license service. Operators must ensure that the entitlement service knows knowledge-base before this release rolls out.