Report context pressure and a compaction recommendation (ok | compact-soon | compact-now | at-limit).

Summarize accumulated history into a dense block, snapshot the ledger, re-hydrate tracked files, and run Pre/PostCompact hooks. Returns the compacted context block to install as new ground truth.

Remove low-value/duplicate tool output without an inference call. Store mode only.

Hard reset turns and boundaries. Keeps rules and ledger by default.

Produce a small, self-contained brief (rules + latest summary + verification ledger + active files) to START A FRESH CHAT with. This is how you actually reclaim tokens on hosts that own their window (e.g. Copilot): open a new chat and seed it with this brief. Always written to disk too, so a new chat can attach the file even if MCP is unavailable.

Append a message to the server-held transcript. Store mode only. When COMPACTION_AUTO=true and pressure crosses the compact-now threshold, compaction fires automatically and the compacted block is returned under autoCompacted.

Mark files to silently re-read from disk on every compaction.

Stop re-hydrating the given files.

Read tracked (or given) files from disk and return current contents.

Read a file from disk and OFFLOAD it: returns a short digest (preview + structural outline + line/byte counts) and a handle, instead of dumping the full contents into the window. Prefer this over a normal file read for large files. Fetch the full body only when needed via offload_fetch or the compaction://blob/{handle} resource.

Stash large text (command output, grep results, logs, API payloads) as a blob and return a digest + handle instead of putting it all in the window.

Retrieve a blob's full content, or a 1-indexed inclusive line slice. Use the smallest slice that answers the question to keep the window small.

Search the verification ledger + offloaded blobs for already-known facts and content. CALL THIS BEFORE querying the codebase / context engine: a cached fact or a known blob line range avoids pulling whole files back into the window (token saver, esp. on hosts with their own retrieval like Augment). Semantic ranking when embeddings are configured, else lexical. Returns ledger hits + blob hits with line ranges (use with offload_fetch).

Replace the CLAUDE.md-equivalent rules that survive every boundary.

Append a rule that survives every boundary.

Return the current persistent rules.

Append an entry to the verification ledger (maker/checker). Survives compaction; verified results are copied verbatim into summaries.

Filter ledger entries by claim substring and/or result.

Return the full current ledger (used at boundaries for re-injection).