obsidian-tc 1.10.0 → 1.11.0

package/README.md

@@ -9,7 +9,7 @@ See the [repo root README](../../README.md) for project overview and the
 
 ## Status
 
-✅ **Shipped — v1.10.0.** The full tool surface (141 tools across 31 domains, milestones
+✅ **Shipped — v1.11.0.** The full tool surface (146 tools across 31 domains, milestones
 M0–M7) is implemented and released. Built on Bun + Hono with Zod 4 schemas; runs under
 Node `>=24` (the test suite runs vitest under Node for `node:sqlite`).
 

package/SKILLS.md

@@ -2,7 +2,7 @@
 
 A working guide for AI agents, and the people configuring them, to use the
 **obsidian-tc** MCP server well. obsidian-tc gives an agent *governed* access to
-one or more Obsidian vaults: **141 capabilities across 31 domains**, every call
+one or more Obsidian vaults: **143 capabilities across 31 domains**, every call
 funneled through one dispatch pipeline (auth, scopes, folder ACL, read-only kill
 switch, idempotency, throttle, human-in-the-loop, response governor, audit).
 
@@ -112,7 +112,7 @@ matches, you are wired up.
 
 ## 3. The core skill: discover, don't guess
 
-By default the server advertises **three meta-tools**, not a wall of 141. This
+By default the server advertises **three meta-tools**, not a wall of 143. This
 keeps agent context lean. Learn this loop before anything else:
 
 1. **`find_capability`**, BM25 search over the capabilities *this caller can see*.
@@ -137,7 +137,7 @@ The facade is boundary-only: no gate is bypassed in any mode.
 ## 4. Capability map (by intent)
 
 Use `find_capability` for exact names; this is the terrain, grouped by what you
-want to do. Counts are approximate; the surface is 141 tools / 31 domains.
+want to do. Counts are approximate; the surface is 143 tools / 31 domains.
 
 | You want to… | Reach for | Notes |
 | --- | --- | --- |
@@ -147,6 +147,8 @@ want to do. Counts are approximate; the surface is 141 tools / 31 domains.
 | **One-call context for a question** | `vault_context` (`get_context(query, token_budget)`) | Budget-packed graph-reranked chunks + synthesis patterns + open contradictions + proactive lessons. The single best entry point for "answer from my vault." |
 | **Grounded synthesis** | `reflect` | Synthesis with source provenance, an adversarial challenge mode, a versioned preference profile. Needs the inference gateway. |
 | **Red-team a claim** | `knowledge_challenge` | Retrieves decision notes to argue against a proposal. |
+| **Search vendor / external docs** | `knowledge_search` (docs corpus) | The docs-scoped analogue of `vault_graph_search`, bound to a reserved read-only docs vault. Gated on `read:docs`; no reranker (THE-441). |
+| **Critical docs to read first** | `knowledge_get_critical` | Frontmatter `severity == critical` pre-filter: breaking changes / security / production gotchas, optionally per source. |
 | **Structured formats** | Bases (`.base` DSL evaluator), Canvas, Kanban, Periodic notes, Tasks, Excalidraw, Bookmarks, Workspaces | Several need live mode (render/DSL). |
 | **Attachments / OCR** | attachment tools, OCR route | OCR needs live mode + the plugin. |
 | **Memory graph** | memory entities + `[[link]]` graph, workspace sessions + JSONL traces | Projections live in the `memory/` folder. |