obsidian-tc 1.20.0 → 1.22.0
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- package/README.md +3 -1
- package/SKILLS.md +13 -8
- package/dist/cli.js +1140 -718
- package/dist/cli.js.map +1 -1
- package/dist/index.js +57 -52
- package/dist/index.js.map +27 -23
- package/dist/migrations/20260814_001_memory_entity_status.sql +17 -0
- package/dist/migrations/20260816_001_episode_type_structural.sql +61 -0
- package/dist/migrations/20260816_002_episode_verdict_at.sql +37 -0
- package/dist/migrations/20260818_001_vault_context_watermark.sql +30 -0
- package/dist/migrations/20260818_002_chunk_access_stats_excludes_advisory.sql +41 -0
- package/dist/migrations/20260819_001_note_summaries.sql +34 -0
- package/dist/migrations/20260819_002_cluster_summaries.sql +59 -0
- package/dist/migrations/20260819_003_capture_queue_poison_scan.sql +21 -0
- package/dist/plugin/manifest.json +1 -1
- package/package.json +5 -6
package/README.md
CHANGED
|
@@ -9,7 +9,7 @@ See the [repo root README](../../README.md) for project overview and the
|
|
|
9
9
|
|
|
10
10
|
## Status
|
|
11
11
|
|
|
12
|
-
✅ **Shipped — v1.
|
|
12
|
+
✅ **Shipped — v1.22.0.** The full tool surface (163 tools across 31 domains, milestones
|
|
13
13
|
M0–M7) is implemented and released. Built on Bun + Hono with Zod 4 schemas; runs under
|
|
14
14
|
Node `>=24` (the test suite runs vitest under Node for `node:sqlite`).
|
|
15
15
|
|
|
@@ -38,3 +38,5 @@ config + caches (no server needed):
|
|
|
38
38
|
| `metrics [--since ms] [--until ms] [--json f]` | Knowledge-health scorecard from the derive layer |
|
|
39
39
|
| `gaps --queries <f> / --calibrate <golden.yaml>` | Knowledge-gap detector / threshold calibration |
|
|
40
40
|
| `forget (--episode <id> \| --note <rel>) [--erase] / --verify` | Dependency-aware deletion + hash-chained audit |
|
|
41
|
+
| `context-export --out <f> [--vault id]` | Export the derived plane (preferences, episodes, note_quality, retrieval feedback, forget_log) as a versioned, vendor-neutral JSON bundle |
|
|
42
|
+
| `context-import <bundle> [--vault id] [--dry-run]` | Import a context-export bundle. `--vault` remaps the bundle's vault-scoped rows to the target vault (refuses a multi-source-vault bundle); forget always wins over import |
|
package/SKILLS.md
CHANGED
|
@@ -163,13 +163,17 @@ want to do. Counts are approximate; the surface is 143 tools / 31 domains.
|
|
|
163
163
|
|
|
164
164
|
These are the skills that set obsidian-tc apart. Teach your agent to prefer them.
|
|
165
165
|
|
|
166
|
-
**Measured retrieval, not asserted.** Every ranking change is gated by an n=
|
|
166
|
+
**Measured retrieval, not asserted.** Every ranking change is gated by an n=250
|
|
167
167
|
multi-hop golden set with a statistical ship rule (paired permutation, BH-FDR,
|
|
168
|
-
a ΔnDCG ≥ 0.010 cost gate).
|
|
169
|
-
**
|
|
170
|
-
|
|
171
|
-
|
|
172
|
-
|
|
168
|
+
a ΔnDCG ≥ 0.010 cost gate). Named "champion" figures previously quoted here were
|
|
169
|
+
**withdrawn on 2026-08-07** (THE-748) as unreproducible; see
|
|
170
|
+
[`docs/EVALUATION.md`](./docs/EVALUATION.md) for what is measured and how.
|
|
171
|
+
Contextual chunk enrichment measured **+0.223 nDCG** and defaults on. The
|
|
172
|
+
practical takeaway for an agent is narrower than it used to read: **the defaults
|
|
173
|
+
are the measured configuration**, and experimental streams that did not beat
|
|
174
|
+
their control ship *dark* behind flags (see below). There is currently **no
|
|
175
|
+
published figure** for how the graph walk compares to plain dense retrieval on
|
|
176
|
+
this corpus (THE-748) — do not quote one.
|
|
173
177
|
|
|
174
178
|
**`vault_context`, the one-call context primitive.** Instead of hand-orchestrating
|
|
175
179
|
search + graph + rerank, call `get_context(query, token_budget)` and get a
|
|
@@ -180,7 +184,8 @@ retrieval skill; reach for it first when answering from the vault.
|
|
|
180
184
|
(retrieval events + dispatch episodes) into `experiential.db`, physically separate
|
|
181
185
|
from your notes, with a pre-ingest secret/poison scanner and an outcome axis. By
|
|
182
186
|
default it records the *action* axis only (tool, status, sizes, hashes, **no
|
|
183
|
-
payloads**); `experiential.captureContent`
|
|
187
|
+
payloads**); `experiential.captureContent` adds secret-scanned args, on under the
|
|
188
|
+
trusted-local posture and off under `hardened`. This is
|
|
184
189
|
the substrate for a knowledge flywheel (`metrics`, `gaps`, `activation-recompute`),
|
|
185
190
|
not something an agent reads as if it were authored content.
|
|
186
191
|
|
|
@@ -344,7 +349,7 @@ The complete option surface (every field, default, env var, and CLI command) is
|
|
|
344
349
|
| `auth.mode` | `none` | `jwt` for anything non-loopback (required by the interlock). |
|
|
345
350
|
| `toolFacade.mode` | `triad` | `flat` if your client prefers the full list. |
|
|
346
351
|
| `transports.http.enabled` | false | Many-client / remote (then set auth). |
|
|
347
|
-
| `experiential.captureContent` |
|
|
352
|
+
| `experiential.captureContent` | true | Stores (scanned) call args. `securityProfile: "hardened"` turns it off. |
|
|
348
353
|
| `OBSIDIAN_TC_GATEWAY_URL` (env) | unset | Enable the generative tier (`reflect`, `densify-llm`, `plane`). |
|
|
349
354
|
|
|
350
355
|
**Gotchas that bite new users**
|