@agenticprimitives/devkit 0.0.0-alpha.6 → 0.0.0-alpha.8

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 CHANGED
@@ -1,5 +1,7 @@
1
1
  # @agenticprimitives/devkit
2
2
 
3
+ > Part of **[Agentic Primitives](https://agenticprimitives.dev)** — the open-source trust substrate for agentic applications: identity that can sign, authority checked at act time, evidence the owner carries. [Developer kit](https://github.com/agentictrustlabs/agentic-primitives) · [All packages](https://agenticprimitives.dev/developers)
4
+
3
5
  The Developer Kit core — `ap`, the CLI that is the packages' own front door (spec 398 §10, spec 399 §3, ADR-0063).
4
6
 
5
7
  ```
@@ -75,6 +77,35 @@ It is the **third** MCP — not the runtime's private MCP behind admission (ADR-
75
77
  and its `ap://developer-mcp/doctrine` resource says so first: no signing key, no vault, no authority, no production
76
78
  effect (spec 398 §10.4, T23). Claude Code: `claude mcp add ap-dev -- npx ap mcp --root .`
77
79
 
80
+ ## `ap generate client|cli|parity` — the fourth and fifth surfaces of one contract (398 §7.2)
81
+
82
+ ```
83
+ ap generate client --registry https://<skills-registry> --definition agentic-trust/person-steward --only web.search,person.memory.remember --out src/lib/agent-client.ts
84
+ ap generate cli --registry … --definition agentic-trust/org-steward --only treasury.payment.execute
85
+ ap generate parity --registry … --definition agentic-trust/org-steward --json
86
+ ```
87
+
88
+ Projected FROM the compiled definition (the registry's, or `--file <definition.json>`) by `@agenticprimitives/harness`'s
89
+ pure `generateCapabilityClient` / `cliArgumentSchema` / `generateParityCases` — the kit dispatches to the consumer's
90
+ install (absent ⇒ `E_MODULE_ABSENT`). The client's every operation posts an intent to the app's `/harness/run` boundary
91
+ through an injected port and carries no authority; the parity cases are the positive pair (screen intent vs Ask
92
+ sentence → the same normalized plan digest) and the negative pair (a forged `surface`, a changed party after approval).
93
+ Regenerate after `ap upgrade` moves a pinned definition.
94
+
95
+ ## `ap eval` — cases as data against a live Home (398 §10 / P1.3)
96
+
97
+ ```
98
+ ap eval evals/faithnet.eval.json --home https://www.faithnet.me --persona alice --report live-gates-reports/eval-faithnet-latest.json
99
+ ap eval --from-runs --home https://www.faithnet.me --persona alice --out evals/from-runs.eval.json
100
+ ```
101
+
102
+ A case is `{ id, incident, persona | (the --session bearer), addressee?, message, plan?, truth?, checks[] }`; a check is
103
+ one of the deterministic judges by name (`answered`, `replyKindIs`, `neverClaims`, `claimsRequire`, `falseEmptiness`,
104
+ `emptinessCarriesReason`, `evidenceFromTool`, `evidenceCountAgrees`, `noPlaceholderLeaks`, `textIncludes`,
105
+ `textExcludes`, `evidenceNoneFrom`). An act's correct outcome in a case is `authority_required` — the twin, as a test;
106
+ an eval never signs. An unrunnable case is a FAILING case. `--from-runs` turns an agent's live run records into case
107
+ skeletons to edit. Exit 1 on any failing case.
108
+
78
109
  ## What it will not do
79
110
 
80
111
  Hold a key, read a vault, mint authority, invoke a production effect. A doctor finding is a review checkpoint;