skills: wait for activation completion notification (CXF-353)

evals/runner/agent.test.ts

@@ -78,7 +78,7 @@ test("buildPrompt pre1 branch names the pre1Path, both skills, and the output co
       basicAuth: {username: "connector@example.com", password: "fixture-token"},
       bearerToken: "fixture-token",
     },
-    skillBundle: {mode: "full", version: "0.5.0"},
+    skillBundle: {mode: "full", version: "0.8.0"},
     model: "together/deepseek-ai/DeepSeek-V4-Flash-0731",
     reasoningEffort: "high",
     kind: "pre1",

evals/runner/scenario.test.ts

@@ -100,7 +100,7 @@ test("loadScenario loads the pre1-directory-proceed scenario (kind pre1, proceed
   assert.equal(s.seed, undefined)
   assert.equal(s.requiredSourceFiles, undefined)
   assert.equal(s.skillBundle.mode, "full")
-  assert.equal(s.skillBundle.version, "0.5.0")
+  assert.equal(s.skillBundle.version, "0.8.0")
 })
 
 test("loadScenario loads the pre1-noiam-park scenario (kind pre1, park)", () => {

evals/runner/skills_bundle.test.ts

@@ -15,7 +15,7 @@ const execFileAsync = promisify(execFile)
 const RUN = "evals/runner/run.ts"
 const BUNDLE = "evals/skills-bundle/bundle.json"
 const SKILLS = ["author-in-app-connector", "read-authoring-contract", "write-connector-source", "build-and-test", "deploy-and-activate", "design-access-model", "source-openapi-spec", "verify-connector-output", "update-and-rollback", "diagnose-authoring-failure"]
-const VERSION = "0.5.0"
+const VERSION = "0.8.0"
 
 function readBundle(): {version: string; skills: {name: string; version: string; path: string}[]} {
   return JSON.parse(readFileSync(BUNDLE, "utf8")) as {version: string; skills: {name: string; version: string; path: string}[]}
@@ -156,7 +156,7 @@ const SKILL_LITERALS: Record<string, string[]> = {
     "Do not redeem the approval token",
     "Do not clear runtime fields, call the provisioner directly, or mutate the",
     "evidence is unsatisfied",
-    "if no ACTIVE row after ~10 polls, STOP and report",
+    "If no ACTIVE row after ~10 polls, STOP and report",
     "no terminal status after ~10 polls, STOP and report",
     "SYNC_STATUS_ERROR",
     "SYNC_STATUS_DISABLED",
@@ -198,7 +198,7 @@ test("(c) each SKILL.md carries the locked section markers, content literals, AS
 test("(d) the full-mode scenario parses with mode full and the two pinned scenarios keep their locked modes", () => {
   const full = loadScenario("evals/scenarios/tier1-directory-full.json")
   assert.equal(full.skillBundle.mode, "full")
-  assert.equal(full.skillBundle.version, "0.5.0")
+  assert.equal(full.skillBundle.version, "0.8.0")
   assert.equal(full.id, "tier1-directory-full")
   const none = loadScenario("evals/scenarios/tier1-directory.json")
   assert.equal(none.skillBundle.mode, "none")
@@ -247,7 +247,7 @@ test("(e) CLI end-to-end: full-mode Tier-0 run exits 0 and the record meta carri
     const lines = readFileSync(join(dir, records[0]), "utf8").trim().split("\n")
     const meta = JSON.parse(lines[0]) as Record<string, unknown>
     assert.equal(meta.skill_bundle_mode, "full")
-    assert.equal(meta.skill_bundle_version, "0.5.0")
+    assert.equal(meta.skill_bundle_version, "0.8.0")
   } finally {
     rmSync(dir, {recursive: true, force: true})
   }

evals/scenarios/pre1-directory-proceed.json

@@ -29,7 +29,7 @@
   },
   "skillBundle": {
     "mode": "full",
-    "version": "0.5.0"
+    "version": "0.8.0"
   },
   "model": "together/deepseek-ai/DeepSeek-V4-Flash-0731",
   "reasoningEffort": "high"

evals/scenarios/pre1-noiam-park.json

@@ -27,7 +27,7 @@
   },
   "skillBundle": {
     "mode": "full",
-    "version": "0.5.0"
+    "version": "0.8.0"
   },
   "model": "together/deepseek-ai/DeepSeek-V4-Flash-0731",
   "reasoningEffort": "high"

evals/scenarios/tier1-directory-full.json

@@ -27,7 +27,7 @@
   },
   "skillBundle": {
     "mode": "full",
-    "version": "0.5.0"
+    "version": "0.8.0"
   },
   "model": "together/deepseek-ai/DeepSeek-V4-Flash-0731",
   "reasoningEffort": "high",

evals/skills-bundle/bundle.json

@@ -1,15 +1,15 @@
 {
-  "version": "0.5.0",
+  "version": "0.8.0",
   "skills": [
-    {"name": "author-in-app-connector", "version": "0.3.0", "path": "../../skills/author-in-app-connector/SKILL.md"},
+    {"name": "author-in-app-connector", "version": "0.3.2", "path": "../../skills/author-in-app-connector/SKILL.md"},
     {"name": "read-authoring-contract", "version": "0.2.0", "path": "../../skills/read-authoring-contract/SKILL.md"},
     {"name": "write-connector-source", "version": "0.2.0", "path": "../../skills/write-connector-source/SKILL.md"},
     {"name": "build-and-test", "version": "0.3.0", "path": "../../skills/build-and-test/SKILL.md"},
-    {"name": "deploy-and-activate", "version": "0.2.0", "path": "../../skills/deploy-and-activate/SKILL.md"},
+    {"name": "deploy-and-activate", "version": "0.3.1", "path": "../../skills/deploy-and-activate/SKILL.md"},
     {"name": "design-access-model", "version": "0.1.0", "path": "../../skills/design-access-model/SKILL.md"},
     {"name": "source-openapi-spec", "version": "0.1.0", "path": "../../skills/source-openapi-spec/SKILL.md"},
     {"name": "verify-connector-output", "version": "0.1.0", "path": "../../skills/verify-connector-output/SKILL.md"},
-    {"name": "update-and-rollback", "version": "0.1.0", "path": "../../skills/update-and-rollback/SKILL.md"},
+    {"name": "update-and-rollback", "version": "0.2.1", "path": "../../skills/update-and-rollback/SKILL.md"},
     {"name": "diagnose-authoring-failure", "version": "0.1.0", "path": "../../skills/diagnose-authoring-failure/SKILL.md"}
   ]
 }

skills/author-in-app-connector/SKILL.md

@@ -1,7 +1,7 @@
 ---
 name: author-in-app-connector
 description: Use when driving the full in-app connector authoring funnel end to end, from guide read through the human-activation handoff. Do not use when you are already mid-funnel and only need one stage's procedure - invoke the stage skill directly.
-version: 0.3.0
+version: 0.3.2
 ---
 
 # author-in-app-connector
@@ -112,9 +112,13 @@ Net-new provider: before S1, run both pre-1 skills - `source-openapi-spec`
 
 ## Human boundary
 
-After S11's deploy + mint, present `activation_url` to a human tenant OWNER
-and STOP. Never redeem the approval token, never poll `REVISION_STATUS_ACTIVE`,
-never call `force_sync` - S11b/S11c are `skipped_human_boundary`.
+After S11's deploy + mint, present `activation_url` to a human tenant OWNER,
+record the handoff table, and STOP. Never redeem the approval token, never
+call `force_sync` - S11b/S11c are `skipped_human_boundary`. Never poll
+`REVISION_STATUS_ACTIVE` in the funnel run: if a notification later resumes
+you, the revision is ACTIVE - record the `activation_epoch` it carries.
+Direct API callers verify per deploy-and-activate once the OWNER reports
+activation.
 
 ## Exit criteria
 

skills/deploy-and-activate/SKILL.md

@@ -1,7 +1,7 @@
 ---
 name: deploy-and-activate
 description: Use when creating the app, provisioning the connector, configuring credentials, deploying the instance, minting the approval, or verifying activation. Do not use when the task is source upload, building, or draft testing - use build-and-test.
-version: 0.2.0
+version: 0.3.1
 ---
 
 # deploy-and-activate
@@ -39,9 +39,10 @@ below are the exact tenant MCP titles; the served guide abbreviates them.
 5. Mint approval: call `c1_connector_authoring_mint_approval_token` with
    `expires_in_seconds` in 1-14400 (max 4 hours); capture `activation_url`.
    GATE: non-empty `activation_url`. STOP if empty.
-6. HARD STOP at the human boundary: present `activation_url` to a human
-   tenant OWNER and stop. Never redeem the approval token, never attempt
-   activation yourself. S11b/S11c are `skipped_human_boundary`.
+6. Present `activation_url` to a human tenant OWNER, record the handoff
+   table, and stop - do not wait for activation first. Never redeem the
+   approval token or attempt activation yourself. S11b/S11c are
+   `skipped_human_boundary`.
 
 ## Post-activation reference (NEVER performed in the funnel run)
 
@@ -50,13 +51,19 @@ or the human/operator. Performing either in the funnel run fails the S11 gate
 (any non-handoff call after mint, including `list_revision_summaries` or
 `force_sync`).
 
-- Verification: after the OWNER confirms approval, poll
-  `c1_connector_authoring_list_revision_summaries` until the target
-  revision's status is `REVISION_STATUS_ACTIVE`; record its
-  `activation_epoch`. GATE: ACTIVE. STOP if not ACTIVE - if approval reports
-  `evidence is unsatisfied`, return to the test step and confirm a PASS row
-  binds this revision before minting a fresh approval URL. Poll with
-  backoff; if no ACTIVE row after ~10 polls, STOP and report.
+- Verification: if your host provides activation notifications, a
+  notification resuming you means the revision is ACTIVE - record the
+  `activation_epoch` it carries; do not poll. If you resume with an
+  outstanding activation and no notification, check
+  `c1_connector_authoring_list_revision_summaries` once; if
+  `REVISION_STATUS_ACTIVE` record `activation_epoch`, otherwise STOP and
+  report. Otherwise (direct API callers): once the OWNER reports
+  activation, poll `c1_connector_authoring_list_revision_summaries` every
+  5-10s, up to ~10 polls, until the target revision's status is
+  `REVISION_STATUS_ACTIVE`; record its `activation_epoch`. GATE: ACTIVE.
+  STOP if not ACTIVE - if approval reports `evidence is unsatisfied`, return
+  to the test step and confirm a PASS row binds this revision before minting
+  a fresh approval URL. If no ACTIVE row after ~10 polls, STOP and report.
 - Sync leg: the full lifecycle continues with
   `c1_connector_service_force_sync` and verification via
   `c1_connector_service_get` that `status.status` is `SYNC_STATUS_DONE` (a

skills/update-and-rollback/SKILL.md

@@ -1,7 +1,7 @@
 ---
 name: update-and-rollback
 description: Use when shipping a change to an activated connector (same-catalog rerun) or rolling back to a previously activated revision. Do not use when verifying a healthy connector's sync output - use verify-connector-output; do not use when diagnosing a failed build, draft test, or sync - use diagnose-authoring-failure.
-version: 0.1.0
+version: 0.2.1
 ---
 
 # update-and-rollback
@@ -24,13 +24,20 @@ the exact tenant MCP titles.
    (`expires_in_seconds` 1-14400). GATE: non-empty `activation_url`.
 5. HARD STOP at the human boundary: present the URL to a human tenant OWNER
    and stop. Do not redeem the approval token for activation.
-6. After the OWNER activates, poll
-   `c1_connector_authoring_list_revision_summaries` until the target
-   revision is `REVISION_STATUS_ACTIVE`; record its `activation_epoch`.
-   GATE: ACTIVE. STOP if not ACTIVE - if approval reports `evidence is unsatisfied`,
+6. After presenting the URL: if your host provides activation
+   notifications, a notification resuming you means the revision is
+   ACTIVE: record the `activation_epoch` it carries; do not poll. If you
+   resume with an outstanding activation and no notification, check
+   `c1_connector_authoring_list_revision_summaries` once; if
+   `REVISION_STATUS_ACTIVE` record `activation_epoch`, otherwise STOP and
+   report. Otherwise (direct API callers): once the OWNER reports
+   activation, poll `c1_connector_authoring_list_revision_summaries` every
+   5-10s, up to ~10 polls, until the target revision is
+   `REVISION_STATUS_ACTIVE`; record its `activation_epoch`. GATE: ACTIVE.
+   STOP if not ACTIVE - if approval reports `evidence is unsatisfied`,
    return to the draft-test step and confirm a fresh PASS row binds this
-   revision before minting a new approval URL. Poll with backoff (e.g. every
-   5-10s); if no ACTIVE row after ~10 polls, STOP and report.
+   revision before minting a new approval URL.
+   If no ACTIVE row after ~10 polls, STOP and report.
 7. Call `c1_connector_service_force_sync`; poll `c1_connector_service_get`
    with backoff (e.g. every 5-10s) until `status.status` is
    `SYNC_STATUS_DONE`, `SYNC_STATUS_ERROR`, or `SYNC_STATUS_DISABLED`; if