skillscript-runtime 0.27.3 → 0.30.0

package/CHANGELOG.md

@@ -2,6 +2,16 @@
 
 Each release carries an **Upgrade impact:** line (first in its section) so a bump's requirements are visible at a glance. Tags (closed set): **BREAKING** (a manual change is needed to keep working) · **RE-APPROVE** (secured-mode signature invalidation — skills must be re-approved before they run) · **CONFIG** (`connectors.json` / config edit needed) · **none (additive)** (no action; backward-compatible). Standard from 0.20.0 forward; the pre-0.20 transitions that need action are flagged inline below (0.14.0, 0.18.8, 0.19.0). Full walkthrough: [UPGRADING.md](UPGRADING.md).
 
+## 0.30.0 — 2026-07-10 — public launch cut
+
+**Upgrade impact:** none (additive). Documentation only; no runtime, API, or behavior change.
+
+The public-announcement release. A final leakage-scrub pass over the shipped docs, closing the coverage gap the 0.27.3 audit left, so no doc names an internal substrate as an example.
+
+- **`sqlite-skill-store.md` (npm-shipped): removed AMP from the three substrate examples** the 0.27.3 audit didn't cover — the "choose your substrate" list (`AMP, Pinecone, S3, Postgres…` → `Pinecone, S3, Postgres, Redis…`), the forking-checklist class-rename example (`AmpSkillStore` → `RedisSkillStore`), and the `manifest()` example (`kind: "amp"` → `kind: "postgres"`). Example-name swaps only; no structural change.
+- **`configuration.md`: genericized two AMP-named examples** — the `connectors.json` `${VAR}`-substitution example (an `"amp"` connector using `${AMP_ENDPOINT}`/`${AMP_TOKEN}` → a generic `"memory"` connector using `${MEMORY_ENDPOINT}`/`${MEMORY_TOKEN}`) and an inline `_comment` ("AMP-style dogfooding" → "local dogfooding").
+- **`language-reference.md` re-rendered from atoms** — the worked-example op dispatches that previously used `$ amp.*` connector calls (mailbox / memory-write / query) now use `$ github.*` / `$ linear.*`, and the substrate-neutrality note lists `$ github.*` / `$ linear.*` as the "substrate-specific tools the adopter declares" example. The "Source of truth: AMP" provenance footer is intentionally retained.
+
 ## 0.27.3 — 2026-07-10 — dashboard highlighter fix + adopter-facing docs audit
 
 **Upgrade impact:** none (additive). One dashboard rendering fix + docs; no runtime behavior change.

package/docs/configuration.md

@@ -83,18 +83,18 @@ Once `.env` populates `process.env`, both `skillscript.config.json` (`runtime-co
 
   ```json
   {
-    "amp": {
+    "memory": {
       "class": "HttpMcpConnector",
       "config": {
-        "endpoint": "${AMP_ENDPOINT}",
-        "headers": { "Authorization": "Bearer ${AMP_TOKEN}" },
+        "endpoint": "${MEMORY_ENDPOINT}",
+        "headers": { "Authorization": "Bearer ${MEMORY_TOKEN}" },
         "identityHeader": "X-Agent-Id"
       }
     }
   }
   ```
 
-  `AMP_ENDPOINT` and `AMP_TOKEN` in `.env`; declarative shape committed to `connectors.json`.
+  `MEMORY_ENDPOINT` and `MEMORY_TOKEN` in `.env`; declarative shape committed to `connectors.json`.
 
 ### `.env` file format
 
@@ -365,7 +365,7 @@ Underscore-prefixed top-level keys (`_comment`, `_note_security`, etc.) are igno
 
 ```json
 {
-  "_comment": "Last edited 2026-05-28 — switched skill_store to sqlite for AMP-style dogfooding",
+  "_comment": "Last edited 2026-05-28 — switched skill_store to sqlite for local dogfooding",
   "substrate": { "skill_store": "sqlite" }
 }
 ```

package/docs/language-reference.md

@@ -460,11 +460,11 @@ Calls a tool through a configured connector. Connector name resolves against `co
 $ <connector>.<tool> kwarg=value, ... [-> R]
 ```
 
-The text before the dot is the connector name (must match an entry in `connectors.json`); the rest is the tool name + args. Named form is canonical for any tool whose semantics are substrate-specific — adopter MCP servers (`amp_*`, `github_*`, `linear_*`, etc.).
+The text before the dot is the connector name (must match an entry in `connectors.json`); the rest is the tool name + args. Named form is canonical for any tool whose semantics are substrate-specific — adopter MCP servers (`github_*`, `linear_*`, etc.).
 
 ```
-$ amp.amp_check_mailbox limit=20 -> MAIL
-$ amp.amp_write_memory summary="..." domain_tags=["x"] vault="private" -> ACK
+$ youtrack.search_issues query="project:INFRA state:Open" limit=20 -> ISSUES
+$ github.create_issue repo="acme/foo" title="..." body="..." -> ACK
 $ github.search_issues query="repo:acme/foo state:open" -> ISSUES
 $ linear.find_issues filter="project:INFRA" -> TICKETS
 ```
@@ -508,7 +508,7 @@ Four surfaces apply to every `$` dispatch and to `shell()` (notably `(fallback:)
 
 ```
 $ llm prompt="..." timeout=30 -> R
-$ amp.amp_olsen_task task_type="scan" timeout=120 -> DISPATCH
+$ youtrack.run_report report_id="INFRA-weekly" timeout=120 -> DISPATCH
 ```
 
 **`approved="<reason>"`** — Author-intent marker for the mutation-gate lint. Any non-empty string satisfies. Extracted at runtime; **not forwarded to the connector**. The value is required but not parsed semantically — presence is the signal.
@@ -523,7 +523,7 @@ Note: an envelope object like `{items: []}` is a non-empty object and does NOT t
 
 ```
 $ llm prompt="Classify: ${INPUT}" -> VERDICT (fallback: "unknown")
-$ amp.amp_query_memories query="${TOPIC}" -> RESULTS (fallback: [])
+$ youtrack.search_issues query="${TOPIC}" -> RESULTS (fallback: [])
 shell(argv=["gh","pr","list","--repo","acme/foo"]) -> PRS (fallback: "No open PRs")
 $ ticketing.search query="..." -> ISSUES (fallback: "search-unavailable")
 ```
@@ -590,8 +590,8 @@ $ json_parse ${RAW_JSON} -> PARSED
 ### Worked examples
 
 ```
-$ amp.amp_olsen_task task_type="scan" -> DISPATCH
-$ amp.amp_query_memories query="recent activity" limit=5 -> RECENT
+$ youtrack.run_report report_id="INFRA-weekly" -> DISPATCH
+$ github.search_issues query="repo:acme/foo updated:>2026-01-01" limit=5 -> RECENT
 $ llm prompt="Classify: ${INPUT}" timeout=30 -> VERDICT
 $ llm prompt="Summarize: ${TEXT}" model="qwen" maxTokens=500 -> SUMMARY
 $ data_read mode=fts query="${TOPIC}" limit=5 -> RESULTS (fallback: [])
@@ -601,7 +601,7 @@ $ ticketing.search query="project:INFRA state:Open" limit=20 -> ISSUES
 
 Tool args are unconstrained `key=value` pairs — the connector forwards them to the underlying MCP tool. If a dispatched call returns `isError: true`, the executor throws via `makeOpError`, which routes through the target's `else:` handler. The inner tool's error text is preserved in `result.errors[]`.
 
-**Substrate-neutrality.** Typed-contract bare ops (`$ llm`, `$ data_read`, `$ data_write`, `$ skill_*`, `$ json_parse`) are not reserved built-ins — they're typed-contract bridges the adopter wires through `substrate.local_model` / `substrate.data_store` / `substrate.skill_store` in `skillscript.config.json`. Substrate-specific tools (`$ amp.*`, `$ github.*`, etc.) are whatever the adopter declares in `connectors.json`. For external MCP servers, three bundled wiring paths cover the common cases:
+**Substrate-neutrality.** Typed-contract bare ops (`$ llm`, `$ data_read`, `$ data_write`, `$ skill_*`, `$ json_parse`) are not reserved built-ins — they're typed-contract bridges the adopter wires through `substrate.local_model` / `substrate.data_store` / `substrate.skill_store` in `skillscript.config.json`. Substrate-specific tools (`$ github.*`, `$ linear.*`, etc.) are whatever the adopter declares in `connectors.json`. For external MCP servers, three bundled wiring paths cover the common cases:
 
 - `HttpMcpConnector` — declarative wiring for any Streamable HTTP MCP server (JSON-RPC over HTTP + SSE). No subprocess. Adopters declare instances by class name in `connectors.json`.
 - `RemoteMcpConnector` — stdio bridging for MCPs distributed as spawnable binaries (YouTrack, GitHub, Linear when run locally) or HTTP MCPs adapted via `npx mcp-remote ... --sse`.
@@ -2173,7 +2173,7 @@ For *data skills* (skills marked `# Type: data`), the compile-time inline primit
 - Recursion is legal but bounded. If your design requires deeper recursion than the configured limit, reshape the workflow — almost always a sign of an iteration that should be expressed as `foreach` rather than recursion.
 
 ## Session isolation — a skill can't mutate the calling agent's session
-A skill executes in its OWN session; agent session state (context, persona) is session-local. Calling `amp_set_session_context` (or similar) inside a skill sets it for the SKILL's session, not the caller's — the caller sees no change. The contract: **skills assemble and RETURN data; the agent owns its SESSION STATE.** To "enter a project," a skill returns the instruction bodies and the AGENT applies its own session context.
+A skill executes in its OWN session; agent session state (context, persona) is session-local. Calling a session-context tool (or similar) inside a skill sets it for the SKILL's session, not the caller's — the caller sees no change. The contract: **skills assemble and RETURN data; the agent owns its SESSION STATE.** To "enter a project," a skill returns the instruction bodies and the AGENT applies its own session context.
 
 ## Static vs Dynamic — skill execution model
 
@@ -2565,5 +2565,5 @@ When any of these primitives ship, the relevant grammar moves into its canonical
 
 ---
 
-*Rendered from `skillscript/skillscript-language-reference` — 2026-07-10 13:59 EDT*  
+*Rendered from `skillscript/skillscript-language-reference` — 2026-07-10 14:34 EDT*  
 *Source of truth: AMP (`amp_render_document("skillscript/skillscript-language-reference")`)*

package/docs/sqlite-skill-store.md

@@ -21,7 +21,7 @@ SkillStore (choose which connector)
    └── Adopter-custom        (you write your own)
 ```
 
-If your substrate is AMP, Pinecone, S3, Postgres, or anything else, write a `class FooSkillStore implements SkillStore { ... }` and call `registry.registerSkillStore("primary", new FooSkillStore(...))`. The runtime is none the wiser.
+If your substrate is Pinecone, S3, Postgres, Redis, or anything else, write a `class FooSkillStore implements SkillStore { ... }` and call `registry.registerSkillStore("primary", new FooSkillStore(...))`. The runtime is none the wiser.
 
 This SqliteSkillStore is one such impl — useful as a copy-paste starting point, or directly usable if your needs match.
 
@@ -160,10 +160,10 @@ The same holds for a fork: your `store()` neither stamps nor verifies — persis
 
 When forking into your codebase:
 
-1. Rename the class (e.g., `PostgresSkillStore`, `AmpSkillStore`)
+1. Rename the class (e.g., `PostgresSkillStore`, `RedisSkillStore`)
 2. Replace the SQL with your substrate's API (HTTP, DataStore, vector DB, etc.)
 3. Update `staticCapabilities()` to match what your substrate actually supports — drop `supports_versioning` if you can't track history, drop `supports_tag_filter` if querying tags isn't tractable
-4. Update `manifest()` to describe your substrate (`kind: "amp"` or whatever)
+4. Update `manifest()` to describe your substrate (`kind: "postgres"` or whatever)
 5. **Optional but high-value for network-backed forks: implement `version()`** — a cheap store-wide change-token computed WITHOUT loading bodies (a list ETag, max-revision, or metadata digest), where any add/remove/edit/status-change moves it. It lets `skill_list` skip its N+1 catalog rebuild on unchanged polls (each entry otherwise costs a `load()` — one network round-trip per skill against a remote store). `SqliteSkillStore` hashes `(name, status, current_version)` in one body-free query. Skip it and `skill_list` just always rebuilds.
 6. Tests: copy `tests/SqliteSkillStore.test.ts` as a starting point + run the conformance suite (`SkillStoreConformance.buildTests()` from `skillscript-runtime/testing`)
 

package/examples/skillscripts/classify-support-ticket.skill.provenance.json

@@ -2,7 +2,7 @@
   "provenance_version": "1.0",
   "language_version": "1.0",
   "compiler_version": "0.1.0-dev",
-  "compiled_at": "2026-07-10T18:06:49.305Z",
+  "compiled_at": "2026-07-10T18:40:34.525Z",
   "source_skill": {
     "name": "classify-support-ticket"
   },

package/examples/skillscripts/data-store-roundtrip.skill.provenance.json

@@ -2,7 +2,7 @@
   "provenance_version": "1.0",
   "language_version": "1.0",
   "compiler_version": "0.1.0-dev",
-  "compiled_at": "2026-07-10T18:06:49.486Z",
+  "compiled_at": "2026-07-10T18:40:34.690Z",
   "source_skill": {
     "name": "data-store-roundtrip"
   },

package/examples/skillscripts/doc-qa-with-citations.skill.provenance.json

@@ -2,7 +2,7 @@
   "provenance_version": "1.0",
   "language_version": "1.0",
   "compiler_version": "0.1.0-dev",
-  "compiled_at": "2026-07-10T18:06:49.652Z",
+  "compiled_at": "2026-07-10T18:40:34.849Z",
   "source_skill": {
     "name": "doc-qa-with-citations"
   },

package/examples/skillscripts/feedback-sentiment-scan.skill.provenance.json

@@ -2,7 +2,7 @@
   "provenance_version": "1.0",
   "language_version": "1.0",
   "compiler_version": "0.1.0-dev",
-  "compiled_at": "2026-07-10T18:06:49.855Z",
+  "compiled_at": "2026-07-10T18:40:35.079Z",
   "source_skill": {
     "name": "feedback-sentiment-scan"
   },

package/examples/skillscripts/hello-world.skill.provenance.json

@@ -2,7 +2,7 @@
   "provenance_version": "1.0",
   "language_version": "1.0",
   "compiler_version": "0.1.0-dev",
-  "compiled_at": "2026-07-10T18:06:50.004Z",
+  "compiled_at": "2026-07-10T18:40:35.257Z",
   "source_skill": {
     "name": "hello-world"
   },

package/examples/skillscripts/morning-brief.skill.provenance.json

@@ -2,7 +2,7 @@
   "provenance_version": "1.0",
   "language_version": "1.0",
   "compiler_version": "0.1.0-dev",
-  "compiled_at": "2026-07-10T18:06:50.178Z",
+  "compiled_at": "2026-07-10T18:40:35.414Z",
   "source_skill": {
     "name": "morning-brief"
   },

package/examples/skillscripts/queue-length-monitor.skill.provenance.json

@@ -2,7 +2,7 @@
   "provenance_version": "1.0",
   "language_version": "1.0",
   "compiler_version": "0.1.0-dev",
-  "compiled_at": "2026-07-10T18:06:50.377Z",
+  "compiled_at": "2026-07-10T18:40:35.595Z",
   "source_skill": {
     "name": "queue-length-monitor"
   },

package/examples/skillscripts/service-health-watch.skill.provenance.json

@@ -2,7 +2,7 @@
   "provenance_version": "1.0",
   "language_version": "1.0",
   "compiler_version": "0.1.0-dev",
-  "compiled_at": "2026-07-10T18:06:50.550Z",
+  "compiled_at": "2026-07-10T18:40:35.815Z",
   "source_skill": {
     "name": "service-health-watch"
   },

package/examples/skillscripts/skill-store-roundtrip.skill.provenance.json

@@ -2,7 +2,7 @@
   "provenance_version": "1.0",
   "language_version": "1.0",
   "compiler_version": "0.1.0-dev",
-  "compiled_at": "2026-07-10T18:06:50.723Z",
+  "compiled_at": "2026-07-10T18:40:35.978Z",
   "source_skill": {
     "name": "skill-store-roundtrip"
   },

package/examples/skillscripts/youtrack-morning-sweep.skill.provenance.json

@@ -2,7 +2,7 @@
   "provenance_version": "1.0",
   "language_version": "1.0",
   "compiler_version": "0.1.0-dev",
-  "compiled_at": "2026-07-10T18:06:50.897Z",
+  "compiled_at": "2026-07-10T18:40:36.165Z",
   "source_skill": {
     "name": "youtrack-morning-sweep"
   },

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "skillscript-runtime",
-  "version": "0.27.3",
+  "version": "0.30.0",
   "description": "Runtime, compiler, lint, CLI, and dashboard for Skillscript — a small declarative language for authoring agent workflows.",
   "license": "MIT",
   "author": "Scott Shwarts <scotts@pobox.com>",