ralphctl 0.17.0 → 0.18.0

package/dist/cli.mjs

@@ -2,5 +2,5 @@
 
 // src/index.ts
 process.env.NODE_ENV ??= "production";
-var { runCli } = await import("./cli-CCNZ2VKB.mjs");
+var { runCli } = await import("./cli-POCRZ3T7.mjs");
 await runCli(process.argv);

package/dist/manifest.json

@@ -1,7 +1,7 @@
 {
   "schemaVersion": 1,
-  "packageVersion": "0.17.0",
-  "generatedAt": "2026-07-27T15:30:39.020Z",
+  "packageVersion": "0.18.0",
+  "generatedAt": "2026-08-02T20:05:02.979Z",
   "assets": [
     "agent-definitions/ralphctl-evaluator.md",
     "agent-definitions/ralphctl-generator.md",

package/dist/prompts/ideate/template.md

@@ -258,11 +258,12 @@ The `outputJson` field is a JSON-encoded string. When decoded it has exactly two
 
 **Required signals:** exactly one `ideated-tickets`.
 
-**Optional signals** (emit when relevant):
+**Optional signals** (emit when relevant). Each carries its prose in a `text` field — never
+`body`; the output contract below shows the exact shape:
 
 - `note` — for status updates or observations worth surfacing.
 - `learning` — for non-obvious repo facts discovered during exploration.
-- `decision` — for architectural choices made during planning (body capped at 500 chars).
+- `decision` — for architectural choices made during planning.
 
 Emit nothing else. No prose responses, no explanatory comments outside the signals file.
 

package/dist/prompts/implement/template.md

@@ -133,9 +133,11 @@ repository now, trust the repository and record the conflict as a `learning` sig
     measurably raises cost without improving agent success.
   - Be specific and verifiable. "Use 2-space indentation" beats "format properly".
   - Stay under 200 lines, max 7 H2 sections, no H4+. Adherence degrades past these limits.
-  - Never embed slash commands, hooks, MCP server config, IDE settings, secrets, or credentials —
-    except when a declared step explicitly calls for adding one of these items to the project context
-    file. Those artefacts otherwise have dedicated homes and do not belong there.
+  - Never embed secrets or credentials — those belong in `.env` files or a secret manager, never a
+    committed context file, with no exception.
+  - Never embed slash commands, hooks, MCP server config, or IDE settings — except when a declared
+    step explicitly calls for adding one of these items to the project context file. Those artefacts
+    otherwise have dedicated homes and do not belong there.
 
 </constraints>
 

package/dist/prompts/plan/template.md

@@ -437,10 +437,11 @@ Once the user has answered "Approved, write it" in Step 4 AND every checklist it
 satisfied, write the `task-plan` signal into `signals.json` per the output contract below.
 The task array goes into the signal's `tasksJson` field as a JSON-encoded string.
 
-**Optional signals** (emit when relevant):
+**Optional signals** (emit when relevant). Each carries its prose in a `text` field — never
+`body`; the output contract below shows the exact shape:
 
 - `note` — for status updates or observations worth surfacing.
 - `learning` — for non-obvious repo facts discovered during exploration.
-- `decision` — for architectural choices made during planning (body capped at 500 chars).
+- `decision` — for architectural choices made during planning.
 
 {{OUTPUT_CONTRACT_SECTION}}

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "ralphctl",
-  "version": "0.17.0",
+  "version": "0.18.0",
   "description": "Agent harness for long-running AI coding tasks — orchestrates Claude Code, GitHub Copilot, and OpenAI Codex across repositories",
   "homepage": "https://github.com/lukas-grigis/ralphctl",
   "type": "module",