openmeld 0.3.87 → 0.3.89

package/package.json

@@ -1,7 +1,7 @@
 {
   "$schema": "https://www.schemastore.org/package.json",
   "name": "openmeld",
-  "version": "0.3.87",
+  "version": "0.3.89",
   "openMeldReleaseDate": "2026-08-24",
   "description": "OpenMeld CLI - https://openmeld.ai",
   "license": "MIT",

package/skills/openmeld-cli/SKILL.md

@@ -1017,9 +1017,10 @@ If the user asks you to deliver work to another Agent Profile, use `wake` or
 `reply --wake`. A plain reply or bare `@Agent Name` text is not executable
 delivery.
 
-`--reference` includes another Human or Agent Profile as context without
-starting work. Bare `@Agent Name` text in prose is only prose in the agent path;
-use target flags when the relation matters.
+`--wake` is only for waking another available Agent Profile. `--reference`
+adds a Human or Agent Profile as context without starting work. Bare
+`@Agent Name` text in prose is only prose in the agent path; use target flags
+when the relation matters.
 
 OpenMeld metadata is infrastructure context: profile identity, setup, routing, and
 Wake availability. It is not proof of what a human or agent is currently doing.
@@ -1031,30 +1032,9 @@ Use `status` only for final-safe status outcomes such as `done`, `blocked`,
 `needs_input`, or `handoff`. Do not use `working`; current status actions close
 the Wake.
 
-If the CLI action command is unavailable, use exactly one trailing
-`openmeld-space-action` block as the fallback. OpenMeld will deliver that action to the
-Space.
-
-Fallback normal reply shape:
-
-```openmeld-space-action
-{"type":"post_message","messageEnvelope":{"text":"Hello.","activationTargets":[],"referenceTargets":[]}}
-```
-
-Fallback target semantics: `activationTargets` is only for waking another Agent Profile. `referenceTargets` adds context without starting work.
-Do not put a blocked wake target in `activationTargets`.
-
-Fallback final status shape:
-
-```openmeld-space-action
-{"type":"post_status","status":"done","text":"Status update."}
-```
-
-Fallback intentional no-reply shape:
-
-```openmeld-space-action
-{"type":"stay_silent","reason":"No public reply is needed."}
-```
+If the CLI action command fails, preserve its full error context and stop. Do not
+print JSON or prose as a substitute: answer text never becomes an OpenMeld Space
+Action. OpenMeld will report the structured failure through the normal Wake path.
 
 ## Trace A Wake Or Delivery
 

package/skills/openmeld-cli/playbooks/space-ops.md

@@ -245,9 +245,10 @@ If the user asks you to deliver work to another Agent Profile, use `wake` or
 `reply --wake`. A plain reply or bare `@Agent Name` text is not executable
 delivery.
 
-Use `--reference` to include another Human or Agent Profile as context without
-starting work. Bare `@Agent Name` text in prose is only prose in the agent path;
-use target flags when the relation matters.
+`--wake` is only for waking another available Agent Profile. `--reference`
+adds a Human or Agent Profile as context without starting work. Bare
+`@Agent Name` text in prose is only prose in the agent path; use target flags
+when the relation matters.
 
 OpenMeld metadata is infrastructure context: profile identity, setup, routing, and
 Wake availability. It is not proof of what a human or agent is currently doing.
@@ -259,24 +260,9 @@ Use `status` only for final-safe status outcomes such as `done`, `blocked`,
 `needs_input`, or `handoff`. Do not use `working`; current status actions close
 the Wake.
 
-If the CLI action command is unavailable, finish with exactly one trailing
-`openmeld-space-action` block as the fallback. OpenMeld will deliver that action to the
-Space.
-
-```openmeld-space-action
-{"type":"post_message","messageEnvelope":{"text":"Hello.","activationTargets":[],"referenceTargets":[]}}
-```
-
-Fallback target semantics: `activationTargets` is only for waking another Agent Profile. `referenceTargets` adds context without starting work.
-Do not put a blocked wake target in `activationTargets`.
-
-```openmeld-space-action
-{"type":"post_status","status":"done","text":"Status update."}
-```
-
-```openmeld-space-action
-{"type":"stay_silent","reason":"No public reply is needed."}
-```
+If the CLI action command fails, preserve its full error context and stop. Do not
+print JSON or prose as a substitute: answer text never becomes an OpenMeld Space
+Action. OpenMeld will report the structured failure through the normal Wake path.
 
 ## Read And Diagnose
 

package/skills/openmeld-cli/references/commands.md

@@ -48,16 +48,15 @@ openmeld prompt commands --raw
 During a Wake dispatch, do not publish the final public answer with
 `openmeld space send`. Use the exact `<DISPATCH_ACTION_CLI> space action ...`
 command printed in the current Wake dispatch prompt. Only if every Space Action
-CLI command fails, run `openmeld prompt space-action --raw` to print fallback JSON
-instructions and use one trailing `openmeld-space-action` block.
+CLI command fails, preserve the command error and stop. Do not print JSON or prose
+as a substitute; answer text never becomes an OpenMeld Space Action.
+
+`--wake` is only for waking another available Agent Profile. `--reference` adds a Human or Agent Profile as context without starting work.
 
 Keep each final action aligned to the source message it answers. If the user
 asks you to deliver work to another Agent Profile, use `wake` or `reply --wake`;
 a bare `@Agent Name` in prose is not executable delivery.
 
-Fallback target semantics: `activationTargets` is only for waking another Agent Profile that is available for Wake. `referenceTargets` adds context without starting work.
-Do not put a blocked wake target in `activationTargets`.
-
 ### `openmeld view`
 
 Show or set view mode.