Fix 14 tool bugs: capability_check tool_name, quality_gate pipefail, 12 doc param fixes, 3 test-suite fixes

prompts/agent.system.tool.artifact_guard.md

@@ -1,11 +1,15 @@
 ### artifact_guard
-Validate whether requested file/artifact operations are allowed by the orchestrator rules.
+Check required project artifacts (5 DB + 10 repo). Returns present/missing counts and lists.
 
 Use this exact Agent Zero tool-call shape:
 ```json
-{"tool_name":"artifact_guard","tool_args":{"action":"check","path":"README.md"}}
+{"tool_name":"artifact_guard","tool_args":{"project_name":"my_project"}}
 ```
 
+Optional args:
+- `project_root` (str): repo root path for file-based artifact checks
+- `format` (str): "summary" (default) or "json"
+
 Rules:
 - Do not use this tool to discover, read, infer, validate, or print credential values.
 - If the tool is not found, stop and report a runtime tool-registration failure. Do not switch to WebUI login, CSRF, HTTP cache-refresh, shell credential scans, or `.env`/config/log searches.

prompts/agent.system.tool.block_compactor.md

@@ -3,7 +3,23 @@ Persist a compact block summary for resume/recovery using the plugin DB-backed s
 
 Use this exact Agent Zero tool-call shape:
 ```json
-{"tool_name":"block_compactor","tool_args":{"project_name":"my_project","summary":"what changed","next_step":"continue with tests"}}
+{"tool_name":"block_compactor","tool_args":{"project_name":"my_project","block_id":"T012","block_summary":"what changed","next_block":"continue with tests","force":false}}
+```
+
+Required args:
+- `project_name` (str): Projektname
+- `block_id` (str): Block identifier, e.g. 'T012', 'B-requirements-v1'
+- `block_summary` (str): What was done in this block (non-empty)
+- `next_block` (str): What comes next (default: "see next_steps.md")
+
+Optional args:
+- `force` (bool): Override context-ratio threshold block (NOT preconditions)
+- `decisions`, `open_questions`, `key_findings` (list): Optional metadata
+- `estimated_context_tokens`, `max_context_tokens` (int): For ratio check
+
+Preconditions (must be met before compact):
+- Pending next_steps must exist (orch_next_steps non-empty)
+- Context ratio must be >= 0.80 (use force=true to override threshold only)
 ```
 
 Rules:

prompts/agent.system.tool.handover_to_specialist.md

@@ -3,9 +3,15 @@ Create a bounded briefing for a specialist profile. It prepares handover text; i
 
 Use this exact Agent Zero tool-call shape:
 ```json
-{"tool_name":"handover_to_specialist","tool_args":{"specialist":"implementation_engineer","task":"implement the approved task","project_name":"my_project"}}
+{"tool_name":"handover_to_specialist","tool_args":{"specialist_profile":"implementation_engineer","task":"implement the approved task","project_name":"my_project","topic":"implement-auth-module"}}
 ```
 
+Required args:
+- `specialist_profile` (str): Specialist profile name (e.g. 'implementation_engineer', 'quality_reviewer', 'deploy_agent')
+- `task` (str): The task description for the specialist
+- `project_name` (str): Project name
+- `topic` (str): Non-empty slug/topic identifier for the handover (e.g. 'implement-auth-module')
+
 Rules:
 - Do not use this tool to discover, read, infer, validate, or print credential values.
 - If the tool is not found, stop and report a runtime tool-registration failure. Do not switch to WebUI login, CSRF, HTTP cache-refresh, shell credential scans, or `.env`/config/log searches.

prompts/agent.system.tool.next_step.md

@@ -6,6 +6,17 @@ Use this exact Agent Zero tool-call shape:
 {"tool_name":"next_step","tool_args":{"action":"list","project_name":"my_project"}}
 ```
 
+Actions:
+- `list` (default): List pending next steps
+- `add`: Add a new next step (requires `next_step` text)
+- `update`: Update an existing step (requires `step_id` and `next_step`)
+- `complete`: Mark a step as complete (requires `step_id`)
+
+Example (add):
+```json
+{"tool_name":"next_step","tool_args":{"action":"add","project_name":"my_project","next_step":"Implement authentication module"}}
+```
+
 Rules:
 - Do not use this tool to discover, read, infer, validate, or print credential values.
 - If the tool is not found, stop and report a runtime tool-registration failure. Do not switch to WebUI login, CSRF, HTTP cache-refresh, shell credential scans, or `.env`/config/log searches.

prompts/agent.system.tool.orchestrator_state.md

@@ -3,7 +3,7 @@ Read or update DB-backed orchestrator state for a project.
 
 Use this exact Agent Zero tool-call shape:
 ```json
-{"tool_name":"orchestrator_state","tool_args":{"action":"get","project_name":"my_project"}}
+{"tool_name":"orchestrator_state","tool_args":{"action":"read","project_name":"my_project"}}
 ```
 
 Rules:

prompts/agent.system.tool.repo_manifest.md

@@ -1,11 +1,19 @@
 ### repo_manifest
-Inspect or generate a repository manifest from explicitly provided repository paths.
+Create, read, update, list or validate project/deployment manifests (DB-backed).
 
 Use this exact Agent Zero tool-call shape:
 ```json
-{"tool_name":"repo_manifest","tool_args":{"project_root":"/a0/usr/workdir/project"}}
+{"tool_name":"repo_manifest","tool_args":{"project_name":"my_project","action":"read","manifest_type":"project"}}
 ```
 
+Args:
+- `project_name` (str): Projektname (bevorzugt)
+- `project_root` (str): Legacy – wird zu basename() aufgelöst
+- `manifest_type` (str): "project" (default), "deployment", "quality"
+- `action` (str): "create" (default), "read", "update", "list", "validate"
+- `data` (str|dict): JSON-string oder dict (für create/update)
+- `format` (str): "summary" (default) oder "json"
+
 Rules:
 - Do not use this tool to discover, read, infer, validate, or print credential values.
 - If the tool is not found, stop and report a runtime tool-registration failure. Do not switch to WebUI login, CSRF, HTTP cache-refresh, shell credential scans, or `.env`/config/log searches.

prompts/agent.system.tool.scorecard_update.md

@@ -3,7 +3,7 @@ Create or update DB-backed scorecard metrics for a project.
 
 Use this exact Agent Zero tool-call shape:
 ```json
-{"tool_name":"scorecard_update","tool_args":{"project_name":"my_project","metric":"tests","value":"pass"}}
+{"tool_name":"scorecard_update","tool_args":{"project_name":"my_project","action":"add","category":"tests","score":95,"max_score":100}}
 ```
 
 Rules: