Simplify Athena operator maintenance workflow
This commit is contained in:
@@ -39,7 +39,7 @@ web:
|
||||
keyless_rescue: true
|
||||
|
||||
agent:
|
||||
max_turns: 100
|
||||
max_turns: 500
|
||||
gateway_timeout: 3600
|
||||
session_stall_timeout: 600
|
||||
tool_loop_guardrails:
|
||||
@@ -57,6 +57,27 @@ agent:
|
||||
max_web_searches: 20
|
||||
max_subagents: 8
|
||||
|
||||
# Compact before a tool-heavy session can grow beyond the selected model's
|
||||
# usable window. Large old tool results are pruned without an LLM call first;
|
||||
# lean tail retention avoids several expensive back-to-back summary passes.
|
||||
compression:
|
||||
enabled: true
|
||||
progress_notices: true
|
||||
threshold: 0.65
|
||||
target_ratio: 0.15
|
||||
tail_mode: "lean"
|
||||
protect_last_n: 20
|
||||
proactive_prune_tokens: 50000
|
||||
proactive_prune_min_result_chars: 4000
|
||||
proactive_prune_min_reclaim_tokens: 4096
|
||||
context_total_ceiling_seconds: 600
|
||||
|
||||
auxiliary:
|
||||
compression:
|
||||
provider: "main"
|
||||
model: ""
|
||||
reasoning_effort: "none"
|
||||
|
||||
# German is the platform default. The display setting localizes the static
|
||||
# messages Hermes currently supports; agent replies are governed by SOUL.md.
|
||||
display:
|
||||
|
||||
@@ -65,6 +65,9 @@ repository and use live measurements only as evidence of current state.
|
||||
5. **Change the source of truth.** Modify repository sources, not only a live
|
||||
container. Prefer `athena_operator_prepare`; show its full preview and stop
|
||||
for the exact user confirmation before `athena_operator_execute`.
|
||||
Use `file_update` for the exact source paths. Never clone the repository in
|
||||
the Hermes sandbox and never request or copy an SSH key; the Operator owns
|
||||
the canonical worktree and its deploy credentials.
|
||||
Completion: the approved ticket matches the intended content.
|
||||
6. **Deploy narrowly.** Change only named services. Never restart the entire
|
||||
stack merely to activate one component. Completion: unrelated containers
|
||||
@@ -72,8 +75,9 @@ repository and use live measurements only as evidence of current state.
|
||||
7. **Verify behavior.** Run syntax/config checks, focused tests, service health,
|
||||
and one bounded functional test. A running container alone is not proof.
|
||||
Completion: expected behavior and rollback path are both verified.
|
||||
8. **Close the maintenance loop.** Update relevant docs, publish the Git
|
||||
change, create a newer recovery bundle, then check maintenance status.
|
||||
8. **Close the maintenance loop.** Update relevant docs, publish only the
|
||||
explicitly selected changed paths with `git_publish`, create a newer
|
||||
recovery bundle, then check maintenance status.
|
||||
Completion: source commit, deployed state, docs, and recovery agree.
|
||||
|
||||
## Persistent Versus Temporary Work
|
||||
@@ -102,7 +106,8 @@ repository and use live measurements only as evidence of current state.
|
||||
- A profile switch can terminate active generation and invalidate prompt cache.
|
||||
- A healthy container can still expose the wrong model, route, or tool set.
|
||||
- `/opt/mike-ai/stack` is deployed source, not automatically the canonical Git
|
||||
worktree. Complete durable changes through the documented Git workflow.
|
||||
worktree. Complete durable changes through Operator operations `file_update`,
|
||||
`run_checks`, `compose_deploy`, `git_publish`, and `recovery`.
|
||||
- New skills are loaded at the next Hermes session; absence in the current
|
||||
session is expected.
|
||||
|
||||
|
||||
@@ -63,7 +63,9 @@ TOOLS = [
|
||||
"and SSH to configured remote systems. Prefer a single focused command and cap noisy output "
|
||||
"with the command itself. The server blocks power control and changes to Athena's SSH, LAN, "
|
||||
"WireGuard, firewall, boot, kernel, mounts and partitions so remote reachability cannot be "
|
||||
"accidentally destroyed. Other commands execute immediately and must be verified afterwards."
|
||||
"accidentally destroyed. Other commands execute immediately and must be verified afterwards. "
|
||||
"Do not clone the canonical repository, request/copy an SSH key, or use Terminal as a substitute "
|
||||
"for the durable file_update, git_publish and recovery workflow."
|
||||
),
|
||||
"inputSchema": {
|
||||
"type": "object",
|
||||
@@ -84,12 +86,14 @@ TOOLS = [
|
||||
"content-bound ticket, exact preview and confirmation phrase. Supported operations: "
|
||||
"file_update (write repository and deployed stack files), run_checks, compose_deploy, "
|
||||
"container_action, openwebui_sync, git_publish, model_download, benchmark, recovery. Show the complete "
|
||||
"preview to the user and stop. Never execute in the same autonomous tool sequence. "
|
||||
"preview to the user and stop. Never execute in the same autonomous tool sequence. This is the "
|
||||
"supported durable source and Git path: never clone the repository inside a sandbox and never "
|
||||
"request or copy an SSH key. "
|
||||
"file_update payload: {files:[{path,content,expected_sha256?}]}; run_checks: "
|
||||
"{checks:[operator-tests,openwebui-filter-tests,platform-verify,compose-main,compose-mcp]}; "
|
||||
"compose_deploy: {compose_file,services,build}; container_action: {action,containers}; "
|
||||
"openwebui_sync: {}; "
|
||||
"git_publish: {message}; model_download: {url,destination,sha256?}; benchmark: "
|
||||
"git_publish: {message,paths:[exact changed repository paths]}; model_download: {url,destination,sha256?}; benchmark: "
|
||||
"{script,arguments}; recovery: {label}."
|
||||
),
|
||||
"inputSchema": {
|
||||
|
||||
@@ -191,7 +191,7 @@ services:
|
||||
build:
|
||||
context: .
|
||||
dockerfile: Dockerfile.athena-operator
|
||||
image: mike-ai/mcp-athena-operator:2.0.0
|
||||
image: mike-ai/mcp-athena-operator:2.1.0
|
||||
container_name: mike-ai-mcp-athena-operator
|
||||
environment:
|
||||
ATHENA_OPERATOR_SOCKET: /operator/operator.sock
|
||||
|
||||
@@ -428,7 +428,7 @@ def read_source(arguments: dict[str, Any]) -> dict[str, Any]:
|
||||
|
||||
|
||||
WORKFLOWS = {
|
||||
"mcp": ["platform/mcp/compose.yaml", "platform/mcp/README.md", "compose.yaml", "docs/COMPONENTS.md", "docs/SECURITY.md", "docs/QWEN_OPERATOR_CONTEXT.md"],
|
||||
"mcp": ["platform/mcp/compose.yaml", "platform/mcp/README.md", "platform/mcp/athena_operator_mcp.py", "platform/hermes/skills/athena-operator/SKILL.md", "compose.yaml", "docs/COMPONENTS.md", "docs/SECURITY.md", "docs/PLATFORM_CONTEXT_MCP.md", "docs/QWEN_OPERATOR_CONTEXT.md"],
|
||||
"model": ["config/install.env.example", "platform/models/manifest.example.yaml", "platform/profiles/", "docs/STANDARD_PROFILE_MATRIX.md", "docs/QWEN_OPERATOR_CONTEXT.md"],
|
||||
"profile": ["platform/profiles/", "router/router_profiles.json", "platform/openwebui/install-models.sh", "docs/STANDARD_PROFILE_MATRIX.md"],
|
||||
"tts": ["compose.yaml", "router/xtts_worker.py", "platform/scripts/rollback-tts-production.sh", "docs/XTTS_EVALUATION_2026-08-23.md"],
|
||||
@@ -453,15 +453,17 @@ def change_workflow(arguments: dict[str, Any]) -> dict[str, Any]:
|
||||
"Capture current state with the narrowest specialist tool.",
|
||||
"Read relevant versioned sources and identify documentation drift.",
|
||||
"Define rollback and protect SSH, LAN, WireGuard and the active inference path.",
|
||||
"Change source-of-truth files, not only a running container.",
|
||||
"Validate syntax/configuration and run a bounded synthetic test.",
|
||||
"Prepare and apply source changes with Athena Operator operation file_update. Never clone the repository inside the sandbox and never request or copy an SSH key.",
|
||||
"Validate syntax/configuration with Athena Operator operation run_checks and run a bounded synthetic test.",
|
||||
"Deploy only named services with Athena Operator operation compose_deploy.",
|
||||
"Verify service health and remote reachability without reading chats or private payloads.",
|
||||
"Update PLATFORM_OVERVIEW/CURRENT_REFERENCE/QWEN_OPERATOR_CONTEXT and the affected runbook.",
|
||||
"Commit and push the private Git repository using a separate authorized Git tool.",
|
||||
"Create and verify a new encrypted recovery bundle and self-contained data-disk kit.",
|
||||
"Commit and push only the explicitly selected changed paths with Athena Operator operation git_publish.",
|
||||
"Create and verify a new encrypted recovery bundle and self-contained data-disk kit with Athena Operator operation recovery.",
|
||||
],
|
||||
"hard_boundaries": [
|
||||
"This context MCP does not modify services, Docker, networking, models or secrets.",
|
||||
"The sandbox needs neither a Git clone nor an SSH key; Athena Operator owns the canonical repository and deploy credentials.",
|
||||
"No shutdown, reboot, kernel/driver, SSH, firewall or VPN change without exact user approval and rollback.",
|
||||
"Never claim Git or recovery is current until separately verified.",
|
||||
],
|
||||
|
||||
@@ -310,12 +310,18 @@ def normalise_operation(operation: str, payload: dict[str, Any]) -> tuple[dict[s
|
||||
message = str(payload.get("message", ""))
|
||||
if not SAFE_COMMIT.fullmatch(message):
|
||||
raise ValueError("invalid commit message")
|
||||
status = run(["git", "status", "--short"], cwd=REPOSITORY, check=True)["output"].strip()
|
||||
paths = payload.get("paths")
|
||||
if not isinstance(paths, list) or not 1 <= len(paths) <= MAX_FILES:
|
||||
raise ValueError("paths must contain 1..24 repository files")
|
||||
selected = [str(safe_relative(str(path))) for path in paths]
|
||||
if len(set(selected)) != len(selected):
|
||||
raise ValueError("paths must be unique")
|
||||
status = run(["git", "status", "--short", "--", *selected], cwd=REPOSITORY, check=True)["output"].strip()
|
||||
if not status:
|
||||
raise RuntimeError("repository has no changes to publish")
|
||||
diff = run(["git", "diff", "--stat"], cwd=REPOSITORY, check=True)["output"]
|
||||
preview = f"Commit message: {message}\n\nChanged and untracked files:\n{status}\n\nDiff summary:\n{diff}"
|
||||
return {"message": message, "reviewed_status": status}, preview
|
||||
raise RuntimeError("selected repository paths have no changes to publish")
|
||||
diff = run(["git", "diff", "--stat", "--", *selected], cwd=REPOSITORY, check=True)["output"]
|
||||
preview = f"Commit message: {message}\nSelected paths: {', '.join(selected)}\n\nSelected changes:\n{status}\n\nDiff summary:\n{diff}"
|
||||
return {"message": message, "paths": selected, "reviewed_status": status}, preview
|
||||
if operation == "model_download":
|
||||
url = str(payload.get("url", ""))
|
||||
parsed = urllib.parse.urlparse(url)
|
||||
@@ -414,12 +420,13 @@ def execute_operation(ticket: str, operation: str, payload: dict[str, Any]) -> d
|
||||
raise FileNotFoundError("versioned Open WebUI synchronisation script is missing")
|
||||
return {"sync": run(["bash", str(installer)], cwd=STACK, timeout=1800, check=True)}
|
||||
if operation == "git_publish":
|
||||
current_status = run(["git", "status", "--short"], cwd=REPOSITORY, check=True)["output"].strip()
|
||||
selected = payload["paths"]
|
||||
current_status = run(["git", "status", "--short", "--", *selected], cwd=REPOSITORY, check=True)["output"].strip()
|
||||
if current_status != payload["reviewed_status"]:
|
||||
raise RuntimeError("repository changed after the Git publish preview")
|
||||
run(["git", "add", "--all"], cwd=REPOSITORY, check=True)
|
||||
run(["git", "diff", "--cached", "--check"], cwd=REPOSITORY, check=True)
|
||||
commit = run(["git", "commit", "-m", payload["message"]], cwd=REPOSITORY, check=True)
|
||||
raise RuntimeError("selected repository paths changed after the Git publish preview")
|
||||
run(["git", "add", "--", *selected], cwd=REPOSITORY, check=True)
|
||||
run(["git", "diff", "--cached", "--check", "--", *selected], cwd=REPOSITORY, check=True)
|
||||
commit = run(["git", "commit", "-m", payload["message"], "--", *selected], cwd=REPOSITORY, check=True)
|
||||
pushed = run(["git", "push", "origin", "HEAD:main"], cwd=REPOSITORY, timeout=300, check=True)
|
||||
head = run(["git", "rev-parse", "HEAD"], cwd=REPOSITORY, check=True)["output"].strip()
|
||||
(STACK / ".mike-ai-source-commit").write_text(head + "\n")
|
||||
|
||||
Reference in New Issue
Block a user