multi-agent-mux/FUTURE_WORKS.md

FUTURE_WORKS.md

Purpose: Track future work candidates for the multi-agent-mux project. For completed items, see DONE.md. Last Updated: 2026-06-22

---

Future Improvements Roadmap

Below is the list of pending future work items. These items were proposed based on the security, concurrency, portability, and workflow analysis of the system.

ID	Task	Priority	Effort	Domain / Description	Dependencies
FW-L4	Migrate Job Registry to SQLite to overcome NFS flock limitations	P3 (Low)	Large	Concurrency/Infrastructure Scalability: Similar to the Session Registry, migrate the individual JSON file lock (fcntl.flock) registry structure into an integrated SQLite database transaction structure, guaranteeing full reliability in distributed/network file systems like NFS.	Conditional (commence only when multi-host/NFS deployment is required)
FW-P1	Eliminate GNU/Linux userland assumptions in lib.sh	P2 (Medium)	Small	Portability: Replace GNU coreutils-specific commands (like df --output=target and Linux-specific mount formats) in lib.sh with portable equivalents, resolving silent failures of NFS detection on macOS/BSD.	None
FW-P2	Add explicit Windows concurrency strategy in mqtt_common.py	P1 (High)	Medium	Portability / Concurrency: Detect non-POSIX systems at module initialization and either fail fast with a descriptive warning or substitute alternative lock strategies (e.g. msvcrt.locking), while preserving the best-effort nature of the _file_lock log appender.	None
FW-P3	Align virtualenv loading and dependency verifications	P2 (Medium)	Medium	Portability: Prevent local interpreter mismatches in Poetry/UV environments and ensure the launch scripts fail early with clear diagnostic warnings if required Python dependencies are missing at startup.	None
FW-P4	Secure default MQTT broker and namespaces	P1 (High)	Medium	Portability / Security: Prevent remote session hijack and eavesdropping by providing a private TLS-enabled broker template rather than defaulting to broker.hivemq.com in public namespaces.	None
FW-P5	Resolve BASH_SOURCE path resolution under zsh	P2 (Medium)	Small	Portability: Fix lib.sh interactive sourcing issues under zsh shell where ${BASH_SOURCE[0]} resolves to empty.	None
FW-P6	Anchor project root dynamically via marker-file lookup	P1 (High)	Medium	Portability: Resolve structural fragility caused by hardcoded ../.. relative directory traversal in lib.sh, status.sh, and reconcile.sh. Use an upward search for root markers (.git, .mam, .env) to export a single source of truth for WORKSPACE_ROOT.	None
FW-P7	Enforce HMAC verification and liveness checks on monitor termination	P1 (High)	Medium	Portability / Security: Prevent remote session killing by unauthorized or spoofed events. Integrate verify_hmac inside the monitor (reconcile.sh's on_message handler) and confirm expected artifacts exist before executing tmux kill-session.	None
FW-W1	Replace global registry lock with fine-grained locks	P2 (Medium)	Medium	Concurrency / Scaling: Eliminate throughput bottlenecks where all progress/sequence updates channel through a single fcntl lock on .mam/jobs/. Implement per-job lock files.	None
FW-W2	Implement readiness probes for blind TUI key inputs	P2 (Medium)	Large	Workflow: Replace fixed timing sleeps in create, resume, and stop scripts with dynamic terminal readiness probes (e.g. scrapers or CLI checking hooks) to dismiss trust dialogs robustly.	None
FW-W3	Consolidate per-job watchdogs into shared wildcard subscriber	P2 (Medium)	Medium	Workflow / Efficiency: Drop per-job watchdog + subscriber churn (which reconnects every 120s) and migrate their handling to the wildcard MQTT subscriber already running in reconcile.sh.	None
FW-W4	Persist subscriber sequence numbers alongside job records	P1 (High)	Medium	Workflow / Security: Persist subscriber.last_seq to disk or SQLite to prevent sequence counter reset on subscriber restart, locking down the replay defense window for the full job lifetime.	None
FW-W5	Define structured message schema for reviewer verdicts	P2 (Medium)	Medium	Workflow: Create a dedicated reviewer topic (e.g., reviews/<job_id>/verdicts) emitting structured JSON verdicts (PASS / NOT_PASS + details) to eliminate raw text grepping by the PM.	None
FW-W6	Expand monitor reconciliation support to Hermes agent	P2 (Medium)	Medium	Workflow / Consistency: Fully integrate hermes sessions into auto-registration (drift-B) and ID materialization (drift-C) under reconcile.sh to match Claude/Agy monitoring coverage.	None

---

Detailed Discussion Results & Directions (Reviewer Consensus)

1. Conditional Deferral of SQLite Integration (FW-L4):

   • Unlike the session registry, maintaining individual job data in JSON files is highly intuitive for management and debugging. Since the current deployment is constrained to a single-host local file system, fcntl.flock locks are sufficient. Thus, this is assigned a low priority (P3) and will be tackled conditionally.

2. Explicit Concurrency Strategy on Windows (FW-P1, FW-P2):

   • Silent failovers are the worst design patterns for concurrency. Instead of letting Windows environments run without a lock (which occurs when fcntl fails silently), we detect POSIX availability at startup. We either fail fast to prompt the user to use a POSIX-compliant shell/wrapper, or dynamically load msvcrt.locking to provide a matching file locking mechanism. This guarantees consistent synchronization behaviors across Windows and Unix platforms.

3. Dynamic Root Anchor (FW-P6):

   • Hardcoding relative depth limits (like ../.. relative to a skill's location) creates direct fragility when moving directories or refactoring. By walking up the directory tree to search for known anchors (like .git or .mam), we establish a single canonical root path and prevent scripts from breaking when their execution wrappers are relocated.

4. Monitor Termination Authorization (FW-P7):

   • Auto-termination must not trust unauthenticated events. Since reconcile.sh listens to a wildcard topic, any client on a public broker could spoof a terminal message and trigger tmux kill-session. Requiring HMAC signature verification on the terminal event path, combined with artifact validation, mitigates spoofing and accidental session cleanup.