Mark/mesh-seed
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

[Phase 6] Operational Utility - Meta Issue #69

New issue
Closed
opened 2026-04-02 20:52:11 +00:00 by Mark · 4 comments
Mark commented 2026-04-02 20:52:11 +00:00
Owner
Copy link

Overview

Make the mesh a sustainable, useful tool - not just technically complete but actually operable.

Problem Statement

The mesh can route intents and call LLMs, but:

  • Generated content disappears into ledger (not usable)
  • Can't read files or documents (no input pipeline)
  • Can't execute commands or call APIs (no tools)
  • No memory across conversations (one-shot only)
  • No cost tracking (economic sustainability unknown)
  • No human interface (hard to interact with)
  • No automation (reactive only)

Sub-Issues

Issue Title Priority Duration
TBD Artifact System P0 1 week
TBD File Input Pipeline P0 1 week
TBD Tool Library P0 1 week
TBD Conversation Memory P0 1 week
TBD Cost & Token Tracking P0 1 week
TBD Chat Interface (Slack/Discord) P1 1 week
TBD Intent Builder UI P1 1 week
TBD Scheduler P2 1 week
TBD Webhook Endpoints P2 1 week
TBD Directory Watchers P2 1 week
TBD Observability (Metrics/Logs) P2 1 week

Success Criteria (Phase 6 Complete)

  • Generated content accessible as artifacts
  • Can ingest files, URLs, documents
  • Can execute shell commands, HTTP requests
  • Multi-turn conversations with memory
  • Know cost per intent, budget limits work
  • Humans can interact via chat interface
  • Recurring tasks run automatically

Architecture Impact

Current:
Intent → Router → LLM → Ledger (result dies here)

Future:
Intent → Router → LLM → Artifact Store → Git/S3/Disk
         ↓
      File Input → Document Parser → Chunked Context
         ↓
      Tool Execution → Shell/HTTP/File → Actions
         ↓
      Conversation Memory → Multi-turn → Project Context

Priority

Critical - Without these, the mesh is technically impressive but practically unusable.

## Overview Make the mesh a sustainable, useful tool - not just technically complete but actually operable. ## Problem Statement The mesh can route intents and call LLMs, but: - Generated content disappears into ledger (not usable) - Can't read files or documents (no input pipeline) - Can't execute commands or call APIs (no tools) - No memory across conversations (one-shot only) - No cost tracking (economic sustainability unknown) - No human interface (hard to interact with) - No automation (reactive only) ## Sub-Issues | Issue | Title | Priority | Duration | |-------|-------|----------|----------| | TBD | Artifact System | P0 | 1 week | | TBD | File Input Pipeline | P0 | 1 week | | TBD | Tool Library | P0 | 1 week | | TBD | Conversation Memory | P0 | 1 week | | TBD | Cost & Token Tracking | P0 | 1 week | | TBD | Chat Interface (Slack/Discord) | P1 | 1 week | | TBD | Intent Builder UI | P1 | 1 week | | TBD | Scheduler | P2 | 1 week | | TBD | Webhook Endpoints | P2 | 1 week | | TBD | Directory Watchers | P2 | 1 week | | TBD | Observability (Metrics/Logs) | P2 | 1 week | ## Success Criteria (Phase 6 Complete) - [ ] Generated content accessible as artifacts - [ ] Can ingest files, URLs, documents - [ ] Can execute shell commands, HTTP requests - [ ] Multi-turn conversations with memory - [ ] Know cost per intent, budget limits work - [ ] Humans can interact via chat interface - [ ] Recurring tasks run automatically ## Architecture Impact ``` Current: Intent → Router → LLM → Ledger (result dies here) Future: Intent → Router → LLM → Artifact Store → Git/S3/Disk ↓ File Input → Document Parser → Chunked Context ↓ Tool Execution → Shell/HTTP/File → Actions ↓ Conversation Memory → Multi-turn → Project Context ``` ## Priority **Critical** - Without these, the mesh is technically impressive but practically unusable.
Mark commented 2026-04-02 20:56:09 +00:00
Author
Owner
Copy link

Updated Issue List

Issue Title Priority Duration
#70 Artifact System P0 1 week
#71 File Input Pipeline P0 1 week
#72 Tool Library P0 1 week
#73 Conversation Memory P0 1 week
#74 Cost & Token Tracking P0 1 week
#75 Chat Interface (Slack/Discord) P1 1 week
#76 Scheduler P2 1 week
#77 Webhook Endpoints P2 1 week
#78 Directory Watchers P2 1 week
#79 Observability (Metrics/Logs/Traces) P2 1 week

Total estimated duration: 10 weeks (can parallelize P0 issues)

Dependencies:

  • #71 (File Input) depends on #70 (Artifacts)
  • #75 (Chat) depends on #73 (Memory) and #70 (Artifacts)
  • #78 (Watchers) depends on #71 (File Input)

Independent (can start immediately):

## Updated Issue List | Issue | Title | Priority | Duration | |-------|-------|----------|----------| | #70 | Artifact System | P0 | 1 week | | #71 | File Input Pipeline | P0 | 1 week | | #72 | Tool Library | P0 | 1 week | | #73 | Conversation Memory | P0 | 1 week | | #74 | Cost & Token Tracking | P0 | 1 week | | #75 | Chat Interface (Slack/Discord) | P1 | 1 week | | #76 | Scheduler | P2 | 1 week | | #77 | Webhook Endpoints | P2 | 1 week | | #78 | Directory Watchers | P2 | 1 week | | #79 | Observability (Metrics/Logs/Traces) | P2 | 1 week | **Total estimated duration: 10 weeks** (can parallelize P0 issues) **Dependencies:** - #71 (File Input) depends on #70 (Artifacts) - #75 (Chat) depends on #73 (Memory) and #70 (Artifacts) - #78 (Watchers) depends on #71 (File Input) **Independent (can start immediately):** - #70, #72, #73, #74, #76, #77, #79
Mark commented 2026-05-18 10:33:49 +00:00
Author
Owner
Copy link

Feature Triage Assessment

Scope: large
Risk: medium
Spec Alignment: aligned
Summary: Meta-issue for Phase 6 of mesh-seed, adding 8 operational utility features (tool execution, conversation memory, cost tracking, chat interface, scheduler, webhooks, directory watchers, observability) to make the mesh practically operable beyond technical completeness.
Recommendation: Issue body is significantly stale — #70 (Artifact System) and #71 (File Input Pipeline) are already complete per ROADMAP.md, sub-issue IDs exist (#70-#79) not TBD, priorities have shifted (Tool Library is P1 not P0, Conversation Memory P1 not P0), and 'Intent Builder UI' was dropped. Update issue body to match ROADMAP current state as source of truth. For remaining work: prioritize #72 (Tool Library — shell_command/http_request/file_ops wrappers already exist in tools/_muscle/ and need integration into worker ToolRunner) and #73 (Conversation Memory) as highest-impact. Several components (#74 cost tracking, #77 webhook_listener, #78 file_watcher, #72 tools) already have partial implementations ready for integration.
Rationale: SCOPE=large: 8 remaining sub-issues, each 1-2 weeks, spanning tools, memory, cost, chat, scheduler, webhooks, watchers, observability. This is a full project phase. RISK=medium: tool library involves shell execution (security-sensitive), chat interface is network-facing, but risk is mitigated by existing implementations (shell_command/file_ops/http_request tools already in tools/_muscle/) and the project's TOOL_ARCHITECTURE.md mandates lightweight sandboxed wrappers. SPEC=aligned: this is literally Phase 6 from ROADMAP.md, which explicitly references #69 as the meta issue. The architecture principles (substrate routes, workers execute) are respected — tool execution, file input, and memory all live at the worker/agent level, not in mesh_node infrastructure.

Labeled blocked:needs-decision — unblock on Forgejo to dispatch to the fixer pipeline.

## Feature Triage Assessment **Scope:** large **Risk:** medium **Spec Alignment:** aligned **Summary:** Meta-issue for Phase 6 of mesh-seed, adding 8 operational utility features (tool execution, conversation memory, cost tracking, chat interface, scheduler, webhooks, directory watchers, observability) to make the mesh practically operable beyond technical completeness. **Recommendation:** Issue body is significantly stale — #70 (Artifact System) and #71 (File Input Pipeline) are already complete per ROADMAP.md, sub-issue IDs exist (#70-#79) not TBD, priorities have shifted (Tool Library is P1 not P0, Conversation Memory P1 not P0), and 'Intent Builder UI' was dropped. Update issue body to match ROADMAP current state as source of truth. For remaining work: prioritize #72 (Tool Library — shell_command/http_request/file_ops wrappers already exist in tools/_muscle/ and need integration into worker ToolRunner) and #73 (Conversation Memory) as highest-impact. Several components (#74 cost tracking, #77 webhook_listener, #78 file_watcher, #72 tools) already have partial implementations ready for integration. **Rationale:** SCOPE=large: 8 remaining sub-issues, each 1-2 weeks, spanning tools, memory, cost, chat, scheduler, webhooks, watchers, observability. This is a full project phase. RISK=medium: tool library involves shell execution (security-sensitive), chat interface is network-facing, but risk is mitigated by existing implementations (shell_command/file_ops/http_request tools already in tools/_muscle/) and the project's TOOL_ARCHITECTURE.md mandates lightweight sandboxed wrappers. SPEC=aligned: this is literally Phase 6 from ROADMAP.md, which explicitly references #69 as the meta issue. The architecture principles (substrate routes, workers execute) are respected — tool execution, file input, and memory all live at the worker/agent level, not in mesh_node infrastructure. Labeled `blocked:needs-decision` — unblock on Forgejo to dispatch to the fixer pipeline.
Mark commented 2026-06-07 06:25:33 +00:00
Author
Owner
Copy link

⏸ Needs Decision

What needs to be decided?

  • Should this be split into smaller sub-issues? If yes, remove the blocked:needs-decision label and the triage will create a decomposition issue.
  • Do you want to proceed despite the risk? If yes, remove the blocked:needs-decision label and the triage will approve it.

Blocking factors:

  • Large scope — may need decomposition into phased sub-issues
  • High risk — needs human sign-off before proceeding

Scope: large Risk: high Spec: aligned Type: feature
Summary: Add 11 operational subsystems (artifacts, file input, tool execution, conversation memory, cost tracking, chat interface, scheduler, webhooks, directory watchers, observability) to make the mesh practically usable beyond technical completeness.
Suggestion: Break remaining sub-issues into individual tracked issues (already partially done). Prioritize: Tool Library first — AGENTS.md already describes ToolRunner conceptually and it's a dependency for workers; Conversation Memory + Cost Tracking next (foundation for Chat). Security sandbox for Tool Library (shell/HTTP exec) must be designed upfront given high risk. Scheduler, Webhooks, Watchers can parallelize. Note: #70 (Artifact System) and #71 (File Input Pipeline) are already marked complete in ROADMAP.md — update the meta-issue's sub-issue table to reflect this and avoid duplication.
Rationale: SCOPE=large: 11 sub-issues spanning multiple new subsystems (tool exec, memory, cost tracking, chat, scheduling, webhooks, watchers, observability) — each is a module or subsystem of its own, well beyond 15+ files. RISK=high: Tool Library introduces shell/HTTP execution (sandboxing critical), Chat Interface adds external attack surface, Webhook Endpoints expose I/O, Directory Watchers touch filesystem — all security-sensitive and IO-heavy. SPEC=aligned: Phase 6 is the explicitly planned next phase in ROADMAP.md, extending the existing Intent→Router→LLM→Ledger flow. TYPE=feature: adding new operational capabilities, not fixing existing bugs.

To unblock: Remove the blocked:needs-decision label. The triage will apply the appropriate outcome based on your choice above.

## ⏸ Needs Decision **What needs to be decided?** - **Should this be split into smaller sub-issues?** If yes, remove the `blocked:needs-decision` label and the triage will create a decomposition issue. - **Do you want to proceed despite the risk?** If yes, remove the `blocked:needs-decision` label and the triage will approve it. **Blocking factors:** - **Large scope** — may need decomposition into phased sub-issues - **High risk** — needs human sign-off before proceeding --- **Scope:** large **Risk:** high **Spec:** aligned **Type:** feature **Summary:** Add 11 operational subsystems (artifacts, file input, tool execution, conversation memory, cost tracking, chat interface, scheduler, webhooks, directory watchers, observability) to make the mesh practically usable beyond technical completeness. **Suggestion:** Break remaining sub-issues into individual tracked issues (already partially done). Prioritize: Tool Library first — AGENTS.md already describes ToolRunner conceptually and it's a dependency for workers; Conversation Memory + Cost Tracking next (foundation for Chat). Security sandbox for Tool Library (shell/HTTP exec) must be designed upfront given high risk. Scheduler, Webhooks, Watchers can parallelize. Note: #70 (Artifact System) and #71 (File Input Pipeline) are already marked complete in ROADMAP.md — update the meta-issue's sub-issue table to reflect this and avoid duplication. **Rationale:** SCOPE=large: 11 sub-issues spanning multiple new subsystems (tool exec, memory, cost tracking, chat, scheduling, webhooks, watchers, observability) — each is a module or subsystem of its own, well beyond 15+ files. RISK=high: Tool Library introduces shell/HTTP execution (sandboxing critical), Chat Interface adds external attack surface, Webhook Endpoints expose I/O, Directory Watchers touch filesystem — all security-sensitive and IO-heavy. SPEC=aligned: Phase 6 is the explicitly planned next phase in ROADMAP.md, extending the existing Intent→Router→LLM→Ledger flow. TYPE=feature: adding new operational capabilities, not fixing existing bugs. **To unblock:** Remove the `blocked:needs-decision` label. The triage will apply the appropriate outcome based on your choice above.
Mark commented 2026-08-12 18:42:05 +00:00
Author
Owner
Copy link

Phase 6 complete — all sub-issues closed: #70, #71, #72, #73, #74, #75, #76, #77, #78, #79. Closing parent; sub-issues tracked separately.

Phase 6 complete — all sub-issues closed: #70, #71, #72, #73, #74, #75, #76, #77, #78, #79. Closing parent; sub-issues tracked separately.
Mark 2026-08-12 18:42:05 +00:00
Sign in to join this conversation.
No Branch/Tag specified
Branches Tags
main
mesh-seed#142-gate-verify-pass-07b1f89
Labels
Clear labels   
blocked:children

   
blocked:commit-ready-failed

   
blocked:depends-231

Depends on #231 (Discord Bot Foundation) landing first. Do not pick until #231 is closed.

  
blocked:depends-236

Depends on #236 (Phase 1) landing first. Do not pick until #236 is closed.

  
blocked:depends-237

Depends on #237 (Phase 2) landing first. Do not pick until #237 is closed.

  
blocked:depends-238

Depends on #238 (Phase 3) landing first. Do not pick until #238 is closed.

  
blocked:depends-239

Depends on #239 (Phase 4) landing first. Do not pick until #239 is closed.

  
blocked:gate-fetch

   
blocked:gate-fetch

   
blocked:gate-lint

   
blocked:gate-research

   
blocked:needs-attention

Janitor escalated: pipeline terminated without producing expected changes. Human review required.

  
blocked:needs-decision

   
blocked:no-changes

   
blocked:no-procedure

   
blocked:preflight

Preflight check failed

  
blocked:verify-failed

   
bug

Something is broken

  
enhancement

New feature or request

  
feature-request

   
high-priority

Critical path items

  
in-progress

Issue is currently being worked on by a quickfix runner

  
lint-cleanup

Repo lint baseline is dirty

  
needs-decompose

   
needs-triage

   
ops-retry

   
ops-task

Operations task — install, configure, deploy, API calls

  
phase-5

Phase 5 Self-Building Infrastructure

  
quickfix

Pipe to opencode for direct fix

  
security/medium

Medium severity security issue

  
self-building

Autonomous code generation and self-improvement

  
triage-approved

Approved by triage — queued for fixer pipeline

No labels
blocked:children
blocked:commit-ready-failed
blocked:depends-231
blocked:depends-236
blocked:depends-237
blocked:depends-238
blocked:depends-239
blocked:gate-fetch
blocked:gate-fetch
blocked:gate-lint
blocked:gate-research
blocked:needs-attention
blocked:needs-decision
blocked:no-changes
blocked:no-procedure
blocked:preflight
blocked:verify-failed
bug
enhancement
feature-request
high-priority
in-progress
lint-cleanup
needs-decompose
needs-triage
ops-retry
ops-task
phase-5
quickfix
security/medium
self-building
triage-approved
Milestone
Clear milestone
No items
No milestone
Projects
Clear projects
No items
No project
Assignees
Clear assignees
No assignees
1 participant
Notifications
Due date
The due date is invalid or out of range. Please use the format "yyyy-mm-dd".

No due date set.

Dependencies

No dependencies set.

Reference
Mark/mesh-seed#69
No description provided.