Reported issues for gitworthy

Pod holds 13 of 13 problems reported by people outside the maintainer team. Issues filed by the project's own owners, members and collaborators are excluded entirely — a maintainer's release checklist is not a warning to a prospective user.

Back to gitworthy.

Most discussed

GW-032: Complete MCP descriptions, annotations, structured results, and errors

Outcome

Complete Gitworthy's MCP surface as the primary agent-facing product contract: clear tool descriptions, safe annotations, validated structured results, protocol-correct errors, cancellation/progress support, and parity with the CLI/core.

An MCP host should be able to discover the right tool, understand whether it is read-only/idempotent, call it with validated input, and act on structured output without parsing prose.

Why this matters

Cursor, ChatGPT, Hermes, and other agents a

Read the thread · 2026-07-30 · open · 2 comments

GW-035: Freeze schemas and add compatibility/deprecation suite

Outcome

Freeze the public 1.0 schemas and add a compatibility/deprecation suite that proves older supported inputs, stored records, CLI JSON, MCP results, and generated artifacts continue to work across upgrades.

This issue turns pre-1.0 draft contracts into an explicit stability promise and defines how future changes are versioned, migrated, deprecated, and rejected.

Why this matters

Gitworthy is intended to sit inside agent workflows. Silent field changes, semantic drift, or incompat

Read the thread · 2026-07-30 · open · 1 comment

GW-034: Run and document first-user beta

Outcome

Run and document Gitworthy's first external-user beta with a small, deliberate cohort using real MCP and CLI workflows.

The beta should validate whether new users can install the tool, configure access, scout and interpret candidate queues, recheck before execution, report incorrect decisions, and understand the local-first data model without maintainer hand-holding.

Why this matters

The maintainer's daily dogfooding proves utility but not onboarding clarity or general reliabil

Read the thread · 2026-07-30 · open · 1 comment

GW-033: Add onboarding, verdict, security, data, eval, and MCP docs

Outcome

Complete the documentation set required for public beta: onboarding, verdict semantics, agent workflow, CLI, MCP, security, local data, capture, evaluation, troubleshooting, and compatibility guidance.

A new user should be able to install Gitworthy, connect it to an MCP host, run a bounded hunt, interpret every verdict and limitation, record an outcome, and recover from common failures without maintainer assistance.

Progress already delivered

PR #63 completed a meaningful first

Read the thread · 2026-07-30 · open · 1 comment

GW-031: Complete full doctor and data doctor

Outcome

Expand doctor into a complete capability and local-data diagnostic that tells a user or agent exactly which Gitworthy workflows are safe to run, which will be degraded, and how to fix each problem.

Add both environment/provider checks and a data doctor path for the versioned local store, migrations, indexes, captures, and disk health.

Why this matters

Agent workflows fail in confusing ways when auth scopes, timeline visibility, git, npm, cache, disk, or local data are parti

Read the thread · 2026-07-30 · open · 1 comment

GW-030: Complete human CLI renderer, strict help, quiet/verbose/progress

Outcome

Complete the human CLI experience: strict and useful help, action-oriented multi-line rendering, clean stdout/stderr separation, and consistent quiet/verbose/progress behavior across primary commands.

Machine users should consume JSON; humans should receive concise output that explains the verdict, next action, strongest evidence, completed checks, and limitations without reading raw envelopes.

Why this matters

Gitworthy's agent/MCP contract is primary, but the CLI is the debug

Read the thread · 2026-07-30 · open · 1 comment

GW-029: Add performance budgets, counters, and regression benchmarks

Outcome

Add explicit performance budgets, provider/request counters, and regression benchmarks for scan, hunt, check, replay, and store operations.

The project should be able to prove that agent scouting remains bounded and responsive as candidate pagination, richer evidence, persistence, and resume support are added.

Why this matters

Gitworthy's wall time is usually the sum of a bounded number of provider checks. Without measured budgets, later features can quietly multiply requests,

Read the thread · 2026-07-30 · open · 1 comment

GW-026: Add transparent ranking contract and explain-ranking output

Outcome

Define and expose a transparent, versioned ranking contract for scan and hunt candidates, including component scores, weights, reasons, and an --explain-ranking view.

Ranking should help an agent order a candidate queue without turning heuristic fit into a hidden eligibility decision or a verdict input.

Why this matters

Gitworthy already computes issue quality and optional skill fit, but users and agents need to understand why one issue ranked above another. Transparent ranki

Read the thread · 2026-07-30 · closed · 1 comment

Most recent

GW-042: Contention P2 — gap analysis, swarm risk, MCP tools

Outcome

Gap analysis vs claiming PRs, swarm-risk posture for zero-claim issues, MCP tools, optional triage ranking flag.

Scope

C3: test coverage / stated-ask / adjacent-risk / scope_excess gaps (operator-facing; read-only)
C4: swarm_risk high|medium|low + posture race|differentiate|defer
MCP: contention, scope_check (additive; existing tool names unchanged)
Optional: triage --contended / hunt ranking signal (coordinate with GW-026; baton overlap open question)

Depends

Read the thread · 2026-08-02 · closed · 0 comments

GW-039: Add Streamable HTTP MCP transport for Cloud Agents and mobile

Outcome

Ship a first-class Streamable HTTP MCP transport so Gitworthy can be used from Cursor Cloud Agents, mobile/iPad, and other remote hosts that cannot rely on local stdio/npx spawn.

This is transport and access, not a hosted SaaS product. The local decision engine stays MIT and open; remote clients connect to a deployable HTTP endpoint with explicit auth.

Why this matters

Cloud Agents recommend HTTP MCP (credentials stay out of the agent VM; tool calls are proxied). Mobile/i

Read the thread · 2026-08-02 · closed · external user · 0 comments

GW-020: Add deterministic brief generation

Outcome

Add deterministic brief generation that turns a saved Gitworthy decision into a compact, evidence-linked handoff artifact for a human or coding agent.

A brief should explain what the target is, why Gitworthy reached its verdict, what remains unresolved, and what the next safe action is—without asking an LLM to reinterpret raw provider output.

Why this matters

The current result envelope is machine-friendly but can still require multiple tool calls and substantial host-agent i

Read the thread · 2026-07-30 · closed · 0 comments

GW-019: Add config/profile/target-manifest support

Outcome

Add a versioned, secret-free configuration system for repeated Gitworthy hunts, personal skill profiles, and explicit repository or organization target manifests.

The first production user should be able to describe their contribution interests and recurring targets once, then run the same agent workflow from Cursor, ChatGPT, Hermes, the CLI, or another MCP host without rebuilding flags manually.

Why this matters

Gitworthy is already useful through MCP, but repeated use still d

Read the thread · 2026-07-30 · closed · 0 comments

GW-007: Add strict input validation and structured CLI/MCP errors

Depends on GW-006.

Read the thread · 2026-07-30 · closed · 0 comments

The remaining reports are on the project's issue tracker.