Skip to content

Commit 0537b04

Browse files
committed
fix(roadmap): scope four over-broad claims from cross-model review round 3
All four verified against GitHub and the tree before applying. 1. windows-tray: "no Windows-tray PR is open or merged" was false. #74 ("feature: windows tray support") merged 2025-10-23 and the cross-platform Go/systray build still ships on Windows. The claim now scopes to what the epic actually tracks — the native WebView2 replacement — for which no PR exists and native/windows/ is a README placeholder. 2. analytics-dashboard: "can never tick from code" conflated two things. A human can run spec 069's T023 Playwright sweep and tick the box; what can never exist is code evidence for it. Reworded so the distinction is explicit. 3. hygiene-spec-gardener: "three gardener runs ... auto-approved by #842" was wrong. Only #999 carries a github-actions APPROVED review. #824 has none and merged ~24 minutes BEFORE the auto-approve workflow landed; #870 records no approving review either. 4. token-bench-public: calling the MCP-specific third "integrated" overstated completion. ToolRet and LiveMCPTool are static retrieval/token corpora and lap-score is a linter — none is a public agent-loop task suite, which is what the task ultimately owes. Also noted for the record: the linux-arm64 Build Binaries failure on the previous commit is a flaky test, not a regression from this docs-only change. TestServiceStartScanDeepOnRunsSourceResolutionAndPass2 (internal/security/scanner) passes locally with -count=3, and two runs of this same branch four minutes apart — 33360429077 and 33360648947, both docs-only — disagreed on it.
1 parent 38bea56 commit 0537b04

2 files changed

Lines changed: 6 additions & 6 deletions

File tree

‎ROADMAP.md‎

Lines changed: 2 additions & 2 deletions
Original file line numberDiff line numberDiff line change
@@ -358,7 +358,7 @@ graph LR
358358
<details>
359359
<summary>⚪ Windows native tray app — Todo · P2 · MCP-43</summary>
360360

361-
> No spec: link — this epic is the native TRAY app; specs/002-windows-installer is the unrelated INSTALLER spec (35/60) and its badge said nothing about tray progress (wrong link removed 2026-07-10). Option C: WebView2 window reusing shipped Web UI. Most exit criteria already ship; gaps = native window, toasts, profile submenu, Win11 smoke. Telemetry: Windows = ~23% of GitHub downloads but only ~4% of active installs (downloads→actives ~12:1 vs macOS ~4:1) — gate WebView2 work on finding the funnel break first. 2026-08-31 audit: reset from in_review to todo — no Windows-tray PR is open or merged, and native/windows/ holds only a README placeholder with no WebView2 code anywhere in the tree, so 'in review' had no PR to point at.
361+
> No spec: link — this epic is the native TRAY app; specs/002-windows-installer is the unrelated INSTALLER spec (35/60) and its badge said nothing about tray progress (wrong link removed 2026-07-10). Option C: WebView2 window reusing shipped Web UI. Most exit criteria already ship; gaps = native window, toasts, profile submenu, Win11 smoke. Telemetry: Windows = ~23% of GitHub downloads but only ~4% of active installs (downloads→actives ~12:1 vs macOS ~4:1) — gate WebView2 work on finding the funnel break first. 2026-08-31 audit: reset from in_review to todo. Scoped precisely: Windows tray support DID ship in 2025 via the cross-platform Go/systray build (#74, merged 2025-10-23, cmd/mcpproxy-tray/ + internal/tray under GOOS=windows) — what this epic tracks is the NATIVE WebView2 replacement, and for that no PR is open or merged and native/windows/ holds only a README placeholder with no WebView2 code anywhere in the tree. So 'in review' had no PR to point at.
362362
363363
```mermaid
364364
graph LR
@@ -626,7 +626,7 @@ graph LR
626626
<details>
627627
<summary>🟢 Analytics dashboard as default page — Done · P1</summary>
628628

629-
> Per-server / per-tool token-drain graphs; make the dashboard the default landing page. 2026-07-10 truth-sync: spec 069 is SHIPPED (25/26 — the only open task is a Playwright verification sweep), so the graphs half is done. 2026-08-31 audit: the default-landing half shipped too - frontend/src/router/index.ts routes path '/' to the Dashboard component, guarded by frontend/tests/unit/dashboard-default-landing.spec.ts. Spec 069's one remaining task is a local Playwright verification sweep that leaves no committed artifact, so it can never tick from code; the epic is complete.
629+
> Per-server / per-tool token-drain graphs; make the dashboard the default landing page. 2026-07-10 truth-sync: spec 069 is SHIPPED (25/26 — the only open task is a Playwright verification sweep), so the graphs half is done. 2026-08-31 audit: the default-landing half shipped too - frontend/src/router/index.ts routes path '/' to the Dashboard component, guarded by frontend/tests/unit/dashboard-default-landing.spec.ts. Spec 069's one remaining task (T023) is a local Playwright verification sweep that leaves no committed artifact: a human can run it and tick the box, but no code evidence can ever confirm it, so it cannot gate the epic. The epic is complete.
630630
631631
Spec: [069-observability-usage-graphs](./specs/069-observability-usage-graphs/)
632632

‎roadmap.yaml‎

Lines changed: 4 additions & 4 deletions
Original file line numberDiff line numberDiff line change
@@ -150,7 +150,7 @@ epics:
150150
priority: P2
151151
mcp: MCP-43
152152
depends_on: []
153-
note: "No spec: link — this epic is the native TRAY app; specs/002-windows-installer is the unrelated INSTALLER spec (35/60) and its badge said nothing about tray progress (wrong link removed 2026-07-10). Option C: WebView2 window reusing shipped Web UI. Most exit criteria already ship; gaps = native window, toasts, profile submenu, Win11 smoke. Telemetry: Windows = ~23% of GitHub downloads but only ~4% of active installs (downloads→actives ~12:1 vs macOS ~4:1) — gate WebView2 work on finding the funnel break first. 2026-08-31 audit: reset from in_review to todo — no Windows-tray PR is open or merged, and native/windows/ holds only a README placeholder with no WebView2 code anywhere in the tree, so 'in review' had no PR to point at."
153+
note: "No spec: link — this epic is the native TRAY app; specs/002-windows-installer is the unrelated INSTALLER spec (35/60) and its badge said nothing about tray progress (wrong link removed 2026-07-10). Option C: WebView2 window reusing shipped Web UI. Most exit criteria already ship; gaps = native window, toasts, profile submenu, Win11 smoke. Telemetry: Windows = ~23% of GitHub downloads but only ~4% of active installs (downloads→actives ~12:1 vs macOS ~4:1) — gate WebView2 work on finding the funnel break first. 2026-08-31 audit: reset from in_review to todo. Scoped precisely: Windows tray support DID ship in 2025 via the cross-platform Go/systray build (#74, merged 2025-10-23, cmd/mcpproxy-tray/ + internal/tray under GOOS=windows) — what this epic tracks is the NATIVE WebView2 replacement, and for that no PR is open or merged and native/windows/ holds only a README placeholder with no WebView2 code anywhere in the tree. So 'in review' had no PR to point at."
154154
tasks:
155155
- id: windows-tray-funnel-qa
156156
title: "Windows first-run QA pass (downloads→actives 12:1 vs macOS 4:1 — find the funnel break before WebView2 work)"
@@ -260,7 +260,7 @@ epics:
260260
priority: P1
261261
spec: specs/069-observability-usage-graphs
262262
depends_on: [ux-audit]
263-
note: "Per-server / per-tool token-drain graphs; make the dashboard the default landing page. 2026-07-10 truth-sync: spec 069 is SHIPPED (25/26 — the only open task is a Playwright verification sweep), so the graphs half is done. 2026-08-31 audit: the default-landing half shipped too - frontend/src/router/index.ts routes path '/' to the Dashboard component, guarded by frontend/tests/unit/dashboard-default-landing.spec.ts. Spec 069's one remaining task is a local Playwright verification sweep that leaves no committed artifact, so it can never tick from code; the epic is complete."
263+
note: "Per-server / per-tool token-drain graphs; make the dashboard the default landing page. 2026-07-10 truth-sync: spec 069 is SHIPPED (25/26 — the only open task is a Playwright verification sweep), so the graphs half is done. 2026-08-31 audit: the default-landing half shipped too - frontend/src/router/index.ts routes path '/' to the Dashboard component, guarded by frontend/tests/unit/dashboard-default-landing.spec.ts. Spec 069's one remaining task (T023) is a local Playwright verification sweep that leaves no committed artifact: a human can run it and tick the box, but no code evidence can ever confirm it, so it cannot gate the epic. The epic is complete."
264264
tasks:
265265
- id: analytics-token-drain-graphs
266266
title: Per-server / per-tool token-drain graphs
@@ -403,7 +403,7 @@ epics:
403403
title: "Run public suites locally (τ-bench / BFCL / MCP-specific — final list verified by a research pass) and record reproducible results"
404404
status: todo
405405
depends_on: [token-bench-harness]
406-
note: "PARTIALLY SHIPPED via spec 083 - the MCP-specific third is already integrated and reproducible: ToolRet (runtime fetch, never committed; seeded subset via -subset/-seed; run by the toolret-subset job in bench.yml), the 527-tool Apache-2.0 LiveMCPBench snapshot, and the pinned external lap-score linter as an independent verdict. Scope precisely: the LiveMCPBench snapshot is load-bearing for spec 102 SC-001 at fleet scale and is runnable via -livemcptool, but bench.yml does NOT run it (the regular job passes only -corpus-v2), and its loader carries no retrieval golden set — so it measures token/scale, not recall. REMAINING: the agent-loop suites, which need a pinned-LLM budget decision. Re-confirm the shortlist against the completed research pass before building - the τ-bench/BFCL naming here predates it."
406+
note: "PARTIALLY SHIPPED via spec 083 - the MCP-specific third is already integrated and reproducible AS RETRIEVAL/TOKEN CORPORA — not as public agent-loop task suites, which is what this task ultimately owes: ToolRet (runtime fetch, never committed; seeded subset via -subset/-seed; run by the toolret-subset job in bench.yml), the 527-tool Apache-2.0 LiveMCPBench snapshot, and the pinned external lap-score linter as an independent verdict. Scope precisely: the LiveMCPBench snapshot is load-bearing for spec 102 SC-001 at fleet scale and is runnable via -livemcptool, but bench.yml does NOT run it (the regular job passes only -corpus-v2), and its loader carries no retrieval golden set — so it measures token/scale, not recall. REMAINING: the agent-loop suites, which need a pinned-LLM budget decision. Re-confirm the shortlist against the completed research pass before building - the τ-bench/BFCL naming here predates it."
407407
- id: token-bench-blog
408408
title: "Publish results + methodology on mcpproxy.app/blog"
409409
status: todo
@@ -650,7 +650,7 @@ epics:
650650
status: done
651651
priority: P2
652652
pr: ["#824", "#870", "#999", "#842"]
653-
note: "SHIPPED and operating: three gardener runs merged (#824 2026-07-13, #870 2026-07-29, #999 2026-08-17), auto-approved by .github/workflows/spec-gardener-auto-approve.yml (#842). The blocker recorded below is cleared - scripts/check-spec-evidence.py is on main. Claude cloud routine 'spec-roadmap gardener' (trig_014GkHno4XSTobu8ViJV7Sno), Mondays 05:07 UTC. Branch claude/spec-gardener (the `claude/` prefix is what the cloud git-proxy allows to push without unrestricted-branch-push). Guardrails: never pushes main; never auto-applies un-ticks (they go in the PR body for a human); evidence required per tick; adversarial refutation pass; 40-tick cap per run."
653+
note: "SHIPPED and operating: three gardener runs merged (#824 2026-07-13, #870 2026-07-29, #999 2026-08-17). Auto-approval is NOT retroactive and did not carry all three — only #999 has a github-actions APPROVED review; #824 carries none and in fact merged ~24 min BEFORE the auto-approve workflow itself (#842, .github/workflows/spec-gardener-auto-approve.yml, merged 2026-07-13 04:40), and #870 records no approving review either. The blocker recorded below is cleared - scripts/check-spec-evidence.py is on main. Claude cloud routine 'spec-roadmap gardener' (trig_014GkHno4XSTobu8ViJV7Sno), Mondays 05:07 UTC. Branch claude/spec-gardener (the `claude/` prefix is what the cloud git-proxy allows to push without unrestricted-branch-push). Guardrails: never pushes main; never auto-applies un-ticks (they go in the PR body for a human); evidence required per tick; adversarial refutation pass; 40-tick cap per run."
654654
depends_on: [hygiene-spec-evidence-check]
655655
- id: hygiene-docs-facts
656656
title: "Generate volatile CLAUDE.md/README facts (Go version, built-in tool list, sample config) from code with --check"

0 commit comments

Comments
 (0)