You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
{{ message }}
Repository navigation
Commit 0537b04
Browse filesBrowse the repository at this point in the historyBrowse files
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.
Copy file name to clipboardExpand all lines: ROADMAP.md
+2-2Lines changed: 2 additions & 2 deletions
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -358,7 +358,7 @@ graph LR
358
358
<details>
359
359
<summary>⚪ Windows native tray app — Todo · P2 · MCP-43</summary>
360
360
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-trayPR 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.
362
362
363
363
```mermaid
364
364
graph LR
@@ -626,7 +626,7 @@ graph LR
626
626
<details>
627
627
<summary>🟢 Analytics dashboard as default page — Done · P1</summary>
628
628
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.
Copy file name to clipboardExpand all lines: roadmap.yaml
+4-4Lines changed: 4 additions & 4 deletions
Original file line number
Diff line number
Diff line change
@@ -150,7 +150,7 @@ epics:
150
150
priority: P2
151
151
mcp: MCP-43
152
152
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-trayPR 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."
154
154
tasks:
155
155
- id: windows-tray-funnel-qa
156
156
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:
260
260
priority: P1
261
261
spec: specs/069-observability-usage-graphs
262
262
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."
264
264
tasks:
265
265
- id: analytics-token-drain-graphs
266
266
title: Per-server / per-tool token-drain graphs
@@ -403,7 +403,7 @@ epics:
403
403
title: "Run public suites locally (τ-bench / BFCL / MCP-specific — final list verified by a research pass) and record reproducible results"
404
404
status: todo
405
405
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."
407
407
- id: token-bench-blog
408
408
title: "Publish results + methodology on mcpproxy.app/blog"
409
409
status: todo
@@ -650,7 +650,7 @@ epics:
650
650
status: done
651
651
priority: P2
652
652
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."
654
654
depends_on: [hygiene-spec-evidence-check]
655
655
- id: hygiene-docs-facts
656
656
title: "Generate volatile CLAUDE.md/README facts (Go version, built-in tool list, sample config) from code with --check"
0 commit comments