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 fa2a28f
Browse filesBrowse the repository at this point in the historyBrowse files
classDef todo fill:#6e7781,stroke:#3d4248,color:#ffffff;
187
189
class sessions_web_ui done;
190
+
class activity_storage_bounds in_progress;
188
191
class action_log_glance_view,action_log_tray_menu,tray_menu_open_telemetry,action_log_retention_tie_in todo;
189
192
```
190
193
@@ -195,6 +198,7 @@ graph LR
195
198
| Activity in the tray menu (recent tool calls + security events, jump to full log) | ⚪ Todo | — |
196
199
| tray_menu_opened counter: Swift menuWillOpen (MCPProxyApp.swift:192) -> lightweight POST /api/v1/telemetry/tray-menu-opened -> registry counter -> heartbeat tray_menu_opened_24h | ⚪ Todo | — |
197
200
| Tie activity retention/size into the glance view | ⚪ Todo | — |
201
+
| Bound every activity-adjacent store: response truncation on the write path (#1173/#1174), per-server tool_calls buckets (#1176), omitempty zero-erasure (#1175) | 🔵 In progress |#1174|
198
202
199
203
</details>
200
204
@@ -203,7 +207,7 @@ graph LR
203
207
204
208
> Measure the real token cost of every routing/savings mode combination — baseline, compact signatures (spec 085), deferred schemas (spec 102), optimistic calling via self-healing pre-dispatch validation, code_execution (spec 096) and stored scripts (spec 097) — on replayed real sessions and on public benchmarks, then publish the results on mcpproxy.app/blog. Every savings number we quote today is an estimate; this turns them into reproducible measurements. Sequenced after schema-deferred so the newest mode is in the matrix. Spec 103 landed 2026-08-31 (#1137 spec+plan, #1139 tasks) after 13 cross-model review rounds; three of its findings changed the design rather than the wording: a recording carries no prompt/conversation/completion oracle so replay CANNOT show agent behaviour (US1 deterministic cost vs US2 live loop are now separate stories); replay needs a FLEET INPUT because the export has no fleet snapshot; and bodies-off yields menu costs plus one cross-mode delta, never an absolute workload cost. The matrix is 5 distinct behaviours, not a 3x2x2 product.
classDef todo fill:#6e7781,stroke:#3d4248,color:#ffffff;
220
-
class token_bench_harness in_progress;
224
+
class token_bench_harness done;
221
225
class token_bench_public,token_bench_blog,token_bench_telemetry todo;
222
226
```
223
227
224
228
| Task | Status | Refs |
225
229
| --- | --- | --- |
226
-
| Replay harness: activity-log sessions re-run under each mode combo; tokens per completed task + first-call success + retries |🔵 In progress |#1141|
230
+
| Replay harness: activity-log sessions re-run under each mode combo; tokens per completed task + first-call success + retries |🟢 Done |#1141#1147#1151#1153#1160|
227
231
| Run public suites locally (τ-bench / BFCL / MCP-specific — final list verified by a research pass) and record reproducible results | ⚪ Todo | — |
228
232
| Publish results + methodology on mcpproxy.app/blog | ⚪ Todo | — |
229
233
| Heartbeat v10: per-tool_response_mode token counters for real-world cohort validation | ⚪ Todo | — |
@@ -381,6 +385,15 @@ graph LR
381
385
382
386
</details>
383
387
388
+
<details>
389
+
<summary>⚪ MCP protocol upgrade to 2026-07-28 revision — Todo · P1</summary>
390
+
391
+
> STABLE GATE CLEARED 2026-09-02: mark3labs/mcp-go v1.0.0 (stable) released; go.mod still pins v0.57.0. Raised P3->P1 on the 2026-09-02 issue-prioritization pass — spec 058 has spec.md only, next step is speckit.plan then tasks (tracker #532). Earlier: UNBLOCKED 2026-08-12: the mcp-go gate cleared — v1.0.0-beta.1 (mark3labs/mcp-go#951) ships full 2026-07-28 support with per-request era detection (the pin was v0.55.x, topping out at 2025-11-25). Spec 058 revision MERGED as PR #1033 on 2026-08-27 (kept in this note, not in pr:, because pr: is implementation evidence and a docs(specs) merge is not that — implementation has not started, hence todo): final error-code renumbering (-32020/-32021/-32022), FR-001..006 / FR-014..016 recast as adopt-and-verify, FR-028 legacy-only transport pin as the safe merge state, plus Risks & Watch Items. CROSS-SPEC CONFLICT still open and now the mandatory first task: FR-012 forbids per-connection */list variation; SHIPPED Spec 057 selects toolset by URL path /mcp/p/<slug> — Option A/B decided at plan time (acceptance = the 2 tests failing under beta.1). 028 agent-token scoping is already compatible (header-carried). Tracker: #532.
<summary>⚪ Windows native tray app — Todo · P2 · MCP-43</summary>
386
399
@@ -464,15 +477,6 @@ graph LR
464
477
465
478
</details>
466
479
467
-
<details>
468
-
<summary>⚪ MCP protocol upgrade to 2026-07-28 revision — Todo · P3</summary>
469
-
470
-
> UNBLOCKED 2026-08-12: the mcp-go gate cleared — v1.0.0-beta.1 (mark3labs/mcp-go#951) ships full 2026-07-28 support with per-request era detection (the pin was v0.55.x, topping out at 2025-11-25). Spec 058 revision MERGED as PR #1033 on 2026-08-27 (kept in this note, not in pr:, because pr: is implementation evidence and a docs(specs) merge is not that — implementation has not started, hence todo): final error-code renumbering (-32020/-32021/-32022), FR-001..006 / FR-014..016 recast as adopt-and-verify, FR-028 legacy-only transport pin as the safe merge state, plus Risks & Watch Items. CROSS-SPEC CONFLICT still open and now the mandatory first task: FR-012 forbids per-connection */list variation; SHIPPED Spec 057 selects toolset by URL path /mcp/p/<slug> — Option A/B decided at plan time (acceptance = the 2 tests failing under beta.1). 028 agent-token scoping is already compatible (header-carried). Tracker: #532.
Copy file name to clipboardExpand all lines: roadmap.yaml
+12-5Lines changed: 12 additions & 5 deletions
Original file line number
Diff line number
Diff line change
@@ -253,6 +253,13 @@ epics:
253
253
status: todo
254
254
note: "No spec: link on purpose — 073-activity-size-retention is the SHIPPED retention backend (13/14); this task is the glance-view tie-in on top of it."
255
255
depends_on: [action-log-glance-view]
256
+
- id: activity-storage-bounds
257
+
title: "Bound every activity-adjacent store: response truncation on the write path (#1173/#1174), per-server tool_calls buckets (#1176), omitempty zero-erasure (#1175)"
258
+
status: in_progress
259
+
priority: P1
260
+
pr: "#1174"
261
+
note: "User report 2026-09-02 (#1173): config.db reached 940MB; activity_max_response_size existed but was never read, and server_<id>_tool_calls buckets have no size, count or age bound at all (the other ~432MB). #1174 (external contributor, CI green) wires the 64KB cap; #1176 and #1175 are the follow-ons. Retention backend (073) prunes activity records only, not the per-server buckets."
262
+
depends_on: []
256
263
257
264
- id: analytics-dashboard
258
265
title: Analytics dashboard as default page
@@ -392,14 +399,14 @@ epics:
392
399
status: in_progress
393
400
priority: P1
394
401
spec: specs/103-token-bench
395
-
pr: "#1141"
396
402
depends_on: [schema-deferred]
397
403
note: "Measure the real token cost of every routing/savings mode combination — baseline, compact signatures (spec 085), deferred schemas (spec 102), optimistic calling via self-healing pre-dispatch validation, code_execution (spec 096) and stored scripts (spec 097) — on replayed real sessions and on public benchmarks, then publish the results on mcpproxy.app/blog. Every savings number we quote today is an estimate; this turns them into reproducible measurements. Sequenced after schema-deferred so the newest mode is in the matrix. Spec 103 landed 2026-08-31 (#1137 spec+plan, #1139 tasks) after 13 cross-model review rounds; three of its findings changed the design rather than the wording: a recording carries no prompt/conversation/completion oracle so replay CANNOT show agent behaviour (US1 deterministic cost vs US2 live loop are now separate stories); replay needs a FLEET INPUT because the export has no fleet snapshot; and bodies-off yields menu costs plus one cross-mode delta, never an absolute workload cost. The matrix is 5 distinct behaviours, not a 3x2x2 product."
398
404
tasks:
399
405
- id: token-bench-harness
400
406
title: "Replay harness: activity-log sessions re-run under each mode combo; tokens per completed task + first-call success + retries"
401
-
status: in_progress
402
-
pr: "#1141"
407
+
status: done
408
+
pr: ["#1141", "#1147", "#1151", "#1153", "#1160"]
409
+
note: "Shipped 2026-08-31..09-01: #1141 replay MVP, #1147 payload decomposition (US4), #1151 tools/list primitive + live fleet source, #1153 live agent loop + reproducibility + publication, #1160 code-execution response-side saving. Epic stays in_progress: public suites, blog post and heartbeat-v10 counters remain todo."
403
410
depends_on: []
404
411
note: "BUILDS ON the existing bench/ harness - do NOT rebuild token counting, encoding arms, break-even or recall. Already shipped there (PRs #747/#748 MCP-42, #851 spec 083): six encoding arms including direct_deferred (spec 102), cl100k_base counting, live response cost, break-even, RecallAtK/NDCGAtK, the v2 report + dashboard, `make bench-discovery` and CI wiring in bench.yml/eval.yml. 2026-08-31 audit correction: the old note claimed this task absorbs discovery-eval-harness because it would measure retrieval recall - recall is ALREADY measured (eval.yml retrieval-d1 + bench/armindex.go), so that is not this task's contribution. GENUINELY OPEN and unique here: (a) activity-log session REPLAY (nothing in bench/ reads the activity log; internal/contracts/activity.go already carries WorkSessionID, ToolName and Response - watch ResponseTruncated, which would undercount tokens); (b) MEASURED first-call success and retry rate — today they are assumed, not observed: bench/session.go defines per-arm literature-derived defaults (armRetryRates, research D8) and bench/report.go only renders and labels them as estimates; (c) tokens-per-SUCCESSFUL-task, which needs a task-completion signal the static harness has no concept of."
405
412
- id: token-bench-public
@@ -715,10 +722,10 @@ epics:
715
722
- id: mcp-2026-upgrade
716
723
title: MCP protocol upgrade to 2026-07-28 revision
717
724
status: todo
718
-
priority: P3
725
+
priority: P1
719
726
spec: specs/058-mcp-2026-upgrade
720
727
depends_on: []
721
-
note: "UNBLOCKED 2026-08-12: the mcp-go gate cleared — v1.0.0-beta.1 (mark3labs/mcp-go#951) ships full 2026-07-28 support with per-request era detection (the pin was v0.55.x, topping out at 2025-11-25). Spec 058 revision MERGED as PR #1033 on 2026-08-27 (kept in this note, not in pr:, because pr: is implementation evidence and a docs(specs) merge is not that — implementation has not started, hence todo): final error-code renumbering (-32020/-32021/-32022), FR-001..006 / FR-014..016 recast as adopt-and-verify, FR-028 legacy-only transport pin as the safe merge state, plus Risks & Watch Items. CROSS-SPEC CONFLICT still open and now the mandatory first task: FR-012 forbids per-connection */list variation; SHIPPED Spec 057 selects toolset by URL path /mcp/p/<slug> — Option A/B decided at plan time (acceptance = the 2 tests failing under beta.1). 028 agent-token scoping is already compatible (header-carried). Tracker: #532."
728
+
note: "STABLE GATE CLEARED 2026-09-02: mark3labs/mcp-go v1.0.0 (stable) released; go.mod still pins v0.57.0. Raised P3->P1 on the 2026-09-02 issue-prioritization pass — spec 058 has spec.md only, next step is speckit.plan then tasks (tracker #532). Earlier: UNBLOCKED 2026-08-12: the mcp-go gate cleared — v1.0.0-beta.1 (mark3labs/mcp-go#951) ships full 2026-07-28 support with per-request era detection (the pin was v0.55.x, topping out at 2025-11-25). Spec 058 revision MERGED as PR #1033 on 2026-08-27 (kept in this note, not in pr:, because pr: is implementation evidence and a docs(specs) merge is not that — implementation has not started, hence todo): final error-code renumbering (-32020/-32021/-32022), FR-001..006 / FR-014..016 recast as adopt-and-verify, FR-028 legacy-only transport pin as the safe merge state, plus Risks & Watch Items. CROSS-SPEC CONFLICT still open and now the mandatory first task: FR-012 forbids per-connection */list variation; SHIPPED Spec 057 selects toolset by URL path /mcp/p/<slug> — Option A/B decided at plan time (acceptance = the 2 tests failing under beta.1). 028 agent-token scoping is already compatible (header-carried). Tracker: #532."
0 commit comments