diff --git a/ROADMAP.md b/ROADMAP.md
index f65258bd7..762f41573 100644
--- a/ROADMAP.md
+++ b/ROADMAP.md
@@ -74,13 +74,13 @@ graph LR
- π΅ **Release qualification gate (auto-QA matrix blocks the tag)** β In progress Β· P0
- π΅ **Planning/docs truth automation** β In progress Β· P2
- π΅ **Discovery-quality eval harness (Spec 065 second half)** β In progress Β· P3
+- βͺ **MCP protocol upgrade to 2026-07-28 revision** β Todo Β· P1
- βͺ **Windows native tray app** β Todo Β· P2
- β« **Server marketplace** β Todo Β· P3 Β· parked
- β« **Audit SIEM integration** β Todo Β· P3 Β· parked
- β« **Paid-tier MVP (billing / seats / license)** β Todo Β· P3 Β· parked
- β« **SDK v1 migration** β Todo Β· P3 Β· parked
- β« **SSO (server edition)** β Todo Β· P3 Β· parked
-- βͺ **MCP protocol upgrade to 2026-07-28 revision** β Todo Β· P3
- βͺ **Security gateway Tracks C/D (per-arg least-privilege + signature provenance)** β Todo Β· P3
- π’ **Upgrade awareness & guided update** β Done Β· P0
- π’ **Connect step trust: preview, visible backup, one-click undo** β Done Β· P0
@@ -178,13 +178,16 @@ graph LR
action_log_tray_menu["Activity in the tray menu (recent tool callsβ¦"]
tray_menu_open_telemetry["tray_menu_opened counter: Swift menuWillOpenβ¦"]
action_log_retention_tie_in["Tie activity retention/size into the glance vβ¦"]
+ activity_storage_bounds["Bound every activity-adjacent store: responseβ¦"]
action_log_glance_view --> action_log_tray_menu
action_log_glance_view --> action_log_retention_tie_in
classDef done fill:#1f7a1f,stroke:#0d3d0d,color:#ffffff;
+ classDef in_progress fill:#1f6feb,stroke:#0b3d91,color:#ffffff;
classDef todo fill:#6e7781,stroke:#3d4248,color:#ffffff;
class sessions_web_ui done;
+ class activity_storage_bounds in_progress;
class action_log_glance_view,action_log_tray_menu,tray_menu_open_telemetry,action_log_retention_tie_in todo;
```
@@ -195,6 +198,7 @@ graph LR
| Activity in the tray menu (recent tool calls + security events, jump to full log) | βͺ Todo | β |
| tray_menu_opened counter: Swift menuWillOpen (MCPProxyApp.swift:192) -> lightweight POST /api/v1/telemetry/tray-menu-opened -> registry counter -> heartbeat tray_menu_opened_24h | βͺ Todo | β |
| Tie activity retention/size into the glance view | βͺ Todo | β |
+| Bound every activity-adjacent store: response truncation on the write path (#1173/#1174), per-server tool_calls buckets (#1176), omitempty zero-erasure (#1175) | π΅ In progress | #1174 |
@@ -203,7 +207,7 @@ graph LR
> Measure the real token cost of every routing/savings mode combination β 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) β 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.
-Spec: [103-token-bench](./specs/103-token-bench/) Β· PR: #1141
+Spec: [103-token-bench](./specs/103-token-bench/)
```mermaid
graph LR
@@ -215,15 +219,15 @@ graph LR
token_bench_harness --> token_bench_public
token_bench_public --> token_bench_blog
- classDef in_progress fill:#1f6feb,stroke:#0b3d91,color:#ffffff;
+ classDef done fill:#1f7a1f,stroke:#0d3d0d,color:#ffffff;
classDef todo fill:#6e7781,stroke:#3d4248,color:#ffffff;
- class token_bench_harness in_progress;
+ class token_bench_harness done;
class token_bench_public,token_bench_blog,token_bench_telemetry todo;
```
| Task | Status | Refs |
| --- | --- | --- |
-| Replay harness: activity-log sessions re-run under each mode combo; tokens per completed task + first-call success + retries | π΅ In progress | #1141 |
+| Replay harness: activity-log sessions re-run under each mode combo; tokens per completed task + first-call success + retries | π’ Done | #1141 #1147 #1151 #1153 #1160 |
| Run public suites locally (Ο-bench / BFCL / MCP-specific β final list verified by a research pass) and record reproducible results | βͺ Todo | β |
| Publish results + methodology on mcpproxy.app/blog | βͺ Todo | β |
| Heartbeat v10: per-tool_response_mode token counters for real-world cohort validation | βͺ Todo | β |
@@ -381,6 +385,15 @@ graph LR
+
+βͺ MCP protocol upgrade to 2026-07-28 revision β Todo Β· P1
+
+> 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 β 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 β 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 β 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/ β 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.
+
+Spec: [058-mcp-2026-upgrade](./specs/058-mcp-2026-upgrade/)
+
+
+
βͺ Windows native tray app β Todo Β· P2 Β· MCP-43
@@ -464,15 +477,6 @@ graph LR
-
-βͺ MCP protocol upgrade to 2026-07-28 revision β Todo Β· P3
-
-> UNBLOCKED 2026-08-12: the mcp-go gate cleared β 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 β 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/ β 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.
-
-Spec: [058-mcp-2026-upgrade](./specs/058-mcp-2026-upgrade/)
-
-
-
βͺ Security gateway Tracks C/D (per-arg least-privilege + signature provenance) β Todo Β· P3
@@ -772,16 +776,16 @@ graph LR
| Web UI + macOS app UX audit | In progress | P0 | β | | |
| Release qualification gate (auto-QA matrix blocks the tag) | In progress | P0 | β | [081-release-qa-gate](./specs/081-release-qa-gate/) | |
| Action log / transparency β info at a glance | In progress | P1 | β | | |
-| Token-efficiency benchmark: measured savings, published results | In progress | P1 | 62/64 (97%) | [103-token-bench](./specs/103-token-bench/) | #1141 |
+| Token-efficiency benchmark: measured savings, published results | In progress | P1 | 62/64 (97%) | [103-token-bench](./specs/103-token-bench/) | |
| Telemetry identity & data quality (machine_id + CI-filter hardening) | In progress | P1 | β | | |
| Telemetry v7: honest funnel + churn instrumentation | In progress | P1 | β | [080-telemetry-v7-churn](./specs/080-telemetry-v7-churn/) | |
| Planning/docs truth automation | In progress | P2 | β | | |
| Discovery-quality eval harness (Spec 065 second half) | In progress | P3 | β | [065-evaluation-foundation](./specs/065-evaluation-foundation/) | |
| tpa-db: versioned TPA signature database for the offline scanner | Todo | P1 | β | [101-tpa-db](./specs/101-tpa-db/) | |
+| MCP protocol upgrade to 2026-07-28 revision | Todo | P1 | β | [058-mcp-2026-upgrade](./specs/058-mcp-2026-upgrade/) | |
| Windows native tray app `MCP-43` | Todo | P2 | β | | |
| Remote access tunnel (feature-flagged MVP, spec 089) | Todo | P2 | β | [089-remote-access-tunnel](./specs/089-remote-access-tunnel/) | |
| Tool co-occurrence graph (experimental, feature-flagged) | Todo | P2 | β | | |
-| MCP protocol upgrade to 2026-07-28 revision | Todo | P3 | β | [058-mcp-2026-upgrade](./specs/058-mcp-2026-upgrade/) | |
| Security gateway Tracks C/D (per-arg least-privilege + signature provenance) | Todo | P3 | β | [054-mcp-security-gateway](./specs/054-mcp-security-gateway/) | |
| Server marketplace `MCP-37` | Todo (parked) | P3 | β | | |
| Audit SIEM integration `MCP-39` | Todo (parked) | P3 | β | | |
diff --git a/roadmap.yaml b/roadmap.yaml
index cd755268a..9f53b98c3 100644
--- a/roadmap.yaml
+++ b/roadmap.yaml
@@ -253,6 +253,13 @@ epics:
status: todo
note: "No spec: link on purpose β 073-activity-size-retention is the SHIPPED retention backend (13/14); this task is the glance-view tie-in on top of it."
depends_on: [action-log-glance-view]
+ - id: activity-storage-bounds
+ title: "Bound every activity-adjacent store: response truncation on the write path (#1173/#1174), per-server tool_calls buckets (#1176), omitempty zero-erasure (#1175)"
+ status: in_progress
+ priority: P1
+ pr: "#1174"
+ note: "User report 2026-09-02 (#1173): config.db reached 940MB; activity_max_response_size existed but was never read, and server__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."
+ depends_on: []
- id: analytics-dashboard
title: Analytics dashboard as default page
@@ -392,14 +399,14 @@ epics:
status: in_progress
priority: P1
spec: specs/103-token-bench
- pr: "#1141"
depends_on: [schema-deferred]
note: "Measure the real token cost of every routing/savings mode combination β 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) β 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."
tasks:
- id: token-bench-harness
title: "Replay harness: activity-log sessions re-run under each mode combo; tokens per completed task + first-call success + retries"
- status: in_progress
- pr: "#1141"
+ status: done
+ pr: ["#1141", "#1147", "#1151", "#1153", "#1160"]
+ 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."
depends_on: []
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 β 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."
- id: token-bench-public
@@ -715,10 +722,10 @@ epics:
- id: mcp-2026-upgrade
title: MCP protocol upgrade to 2026-07-28 revision
status: todo
- priority: P3
+ priority: P1
spec: specs/058-mcp-2026-upgrade
depends_on: []
- note: "UNBLOCKED 2026-08-12: the mcp-go gate cleared β 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 β 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/ β 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."
+ 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 β 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 β 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 β 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/ β 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."
- id: security-gateway-cd
title: Security gateway Tracks C/D (per-arg least-privilege + signature provenance)
status: todo