From e0836d6e1a4270941b8ee56c179428b48cca6299 Mon Sep 17 00:00:00 2001
From: Jeffrey Phillips Freeman <the@jeffreyfreeman.me>
Date: Fri, 27 Feb 2026 22:17:16 -0500
Subject: [PATCH] Docs: Updated timeline

---
 docs/timeline.md | 429 ++++++++++++++++++++++++++++-------------------
 1 file changed, 259 insertions(+), 170 deletions(-)

diff --git a/docs/timeline.md b/docs/timeline.md
index 434a57dcd3..fd84ceb9fe 100644
--- a/docs/timeline.md
+++ b/docs/timeline.md
@@ -10,14 +10,14 @@ The following chart shows all 29 epics across 9 legendary workstreams, 7 milesto
 @startgantt
 
 title CleverAgents Core — Epic-Level Project Schedule
-footer Generated 2026-02-26 | 29 Epics | 9 Legendaries | 7 Milestones | 6 Developers | ~1350 SP
+footer Generated 2026-02-28 | 29 Epics | 9 Legendaries | 7 Milestones | 6 Developers | ~1500 SP
 
 Project starts 2026-02-03
 saturday are closed
 sunday are closed
 printscale weekly zoom 2
 
-today is 2026-02-26
+today is 2026-02-28
 today is colored in #FF6666
 
 <style>
@@ -150,8 +150,8 @@ ganttDiagram {
 
 [Additional CLI Commands (#364)] as [CLI] on {Jeff} {Brent} requires 2 days
 [CLI] starts 2026-02-23
-[CLI] is 0% completed
-[CLI] is colored in #E8E8E8/Silver
+[CLI] is 100% completed
+[CLI] is colored in PaleGreen/SeaGreen
 
 [Concurrency + Cleanup (#365)] as [CONCUR] on {Luis} requires 2 days
 [CONCUR] starts 2026-02-23
@@ -183,7 +183,7 @@ ganttDiagram {
 '  Scope: Actor YAML, skill resolver, tool runtime, MCP adapter, tool sources
 '  Owner: Jeff (lead), Aditya (schema/docs), Luis (persistence), Brent (QA)
 '  Story Points: 158
-'  RISK: C0 at 93% (2 issues remain), M1 at 34% (blocked on Hamza/Luis)
+'  COMPLETED: C0 100%, M1 100%, M2 100% — all actor/skill/tool work done
 ' ================================================================
 -- Actors, Skills & Tools — Workstream C (Legendary #374) | v3.1.0 - v3.3.0 --
 
@@ -194,13 +194,13 @@ ganttDiagram {
 
 [Actor Runtime + Tool Exec (#355)] as [M1] on {Jeff} {Hamza} {Luis} {Brent} requires 3 days
 [M1] starts at [PROJ]'s end
-[M1] is 60% completed
-[M1] is colored in LightSkyBlue/SteelBlue
+[M1] is 100% completed
+[M1] is colored in PaleGreen/SeaGreen
 
 [Actor Graphs + Tool Sources (#356)] as [M2] on {Aditya} {Jeff} {Luis} {Brent} {Hamza} requires 5 days
 [M2] starts at [M1]'s end
-[M2] is 15% completed
-[M2] is colored in LightSkyBlue/SteelBlue
+[M2] is 100% completed
+[M2] is colored in PaleGreen/SeaGreen
 
 ' ── v3.2.0 MILESTONE ─────────────────────────────────────────
 '  Gate: Sessions + Actor runtime + Tool execution operational
@@ -219,7 +219,7 @@ ganttDiagram {
 
 [Decisions + Validations M3 (#357)] as [M3] on {Luis} {Hamza} {Brent} {Jeff} requires 4 days
 [M3] starts at [M2]'s end
-[M3] is 50% completed
+[M3] is 87% completed
 [M3] is colored in LightSkyBlue/SteelBlue
 
 ' ── v3.3.0 MILESTONE ─────────────────────────────────────────
@@ -234,24 +234,24 @@ ganttDiagram {
 '  Scope: Corrections, subplans, checkpoints, security fixes, provider fixes
 '  Owner: Luis (security/corrections), Jeff (phase reversion), Hamza (sandbox)
 '  Story Points: 58
-'  RISK: SEC at 20% — security-critical work, needs attention
+'  RISK: SEC at 80% — safety profiles remaining
 ' ================================================================
 -- Hardening, Testing & Security (Legendary #376) | v3.3.0 - v3.5.0 --
 
 [Corrections + Checkpoints M4 (#358)] as [M4] on {Luis} {Jeff} {Brent} {Hamza} requires 3 days
 [M4] starts at [M3]'s end
-[M4] is 40% completed
+[M4] is 95% completed
 [M4] is colored in LightSkyBlue/SteelBlue
 
 [Security + Safety Hardening (#362)] as [SEC] on {Luis} requires 3 days
 [SEC] starts 2026-03-02
-[SEC] is 60% completed
+[SEC] is 80% completed
 [SEC] is colored in LightSkyBlue/SteelBlue
 
 [Provider Fixes + Runtime (#363)] as [PROV] on {Luis} requires 2 days
 [PROV] starts 2026-02-12
-[PROV] is 0% completed
-[PROV] is colored in #E8E8E8/Silver
+[PROV] is 100% completed
+[PROV] is colored in PaleGreen/SeaGreen
 
 ' ── v3.4.0 MILESTONE ─────────────────────────────────────────
 '  Gate: Decisions + Validations + CLI polish + Concurrency
@@ -270,12 +270,12 @@ ganttDiagram {
 
 [ACMS v1 + Context Scaling M5 (#359)] as [M5] on {Hamza} {Jeff} {Aditya} {Brent} requires 4 days
 [M5] starts at [M4]'s end
-[M5] is 5% completed
+[M5] is 12% completed
 [M5] is colored in LightSkyBlue/SteelBlue
 
 [Autonomy Hardening + Stubs M6 (#360)] as [M6] on {Luis} {Jeff} {Hamza} {Brent} requires 5 days
 [M6] starts at [M5]'s end
-[M6] is 5% completed
+[M6] is 32% completed
 [M6] is colored in LightSkyBlue/SteelBlue
 
 [Subplans + Parallelism (#368)] as [SUBP] on {Luis} {Brent} requires 2 days
@@ -285,7 +285,7 @@ ganttDiagram {
 
 [Large Project Autonomy (#369)] as [LARGE] on {Luis} {Brent} {Jeff} requires 4 days
 [LARGE] starts 2026-03-17
-[LARGE] is 55% completed
+[LARGE] is 60% completed
 [LARGE] is colored in LightSkyBlue/SteelBlue
 
 ' ── v3.5.0 MILESTONE ─────────────────────────────────────────
@@ -370,12 +370,12 @@ legend right
   ----
   **Per-Milestone Allocation (done / total story points)**
   |= Dev |= v3.0.0 |= v3.1.0 |= v3.2.0 |= v3.3.0 |= v3.4.0 |= v3.5.0 |= v3.6.0 |
-  | Jeff | 172/172 | 105/142 | 37/37 | 31/34 | 5/45 | 13/42 | 0/8 |
-  | Luis | 8/32 | 29/66 | 0/34 | 16/61 | 13/21 | 0/68 | 0/56 |
-  | Aditya | 55/94 | 44/81 | - | - | 0/8 | - | - |
-  | Hamza | 11/19 | 0/5 | 0/23 | 0/5 | 0/45 | 0/21 | 0/53 |
-  | Brent | 65/70 | 10/20 | 0/10 | 21/26 | 5/10 | 24/29 | 0/5 |
-  | Rui | - | - | - | - | - | - | 0/8 |
+  | Jeff | 188/188 | 176/176 | 58/58 | 47/47 | 5/61 | 13/92 | 0/64 |
+  | Luis | 16/16 | 29/29 | 21/21 | 29/34 | - | 0/39 | 0/24 |
+  | Aditya | 128/128 | 86/86 | - | - | 0/8 | - | - |
+  | Hamza | 19/19 | 5/5 | 13/23 | 32/32 | 0/37 | - | 0/29 |
+  | Brent | 71/71 | 21/21 | 11/11 | 24/24 | 8/14 | 25/30 | 0/5 |
+  | Rui | - | - | - | - | - | - | - |
   ----
   **Milestone Scope**
   |= Milestone |= Target |= Epics |= SP |= Key Deliverables |
@@ -389,10 +389,10 @@ legend right
   ----
   **Risk Register**
   |= Epic |= Completion |= Risk |= Blocker |
-  | PRE_TEST (#24) | 0% | Medium | Test framework gap |
-  | M1 (#355) | 60% | Medium | MCP adapter + agent skills loader |
-  | SEC (#362) | 60% | Medium | Remaining security hardening |
-  | PROV (#363) | 0% | Low | Provider fixes deferred |
+  | M5 (#359) | 12% | High | ACMS pipeline + UKO + context strategies |
+  | M6 (#360) | 32% | Medium | Autonomy hardening + server stubs |
+  | M3 (#357) | 87% | Medium | Decision recording + plan explain (Hamza PRs) |
+  | SEC (#362) | 80% | Low-Med | Safety profiles remaining |
   | A9 (#352) | 0% | Low | Config deferred to v3.4 |
   ----
   **Color Key**
@@ -401,10 +401,10 @@ legend right
   | <back:LightSkyBlue>    </back> | In Progress |
   | <back:#E8E8E8>    </back> | Not Started |
   | <back:Gold>  <>  </back> | Milestone Target |
-  | <back:#FF6666>  |  </back> | Today (2026-02-26) |
+  | <back:#FF6666>  |  </back> | Today (2026-02-28) |
   ----
   29 Epics | 9 Legendaries | 7 Milestones | 6 Developers
-  ~1350 total story points | ~2700 estimated hours
+  ~1500 total story points | ~3000 estimated hours
 end legend
 
 @endgantt
@@ -428,7 +428,7 @@ saturday are closed
 sunday are closed
 printscale weekly zoom 2
 
-today is 2026-02-26
+today is 2026-02-28
 today is colored in #FF6666
 
 <style>
@@ -935,7 +935,7 @@ ganttDiagram {
 ' --- Actor & Skill Schema + CLI (C0) (#354) ---
 [Actor & Skill Schema + CLI (C0) (#354)] as [C0] on {Aditya} {Brent} {Jeff} {Luis} requires 7 days
 [C0] starts 2026-02-11
-[C0] is 93% completed
+[C0] is 100% completed
 [C0] is colored in DarkSeaGreen/ForestGreen
 
 [feat(tool): add tool runtime core (#275)] as [I275] on {Jeff} lasts 1 day
@@ -992,8 +992,8 @@ ganttDiagram {
 [I302] is colored in PaleGreen/SeaGreen
 [feat(cli): align actor commands to YAML (#288)] as [I288] on {Jeff} lasts 1 day
 [I288] starts 2026-03-02
-[I288] is 0% completed
-[I288] is colored in #E8E8E8/Silver
+[I288] is 100% completed
+[I288] is colored in PaleGreen/SeaGreen
 [test(tool): add robot tool model smoke tests (#278)] as [I278] on {Brent} lasts 1 day
 [I278] starts 2026-02-11
 [I278] is 100% completed
@@ -1020,8 +1020,8 @@ ganttDiagram {
 [I301] is colored in PaleGreen/SeaGreen
 [feat(change): add diff review artifacts (#303)] as [I303] on {Luis} lasts 1 day
 [I303] starts 2026-02-17
-[I303] is 0% completed
-[I303] is colored in #E8E8E8/Silver
+[I303] is 100% completed
+[I303] is colored in PaleGreen/SeaGreen
 [docs(skill): add skill YAML schema and examples (#281)] as [I281] on {Aditya} lasts 1 day
 [I281] starts 2026-02-11
 [I281] is 100% completed
@@ -1058,8 +1058,8 @@ ganttDiagram {
 ' --- Actor Runtime & Tool Execution (M1) (#355) ---
 [Actor Runtime & Tool Execution (M1) (#355)] as [M1] on {Brent} {Hamza} {Jeff} {Luis} requires 3 days
 [M1] starts at [PROJ]'s end
-[M1] is 40% completed
-[M1] is colored in CornflowerBlue/MediumBlue
+[M1] is 100% completed
+[M1] is colored in DarkSeaGreen/ForestGreen
 
 [feat(actor): add tool-calling runtime for execu... (#152)] as [I152] on {Jeff} lasts 1 day
 [I152] starts 2026-02-18
@@ -1071,75 +1071,75 @@ ganttDiagram {
 [I153] is colored in PaleGreen/SeaGreen
 [feat(resource): add handler runtime for git-che... (#154)] as [I154] on {Hamza} lasts 1 day
 [I154] starts 2026-02-18
-[I154] is 0% completed
-[I154] is colored in #E8E8E8/Silver
+[I154] is 100% completed
+[I154] is colored in PaleGreen/SeaGreen
 [feat(apply): merge sandbox changes into targets... (#155)] as [I155] on {Luis} lasts 1 day
 [I155] starts 2026-02-18
-[I155] is 0% completed
-[I155] is colored in #E8E8E8/Silver
+[I155] is 100% completed
+[I155] is colored in PaleGreen/SeaGreen
 [test(e2e): add M1 source-code plan lifecycle suite (#156)] as [I156] on {Brent} lasts 1 day
 [I156] starts 2026-02-18
-[I156] is 0% completed
-[I156] is colored in #E8E8E8/Silver
+[I156] is 100% completed
+[I156] is colored in PaleGreen/SeaGreen
 
 ' --- Actor Graphs + Tool Sources (M2) (#356) ---
 [Actor Graphs + Tool Sources (M2) (#356)] as [M2] on {Aditya} {Brent} {Hamza} {Jeff} {Luis} requires 5 days
 [M2] starts at [M1]'s end
-[M2] is 7% completed
-[M2] is colored in CornflowerBlue/MediumBlue
+[M2] is 100% completed
+[M2] is colored in DarkSeaGreen/ForestGreen
 
 [feat(actor): extend hierarchical actor YAML sch... (#157)] as [I157] on {Aditya} lasts 1 day
 [I157] starts 2026-02-23
-[I157] is 0% completed
-[I157] is colored in #E8E8E8/Silver
+[I157] is 100% completed
+[I157] is colored in PaleGreen/SeaGreen
 [feat(skill): add MCP adapter for external tools (#159)] as [I159] on {Aditya} lasts 1 day
 [I159] starts 2026-02-24
-[I159] is 0% completed
-[I159] is colored in #E8E8E8/Silver
+[I159] is 100% completed
+[I159] is colored in PaleGreen/SeaGreen
 [feat(skill): add agent skills loader (#160)] as [I160] on {Aditya} lasts 1 day
 [I160] starts 2026-02-25
-[I160] is 0% completed
-[I160] is colored in #E8E8E8/Silver
+[I160] is 100% completed
+[I160] is colored in PaleGreen/SeaGreen
 [feat(cli): add skill tools and refresh commands (#167)] as [I167] on {Aditya} lasts 1 day
 [I167] starts 2026-02-26
-[I167] is 0% completed
-[I167] is colored in #E8E8E8/Silver
+[I167] is 100% completed
+[I167] is colored in PaleGreen/SeaGreen
 [feat(skill): add MCP refresh hooks (#168)] as [I168] on {Aditya} lasts 1 day
 [I168] starts 2026-02-27
-[I168] is 0% completed
-[I168] is colored in #E8E8E8/Silver
+[I168] is 100% completed
+[I168] is colored in PaleGreen/SeaGreen
 [feat(lsp): add registry and runtime stubs (#164)] as [I164] on {Jeff} lasts 1 day
 [I164] starts 2026-02-23
 [I164] is 100% completed
 [I164] is colored in PaleGreen/SeaGreen
 [feat(actor): compile hierarchical actor configs... (#158)] as [I158] on {Jeff} lasts 1 day
 [I158] starts 2026-02-24
-[I158] is 0% completed
-[I158] is colored in #E8E8E8/Silver
+[I158] is 100% completed
+[I158] is colored in PaleGreen/SeaGreen
 [feat(skill): integrate agent skills discovery (#161)] as [I161] on {Jeff} lasts 1 day
 [I161] starts 2026-02-25
-[I161] is 0% completed
-[I161] is colored in #E8E8E8/Silver
+[I161] is 100% completed
+[I161] is colored in PaleGreen/SeaGreen
 [feat(skill): add registry flattening and capabi... (#165)] as [I165] on {Jeff} lasts 1 day
 [I165] starts 2026-02-26
-[I165] is 0% completed
-[I165] is colored in #E8E8E8/Silver
+[I165] is 100% completed
+[I165] is colored in PaleGreen/SeaGreen
 [feat(resource): add resource registry and DAG m... (#162)] as [I162] on {Hamza} lasts 1 day
 [I162] starts 2026-02-23
-[I162] is 0% completed
-[I162] is colored in #E8E8E8/Silver
+[I162] is 100% completed
+[I162] is colored in PaleGreen/SeaGreen
 [feat(changeset): persist changesets and diff ar... (#163)] as [I163] on {Luis} lasts 1 day
 [I163] starts 2026-02-23
-[I163] is 0% completed
-[I163] is colored in #E8E8E8/Silver
+[I163] is 100% completed
+[I163] is colored in PaleGreen/SeaGreen
 [feat(skill): persist flattened tool sets (#166)] as [I166] on {Luis} lasts 1 day
 [I166] starts 2026-02-24
-[I166] is 0% completed
-[I166] is colored in #E8E8E8/Silver
+[I166] is 100% completed
+[I166] is colored in PaleGreen/SeaGreen
 [test(e2e): add M2 actor + tool source smoke suite (#169)] as [I169] on {Brent} lasts 1 day
 [I169] starts 2026-02-23
-[I169] is 0% completed
-[I169] is colored in #E8E8E8/Silver
+[I169] is 100% completed
+[I169] is colored in PaleGreen/SeaGreen
 
 ' ================================================================
 '  LEGENDARY #375: Execution Pipeline & Decisions
@@ -1168,7 +1168,7 @@ ganttDiagram {
 ' --- Decisions + Validations + Invariants (M3) (#357) ---
 [Decisions + Validations + Invariants (M3) (#357)] as [M3] on {Brent} {Hamza} {Jeff} {Luis} requires 4 days
 [M3] starts at [M2]'s end
-[M3] is 9% completed
+[M3] is 87% completed
 [M3] is colored in CornflowerBlue/MediumBlue
 
 [feat(decision): add decision domain and context... (#170)] as [I170] on {Hamza} lasts 1 day
@@ -1177,8 +1177,8 @@ ganttDiagram {
 [I170] is colored in #E8E8E8/Silver
 [feat(decision): add decision persistence (#171)] as [I171] on {Hamza} lasts 1 day
 [I171] starts 2026-03-03
-[I171] is 0% completed
-[I171] is colored in #E8E8E8/Silver
+[I171] is 100% completed
+[I171] is colored in PaleGreen/SeaGreen
 [feat(service): add decision recording and snaps... (#172)] as [I172] on {Hamza} lasts 1 day
 [I172] starts 2026-03-04
 [I172] is 0% completed
@@ -1189,32 +1189,32 @@ ganttDiagram {
 [I174] is colored in #E8E8E8/Silver
 [feat(di): wire decision services (#173)] as [I173] on {Luis} lasts 1 day
 [I173] starts 2026-03-02
-[I173] is 0% completed
-[I173] is colored in #E8E8E8/Silver
+[I173] is 100% completed
+[I173] is colored in PaleGreen/SeaGreen
 [feat(validation): add validation pipeline and r... (#175)] as [I175] on {Luis} lasts 1 day
 [I175] starts 2026-03-03
-[I175] is 0% completed
-[I175] is colored in #E8E8E8/Silver
+[I175] is 100% completed
+[I175] is colored in PaleGreen/SeaGreen
 [feat(validation): add validation runner and app... (#176)] as [I176] on {Luis} lasts 1 day
 [I176] starts 2026-03-04
-[I176] is 0% completed
-[I176] is colored in #E8E8E8/Silver
+[I176] is 100% completed
+[I176] is colored in PaleGreen/SeaGreen
 [feat(dod): enforce definition-of-done gating (#178)] as [I178] on {Luis} lasts 1 day
 [I178] starts 2026-03-05
-[I178] is 0% completed
-[I178] is colored in #E8E8E8/Silver
+[I178] is 100% completed
+[I178] is colored in PaleGreen/SeaGreen
 [feat(invariant): add invariant models and enfor... (#177)] as [I177] on {Jeff} lasts 1 day
 [I177] starts 2026-03-02
 [I177] is 100% completed
 [I177] is colored in PaleGreen/SeaGreen
 [test(e2e): add M3 decision + validation suites (#179)] as [I179] on {Brent} lasts 1 day
 [I179] starts 2026-03-02
-[I179] is 0% completed
-[I179] is colored in #E8E8E8/Silver
+[I179] is 100% completed
+[I179] is colored in PaleGreen/SeaGreen
 [test(persistence): add decision persistence suites (#180)] as [I180] on {Brent} lasts 1 day
 [I180] starts 2026-03-03
-[I180] is 0% completed
-[I180] is colored in #E8E8E8/Silver
+[I180] is 100% completed
+[I180] is colored in PaleGreen/SeaGreen
 
 ' ================================================================
 '  LEGENDARY #376: Hardening, Testing & Security
@@ -1224,7 +1224,7 @@ ganttDiagram {
 ' --- Corrections + Subplans + Checkpoints (M4) (#358) ---
 [Corrections + Subplans + Checkpoints (M4) (#358)] as [M4] on {Brent} {Hamza} {Jeff} {Luis} requires 3 days
 [M4] starts at [M3]'s end
-[M4] is 28% completed
+[M4] is 95% completed
 [M4] is colored in CornflowerBlue/MediumBlue
 
 [feat(correction): add correction model and CLI ... (#181)] as [I181] on {Jeff} lasts 1 day
@@ -1241,25 +1241,25 @@ ganttDiagram {
 [I185] is colored in #E8E8E8/Silver
 [feat(sandbox): add checkpoint and rollback hooks (#183)] as [I183] on {Hamza} lasts 1 day
 [I183] starts 2026-03-06
-[I183] is 0% completed
-[I183] is colored in #E8E8E8/Silver
+[I183] is 100% completed
+[I183] is colored in PaleGreen/SeaGreen
 [feat(subplan): execute and merge subplans (#184)] as [I184] on {Luis} lasts 1 day
 [I184] starts 2026-03-06
 [I184] is 0% completed
 [I184] is colored in #E8E8E8/Silver
 [feat(plan): add error recovery patterns and CLI... (#186)] as [I186] on {Luis} lasts 1 day
 [I186] starts 2026-03-09
-[I186] is 0% completed
-[I186] is colored in #E8E8E8/Silver
+[I186] is 100% completed
+[I186] is colored in PaleGreen/SeaGreen
 [test(e2e): add M4 correction + subplan suites (#187)] as [I187] on {Brent} lasts 1 day
 [I187] starts 2026-03-06
-[I187] is 0% completed
-[I187] is colored in #E8E8E8/Silver
+[I187] is 100% completed
+[I187] is colored in PaleGreen/SeaGreen
 
 ' --- Security & Safety Hardening (#362) ---
 [Security & Safety Hardening (#362)] as [SEC] on {Luis} requires 3 days
 [SEC] starts 2026-03-02
-[SEC] is 20% completed
+[SEC] is 80% completed
 [SEC] is colored in CornflowerBlue/MediumBlue
 
 [fix(security): remove eval-based config parsing (#318)] as [I318] on {Luis} lasts 1 day
@@ -1268,20 +1268,20 @@ ganttDiagram {
 [I318] is colored in PaleGreen/SeaGreen
 [fix(security): harden template rendering (#319)] as [I319] on {Luis} lasts 1 day
 [I319] starts 2026-03-03
-[I319] is 0% completed
-[I319] is colored in #E8E8E8/Silver
+[I319] is 100% completed
+[I319] is colored in PaleGreen/SeaGreen
 [fix(security): enforce explicit exception handling (#320)] as [I320] on {Luis} lasts 1 day
 [I320] starts 2026-03-04
-[I320] is 0% completed
-[I320] is colored in #E8E8E8/Silver
+[I320] is 100% completed
+[I320] is colored in PaleGreen/SeaGreen
 [fix(security): close async resources and leaks (#321)] as [I321] on {Luis} lasts 1 day
 [I321] starts 2026-03-05
-[I321] is 0% completed
-[I321] is colored in #E8E8E8/Silver
+[I321] is 100% completed
+[I321] is colored in PaleGreen/SeaGreen
 [feat(security): enforce read-only actions (#322)] as [I322] on {Luis} lasts 1 day
 [I322] starts 2026-03-06
-[I322] is 0% completed
-[I322] is colored in #E8E8E8/Silver
+[I322] is 100% completed
+[I322] is colored in PaleGreen/SeaGreen
 
 ' --- Provider Fixes & Runtime Tweaks (#363) ---
 [Provider Fixes & Runtime Tweaks (#363)] as [PROV] on {Luis} requires 2 days
@@ -1948,15 +1948,15 @@ This section provides a high-level overview of the CleverAgents implementation r
 
 ### Current Status Summary
 
-As of Day 18 (2026-02-26), the project has **~168 closed issues out of ~225 assigned issues** across all milestones (~75% overall completion rate). A major productivity surge over Days 16-18 closed **65 issues in 3 days**, substantially advancing M1, M2, M3, and M4. The foundational layers — domain models, persistence, YAML schemas, CLI commands, quality automation, CI/CD, validation pipeline, and security hardening — are now mature.
+As of Day 20 (2026-02-28), the project has **~347 closed milestone issues out of ~394 assigned milestone issues** across all milestones (~88% overall completion rate). A continued productivity surge over Days 18-20 closed **~20 additional issues** since the last update, completing the M1 and M2 critical paths entirely and advancing M4 security hardening.
 
-**Days 17-18 highlights**: Apply pipeline + validation-gated apply + diff review merged (Luis, PR #417 — #155, #175, #176, #178, #303, #186). Changeset persistence (Jeff, #163). Plan resume + concurrency locks (Jeff, #327, #328). Provider cost controls (Jeff, #324). Decision persistence (Hamza, PR #131 — #171). Async resource cleanup (Hamza, #321). Actor YAML hierarchy (Aditya, PR #432 — #157). Security hardening — template rendering + exception handling (Hamza, #319, #320). Brent QA batches: M1/M2 E2E suites (#156, #169, #326, #402, #403) and M3/M4 E2E suites (#179, #180, #404, #405, #187). CI concurrency groups (#452).
+**Days 19-20 highlights**: FakeListLLM defaults removed (#459, Jeff) — M1 is now **fully closed**. MCP adapter merged (#434, Aditya). Agent skills loader merged (#453, Aditya). Skill CLI tools+refresh merged (#454, Aditya). MCP refresh hooks merged (#455, Aditya). Skill persistence with flattened tool sets merged (#460, Jeff). Decision service wiring merged (#461, Jeff). Security read-only actions (#436, Hamza). Async cleanup (#435, Hamza). Sandbox checkpoint/rollback hooks (#462, Jeff). M6 E2E suite merged (#457, Brent). Coverage improvements for 9 under-covered modules (#468). SafetyProfile spec composition docs (#471/#472).
 
-**M1 is essentially complete** — only #323 (remove FakeListLLM defaults) remains open. The M2 blockers are the **MCP adapter** (#159, Aditya), **agent skills loader** (#160, Aditya), and **skill persistence/CLI** (#166, #167, #168). The M3 target date is today; 3 issues remain (#172 decision recording, #173 invariant enforcement, #174 plan explain CLI).
+**M1 and M2 are now complete.** M3 has 2 remaining issues (#172 decision recording, #174 plan explain CLI). M4 has 1 remaining issue (#184 subplan execute, In Review with open PR #444). **The critical focus now shifts to M5 (ACMS/context)** which has 15 open issues and only 6 days to target.
 
-!!! warning "Schedule Risk: 5-7 Days Behind (Narrowing)"
+!!! warning "Schedule Risk: 4-6 Days Behind (Stable)"
 
-    The project is running **5-7 days behind** the original aggressive schedule, improved from 7-9 days at Day 16. The 65-issue closure burst over Days 16-18 substantially narrowed the gap. M1 (target Feb 15) is overdue by 11 days but essentially complete. M2 (target Feb 22) has 6 remaining issues. M3 (target Feb 26) has 3 remaining issues. The workload rebalancing executed on Day 16 is paying off — Jeff's throughput has been exceptional, and the validation/security batch from Luis/Hamza landed cleanly.
+    The project is running **4-6 days behind** the original aggressive schedule, improved from 5-7 days at Day 18. M1 and M2 are now fully complete. M3 and M4 are nearly complete (2 and 1 remaining issues respectively). The bottleneck has shifted to **M5 (ACMS v1 + context scaling)** which has 15 open issues (all unassigned) with a 6-day runway to its Mar 6 target. M6 (autonomy hardening) has 13 open issues with 10 days to target. Rui returned from leave on Feb 27 and is now available for testing assignments.
 
 ### Parallel Workstreams
 
@@ -1964,14 +1964,14 @@ Development is organized into six concurrent workstreams plus continuous quality
 
 | Track | Focus Area | Status |
 | :---- | :--------- | :----- |
-| **A** — Plan Lifecycle | Action/plan domain models, persistence, CLI alignment, execute/apply wiring | **Substantially complete.** Apply pipeline with validation gating merged (#155). Changeset persistence merged (#163). Concurrency locks + plan resume merged (#327, #328). Config service (#352) deferred to M5. |
+| **A** — Plan Lifecycle | Action/plan domain models, persistence, CLI alignment, execute/apply wiring | **Complete.** Apply pipeline with validation gating merged (#155). Changeset persistence merged (#163). Concurrency locks + plan resume merged (#327, #328). Config service (#352) deferred to M5. Decision service wiring merged (#461). |
 | **B** — Projects & Resources | Resource registry, project model, resource types, sandbox strategies, CLI | **Complete.** Registry, models, CLI, handler runtime (git-checkout + fs-directory), DAG metadata all done. |
-| **C** — Actors, Tools, Skills | Actor YAML schema/loader/compiler, tool registry/runtime, skill framework, MCP adapter, validation runner | Actor compiler, agent skills discovery, actor CLI, skill registry flattening, validation pipeline all DONE. Actor YAML hierarchy merged (#157). **MCP adapter** (#159, Aditya) and **agent skills loader** (#160, Aditya) remain. Skill persistence (#166) and skill CLI (#167, #168) remain. |
-| **D** — Decisions & Apply | Decision tree model, change tracking, diff review, apply pipeline, correction engine | **Major progress.** Decision persistence merged (#171). Validation-gated apply merged (#176). DoD gating merged (#178). Diff review artifacts merged (#303). Error recovery patterns merged (#186). Remaining: decision recording (#172), invariant enforcement (#173), plan explain CLI (#174). |
-| **E** — Subplans | Subplan domain model, orchestration, parallel execution, three-way merge | Domain model done; orchestrator and merge logic remaining. E2E M4 correction + subplan suites merged (#405). |
-| **F** — ACMS & Context | UKO ontology, CRP protocol, context strategies, assembly pipeline, hot/warm/cold tiers | Not yet started; scheduled for M5-M6 milestones |
-| **Q** — Quality & CI | Pre-commit hooks, Forgejo CI/CD, coverage enforcement (97%), security scanning | Complete. CI concurrency groups and job timeouts added (#452). Security hardening: template rendering (#319) and exception handling (#320) merged. Async resource cleanup merged (#321). |
-| **T** — Testing | Behave unit tests, Robot integration tests, ASV benchmarks, end-to-end smoke suites | **Strong progress.** M1 E2E suite (#156), M2 E2E suite (#169, #403), M3 E2E suite (#179, #180, #404), M4 E2E suite (#405) all merged via Brent QA batches. M5 (#406) and M6 (#407) E2E suites remain. Rui returns Feb 27. |
+| **C** — Actors, Tools, Skills | Actor YAML schema/loader/compiler, tool registry/runtime, skill framework, MCP adapter, validation runner | **Complete.** Actor compiler, agent skills discovery, actor CLI, skill registry flattening, validation pipeline all done. MCP adapter merged (#434). Agent skills loader merged (#453). Skill CLI merged (#454). MCP refresh hooks merged (#455). Skill persistence merged (#460). |
+| **D** — Decisions & Apply | Decision tree model, change tracking, diff review, apply pipeline, correction engine | **Nearly complete.** Decision persistence merged (#171). Validation-gated apply merged (#176). Decision service wiring merged (#461). Remaining: decision recording (#172), plan explain CLI (#174). Invariant enforcement (#173) closed. |
+| **E** — Subplans | Subplan domain model, orchestration, parallel execution, three-way merge | **Nearly complete.** Domain model done. Subplan execute+merge (#184) In Review with PR #444. |
+| **F** — ACMS & Context | UKO ontology, CRP protocol, context strategies, assembly pipeline, hot/warm/cold tiers | **In progress.** ACMS v1 context pipeline (#188) and UKO scaffolding (#189) are In Progress. 12 additional M5 issues remain unassigned. This is the new critical path. |
+| **Q** — Quality & CI | Pre-commit hooks, Forgejo CI/CD, coverage enforcement (97%), security scanning | **Complete.** Security read-only actions (#436) and async cleanup (#435) merged. Coverage improvements for 9 modules (#468) merged. Sandbox checkpoint hooks (#462) merged. |
+| **T** — Testing | Behave unit tests, Robot integration tests, ASV benchmarks, end-to-end smoke suites | **Strong progress.** M1-M4 E2E suites all merged. M6 E2E suite merged (#457). M5 E2E suite (#406) In Review. Rui returned Feb 27 and is available. |
 
 ### What Has Been Completed
 
@@ -2000,21 +2000,29 @@ The following major areas are fully or substantially implemented:
 - **Actor YAML hierarchy**: Extended hierarchical actor YAML schema with namespace inheritance, multi-level includes, and loader improvements (#157 merged 2026-02-26, Aditya).
 - **E2E milestone suites**: M1 source-code plan lifecycle suite (#156), M2 actor + tool source suite (#169), M1/M2 success criteria verification (#402, #403), M3 decision + validation suites (#179, #180, #404), M4 correction + subplan suite (#405) — all merged via Brent QA batches (2026-02-25 and 2026-02-26).
 - **Quality automation**: Pre-commit hooks (12 hooks across 5 categories), Forgejo CI/CD pipeline with 10 nox-routed jobs, nightly quality monitoring, ADR compliance checking, 97% test coverage enforcement, comprehensive security scanning (Bandit + Semgrep + Vulture), per-scenario temp database isolation for parallel Behave execution (#418 merged 2026-02-24), and CI concurrency groups with job timeouts (#452 merged 2026-02-26).
+- **MCP adapter runtime**: Live MCP server connection for external tool discovery and invocation (#434 merged 2026-02-27, Aditya). Agent skills loader with filesystem scanning for SKILL.md folders (#453 merged 2026-02-27, Aditya). MCP refresh hooks for dynamic tool updates (#455 merged 2026-02-27, Aditya). Skill CLI tools and refresh commands (#454 merged 2026-02-27, Aditya). Skill persistence with flattened tool sets (#460 merged 2026-02-27, Jeff). **M2 critical path fully resolved.**
+- **Decision service wiring**: Decision services wired into DI container for runtime use (#461 merged 2026-02-27, Jeff).
+- **Sandbox checkpoint hooks**: Checkpoint and rollback hook infrastructure for plan execution safety (#462 merged 2026-02-28, Jeff).
+- **Security hardening (Days 19-20)**: Read-only action enforcement (#436 merged 2026-02-26, Hamza). Async resource cleanup and leak prevention improvements (#435 merged 2026-02-26, Hamza).
+- **Provider cleanup**: FakeListLLM defaults removed (#459 merged 2026-02-27, Jeff). **M1 fully closed.**
+- **Coverage improvements**: Behave BDD scenarios added for 9 under-covered modules (#468 merged 2026-02-27), improving overall test coverage.
+- **M6 E2E suite**: Firefox-scale autonomous porting verification suite merged (#457 merged 2026-02-27, Brent).
+- **SafetyProfile specification**: SafetyProfile recognized as composed sub-model of AutomationProfile in spec docs (#471/#472 merged 2026-02-28).
 
 ### What Remains To Be Done
 
-The majority of the specification's domain models, services, CLI commands, and infrastructure modules are now implemented. The following areas still require completion or have only partial implementations:
+The majority of the specification's domain models, services, CLI commands, and infrastructure modules are now implemented. M1 and M2 are fully complete. The following areas still require completion:
 
-- **MCP runtime adapter**: Live connection to MCP servers for external tool discovery and invocation at runtime. Aditya's previous PR #382 merged the foundation; the agent skills loader (#160) and MCP adapter runtime (#159) remain. **This is the remaining M2 critical-path blocker.**
-- **Decision recording service**: Wire decision recording into the strategize/execute phases so decisions are automatically captured during plan execution (#172, Hamza).
-- **Invariant enforcement**: Runtime enforcement of invariant constraints with scoped precedence and reconciliation (#173, Jeff).
-- **Plan explain CLI**: Plan tree and explain commands for decision tree visualization (#174, Hamza).
-- **Skill persistence and CLI**: Persist flattened tool sets (#166, Jeff), skill CLI commands (#167, Aditya), MCP refresh hooks (#168, Aditya).
-- **Estimation actor logic**: The `estimation_actor` field is plumbed through Plan, Action, CLI, and service layers, but no actual estimator implementation exists to compute cost/risk estimates before execution.
-- **ACMS v1 full pipeline**: Context policy with phase-scoped views and the context service exist. Still pending: Universal Knowledge Ontology (UKO) with RDF-based resource representation, Context Request Protocol (CRP), pluggable context strategies, the full ten-component Context Assembly Pipeline, and hot/warm/cold tiered storage with per-actor scoped views.
-- **Large-project context management**: Indexing 10,000+ file codebases with bounded memory context assembly, skeleton compression for parent-to-child context propagation, and performance validation at scale.
-- **E2E smoke test suites**: M5 (#406) and M6 (#407) E2E verification suites remain. M1-M4 suites are complete.
-- **FakeListLLM default removal**: Provider defaults cleanup (#323, Jeff).
+- **Decision recording service**: Wire decision recording into the strategize/execute phases so decisions are automatically captured during plan execution (#172, In Progress, branch exists).
+- **Plan explain CLI**: Plan tree and explain commands for decision tree visualization (#174, In Progress, branch exists).
+- **Subplan execute and merge**: Orchestrator for spawning and merging subplans (#184, In Review with PR #444).
+- **ACMS v1 full pipeline (M5 critical path)**: This is now the primary focus area. The specification mandates a 10-component Context Assembly Pipeline with Universal Knowledge Ontology (UKO), Context Request Protocol (CRP), pluggable context strategies (keyword, semantic, graph, temporal), strategy coordinator/fusion engine, scoped backend view filtering, skeleton compressor, and hot/warm/cold tiered storage with per-actor scoped views. 14 open issues in M5 (#188-#200, #258, #259) cover this work — all currently unassigned.
+- **Config service**: Multi-level configuration resolution with project-scoped overrides (#258, #259). Deferred from M2 to M5.
+- **Estimation actor logic**: The `estimation_actor` field is plumbed through Plan, Action, CLI, and service layers, but no actual estimator implementation exists to compute cost/risk estimates before execution (#209).
+- **Large-project context management**: Indexing 10,000+ file codebases with bounded memory context assembly, skeleton compression for parent-to-child context propagation, and performance validation at scale (#205, #208).
+- **Autonomy hardening (M6)**: Checkpointing and rollback integration (#206, In Review), semantic validation service (#207, In Review), autonomy guardrails and audit trail (#204, In Review), LSP server stub (#203), server client stubs (#201), async command execution (#312, #313), CLI polish (#210).
+- **Post-MVP deferred work (v3.6.0)**: Database resources (#342), cloud infrastructure resources (#343), safety profile enforcement (#345), permission system (#344, In Review), TUI/Web interface (#341), auth/team commands (#340), remote project support (#338), client stubs (#335-#337), virtual resource types (#329-#334).
+- **E2E smoke test suites**: M5 E2E suite (#406, In Review). M6 E2E suite (#457) now merged. Semantic validation test suites (#316) remain.
 
 The following areas are substantially implemented and are no longer blocking:
 
@@ -2043,79 +2051,68 @@ The following areas are substantially implemented and are no longer blocking:
 
 **Goal**: A minimally usable local-mode flow where a user can register an action from YAML, link a git repository resource to a project, and run a plan end-to-end (`plan use` -> `plan execute` -> `plan diff` -> `plan apply`) with a sandboxed workspace and tool-based change capture.
 
-**Current status**: **~99% complete** (1 open out of ~154 total M1 issues). Apply pipeline merged (#155). E2E M1 suite merged (#156, #402). Provider cost controls merged (#324).
+**Current status**: **100% complete** (0 open out of ~152 total M1 issues). Apply pipeline merged (#155). E2E M1 suite merged (#156, #402). Provider cost controls merged (#324). FakeListLLM default removal merged (#459).
 
-**Key remaining work**:
+**Key remaining work**: None — milestone complete.
 
-- FakeListLLM default removal (#323, Jeff)
-
-#### Milestone 2: Actor Compiler + Full LLM Integration (Target: Feb 22, ETA: ~Mar 1)
+#### Milestone 2: Actor Compiler + Full LLM Integration (Target: Feb 22, ETA: Done)
 
 **Goal**: Actor YAML files compile into live LangGraph graphs. Custom actors (strategy, execution, estimation) are fully operational. The tool router normalizes calls across providers, the validation runner enforces resource-attached validations, and the MCP adapter connects to external tool servers.
 
-**Current status**: **~95% complete** (5 open out of ~97 total M2 issues). Actor compiler (#158), actor YAML hierarchy (#157), changeset persistence (#163), concurrency locks (#327), plan resume (#328), validation pipeline (#175, #176), M2 E2E suite (#169, #403), CI concurrency (#451) all merged. MCP adapter and agent skills loader remain as critical-path items.
+**Current status**: **100% complete** (0 open out of ~99 total M2 issues). MCP adapter (#434), agent skills loader (#453), skill CLI (#454), MCP refresh hooks (#455), skill persistence (#460) all merged in Days 19-20.
 
-**Key remaining work**:
-
-- MCP adapter runtime (#159, Aditya)
-- Agent skills loader (#160, Aditya)
-- Skill persistence — persist flattened tool sets (#166, Jeff)
-- Skill CLI — tools and refresh commands (#167, Aditya)
-- MCP refresh hooks (#168, Aditya)
+**Key remaining work**: None — milestone complete.
 
 #### Milestone 3: Decisions + Validations + Invariants (Target: Feb 26, ETA: ~Mar 2)
 
 **Goal**: Decisions are recorded during Strategize and Execute phases and persisted to the database. Users can view the decision tree (`plan tree`), inspect individual decisions (`plan explain`), manage invariants (`invariant add/list/remove`), and correct decisions (`plan correct --mode revert|append`) with selective subtree recomputation.
 
-**Current status**: **~75% complete** (3 open out of ~12 total M3 issues). Decision persistence merged (#171). Validation pipeline and gating merged (#175, #176). DoD gating merged (#178). Diff review artifacts merged (#303). M3 E2E suites merged (#179, #180, #404).
+**Current status**: **~87% complete** (2 open out of ~16 total M3 issues). Decision persistence merged (#171). Decision service wiring merged (#461). Validation pipeline and gating merged (#175, #176). DoD gating merged (#178). Diff review artifacts merged (#303). M3 E2E suites merged (#179, #180, #404). Invariant enforcement merged (#173).
 
 **Key remaining work**:
 
-- Decision recording during strategize/execute phases (#172, Hamza)
-- Invariant enforcement and reconciliation (#173, Jeff)
-- Plan tree and explain CLI commands (#174, Hamza)
+- Decision recording during strategize/execute phases (#172, Hamza — In Progress, PR #433)
+- Plan tree and explain CLI commands (#174, Hamza — In Progress, PR #464)
 
-#### Milestone 4: Corrections + Subplans + Checkpoints (Target: Mar 2, ETA: ~Mar 6)
+#### Milestone 4: Corrections + Subplans + Checkpoints (Target: Mar 2, ETA: ~Mar 4)
 
 **Goal**: Plans can spawn child plans (subplans) during execution. Subplans execute in parallel with configurable concurrency limits. Results are merged back using three-way merge strategies. Correction engine supports revert and append modes. Checkpointing enables rollback to previous plan states.
 
-**Current status**: **~86% complete** (3 open out of ~22 total M4 issues). DoD gating (#178), error recovery (#186), security hardening (#319, #320, #321), M4 E2E suites (#405, #187) all merged and closed.
+**Current status**: **~95% complete** (1 open out of ~21 total M4 issues). DoD gating (#178), error recovery (#186), security hardening (#319, #320, #321), M4 E2E suites (#405, #187), sandbox checkpoint hooks (#462), invariant template hardening (#322) all merged and closed.
 
 **Key remaining work**:
 
-- Subplan orchestrator and scheduler (#183, Jeff)
-- Correction service runtime wiring (#184, Luis)
-- Invariant template hardening (#322, Hamza)
+- Subplan execution and merge (#184, Luis — In Review, PR #444)
 
 #### Milestone 5: ACMS v1 + Context Scaling (Target: Mar 6, ETA: ~Mar 10)
 
 **Goal**: The Advanced Context Management System v1 is operational. Projects with 10,000+ files can be indexed and queried. The context assembly pipeline produces scoped, budget-constrained context views for actors. Hot/warm/cold storage tiers manage context lifecycle.
 
-**Current status**: ~7% of M5 tasks complete (14 open out of ~15 total M5 issues). UKO/RDF groundwork started (Hamza). Config service foundations exist.
+**Current status**: **~12% complete** (15 open out of ~17 total M5 issues). UKO/RDF groundwork started (Hamza, PRs #465/#466 in review). Context assembly pipeline in progress.
 
 **Key remaining work**:
 
-- UKO ontology with RDF-based resource representation (#338, #342, #343, Jeff)
+- UKO ontology scaffolding (#189, Hamza — In Progress, PR #466)
+- ACMS v1 context pipeline (#188, Hamza — In Progress, PR #465)
 - CRP protocol for actor context requests (#199, Jeff)
 - Context strategies — keyword, semantic, graph, temporal (#208, #209, Jeff)
-- Ten-component context assembly pipeline (Hamza)
-- Hot/warm/cold tiered storage with skeleton compression (Hamza)
-- M5 E2E ACMS integration suite (#406, Brent)
+- Plan-subplan tool and decision emission (#198, Aditya, PR #463)
+- M5 E2E ACMS integration suite (#406, Brent — In Review, PR #456)
 
 #### Milestone 6: Autonomy Hardening + Server Stubs (Target: Mar 10, ETA: ~Mar 12)
 
 **Goal**: The system can autonomously execute a large-scale task (e.g., porting a substantial codebase) using hierarchical plan decomposition with 4+ levels of subplans, decision correction with selective subtree recomputation, parallel execution scaling to 10+ concurrent subplans, and validation-gated apply. Client-side server stubs are in place for future connectivity.
 
-**Current status**: ~7% of M6 tasks complete (14 open out of ~15 total M6 issues). Foundation work from M3-M5 will accelerate M6.
+**Current status**: **~32% complete** (13 open out of ~19 total M6 issues). M6 E2E suite merged (#457). Security enforcement (#436), async cleanup (#435) merged. Coverage improvements (#468) merged.
 
 **Key remaining work**:
 
 - Hierarchical decomposition — recursive subplan planning (#335, #336, Jeff)
 - Autonomous estimation — cost/risk/time (#337, Jeff)
-- Performance tuning for large-project context assembly (#340, Jeff)
-- Server connectivity client stubs (Jeff)
-- End-to-end porting run with validation gates (all)
-- M6 E2E autonomy integration suite (#407, Brent)
+- Autonomy guardrails and audit trail (#204, Luis — In Review, PR #443)
+- Checkpointing and rollback (#206, Luis — In Review, PR #445)
+- Semantic validation service (#207, Luis — In Review, PR #449)
+- M6 E2E autonomy acceptance suite (#211, Brent — In Review, PR #470)
 
 ### Beyond Day 38: Extended Roadmap
 
@@ -2141,9 +2138,9 @@ Final refinements to achieve the complete specification:
 
 ### Schedule Risk Summary
 
-The project is currently running approximately **5-7 days behind** the original aggressive schedule, narrowed from 7-9 days at Day 16. The primary causes of the original delay were: (1) the scope of v2-to-v3 architectural transition was larger than anticipated; (2) CI/CD pipeline stabilization consumed more effort than planned; and (3) the execute/apply pipeline was deferred in favor of breadth-first foundation work.
+The project is currently running approximately **3-5 days behind** the original aggressive schedule, narrowed from 5-7 days at Day 18 and 7-9 days at Day 16. The primary causes of the original delay were: (1) the scope of v2-to-v3 architectural transition was larger than anticipated; (2) CI/CD pipeline stabilization consumed more effort than planned; and (3) the execute/apply pipeline was deferred in favor of breadth-first foundation work.
 
-The gap has been **actively narrowing** since Day 16: (a) the workload redistribution moved 25 issues to Jeff and paid off with a 65-issue closure burst over Days 16-18; (b) the validation pipeline, apply pipeline, security hardening, and decision persistence all landed in a concentrated 2-day window; (c) M1 is essentially complete and M2/M3 are close behind with only 6 and 3 issues remaining respectively; (d) Brent's QA batch merges (M1-M4 E2E suites) eliminated the testing backlog through M4.
+The gap has been **actively narrowing** since Day 16 and accelerated through Days 19-20: (a) M1 and M2 are now **fully complete** — all issues closed including MCP adapter, agent skills, skill CLI, MCP hooks, and FakeListLLM fix; (b) M3 is down to 2 issues (both Hamza's, both with PRs in review); (c) M4 has only 1 issue remaining (Luis's subplan execution, PR in review); (d) the workload redistribution to Jeff continues to pay dividends; (e) Rui returned from leave on Feb 27 and is available for testing work; (f) Luis has 6 PRs open across M4-M6+ representing substantial in-flight work.
 
 !!! note "Server Mode"
 
@@ -2155,13 +2152,13 @@ The gap has been **actively narrowing** since Day 16: (a) the workload redistrib
 
 | Developer | Role | Primary Focus Areas | Notes |
 |-----------|------|---------------------|-------|
-| **Jeff** (freemo) | CTO/Lead Architect | Critical path items, M3-M6 feature work (validation, corrections, subplans, ACMS, server stubs) | Fastest developer — absorbed 25 issues from Luis/Hamza to unblock schedule |
-| **Luis** (CoreRasurae) | Senior Python Architect | Apply pipeline (#155), diff review (#303) — active branches only | Workload reduced from 41 to ~4 open issues; 22 reassigned out. Focus on completing active branches |
-| **Aditya** (aditya) | Domain Expert (Agents/LLMs) | MCP adapter (#159), agent skills (#160), actor YAML hierarchy (#157) | 3 PRs in flight; highest domain expertise for actor system |
-| **Hamza** (hamza.khyari) | Python/RDF Expert | Decision persistence (#171), decision recording (#172), invariant enforcement (#319-#322) | Picks up 4 invariant issues from Luis; decision track is critical path for M3 |
-| **Rui** (rui.vieira) | Fast Developer | Testing (Behave/Robot), simpler implementations | Returns 2026-02-27; will take M3+ integration test suites |
-| **Brent** (brent.edwards) | Quality Specialist | E2E milestone suites (#402-#407), CLI extension tests (PR #420), coverage enforcement | Detail-oriented — owns all milestone verification testing |
-| **Mike** (mngrif) / **Brian** (brian) | Sysadmins | Deployment, infrastructure setup, CI/CD, ASV runner (PR #388) | Minimal coding tasks |
+| **Jeff** (freemo) | CTO/Lead Architect | M5-M6 feature work (ACMS, context strategies, autonomy, decomposition) | Fastest developer — 23 open issues, 199 story points remaining across M5-M6+ |
+| **Luis** (CoreRasurae) | Senior Python Architect | Subplan execution (#184), checkpointing (#206), semantic validation (#207), autonomy guardrails (#204) | 6 PRs open across M4-M6+; 8 open issues, 68 story points remaining |
+| **Aditya** (aditya) | Domain Expert (Agents/LLMs) | Plan-subplan tool (#198, PR #463) | M2 track complete; 1 open issue in M5 |
+| **Hamza** (hamza.khyari) | Python/RDF Expert | Decision recording (#172), plan explain (#174), ACMS pipeline (#188), UKO ontology (#189) | 4 PRs in progress/review; 11 open issues, M3 critical path |
+| **Rui** (rui.vieira) | Fast Developer | Testing (Behave/Robot), M5+ integration test suites | Returned from leave 2026-02-27; available for test assignments |
+| **Brent** (brent.edwards) | Quality Specialist | M5 E2E suite (#406), M6 E2E suite (#211, PR #470), coverage enforcement | 4 open issues; detail-oriented — owns all milestone verification testing |
+| **Mike** (mngrif) / **Brian** (brian) | Sysadmins | Deployment, infrastructure setup, CI/CD | Minimal coding tasks; ASV runner fix merged (#388) |
 
 ## Weekly Development Schedules
 
@@ -2234,12 +2231,13 @@ The gap has been **actively narrowing** since Day 16: (a) the workload redistrib
 
 | Risk | Mitigation | Owner |
 |------|------------|-------|
-| Apply pipeline completion (#155) | Luis has active branch; Jeff available to pair if blocked beyond Feb 26 | Luis (Jeff backup) |
-| MCP adapter + agent skills merge | Aditya has 2 PRs in review (#382, #416); expedite review cycle | Aditya + Jeff (reviewer) |
-| Decision system critical path | Hamza's PR #131 blocks M3; invariant issues (#319-#322) now assigned to Hamza | Hamza + Jeff (reviewer) |
-| Jeff overload post-redistribution | 25 new issues absorbed; mitigate via parallel execution + prioritization of Must-Have items first | Jeff |
+| ~~Apply pipeline completion (#155)~~ | ~~RESOLVED — merged Day 18~~ | ~~Luis~~ |
+| ~~MCP adapter + agent skills merge~~ | ~~RESOLVED — all merged Days 19-20 (#434, #453, #454, #455, #460)~~ | ~~Aditya~~ |
+| M3 decision recording + plan explain | Hamza has both PRs (#433, #464) in review; Jeff available to assist | Hamza + Jeff (reviewer) |
+| M5 ACMS pipeline critical mass | 15 open issues; Hamza has ACMS/UKO PRs in progress; Jeff carries 7 M5 items | Jeff + Hamza |
+| Luis PR throughput (6 open PRs) | Luis has substantial in-flight work across M4-M6+; prioritize M4 #184 first | Luis + Jeff (reviewer) |
 | Large codebase performance | Profile ACMS indexing + hot/warm/cold tiers; enforce bounded memory tests | Jeff + Hamza |
-| Rui ramp-up after return | Pre-assign Behave/Robot test suites for M3+; pair with Brent first day back | Rui + Brent |
+| Rui ramp-up after return | Rui returned Feb 27; assign Behave/Robot test suites for M5+; pair with Brent | Rui + Brent |
 | Server connectivity stubs stability | Keep client-only stubs isolated; gate with feature flags and contract tests | Jeff |
 
 ## Schedule Adherence History
@@ -3071,3 +3069,94 @@ Note: Each cell is **completed/total story points** for that milestone/owner per
 | M6 | 13/92 | - | 0/39 | - | 24/30 | - | - | 37/161 |
 | M6+ | 0/64 | - | 0/24 | 0/29 | 0/5 | - | 8/8 | 8/130 |
 | **Total** | **432/686** | **177/222** | **95/163** | **45/145** | **159/176** | **0/0** | **108/108** | **1016/1500** |
+
+### 2026-02-28 (Day 20)
+
+**Summary**
+
+Status: Behind ~3-5d  
+Deadline risk: HIGH (narrowing)  
+Overall completion: 86.3% (~297/344 milestone issues closed, excluding Epics/Legendaries)
+
+**Notes**
+
+- **M1 fully complete**: FakeListLLM default removal (#459) merged — 0 open M1 issues
+- **M2 fully complete**: MCP adapter (#434), agent skills loader (#453), skill CLI (#454), MCP refresh hooks (#455), skill persistence (#460) all merged — 0 open M2 issues
+- Decision service wiring (#461) and sandbox checkpoint hooks (#462) merged
+- Security: read-only actions (#436), async resource cleanup (#435) merged
+- M6 E2E autonomy suite (#457) merged; coverage improvements (#468) merged
+- SafetyProfile spec documentation (#471, #472) merged
+- **Rui returned from leave** (Feb 27) — available for M5+ test assignments
+- **Hamza** has 4 active items: decision recording (#172, PR #433), plan explain (#174, PR #464), ACMS pipeline (#188, PR #465), UKO ontology (#189, PR #466) — all In Progress or In Review
+- **Luis** has 6 open PRs: subplan execution (#444), autonomy guardrails (#443), checkpointing (#445), semantic validation (#449), safety profiles (#450), permissions (#448)
+- M3 down to **2 issues** (both Hamza's with PRs open); M4 down to **1 issue** (Luis's, PR in review)
+- All open issues now have assignees (0 unassigned)
+
+
+#### Milestone forecast 
+
+| Milestone | Target -> ETA | Delta | Risk |
+|-----------|---------------|-------|------|
+| M1 (v3.0.0) | (2026-02-15) -> Done | +13d actual | COMPLETE |
+| M2 (v3.1.0) | (2026-02-22) -> Done | +6d actual | COMPLETE |
+| M3 (v3.2.0) | (2026-02-26) -> ETA 2026-03-02 | +4d | MEDIUM — 2 open issues; Hamza has PRs for both |
+| M4 (v3.3.0) | (2026-03-02) -> ETA 2026-03-04 | +2d | LOW-MED — 1 open issue; Luis PR #444 in review |
+| M5 (v3.4.0) | (2026-03-06) -> ETA 2026-03-10 | +4d | MED-HIGH — 15 open issues; ACMS pipeline + context scaling + UKO |
+| M6 (v3.5.0) | (2026-03-10) -> ETA 2026-03-12 | +2d | MEDIUM — 13 open issues; 6 Luis PRs in flight; autonomy hardening |
+
+#### Track forecast 
+
+| Track | Status | ETA | Risk | Blocking |
+|-------|--------|-----|------|----------|
+| Track A (Plan lifecycle) | **complete** | Done | LOW | none |
+| Track B (Resources + sandbox) | **complete** | Done | LOW | none |
+| Track C (Actors/tools/skills/MCP) | **complete** | Done | LOW | none |
+| Track D (Decisions/validations) | behind ~4d | ETA 2026-03-02 | MEDIUM | decision recording (#172) + plan explain (#174) — both Hamza with PRs |
+| Track E (Corrections/subplans) | behind ~2d | ETA 2026-03-04 | LOW-MED | subplan execution (#184) — Luis PR in review |
+| Track F (ACMS/context) | in progress | ETA 2026-03-10 | MED-HIGH | ACMS pipeline (#188) + UKO (#189) + context strategies |
+| Track Q (Quality automation) | **complete** | Done | LOW | maintenance only |
+| Track T (Testing) | strong progress | ETA ongoing | LOW-MED | M5/M6 E2E remain; Rui now available |
+
+#### Developer forecast 
+
+| Name | Days Ahead/Behind | Availability | Risk | Focus |
+|------|-------------------|--------------|------|-------|
+| Jeff | +3d ahead (M1/M2 complete, 69/92 closed = 75%; throughput remains exceptional) | available | MEDIUM | M5 ACMS items (#190, #192, #194, #197, #199, #258, #259), M6 decomposition (#201, #203, #205, #208, #209) |
+| Luis | -2d behind (11/19 closed = 58%; but 6 PRs in review represent massive in-flight work) | available | MEDIUM | M4 subplan merge (#184, PR #444), M6 checkpointing/validation/autonomy PRs |
+| Hamza | -1d behind (11/22 closed = 50%; 4 PRs in progress covering M3/M5) | available | MEDIUM | M3 decision recording (#172, PR #433), plan explain (#174, PR #464), M5 ACMS/UKO (#188, #189) |
+| Aditya | on track (25/26 closed = 96%; only 1 open issue) | available | LOW | M5 plan-subplan tool (#198, PR #463) |
+| Brent | +1d ahead (28/32 closed = 88%; M1-M4 E2E complete, M6 E2E merged) | available | LOW | M5 E2E suite (#406, PR #456), M6+ items |
+| Rui | N/A (just returned Feb 27) | available | LOW-MED | Behave/Robot test suites for M5+; ramping up |
+| Mike/Brian | N/A | standby | LOW | none |
+
+#### Task inventory 
+
+Milestone per developer as of the current date.
+Note: Each cell is **completed/total issues** for that milestone/owner per Forgejo tracker. Epics and Legendaries excluded.
+
+| Milestone | Jeff | Aditya | Luis | Hamza | Brent | Rui | Unassigned | Total |
+|-----------|------|--------|------|-------|-------|-----|------------|-------|
+| M1 | 27/27 | 12/12 | 2/2 | 4/4 | 10/10 | 0/0 | 97/97 | 152/152 |
+| M2 | 24/24 | 13/13 | 4/4 | 1/1 | 5/5 | 0/0 | 52/52 | 99/99 |
+| M3 | 7/7 | 0/0 | 2/2 | 2/4 | 3/3 | 0/0 | 0/0 | 14/16 |
+| M4 | 8/8 | 0/0 | 3/4 | 4/4 | 5/5 | 0/0 | 1/1 | 21/22 |
+| M5 | 1/8 | 0/1 | 0/0 | 0/5 | 1/3 | 0/0 | 2/2 | 4/19 |
+| M6 | 2/10 | 0/0 | 0/4 | 0/0 | 4/5 | 0/0 | 0/0 | 6/19 |
+| M6+ | 0/8 | 0/0 | 0/3 | 0/4 | 0/1 | 0/0 | 1/1 | 1/17 |
+| **Total** | **69/92** | **25/26** | **11/19** | **11/22** | **28/32** | **0/0** | **153/153** | **297/344** |
+
+#### Story point allocation 
+
+Story points per developer per milestone.
+Note: Each cell is **completed/total story points** for that milestone/owner per Forgejo tracker. Issues without a `Points/X` label or milestone are excluded. Epics and Legendaries (organizational items) are excluded.
+
+| Milestone | Jeff | Aditya | Luis | Hamza | Brent | Rui | Unassigned | Total |
+|-----------|------|--------|------|-------|-------|-----|------------|-------|
+| M1 | 188/188 | 128/128 | 16/16 | 19/19 | 71/71 | - | 95/95 | 517/517 |
+| M2 | 176/176 | 86/86 | 29/29 | 5/5 | 21/21 | - | - | 317/317 |
+| M3 | 58/58 | - | 21/21 | 13/23 | 11/11 | - | - | 103/113 |
+| M4 | 47/47 | - | 29/34 | 32/32 | 24/24 | - | 1/1 | 133/138 |
+| M5 | 5/61 | 0/8 | - | 0/37 | 8/14 | - | 4/4 | 17/124 |
+| M6 | 13/92 | - | 0/39 | - | 25/30 | - | - | 38/161 |
+| M6+ | 0/64 | - | 0/24 | 0/29 | 0/5 | - | 8/8 | 8/130 |
+| **Total** | **487/686** | **214/222** | **95/163** | **69/145** | **160/176** | **0/0** | **108/108** | **1133/1500** |