This commit is contained in:
Oleg Maslov
360
docs/plans/BACKLOG-CONSOLIDATED-2026-04-17.md
Normal file
360
docs/plans/BACKLOG-CONSOLIDATED-2026-04-17.md
Normal file
@@ -0,0 +1,360 @@
|
||||
# Consolidated Backlog β MILESTONE 2026-04-17
|
||||
|
||||
**Purpose:** Single source of truth for everything remaining. Merges the 124-item master backlog (2026-04-16), the 21 PDF deferred items (2026-04-17), the installer cluster, and the agent-harness items.
|
||||
|
||||
**State:** main @ `ac586f7`, tree clean, 5193 unit tests pass (144 skipped), 89/89 E2E, tsc clean on all 5 projects. 13/13 LLM providers green.
|
||||
|
||||
---
|
||||
|
||||
## β
DONE β PromptAssembler v4 PoC (2026-04-17 session)
|
||||
|
||||
**Commits:** `7467e11` Β· `9d424cc` Β· `3a055f2` on top of `ac586f7`. Eval ran 60.2 min, 342 LLM calls, zero cleanup failures.
|
||||
|
||||
**Outcome: primary hypothesis FAILED** (gap closure β21.5% vs β₯40% target) with nuanced findings:
|
||||
- F > E on 5/6 scenarios (Opus 4.6 GAINS from PA β sign inverted)
|
||||
- Qwen3-30B-A3B +26.7pp on compare (reasoning-tuned small models benefit)
|
||||
- Gemma 4 31B specifically hurt by PA structure
|
||||
- Opus 4.7 beats Opus 4.6 by 22.46pp on Waggle reasoning (separate useful datapoint)
|
||||
|
||||
**Artifacts:** `docs/specs/PROMPT-ASSEMBLER-V4.md`, `EVAL-RESULTS.md`, `tmp_bench_results.json` (gitignored), `project_session_handoff_0417_prompt_assembler.md` memory.
|
||||
|
||||
**Feature flag default OFF confirmed correct.** Shipped as landed; not default on.
|
||||
|
||||
---
|
||||
|
||||
## π NEXT SESSION β EXPLORING MILESTONE (TBD β briefed at fresh-context start)
|
||||
|
||||
Marko has one more exploring milestone queued before we return to the P0/P1/P2 backlog continuation. The brief will be provided in a fresh context window. This section is a placeholder so the backlog stays the single source of truth.
|
||||
|
||||
**What to expect when fresh context starts:**
|
||||
1. Read this milestone file + the latest handoff
|
||||
2. Read Marko's brief for the exploring milestone
|
||||
3. Execute per that brief (code + eval/verification as applicable)
|
||||
4. Commit + handoff
|
||||
5. THEN return to the P0 critical path below
|
||||
|
||||
**Constraint:** The exploring milestone is additive. It does not replace or de-prioritize any of the P0/P1/P2/P3 items below. When complete, the main plan continues.
|
||||
|
||||
---
|
||||
|
||||
## π MAIN PLAN CONTINUATION (after exploring milestone)
|
||||
|
||||
Everything below is the unchanged consolidated backlog. Resume here once the exploring milestone is shipped.
|
||||
|
||||
---
|
||||
|
||||
## Legend
|
||||
|
||||
- β
DONE (shipped between 2026-04-16 master snapshot and now)
|
||||
- π’ PENDING (actively doable this week)
|
||||
- π DEFERRED (needs design or bigger chunk)
|
||||
- π΄ BLOCKED (waits on Stripe / cert / Marko / external)
|
||||
- β³ MARKO ACTION (not engineering)
|
||||
|
||||
---
|
||||
|
||||
## Snapshot: What shifted since 2026-04-16
|
||||
|
||||
Since the mega-polish session closed at `2442d8f`, these blocks moved forward:
|
||||
|
||||
| Block | Movement |
|
||||
|-------|----------|
|
||||
| Block 1b E2E gate | β
298/298 E2E green (0416 S2), 89/89 current |
|
||||
| CR-2 Light mode | π‘ Partial β 6 token swaps + boot screen still ugly (P40/P41) |
|
||||
| OW-7 Stripe webhooks audit | Still π΄ β waits on M7 |
|
||||
| Task 6 (vault-first, onboarding tiers) | β
Full (6A-6E); 6F β INST-1/2/3 |
|
||||
| PDF E2E triage | β
20 items; π 21 deferred |
|
||||
| Marketplace seed | β
10 E2E green, 148 pkgs |
|
||||
|
||||
The 3 P0s from the 2026-04-12 backlog (light mode / upgrade UX / trial timestamp) are mostly resolved:
|
||||
- Light mode: partial (boot screen + a few tokens still TODO β P40/P41)
|
||||
- Upgrade UX: shipped as trial expiry modal + tier cards
|
||||
- Trial timestamp: shipped in 0412 S2 (trial modal + budget cap)
|
||||
|
||||
---
|
||||
|
||||
## P0 β Launch Blockers (must-have)
|
||||
|
||||
These are on the critical path to ship. Most are test execution + external deps, not code.
|
||||
|
||||
### Block 1: Marko External Actions β³
|
||||
|
||||
| # | Action | Blocks | Time |
|
||||
|---|--------|--------|------|
|
||||
| M1 | Export ChatGPT conversations | Phase 1 harvest | 5 min |
|
||||
| M2 | Export Claude conversations (claude.ai) | Phase 1 harvest | 5 min |
|
||||
| M3 | Export Gemini (Google Takeout) | Phase 1 harvest | 10 min |
|
||||
| M4 | Export Perplexity threads | Phase 1 harvest | 5 min |
|
||||
| M5 | Top up API credits (Anthropic/OpenAI/Google) | Phase 4+5 judging | 15 min |
|
||||
| M6 | Confirm judge models (Opus 4.6, GPT-5.4, Gemini 2.5 Pro, Haiku 4.5) | Phase 5 | Decision |
|
||||
| M7 | Create Stripe products (Pro $19, Teams $49/seat) | Phase 7 launch | 1 hour |
|
||||
| M8 | Buy Windows EV code signing cert ($300-500/yr) | Phase 7 launch | 1-3 days |
|
||||
| M9 | Contact ML peer reviewer for papers | Phase 6 | 1 day |
|
||||
| M10 | Greenlight launch date | Everything | Decision |
|
||||
|
||||
### Block 2: Phase 1 β Harvest Marko's Real Data π’ (blocked on M1-M4)
|
||||
|
||||
| # | Task | Depends on | Status |
|
||||
|---|------|-----------|--------|
|
||||
| 1.1 | Import ChatGPT conversations β harvest | M1 | π’ |
|
||||
| 1.2 | Import Claude conversations β harvest | M2 | π’ |
|
||||
| 1.3 | Re-harvest Claude Code (fresh, all sessions) | β | π’ |
|
||||
| 1.4 | Import Gemini conversations β harvest | M3 | π’ |
|
||||
| 1.5 | Import Perplexity threads β harvest | M4 | π’ |
|
||||
| 1.6 | BUILD Cursor adapter (0.5-1 day) | β | π’ |
|
||||
| 1.7 | Post-harvest cognify on imported frames | 1.1-1.6 | π’ |
|
||||
| 1.8 | Identity auto-populate from harvest | 1.7 | π’ |
|
||||
| 1.9 | Wiki compile from real data | 1.7 | π’ |
|
||||
| **GATE** | 10K-50K frames, dedup verified, KG populated | β | |
|
||||
|
||||
Budget: ~$50.
|
||||
|
||||
### Block 5: Phase 4 β Memory Proof Test π’
|
||||
|
||||
From `docs/test-plans/MEMORY-HARVEST-TEST-PLAN.docx`. 10 days Β· ~$300-500.
|
||||
|
||||
### Block 6: Phase 5 β GEPA Full-System Proof π’
|
||||
|
||||
From `docs/test-plans/GEPA-EVOLUTION-TEST-PLAN.docx`. 18 days Β· ~$1,500-2,500. Critical path.
|
||||
|
||||
### Block 7: Phase 5b β Combined Effect Proof π’
|
||||
|
||||
From `docs/test-plans/COMBINED-EFFECT-TEST-PLAN.docx`. 6 days Β· ~$500.
|
||||
|
||||
### Block 8: Phase 6 β Write Papers π’
|
||||
|
||||
5 days writing + Marko peer review.
|
||||
|
||||
### Block 9: Phase 7 β Launch Prep
|
||||
|
||||
| # | Task | Status |
|
||||
|---|------|--------|
|
||||
| 9.1 | Stripe dashboard setup + smoke test | π΄ blocked M7 |
|
||||
| 9.2 | Code signing cert + updater keypair | π΄ blocked M8 |
|
||||
| 9.3 | hive-mind source extraction (Apache 2.0 cut) | π’ (scaffold DONE, extraction TODO) |
|
||||
| 9.4 | Binary build + smoke test on clean Windows VM | π’ |
|
||||
| 9.5 | Clerk auth integration | π΄ after 9.1 |
|
||||
| 9.6 | Onboarding flow finalized (harvest-first) | π’ (needs Block 4) |
|
||||
| 9.7 | Mac notarization | β³ Marko |
|
||||
| 9.8 | Landing page final polish | π’ |
|
||||
|
||||
### Block 10: Launch Day π΄ (gated)
|
||||
|
||||
Simultaneous: Waggle binary + hive-mind OSS + 2 arXiv papers + LinkedIn sequence + Pro/Teams live.
|
||||
|
||||
---
|
||||
|
||||
## P1 β Ship Quality (do before launch)
|
||||
|
||||
### Block 3c Quick Wins π’ (<1 hr each, ~5 hr total)
|
||||
|
||||
| # | Fix | Effort |
|
||||
|---|-----|--------|
|
||||
| QW-1 | Auto-open chat window after onboarding | 15 min |
|
||||
| QW-2 | Text labels to Memory app tabs (Timeline/Graph/Harvest/Weaver/Wiki/Evolution) | 30 min |
|
||||
| QW-3 | Skip boot screen on return visits | 15 min |
|
||||
| QW-4 | Back button in onboarding wizard steps 2-6 | 20 min |
|
||||
| QW-5 | Rename dock tiers (SimpleβEssential, ProβStandard, FullβEverything) + clarify vs billing | 15 min |
|
||||
|
||||
### Block 3d: CLAUDE.md Open Work
|
||||
|
||||
| # | Item | Status |
|
||||
|---|------|--------|
|
||||
| OW-6 | **PersonaSwitcher two-tier redesign** β UNIVERSAL MODES (8) + WORKSPACE SPECIALISTS (template-scoped); hover tooltip with tagline/bestFor/wontDo | π’ 0.5 day |
|
||||
| OW-7 | Stripe webhooks smoke test against real Stripe | π΄ blocked M7 |
|
||||
|
||||
### Block 3b: Compliance Report UX + Template System π’ (3.5 days)
|
||||
|
||||
| # | Task | Notes |
|
||||
|---|------|-------|
|
||||
| 3b.1 | PDF generation route: POST /api/compliance/export-pdf β pdfmake β buffer β download | `buildComplianceDocDefinition` exists, needs pdfmake render + route |
|
||||
| 3b.2 | Template system: report templates as JSON (sections, logo, branding, footer) | Currently hardcoded |
|
||||
| 3b.3 | Full-page ComplianceReport viewer + date range picker + section toggles + PDF download button | Currently 324-line card |
|
||||
| 3b.4 | Custom branding: company logo upload, org name, risk classification override | Template field |
|
||||
| 3b.5 | KVARK template: IAM audit section, data residency proof, department breakdown | Enterprise variant |
|
||||
|
||||
### Block 3e: Cross-Reference Items
|
||||
|
||||
| # | Item | Status |
|
||||
|---|------|--------|
|
||||
| CR-1 | **MS Graph OAuth connector** β harvest email, calendar, files | π’ 2-3 days |
|
||||
| CR-2 | **Light mode full audit** β only partial; boot screen + tokens | π‘ 0.5 day |
|
||||
| CR-3 | **KG Viewer top-5 demo gaps** β loading, error, export-PNG, touch | π’ 4-6 hr |
|
||||
| CR-4 | **Demo video script** β 90-s harvestβwikiβinsight + 5-min deep dive | π’ 1 day content |
|
||||
| CR-5 | **LinkedIn launch posts** (3-post sequence over 10 days) | π’ content |
|
||||
| CR-6 | **hive-mind actual source extraction** β scaffold done, code copy TODO | π’ 2-3 days |
|
||||
| CR-7 | **CLAUDE.md update** β Section 10 Open Work is stale | π’ 15 min |
|
||||
| CR-8 | **Tauri binary build verification** β haven't built since mega code changes | π’ 1 day |
|
||||
| CR-9 | **Mac notarization setup** | β³ Marko |
|
||||
|
||||
### Block 3da: Installer Flow (deferred from Task 6)
|
||||
|
||||
| # | Item | Effort |
|
||||
|---|------|--------|
|
||||
| INST-1 | **Ollama bundled installer** β "Install Ollama + pull Gemma 4" step | π’ 1 day |
|
||||
| INST-2 | **Hardware scan** β RAM/GPU read, recommend which models fit locally | π’ 4-6 hr |
|
||||
| INST-3 | **Ollama daemon auto-start** β Windows service / macOS launchd | π’ 4-6 hr |
|
||||
|
||||
---
|
||||
|
||||
## P2 β Polish (can ship without, do soon after)
|
||||
|
||||
### Block 3c Medium UX Fixes π’ (1-4 hr each)
|
||||
|
||||
| # | Fix | Effort |
|
||||
|---|-----|--------|
|
||||
| UX-1 | Reduce onboarding decisions: default Blank + General Purpose, skip to Ready | 2 hr |
|
||||
| UX-3 | Memory app: labeled tab bar replacing 6 unlabeled icons | 1 hr |
|
||||
| UX-4 | Dock: show text labels for first 7 days / 20 sessions | 2 hr |
|
||||
| UX-5 | Status bar: hide token count + cost behind developer mode toggle | 1 hr |
|
||||
| UX-6 | Chat header: collapse secondary controls into overflow menu | 2 hr |
|
||||
| UX-7 | Onboarding tier step: clarify dock tier β billing tier | 30 min |
|
||||
|
||||
### Block 3c Engagement Features π’ (half-day each)
|
||||
|
||||
| # | Feature | Effort |
|
||||
|---|---------|--------|
|
||||
| ENG-1 | "I just remembered" toast after 5th message | 4 hr |
|
||||
| ENG-2 | WorkspaceBriefing as collapsible sidebar | 4 hr |
|
||||
| ENG-3 | Progressive dock unlock nudge at 10/50 sessions | 2 hr |
|
||||
| ENG-4 | LoginBriefing on every launch (per-session reset + "don't show again") | 2 hr |
|
||||
| ENG-5 | Harvest-first onboarding: move import pitch to step 2 | 3 hr |
|
||||
| ENG-6 | Memory Score / Brain Health metric in dashboard + status bar | 4 hr |
|
||||
| ENG-7 | Suggested next actions after assistant response (2-3 buttons) | 4 hr |
|
||||
|
||||
### Block 3: Wiki Compiler v2 π’ (5 days)
|
||||
|
||||
| # | Task | Status |
|
||||
|---|------|--------|
|
||||
| 2.1 | Markdown export | β
|
|
||||
| 2.2 | Incremental recompilation after harvest | π’ (engine supports) |
|
||||
| 2.3 | Obsidian vault adapter | π’ |
|
||||
| 2.4 | Notion structured export adapter | π’ |
|
||||
| 2.5 | Wiki health report dashboard UI | π’ (types exist) |
|
||||
|
||||
### Block 4: Phase 3 β Harvest UX Full Polish π’ (5 days)
|
||||
|
||||
| # | Task | Status |
|
||||
|---|------|--------|
|
||||
| 3.1 | Privacy headline | β
|
|
||||
| 3.2 | Dedup summary | β
|
|
||||
| 3.3 | Live progress streaming (SSE from pipeline) | π’ |
|
||||
| 3.4 | Resumable harvests (checkpoint every 100 frames) | π’ |
|
||||
| 3.5 | Identity auto-populate screen | π’ |
|
||||
| 3.6 | Harvest-first onboarding tile ("Where does your AI life live?") | π’ |
|
||||
|
||||
### Block 3c-R: Responsive Gaps π’
|
||||
|
||||
| # | Component | Issue |
|
||||
|---|-----------|-------|
|
||||
| R-1 | Dock | Power tier (14 items) overflows < 768px |
|
||||
| R-2 | StatusBar | 10+ items β hide non-essential < 900px |
|
||||
| R-3 | ChatApp | Session sidebar 192px β collapse on narrow |
|
||||
| R-4 | OnboardingWizard | Template grid responsive columns |
|
||||
| R-5 | AppWindow | Default sizes exceed mobile viewport |
|
||||
|
||||
---
|
||||
|
||||
## PDF E2E β Deferred 21 items (π ) from 2026-04-17
|
||||
|
||||
Full triage in `docs/plans/PDF-E2E-ISSUES-2026-04-17.md`.
|
||||
|
||||
| # | Item | Effort |
|
||||
|---|------|--------|
|
||||
| P4 | Mutation Gates vs 3-level tool approval β UX redesign | π big |
|
||||
| P6 | Room feature functional verification (2 parallel agents viz) | π |
|
||||
| P8 | Agents vs Personas unify naming | π‘ partial |
|
||||
| P10 | **Agent icons β bee-style per-agent, dark + light variants** | π design-heavy |
|
||||
| P14 | Local browser only drive D, needs C (multi-drive) | π |
|
||||
| P15 | Create Template modal overlaps Dashboard β can't drag | π |
|
||||
| P16 | Files app local folder create + explorer-style browse | π big |
|
||||
| P17 | **App-wide tooltips on badges/options** | π broad |
|
||||
| P18 | Waggle Dance real signal display | π |
|
||||
| P21 | Timeline always empty β wire to event stream | π |
|
||||
| P25 | Scheduled Jobs toggle stays off after trigger | π |
|
||||
| P26 | New scheduled job creation unclear | π |
|
||||
| P28 | Marketplace empty β was β
this session (10 E2E green, 148 pkgs) | β
|
|
||||
| P29 | Skills & Apps cards not clickable β no detail card | π |
|
||||
| P30 | MCP install CLI simplification | π |
|
||||
| P34 | Approvals app β move to Ops or delete | π |
|
||||
| P35 | **Spawn Agent "no models available"** β wrong, 13 providers | π core bug |
|
||||
| P36 | **Dock spawn-agent icon wiring** β clicking does nothing | π core bug |
|
||||
| P39 | Status bar left β static, should be dynamic model + folder | π‘ |
|
||||
| P40 | **Light mode boot screen β no Waggle logo / animation** | π |
|
||||
| P41 | **Light mode "Waggle AI" text styling ugly** | π |
|
||||
|
||||
---
|
||||
|
||||
## hive-mind Integration π’ (7 days)
|
||||
|
||||
From `docs/HIVE-MIND-INTEGRATION-DESIGN.md`. 8 items across MCP resources, CLI, hooks, installer.
|
||||
|
||||
---
|
||||
|
||||
## Accessibility π’ (1 day β post-launch OK)
|
||||
|
||||
| # | Fix | WCAG |
|
||||
|---|-----|------|
|
||||
| A11Y-1 | Boot screen: announce skip for screen readers | 2.1.1 |
|
||||
| A11Y-2 | Dock: 44x44px touch targets | 2.5.8 |
|
||||
| A11Y-3 | Window title bar: icons on min/max buttons | 1.4.1 |
|
||||
| A11Y-4 | PersonaSwitcher: aria-disabled on locked cards | 4.1.2 |
|
||||
| A11Y-5 | Settings: role="switch" + aria-checked on toggles | 4.1.2 |
|
||||
| A11Y-6 | Dashboard: health dots shape differentiation | 1.4.1 |
|
||||
| A11Y-7 | Chat feedback dropdown: focus trap + arrow keys | 2.1.1 |
|
||||
| A11Y-8 | Global Search: role="dialog" | 1.3.1 |
|
||||
| A11Y-9 | Memory: aria-label on importance slider | 1.3.1 |
|
||||
|
||||
---
|
||||
|
||||
## Strategic Decisions Pending β³
|
||||
|
||||
| # | Decision | Unlocks |
|
||||
|---|----------|---------|
|
||||
| C1 | hive-mind OSS timing β ship with Waggle or before? | Launch sequencing |
|
||||
| C5 | Harvest-first onboarding β replace step 2 or parallel opt-in? | Block 4 UX |
|
||||
| C8 | Warm list β 5-10 names to pre-email 72h before launch | Launch credibility |
|
||||
| C9 | Single-author or dual-author on papers? | Paper attribution |
|
||||
| C11 | Marketplace model β free+attribution / freemium / enterprise-only? | Skills monetization |
|
||||
| β | EvolveSchema attribution β keep "Mikhail" or cite ACE (Zhang et al.)? | Paper 2 framing |
|
||||
|
||||
---
|
||||
|
||||
## Totals
|
||||
|
||||
| Category | Items | Eng days | Budget |
|
||||
|----------|-------|---------|--------|
|
||||
| P0 launch blockers (tests, papers, launch prep) | 50 | 50 | $2,650-4,000 |
|
||||
| P1 ship quality (QW, OW-6, CR-*, 3b, INST) | ~25 | 6.5 | β |
|
||||
| P2 polish (medium UX, ENG, wiki v2, harvest UX, responsive) | ~30 | 22 | β |
|
||||
| P3 future (a11y, Mac notarization, LinkedIn) | ~15 | 6.5 | β |
|
||||
| **PDF deferred 21** | 21 | ~7 | β |
|
||||
| **Total everything** | **~145** | **~92 days** | **~$3,000-4,000** |
|
||||
|
||||
Calendar with parallelism: **~7-8 weeks to launch.**
|
||||
|
||||
---
|
||||
|
||||
## Critical Path
|
||||
|
||||
```
|
||||
Marko exports (M1-M4) βββΊ Phase 1 Harvest (3d) βββΊ Phase 4 Memory Proof (10d) βββΊ Paper 1
|
||||
ββ parallel ββΊ Phase 2 Wiki v2 (7d) β
|
||||
ββ parallel ββΊ Phase 3 Harvest UX (7d) Phase 7b Combined (7d) βββΊ Paper 2
|
||||
β
|
||||
API credits (M5) βββΊ Phase 5 GEPA Proof (21d) βββββββββββββββββββββββββββββββββββββββ
|
||||
|
||||
Stripe (M7) + Signing (M8) βββΊ Phase 7 Launch Prep βββΊ LAUNCH DAY
|
||||
hive-mind extraction βββββββββββββββββββββββββββββββββββΊ LAUNCH DAY
|
||||
```
|
||||
|
||||
---
|
||||
|
||||
## Related docs
|
||||
|
||||
- `docs/REMAINING-BACKLOG-2026-04-16.md` β canonical source
|
||||
- `docs/TOTAL-WORK-ESTIMATE.md` β effort breakdown
|
||||
- `docs/plans/PDF-E2E-ISSUES-2026-04-17.md` β PDF triage
|
||||
- `docs/HIVE-MIND-INTEGRATION-DESIGN.md` β OSS package design
|
||||
- `docs/UX-ASSESSMENT-2026-04-16.md` β UX findings source
|
||||
- `docs/test-plans/*.docx` β Phase 4/5/7 protocols
|
||||
Reference in New Issue
Block a user