The hooks for Claude Code, Codex and the other agents ran the
hive-mind-hooks-* packages, which left the repository; ADR-0002 hides
the feature in v1. Remove the hook installer surface from the tool
launcher, the POST /api/tools/hooks route, the hook status probe in
tool detection, and the hook fields of the tool manifest and detection
envelope (hookCapable, hookRoot, hookPointer, hooksInstalled,
hookPointerPath). Third-party adapter manifests no longer accept the
hook fields.
In the web UI, remove the hidden hook actions and the "How memory is
shared" explainer from the Launcher, adapter.manageHooks, the
hook-wired count in Mission Control and the agentHooks and memoryMcp
memory feature flags. Launch, watch and stop are unchanged; the
roadmap tool note no longer mentions hooks.
A provider without its key lists no models, so Model Pilot could not tell
the primary needed a key, and it compared a prefixed active id with a bare
one. The provider now also comes from the id's prefix or family name, and
prefixed and bare ids count as the same model. The account row's fallback
initial is A for Account, not W.
Anti-slop audit-002, item 13 (R-02). Every em dash in text the user sees
(web UI labels, toasts, tooltips, empty and error states, chat steps,
API messages, notifications and channel replies) became a period, comma,
colon or parentheses. Model prompts, logs, comments, regexes and the lone
dash that marks an empty value are unchanged. Text the client matches
against server copy (the default workspace summary, the quiet-night dream
summary) accepts the old wording too, so cached and saved data still match.
At 375px the 64px icon rail took a fifth of the screen and Home's heading
wrapped over five lines. Below sm the rail hides, a bottom bar carries the
five places plus More (⌘K), and Home tightens its padding and heading.
Sparkles and Zap stood in as the icon for unrelated things: tools, MCP,
imports, model routing, workspaces, memory highlights (anti-slop audit-002,
item 16). Each now gets an icon for what it is (Wrench, Plug, Import, Route,
Hexagon, Brain and so on) or none. Chevrons and arrows on Resume, Continue,
Open, Set up a model and the onboarding buttons are gone (item 17); arrows
in settings paths, relations and the launcher flow diagram stay.
Bees, sparkle glyphs, fire, check and warning marks decorated buttons,
toasts, activity steps and channel replies (anti-slop audit-002, item 18).
Marks that carry state (key set, importance, the hive glyph) stay.
Home and the sidebar read the user's name from the identity row, which the
sidecar fills with the assistant's identity named Waggle. Both now use the
profile name, with the identity name as a fallback that skips the default.
Settings showed the configured primary while the status bar showed the
model new chats fall back to, so the two screens disagreed. Model Pilot now
says the primary needs a key and names the model in use.
Fixes items 3-11 of anti-slop/audit-002, all scoped to data-design=calm:
- no colored edges on Model Pilot rows, a connected extension or the
active file workspace;
- section labels and eyebrows in the text face, mono for data only;
- one accent: honey text, washes and hover lines turn neutral, honey stays
on primary buttons, the switch, focus and attention counts;
- dots with no state behind them are hidden and live dots no longer pulse;
- no card shadow or hover lift, including the --shadow token;
- inline-style gradients go solid or flat, glows go;
- no entrance motion: framer-motion animations finish instantly and the
inline card-enter and scroll reveals are off;
- stock Tailwind hues map onto Hive status tokens, mixed toward --text so
small status text keeps 4.5:1 in light;
- radii follow the 6 / 10 / 14 scale, text pills become chips.
The classic design is unchanged.
"Pick up where you left off" listed every recent workspace, including the
one the Start here card already offers. The list now leaves it out and
hides when nothing else is left.
The card headline was a fixed "Worked across your memory, web & files".
It is now built from the turn: memory, web and file tools it called and
the memory steps the server reported, or a plain Working / Done.
The title carries a framer-motion layoutId for the card-to-header hero morph,
which also animates any change of its box. With a short workspace name the
title is as wide as the subtitle row; hiding that row on the Chat tab changed
the width, and framer animated it as a horizontal scale (2.9x for "Eng").
Both titles now use layout="position": only the position animates, and the
hero morph still moves the name into place. The hero-morph test checks it.
The ⌘K search input had no padding but drew its own focus ring with an
offset, so the ring ran right against the text. It now has inner padding
and no offset, so the ring reads as the field's outline; the palette test
checks both.
The sidebar account row had 8px above its content and 22px below, because
its bottom padding added to the nav's own. It now has 14px above and none
below, matching the nav padding underneath.
The redesign proposed after the anti-slop audit (anti-slop/audit-001) is now
an opt-in design layer. The "New design" switch at the bottom of the sidebar
sets data-design="calm" on <html> and remembers it; theme-init.js applies the
stored choice before the first paint. The classic look stays the default and
is unchanged.
styles/calm.css, scoped to that attribute, keeps the Hive DS colors and:
bundles Hanken Grotesk and JetBrains Mono (@fontsource-variable, OFL-1.1);
uses three radii (6 / 10 / 14 px); drops the honeycomb wallpaper, gradient
fills, glass, glows and pulsing dots; keeps shadows only on menus and
dialogs; shows labels as written instead of tracked capitals; and marks the
active sidebar item with fill, a 1px line and weight instead of a stripe.
Screen layouts are unchanged.
The composer textarea drew its own focus ring inside the rounded box, which
already turns amber on focus-within. The ring is gone; the box's border stays
the focus indicator (8.14:1 dark, 4.92:1 light against the composer).
With the full-width sidebar every item showed a hover hint that repeated its
visible label, and the part of the hint that reached past the sidebar was
hidden wherever the main area had content: the hint rendered inside the nav,
and the nav and <main> are sibling z-10 layers.
Sidebar hints now show only on the icon rail below lg, where they are the
only label, and render in document.body through a new opt-in `portal` flag
on HintTooltip. Other hints keep rendering in place, since several sit in
overlays above z-50 where a portaled hint would end up underneath.
The local sidecar has no /api/team/* routes since P1.1.
- Remove searchTeamMemory, getTeamMembers, getTeamActivity and
getTeamMessages from the adapter.
- Mission Control loses its Team and Activity tabs (both read the team
server) and keeps the fleet view, with its own load-error state.
- Drop the stale adapter mocks from the web tests; the Mission Control
test checks that no team tab is offered.
- adapter: memory ids are strings; single-memory calls take only the id
(no ?mind= disambiguation). searchMemory takes the workspace as its own
parameter. New getMemoryCapabilities / setMemoryExtraction. Removed:
incrementFrameAccess, getMemoryOriginalSource, listSuppression,
allowReimport, getWeaverStatus, and the dead importPreview, importCommit
and getWikiWatermark. eraseMemory takes { id } or { sessionId }.
- memory-features reads GET /api/memory/capabilities for the knowledge
graph; history import, wiki, hooks, Room and the memory MCP stay hidden
(ADR-0002). useMemoryCapabilities re-renders the Memory screens.
- Settings > General has a Memory toggle for background fact extraction.
- Memory Center: the confidence filter, the erased-sources panel, the
original-source view and the Deprecated chip are gone; Erase forgets
every memory saved from the chat a memory came from and is offered only
for memories with a chat session. Memory kinds follow the contract.
- Trust views show short memory labels for the new string ids and drop the
per-row "not scored yet" badge (v1 stores no confidence).
- The Weaver maintenance view and the Cockpit weaver card are removed
(the weaver package and its routes are deleted).
- Timeline uses the contract kinds and maps important/temporary
importance.
Logs UF-033 (search scope sent as the workspace id), UF-034 (importance
mapping) and UF-035 (restore over open databases, open).
The WhatsApp card in Settings > Channels now says the client is
unofficial, that WhatsApp may block the account, and that a browser is
downloaded (about 170 MB) when none is installed. While the adapter
looks for or downloads the browser, its status detail is shown above
the QR.
The setup hint told users to send /pair from the "Message yourself"
chat, which the adapter never reads because own messages are dropped.
It now says to send it from another WhatsApp account (UF-030).
- Analytics are opt-in (decision Q7, ADR-0006). PostHog does not start or
capture anything until the user clicks Allow in a first-run dialog that
says what is sent. Escape or closing stores nothing and asks again. The
existing Privacy & Telemetry toggle in Settings withdraws consent at once.
Builds without VITE_POSTHOG_KEY show no dialog and send nothing.
- Remove the remaining upsell copy: the /team page with its per-seat price,
Stripe and Teams wording in the erase-data dialog, Teams/Enterprise hints.
- Remove team screens (decision Q3): Waggle Dance, team presence in chat,
team storage and sharing in workspace creation, storage and files.
- Hide memory features that are not in v1 (decision Q2) behind one map in
lib/memory-features.ts: the knowledge graph, import history, wiki, agent
memory hooks and Room launches. The map is the seam P1.5 fills from the
memory store's capabilities.
- Say Windows, macOS and Linux instead of "Linux soon".
- Update the e2e specs for the removed and hidden screens.
Also logs UF-029: the Settings "Import Data" button has no handler.
Self-learning is excluded from the community edition (ADR-0004); the
project owner reworks it separately. Cost tracking stays.
- agent: delete behaviour evolution (evolve-schema, iterative GEPA,
compose-evolution, evolution gates, orchestrator and deploy),
improvement and correction detection, AgentLearning, the eval-dataset
builder, optimization-capture and the agent_insights tool. Secret
detection moves from eval-dataset to secret-patterns. The LLM wiring
keeps only the Haiku adapter and judge call used by skill audit and
hygiene, so @ax-llm/ax is now declared by agent instead of server.
- server: delete /api/evolution/*, the evolution and optimizer services,
GEPA expansion of the first chat message, the prompt_optimization and
monthly_assessment jobs, the idle-session reviewer and its
session-reviewer persona, prompt injection of past corrections and
thumbs-down recorded as correction signals. Existing job rows of the
removed types are ignored, not deleted.
- core: delete OptimizationLogStore; stop re-exporting the improvement
signal and evolution run stores.
- web: delete the Evolution screen and the two job types in the
automation editor.
- delete packages/optimizer.
Also logs UF-027 (self-learning loops read data nothing collects) and
UF-028 (the Settings prompt-shape choice is ignored by chat).
KVARK is the commercial enterprise product and is not part of the community
edition. The agent's KVARK tools were never wired into the server, so
removing them changes no runtime behaviour beyond the routes listed here.
- agent: delete kvark-tools; CombinedRetrieval and formatCombinedResult now
merge workspace and personal memory only (no KVARK lane, no source
conflict note); connector substrate is always 'waggle'
- agent: promote_skill stops at workspace scope; team and enterprise scopes
answer "not available in this edition" instead of an upgrade prompt
- server: delete src/kvark and GET /api/marketplace/enterprise-packs
- marketplace: delete ENTERPRISE_PACKS
- compliance (EU AI Act dashboard, its templates and the KVARK template
seeded on every boot): delete core/src/compliance, the /api/compliance/*
routes, agent compliance-pdf and the Cockpit compliance panel. The
ai_interactions table lives in the memory substrate and goes with P1.5.
The community edition has no monetization (ADR-0001). Remove the tier
model (packages/shared/src/tiers.ts), the requireTier middleware and every
tier gate, GET/PATCH /api/tier and the trial start, and the Stripe
integration, which depends on the tier model.
Personal features a tier used to limit are open to everyone: unlimited
workspaces and connectors, every embedding provider including LiteLLM,
per-workspace costs, Approvals. The workspace session cap is one constant
(100). Team and enterprise surfaces are hidden instead of unlocked (team
dock zone, Settings Team/Enterprise/Plan tabs, workspace Team tab);
cloud sync reports unavailable, as it did for free users.
The sidecar ignores the tier keys in config.json but does not delete them:
both editions may still share ~/.waggle.
Web billing UI is deleted: plan cards, upgrade and trial modals, payment
success route, the KVARK sales block, tier 403 handling.
The Select dropdown is portaled to <body> with z-50, under the wizard's
z-[9999] scrim, so it was invisible yet clickable through the scrim.
Lift it to z-[10000] and cover the stacking order with a test (UF-007).