What's being built and why.
A running record of architectural decisions, design choices, and daily progress.
Weave thread UI: card redesign, live binding, Weave restyle
The chat UI gets a thorough Weave redesign across nine commits, centered on threaded conversations
Thread system ships end-to-end + security & cleanup sweep
Threading lands across the full stack in six coordinated workstreams
Token hashing, Deno sandbox, provider timeouts, dock toast
Session tokens are now stored as sha256 hashes in SQLite, mirroring the wrapper-auth path
v1.0.0-beta: unified discovery + ACT loop-guard
Tagging v1
search hang fix, browser style verb, provider timeout guard
The search_files tool was reworked around four problems
Native mobile + Auto Research land on rc-0.9.0
Native mobile (Tauri) client landed on rc-0
Mobile pairing ships, transcript GC repaired, interface polished
TKT-1099 mobile pairing/unlock flow ships end-to-end
TKT-1070 lands: recursive turn chain + multi-surface sync
TKT-1070: MessageProcessor becomes a recursive continuation chain
Collapse tool scoping into one DISCOVERABLE flag
TKT-1066 starts with a failing baseline test pinning the news→web_search exclusivity contract: news must be blocked on the user channel via the real find_tools
Search gets parseable format; docstring cleanup epic wraps
The search ability got a major redesign (TKT-1067)
Sweeping docstring cleanup hits batch 21/47
A long-running docstring refactor continued with batches 9 through 21 of a planned 47, trimming docstrings across abilities, API routes, capabilities, services,
document attachments, async composable, timer auto-silence, api-client auth
TKT-990 closes out the document-attachment bug in chat across both frontends
Vue frontend cutover, delegate provider, memory v2
Major frontend milestone: the legacy static apps and auth-gate are deleted after a full Vue 3 cutover
Vue foundation, whole-instance snapshots, per-source memory profiles
The biggest push is TKT-952, the Vue frontend migration: a pnpm workspace skeleton, a shared `@chalie/shared` package with SCSS theme port preserving `[data-the
Popular providers, durable tool-calls, fact extraction
Added a 'Popular Providers' tab to the Add Provider dialog, sourced from the models
Memory redesign + ToolResult contract sweep
A major memory subsystem overhaul landed in three coordinated pieces
ToolResult contract lands across the ability fleet
A coordinated migration closes the TKT-882 ToolResult contract sweep across the ability surface
Browser rebuilt, delegate act-trail restored, recall fan-out removed
The browser tool is rebuilt from the ground up as 9 flat verbs (open/read/find/click/fill/select/scroll/back/screenshot) on a single persistent Playwright page
Ollama cleanup lands, markdown escape hatch added
TKT-846 closed out its leftover smell: services/ollama_service
TKT-846 refactor lands, plus mobile picker fix
TKT-846 introduces a unified provider API: ProviderApiRequest/ProviderApiResponse DTOs plus a thin ProviderClient ABC per platform (anthropic, openai, gemini, o
Path-only uploads, vision pipeline, ability getter refactor
Killed the base64 act-trail bloat that was blowing the context window
compaction rewritten compact-first; thinking becomes internal ability
The dominant thread is a full redesign of the compaction system
Eliminate _base refactor lands; ProcessorConfig goes explicit-mp
Today's headline is TKT-828: the eliminate-abilities/_base refactor spanning P0–P8
policy flat gate, dispatch refactor, all timeouts gone
Massive policy refactor lands: PolicyManager is now the sole gate against a flat policy(channel, permission, setting) table, and PolicyService plus policy_rules
Flat ACT loop lands: delegates, universal compaction, big test cut
34 commits land the ACT Loop Orchestrator Refactor (TKT-795), replacing the per-channel MessageProcessor subclass architecture with a single flat MessageProcess
Act-loop refactor lands T1–T5; provider & chat fixes
The bulk of this batch is the flat MessageProcessor refactor across T1–T5 of TKT-795 / doc-112
MCP outbound client lands; vision probes; bug fixes
The headline addition is outbound MCP (TKT-763): Chalie can now act as an MCP client against remote MCP servers
Compaction ability, system memory tool, theme shadow cleanup
Compaction now flows through a new internal CompactionAbility (TKT-731) so it earns an ACT-trail pill and durable audit row without ever being LLM-callable — it
v0.8.0 pre-release polish: lint, refactors, theme & test fixes
Pre-release cleanup for rc-0
Vault recovery, image OCR, code_eval silent-fail, bash safety
A major vault hardening landed across four commits
Subconscious skill building, brain polish, 200k context cap
Skill suggestion has been reworked to run fully in the background (TKT-675)
Subagent Management & ACT Loop Rework
Subagents can now be listed, stopped, and redirected via new subagent actions
Runtime Dependency Injection and Bash Ability
Migrated dependency management to pyproject
Tool Spec Alignment, Policy Cleanup & chmod
Developed and hardened the search_files cross-platform glob and grep tool to match its spec
Skills overhaul, policy unification, and UI polish
The skills ecosystem received a major overhaul with the introduction of skill_builder ability, enabling full CRUD operations on user-defined YAML playbooks
Self-Refining Skill Library and Cooperative Cancellation
Extracted a SearchableAbility base class to replace procedural logic in ability modules
Core Refactor & Geo-Tagging Release
Installer configuration shifted the default port to 31025 and dropped automatic Python installation in favor of explicit platform instructions
v0.7.1: UniFi Control, External Chat Safety & Geo-Search
Added a new Ubiquiti network control capability with nine actions, dual authentication, and SSL fallback
v0.7.0 release: geo-tagging and brain UI fixes
Launched geo-tagging across transcripts, episodes, and the scheduler
Refactor chat dispatch, fix save_graph infinite loop
Refactored chat message routing into a single dispatch_message() chokepoint with hidden_input and intercept knobs
Steer Dispatch Overhaul and Communication Stack Rebuild
The steer mechanism was rebuilt from the ground up
Brain 2.0: Modular dashboard, MCP server, and voice pipeline overhaul
The brain dashboard received a complete ground-up redesign, replacing the monolithic 6
Policy Enforcement, Home Automation, and Full Email SMTP Send
A policy enforcement layer landed, bringing per-action allow/ask/deny controls across chat, subagent, and subconscious contexts
Rich-Media Cards, Voice Robustness, and Prompt Tightening
Calendar and contacts abilities now return rich-media payloads on the user channel, rendering as themed cards instead of plain text
Token Dashboard, Slideout Tasks, Drafts, Scheduler
A new token usage pipeline captures five token metrics with usage_class bucketing into llm_call_log
Full Contact Profiles, Email Manage, and Ability Rewire
After Phase 4 removed tool_library_service, MailCapability’s IMAP/CalDAV/CardDAV handlers were unreachable
Chalie v0.6.2: ONNX Voice Rebuild and Installer Fixes
Chalie v0
Voice refactor, prosody fixes, and dead code purge
The voice pipeline was collapsed onto the moonshine_voice package, eliminating kokoro-onnx and espeak-ng entirely
v0.6.0: voice overhaul, live models, code diet
Chalie v0
Voice, Memory, and Massive Code Cleanup Ahead of v0.6.0
Hundreds of lines of dead code were removed across services: EventBusService (384 LOC) and its test suite, three orphan public methods on InterfaceRegistryServi
Memory recall refactored: tool delegation, single-pass factors
Memory recall’s internal schedule search was removed and replaced with a delegation to the schedule ability via handleTool()
Refactoring, Subagent routing, and reliability improvements
We refined the model's routing logic by moving `subagent` to `DISCOVERABLE`
Major Refactor: Lists Go ID-Only & Rich Media Support
The ListAbility CRUD interface was rebuilt to be strictly deterministic, using 8-char hex IDs for addressing
Voice Stability and Rich Media Overhaul
The TTS pipeline was fundamentally refactored to drop fragile chunked streaming in favor of a single Kokoro call, resulting in one WAV blob
AI Assistant Refinements: Media, Timer, and UI Theming
New rich-media cards were introduced, enabling tools to shortlist and run local OCR on up to three image candidates
Chalie Dev Log: Rich Media, Compaction, and UI Polish
Compaction testing and robustness were heavily fortified, removing obsolete test files for deleted modules and adding new feature tests for surviving services l
Massive Compaction Overhaul: Append-Only State
The compaction subsystem underwent a major architectural rewrite, shifting from a dedicated `compactions` table to an append-only approach using the `tool_calls
Chalie v0.6.0: Subagents, Timeouts, and Native Tooling
Test suite cleanup occurred, consolidating many tautological or static-data tests in favor of behavioral tests, resulting in a net increase of unit test coverag
v0.5.0: Leaner, Faster, Sharper AI Assistant
v0
Major XML Markup Cutover & Complexity Reduction
The system transitioned from a block protocol to a strict XML markup format, replacing legacy markdown and rich_render functionalities
Ability Framework Migration to Per-Processor Scope
The tool scope (ALWAYS_AVAILABLE / DISCOVERABLE) has been moved from the Ability ABC to each MessageProcessor subclass
ACT Visual Feedback & System Refinements
Inline tool start/end events and UI feedback are now available for ACT loops, showing progress via inline pills
Subconscious Worker V0.5.0 Refinements
The SubconsciousWorker tick was finalized, establishing a single daemon thread for latent cognition, which executes consolidation, decay, pattern extraction, an
Increased Python minimum version for stability
The minimum supported Python version has been raised from 3
Release v0.3.3 & v0.4.0 updates
Chalie v0
SES Daemon & Embedding Optimizations
The system introduced a single FIFO daemon to handle search expansion, replacing per-write doc2query threads and absorbing _schedule_embeddings
Refining Tooling and Enhancing Personalization
Tool descriptions were sharpened to require imperative triggers like "deep dive" or "research" to ensure models dispatch tools before timing out on inline answe
Weather tool handles country-only location
A smoke test was added for the weather tool to verify it resolves 'germany' without error
AI Core Refactor: World State, Memory, and User Summary
The system refactors WorldState into an in-process singleton, removing WorldStateService and related APIs, and introduces a new TimeFormatterService for elapsed
AI Memory Overhaul: Episodic Simplification & Providers
A major episodic memory simplification was performed, dropping nine columns from the episodes table and adding a consolidated_into back-pointer
AI Assistant Refactors Core Memory & Extraction
The ToolSynthesisProcessor was completely removed as the hourly sweep over tool_calls was an inefficient abstraction that duplicated existing ACT loop memory sk
Major Refactor: Thinking Gate, Data Graph & Classifier
The thinking-gate was redesigned to utilize provider-native deliberation flags instead of a classifier-driven approach, moving exploration to a single, same-job
v0.9.0 Classifier Stack & Schema Refactor
The classifier stack was integrated in v0
Chalie v0.3.2 Release & Refactoring Updates
The repository was merged into main for the v0
Refactor: Document Handling & Memory Pipeline
Documents are now split into 512-1024 char overlapping artifacts stored in data_graph, replacing the heavy document_processing_service
Major Memory & Tooling Overhaul
A complete memory recall overhaul introduced a new tool output format of [id:{id},relevance:{level}] {value} and added a `reflect` action featuring deep episode
Major Refactor: Message Processing & System Prompting
The underlying message processing pipeline underwent a substantial refactor, shifting to a MessageProcessor v2 architecture with a per-turn instance model, elim
MessageProcessor v2 Core Wiring Complete
SystemPrompt hierarchy was standardized, moving toward a pure template renderer
AI Core Updates: DMN, Context, and Performance Boosts
The DMN functionality was stabilized by replacing the broken unified_generate path with DMNMessageProcessor, enabling the full tool loop for DMN interactions
Core AI Overhaul: Schema, Tools, and Performance Gains
The schema management system was completely replaced by a declarative SchemaConvergenceService, which introspects the live database to ensure desired state
Major Pipeline Overhaul & Prompt Architecture Refactor
A major migration replaced the 20-step digest_worker pipeline with a new 4-step flow: WebSocket → UserMessageProcessor → MessageProcessor → Providers
Memory Pipeline Redesign & Knowledge Recall Boost
The episodic memory pipeline has been entirely replaced with a psychology-grounded architecture, featuring transcript-linked episodes via a rolling trigger at i
AI Assistant Updates: News, Tasks, and Prompts
The news tool has been simplified from six parameters/four actions to a two-parameter interface: query and an optional category
Feature Overhaul: Tool Discovery, DMN, and Resilience
Two-axis tool discovery is implemented, scoring tools using both semantic k-NN distance and exact keyword matches, which replaces the previous reliance on full_
Chalie Dev Log: Core Reliability & Workflow Overhaul
The trait correction logic now allows for overwriting stale values when the confidence is greater than or equal to 80% of the old confidence, fixing issues wher
AI Core Updates: Search, Contradiction, and Prompt Fixes
The stale "{{focus}}" placeholder was removed from frontal-cortex prompts to resolve failures in unified_generate()
Major Overhaul: Episode-Based Goal Emergence
The system replaces its old goal creation pipeline with episode-based emergence
AI Core Update: Goals, Tracing, and Stability
Several changes focused on enhancing meta-harness diagnostics and AI reasoning stability
Chalie Dev Log: Goals, Traits, and FTS Fixes
The Goals skill now supports explicit goal creation, accepting a description and timescale
Kill Topic Classifier & Refactor Digest Worker
The TopicClassifierService, TwoSignalBoundaryService, and RecentTopicService were completely removed, along with all associated tests and benchmarks
AI Core Upgrades: Vault, Contact, & Briefing Features
The AI core implemented a major encryption upgrade, moving from legacy Fernet methods to AES-256-GCM via a centralized VaultService and related migrations
Refactor: Real MemoryStore replaces Mocks
Multiple tests across goal signal, adaptive layer, and onboarding integrations have been refactored to use real MemoryStore instances instead of mocking infrast
Cleanup Phase: Finalizing Knowledge Store Migration
This batch focuses on finalizing the knowledge store consolidation and cleaning up residual references from the deleted legacy services
New Visual Output & Knowledge Store Unification
A rich_render skill was introduced to produce visual output like charts and progress bars in a single generation pass, using block directives for rendering
Major Updates: Multi-Model Support & News Tool
Multi-model providers are integrated, supporting multiple models per API key across 4 capability-derived job groups: Vision, Reasoning, Analytical, and Utility
AI Core Enhancements & Observability
A new system for telemetry collection was implemented, including the creation of `backend/services/telemetry_service
AI Core & Goal Ecology Major Updates
The encryption key service now stores the key directly in the database, ensuring the key and encrypted data are never separated, and it automatically migrates f
Chalie Dev Log: Search, Docs & State Visibility
A unified multi-provider search tool was implemented, supporting 12 providers including Wikipedia, Wikidata, and GitHub, with DDG fallback and query routing via
Tooling and Context Overhaul in Chalie
Tools have been refactored to be direct-invocation Python modules, eliminating tool directories, manifest files, and subprocess execution
Major AI Pipeline Simplification and Refactoring
Routing infrastructure, including routing_decisions table and related services, has been entirely removed as it was unused in production
Major Refactors & New Daemon Gateway
Refactored the embodiment system to be internally managed, version-pinned, and auto-synced at boot, removing the marketplace model and several related API endpo
Chalie Dev Log: Interface & World State Upgrades
The interface layer was significantly expanded to include a Bluetooth-style pairing protocol and registered interface tools in ToolRegistryService
AI Core Enhancements: Mode-Gate, Context, and Stability
The mode-gate ONNX classifier has been deployed, a binary RESPOND/ACT classifier achieving 97
Chalie Dev Log: AI Refinements and Image Pipeline
The triage pipeline underwent significant refactoring, leading to the removal of CLARIFY mode and the simplification of routing logic
AI Core & ACT Loop Refinements
Trait extraction is now wired into the standard chat path and includes location data, and markdown fences are stripped before JSON parsing for traits
Major Refactor: Killing Memory Chunker
The memory chunker worker has been removed, significantly reducing codebase size by approximately 3,000 lines
World Model, Goal Inference, User Signals Integrated
WorldStateService now uses a MemoryStore cache, refreshed during idle periods and updated by signal handlers, providing ambient context, active conversation top
Docstrings & Tooling Enhancements
Multiple service files across Phase 1 and Phase 2a received comprehensive Google-style docstrings, covering modules, classes, and public/private methods with de
Core Architecture Deep Dive: Salience & Constraints
A new WorldStateService is introduced to aggregate contextual items using temporal and semantic salience scoring, surfacing relevant goals and tasks based on re
AI Stability & Pipeline Improvements
Added established signal and created_at to the contradiction pipeline, preparing for the ONNX contradiction classifier
AI Assistant Refinements & Uncertainty Engine
The Uncertainty Engine saw Phases 2, 3, and 4 complete, adding ContradictionClassifierService, ReconcileAction, and refining source reliability checks in ActDis
Stability and Intelligence Updates
60-second timeouts were added to all vision LLM OCR calls across Anthropic, OpenAI, and Gemini to prevent long-running pipeline hangs
AI Assistant Updates: Watch Folders, Classification & Stability
Watched Folder functionality is now available with a dedicated service handling CRUD, server-side browsing, and a scan algorithm using mtime fast-skip
Refining Timeouts and Schema Handling
Significant stability and reliability improvements were introduced today, focusing heavily on thread management and data integrity
Learning Behavioral Rhythms
Implemented temporal pattern mining to learn user rhythms from ambient signals and promoted the news tool to a trusted, default integration.
Consolidating the Architecture
Finalized the migration from external services to a unified internal architecture while improving intent detection and startup reliability.
Simplification and First-Party Tools
Shifted to a single-process architecture and introduced a background auto-installation system for trusted default tools.
Marketplace Foundations and Orchestrator Unification
This update introduces a dynamic embodiment catalog, unifies the core ACT execution logic, and adds a multi-stage document intelligence pipeline.
Self-Narrative and Conversational Control
Reframing the autobiography as a first-person narrative while introducing temporal pattern mining and conversational belief correction.
Cognitive Reflexes and Structured Planning
Introduced semantic fast-paths for simple queries and DAG-based plan decomposition for persistent tasks.
Visible Intent and Integrated Voice
Massive push on system observability, local voice integration, and closing the feedback loop for tool performance and selection.
Ambient Awareness and Autonomous Reliability
Implemented a zero-LLM ambient inference pipeline, a relationship state machine for user onboarding, and a post-action critic loop to verify tool results.
Memory Moments and Curiosity Threads
Introduced semantic message pinning with background enrichment and replaced the legacy goal system with autonomous curiosity threads.
Resilient Multi-Instance & Skill Refactoring
Implementation of multi-instance host support, a major refactor of innate skills, and the introduction of markdown rendering for responses.
System Maturation and UI Capabilities
Implemented list and scheduler management, refined the cognitive routing pipeline, and optimized database connection handling for multi-process stability.
Cognitive Triage and Innate Skills
Introduced a sophisticated cognitive triage system for tool execution and established a suite of core innate skills for identity, goals, and focus management.
Hot Tool Discovery and Orchestration
Implemented a background scanner for dynamic tool registration and streamlined the entire repository structure.