v0.4.11

CCCC v0.4.11 Release Notes

v0.4.11 replaces the Weixin Node.js sidecar with a Python SDK-based bridge, makes runtime state and streaming history harder to desynchronize, improves actor/runtime configuration surfaces, and adds clearer Weixin subscription guidance after login.

Highlights

1) Weixin bridge moved from a Node sidecar to wechatbot-sdk

The largest implementation change in v0.4.11 is the Weixin bridge migration.

The previous packaged Node.js sidecar and bundled .mjs bridge assets were removed. The Weixin adapter now runs through the Python wechatbot-sdk path, with the SDK dependency declared directly in the Python package metadata. This reduces packaging complexity and keeps Weixin login, inbound messages, media downloads, context-token handling, and outbound sends inside the same Python adapter layer as the rest of the IM bridge.

Key improvements:

• wechatbot-sdk>=0.2.0 is now the Weixin bridge dependency
• Node sidecar package files and packaged sidecar resources were removed
• Weixin login status and start/logout routes now operate against the Python SDK-backed state
• media downloads, message normalization, context tokens, and outbound readiness are handled in the Python adapter
• adapter and Web route tests were refreshed around the new implementation

2) Weixin setup is clearer after login

v0.4.11 adds a more explicit Web settings path for Weixin users.

Logging into Weixin only connects the account; it does not automatically tell CCCC which Weixin bot chat should receive group messages. The IM Bridge settings panel now makes that distinction visible after login and explains the next step: send /subscribe in the target Weixin bot chat, then approve the request from Pending Requests.

The guidance adapts to the current state:

• if the IM Bridge config has not been saved, the panel tells the user to save and start the bridge first
• if the bridge is configured but stopped, it tells the user to start it first
• if the bridge is ready and no Weixin chat is bound, it explains the /subscribe and approval flow
• if Weixin chats are already bound, it shows the bound count and how to add another chat

This release also moves the remaining bare Chinese placeholder in the Weixin panel into the English, Chinese, and Japanese locale files.

3) Headless streaming and live work reconciliation were hardened

This release continues the v0.4.10 work on headless runtime visibility, but with a narrower bug-fix focus.

The Web streaming reducers now preserve terminal reply sessions more carefully, bind pending placeholders more conservatively, dedupe placeholder stream entries, and avoid moving a completed reply session back into a non-terminal phase. These changes reduce the chance that Codex or Claude headless output appears to reset, disappear, or stay incorrectly live after the canonical reply has already arrived.

Key improvements:

• pending placeholders are only rebound when they are still safe to bind
• completed or failed reply sessions are protected from accidental phase regression
• stream-id promotion and canonical reply reconciliation carry cached text and activities more consistently
• actor-scoped streaming cleanup avoids removing real activity timelines too early
• focused reducer tests now cover the edge cases that previously caused stale or unstable streaming UI

4) Runtime Dock state is more coherent for both PTY and headless actors

v0.4.11 clarifies the Runtime Dock ring-state model.

The ring tone calculation was extracted into a dedicated helper and simplified to shared state categories: stopped, ready, queued, active, and attention. That makes the visual state model less tied to headless-only stream phases and better suited to both PTY and headless actors.

The daemon-side runtime projection was also tightened. When an actor disappears from the runtime snapshot, the actor activity thread now emits a stopped entry into the ledger so the Web frontend can clear stale working halos and live indicators instead of relying only on in-memory activity broadcasts.

Key improvements:

• Runtime Dock state mapping now covers PTY and headless actors through the same helper
• stale working halos are cleared when actors disappear from runtime snapshots
• actor.activity ledger append failures are logged instead of silently ignored
• Web SSE/runtime projections now reduce sidebar and dock state drift after lifecycle changes

5) Actor and chat surfaces received targeted UX fixes

Several smaller Web-facing improvements are included in this release.

The actor edit modal now opens more reliably with the actor's stored runtime/profile state instead of defaulting to the wrong custom/PTY view. The chat composer mention menu now shows actor display labels and secondary IDs where useful, making @ suggestions easier to scan in groups where actor IDs and display names differ. The mention preview can also be closed with Escape.

Key improvements:

• actor edit state sync is more faithful for profile-backed and custom actors
• mention suggestions show display labels while preserving actor IDs
• Escape closes the mention preview
• composer behavior keeps the existing send and resize behavior intact

6) CLI, contracts, and IM edge cases were tightened

v0.4.11 also includes a set of smaller correctness fixes that reduce confusing failure modes.

The CLI daemon fallback path now distinguishes real daemon unavailability from explicit daemon rejections, so local fallback does not accidentally bypass a daemon-side error. EventKind documentation parity is now checked by tests. Weixin configuration canonicalization received additional route-level and adapter-level coverage, including empty and legacy account fields.

Key improvements:

• daemon rejections are returned as daemon rejections instead of silently falling back to local behavior
• EventKind documentation parity has explicit test coverage
• Weixin config canonicalization is covered in Web route tests
• Weixin context-token and outbound behavior have broader adapter coverage
• the release range adds tests across CLI daemon fallback, actor lifecycle, Web SSE projection, streaming reducers, runtime dock items, and Weixin IM flows

v0.4.10

CCCC v0.4.10 Release Notes

v0.4.10 expands headless runtime support beyond Codex, improves live runtime visibility in the Web product, hardens startup and delivery flows, and continues smoothing reply, preview, and activity behavior across the collaboration stack.

Highlights

1) Headless runtime support was generalized beyond Codex

The most important architectural step in v0.4.10 is the move from a Codex-specific streaming path to a broader headless runtime model.

Claude now joins Codex as a structured headless runtime, and the daemon, Web, and MCP layers now speak in more consistent headless terms. This makes runtime behavior easier to reason about and removes a growing amount of special-case handling that had accumulated around the original Codex path.

Key improvements:

• Claude headless runtime support was added alongside the generalized headless pipeline
• daemon and Web runtime plumbing were aligned around shared headless concepts
• runtime session handling, previews, and projections now behave more consistently across supported headless actors

2) Web runtime visibility and live trace UX improved substantially

v0.4.10 includes a broad pass on the Web chat and runtime surfaces, especially for streaming and headless sessions.

Runtime Dock behavior, compact activity timelines, grouped runtime inspectors, and preview surfaces were refined so operators can understand what a running actor is doing without losing message continuity. Message reconciliation and canonical reply transitions were also tightened so activity bubbles and final replies coexist more predictably.

Key improvements:

• richer runtime previews and live trace presentation in chat and actor views
• better activity persistence during streaming-to-canonical reply transitions
• cleaner composer behavior, text scaling alignment, and per-message identity rendering
• more coherent runtime controls and grouped runtime inspection flows

3) Delivery and startup reliability were hardened across PTY and headless actors

This release closes a long list of runtime edge cases that previously showed up as missing replies, unstable startup state, or mismatched delivery semantics.

That includes continued PTY hardening, better fallback behavior for headless replies, and a fix for an important automation gap where automation-generated system.notify events could reach the inbox without being injected into running headless agents.

Key improvements:

• fixed headless reply and fallback-flow regressions
• improved startup-state projection and delivery stabilization across runtime types
• hardened PTY teardown and related lifecycle behavior
• fixed missed headless injection for automation-generated system.notify events
• fixed group start/pause button UI not updating due to stale runtime_status in the frontend store
• resolved additional unread/index and message-parity edge cases

4) IM bridge and integration support continued to mature

v0.4.10 also expands and stabilizes the IM integration layer.

Weixin sidecar support was refreshed and validated more broadly, while adapter behavior and mention handling in other IM paths received further cleanup. This keeps the bridge layer moving toward the same reliability standard as the daemon and Web surfaces.

5) CI and release verification were tightened

The release pipeline and smoke coverage were strengthened to catch long-tail failures earlier.

Timeout coverage was expanded, pytest-timeout was introduced into smoke paths, and release checks were tightened so packaging and tag/version alignment are validated more explicitly.

v0.4.9

CCCC v0.4.9 Release Notes

v0.4.9 builds on v0.4.8 with significant daemon-side reliability work, a new IM bridge, and a broad round of Web and operator-surface improvements.

Compared with v0.4.8, this release unifies actor launch resolution, adds assistive-job truth boundaries for pet and context flows, introduces the WeChat (Weixin) IM bridge, refines presentation workflows, and includes a new text-size accessibility control for the Web UI.

Highlights

1) Actor launch resolution and pet runtime sync were unified

The most impactful daemon change in v0.4.9 is a unified actor launch pipeline.

Actor add, update, lifecycle, and runtime operations now follow a single resolution path with consistent async-result semantics. Group lifecycle start/stop flows share the same actor-status tracking, and the pet runtime gained explicit sync with group settings (including desktop-pet enablement). A new async_result contract formalizes accepted/completed/queued signaling across the daemon IPC surface.

Key improvements:

• actor add/update operations use a shared resolution pipeline with preflight validation
• group start/stop reliably awaits per-actor results instead of fire-and-forget
• pet runtime state tracks desktop-pet group settings and syncs on change
• execution queues enforce stricter ordering guarantees
• MCP dynamic capability tools reflect real-time actor state

2) Truth boundaries were tightened across pet and context flows

v0.4.9 introduces an assistive-jobs layer that enforces canonical readback for task and context writeback paths.

Pet review scheduling was refactored from a monolithic scheduler into distinct job kinds (review, profile refresh) with explicit trigger classification. Context operations now distinguish accepted versus completed status, and pet profile refresh completes only on real assistive outputs rather than fire-and-forget.

Key improvements:

• pet review and profile jobs require verified completion before marking done
• context sync and group-space writeback report accepted vs. completed separately
• immediate pet reviews flush synchronously instead of entering the timer queue

3) WeChat (Weixin) IM bridge

v0.4.9 adds the WeChat bridge as a first-class IM adapter alongside Telegram, Slack, Discord, Feishu/Lark, and DingTalk.

The implementation includes a Node.js sidecar for the WeChat desktop protocol, a CLI login/logout flow, QR-code-based authentication in the Web UI, and daemon routes for bridge lifecycle management. The Weixin adapter follows the same bridge contract and bind-key authorization model as the existing adapters.

4) Presentation workflow and outbound delivery were refined

The presentation viewer gained inline web-preview support, topic-aware slide navigation, and improved full-screen behavior. Outbound delivery through the IM surface now handles richer content types, and the chat tab integrates a split-layout mode for simultaneous conversation and presentation viewing.

5) Web Pet task advisor became local-first

The Web Pet task proposal pipeline was reworked to run a local task advisor that evaluates evidence before surfacing proposals. This reduces noise from speculative suggestions and makes the pet's task-related nudges more reliable. The idle-standup suppression and silence-activity filters also improved, so the pet stays quiet when there is genuinely nothing to act on.

6) Web UI polish and accessibility

A broad round of Web improvements landed in this release:

• Text size control: a new three-tier text-scale selector (90% / 100% / 125%) in the header rail and mobile menu, persisted per-browser via localStorage.
• System theme icon: the system-theme toggle now uses a monitor/display icon instead of the previous terminal icon, improving clarity.
• Mobile theme cycling: the mobile menu now cycles through light → dark → system instead of binary toggling.
• Group sidebar extraction: the sortable group list was extracted into a standalone component with optimized chunk splitting.
• Runtime visibility controls: peer and pet tabs gained explicit show/hide toggles based on actor composition.
• Layout and polling: follow-bottom logic was removed in favor of explicit auto-follow heuristics, and group-space polling behavior was simplified.
• Automation snippet catalog: builtin snippet overrides were separated into a distinct catalog contract for cleaner customization.

v0.4.8

CCCC v0.4.8 Release Notes

v0.4.8 makes Web Pet materially more useful, tightens task and messaging behavior across Web and MCP, improves actor/runtime visibility, hardens projected browser flows, and adds another round of platform polish.

Highlights

1) Web Pet became a real attention assistant

Review scheduling, reminder generation, decision handling, and the Web Pet panel/bubble flow were substantially reworked so the system can surface clearer reminders, better suggestions, and more stable task proposals from live group state.

2) Task workflow handling is more reliable

Task handling across Web and MCP is more consistent, peer-created MCP tasks now default to self-assignment, and status/update flows are less fragile in day-to-day use.

3) Actor and runtime state are easier to trust

The actor list now exposes richer terminal-derived working state, startup paths gained stronger runtime preflight checks, and daemon transport diagnostics are surfaced more clearly for operators.

4) Browser-backed and auth flows were hardened

Projected browser support took a meaningful step forward in this release.

Browser-backed sessions used for embedded views and NotebookLM / Google auth are more robust, with better reconnect and compatibility behavior across the supported desktop environments.

5) Messaging, search, and Web behavior were cleaned up further

This release also includes a broad reliability pass across the Web and daemon surfaces.

v0.4.7

CCCC v0.4.7 Release Notes

v0.4.7 makes Presentation a first-class shared workspace, tightens task workflow handling across Web and MCP, adds Web branding controls, and cleans up several runtime and operator-facing rough edges.

Highlights

1) Presentation became a real shared workspace

The main change in v0.4.7 is the new Presentation surface.

Groups can now publish and manage slot-based presentation content through the daemon, Web UI, and MCP layer. The Chat surface also gained a dedicated Presentation rail and viewer flow, so shared artifacts no longer have to live only as chat text.

2) Interactive browser-backed views landed

v0.4.7 also adds the browser-surface path for Presentation.

This makes it possible to handle harder Web content in a more useful way than a simple static preview. The viewer lifecycle and controls were refined as part of the same work, including better handling for refresh, fullscreen, replacement, and URL entry.

3) Chat and Presentation are now connected by references

Presentation references were added to the message flow, which means chat can point back to a specific Presentation view instead of relying on vague text-only handoffs.

Snapshot and compare behavior were also added so the quoted view can be preserved more clearly when users and agents are discussing live content.

4) Task workflow handling is stricter

This release also improves the task workflow layer.

Task state handling in the Web UI is more structured, context/task workflow logic is tighter, and MCP-side task update compatibility was improved so task status changes are less fragile in practice.

5) Web polish and branding moved forward

v0.4.7 includes a broad Web polish pass as well.

Highlights include:

• Web branding controls for product name and logo assets
• stronger group/context/unread refresh behavior
• general message, panel, and console usability cleanup

6) Runtime and startup behavior were cleaned up further

This release also includes smaller but important runtime fixes.

Notably, the default cccc entry path now respects top-level --host / --port overrides throughout supervised Web startup and restart, and Kimi runtime defaults were updated to match the current preferred path.

v0.4.6

CCCC v0.4.6 Release Notes

v0.4.6 builds on v0.4.5 with a broader set of improvements than a pure prompt/preset polish release.

Compared with v0.4.5, this version extends IM bridge coverage, tightens Web-side context and cache behavior, introduces the first built-in role preset workflow, and hardens startup/shutdown behavior further across Windows and the supervised Web runtime.

Highlights

1) WeCom IM bridge support is now real and documented

The biggest functional addition in v0.4.6 is WeCom bridge support.

Key changes:

• a dedicated WeCom adapter was added instead of trying to force everything through the older bridge path
• Web-side IM bridge settings were extended so WeCom can be configured from the same operator surface as other bridge providers
• authentication and readiness behavior for the bridge were repaired and covered by targeted tests
• the docs now include a dedicated WeCom guide and screenshots for the operator flow

This matters because v0.4.5 still treated IM bridge support as narrower and more uneven in practice. v0.4.6 makes WeCom a real supported path instead of a partial edge lane.

2) Web context and cache behavior are tighter and less wasteful

v0.4.6 also improves how the Web surface reads and refreshes shared control-plane state.

Key improvements:

• actor and context route caching is more deliberate and more thoroughly tested
• cache invalidation after writes is less fragile, which reduces stale readback after actor/context updates
• related API/client/store coverage was expanded significantly so the Web state layer is less likely to drift silently
• surrounding settings and control surfaces were cleaned up so context-related interactions behave more predictably

This is not a flashy feature, but it is a meaningful quality improvement over v0.4.5 because it reduces a class of “the write succeeded but the UI still feels stale or noisy” problems.

3) Built-in role presets and prompt discipline landed

This release introduces the first built-in role preset workflow in the Web actor surfaces and strengthens the default collaboration guidance around those roles.

Highlights:

• built-in role presets were added for the first-wave roster, including planner, implementer, reviewer, debugger, explorer, and related roles
• preset application now gives actors a faster way to start from a strong role note instead of writing everything from scratch
• the prompt/help surface was tightened so startup guidance stays lean while richer discipline lives in the longer-lived help/preset layers
• planning, implementation, review, and debugging guidance are now sharper about things like existing-code leverage, full-diff-first review, regression thinking, and one-pass blast-radius cleanup

Relative to v0.4.5, this is the biggest day-to-day agent-behavior improvement in the release.

4) Windows and runtime lifecycle handling were hardened again

v0.4.5 already improved startup and shutdown behavior. v0.4.6 continues that line with another pass of runtime hardening.

Important changes:

• Windows shutdown cleanup was tightened further so lingering process/lifecycle edge cases are handled more reliably
• daemon/Web supervised runtime ownership and cleanup paths were hardened with additional lifecycle coverage
• Web readiness checks now tolerate more real failure modes, including OSError and HTTPException, instead of surfacing brittle behavior
• process-path handling and related platform-sensitive helpers received more validation, especially around mocked Windows path resolution and runtime probing

This makes v0.4.6 a stronger operational release than v0.4.5, especially if you are running CCCC on Windows or frequently exercising stop/start/restart flows.

5) Quality bar and verification

Beyond the visible changes above, v0.4.6 also includes:

• additional tests around Web cache behavior and stores
• stronger coverage for IM bridge startup/config flows
• targeted prompt-default and role-preset tests so the new guidance surfaces are less likely to regress silently
• follow-up lint/typecheck cleanup after the role preset work landed

In short, v0.4.6 is not just “the preset release.” It is the release that combines:

1. WeCom bridge support
2. better Web context/cache behavior
3. the first built-in role preset workflow
4. another round of Windows/runtime hardening

relative to the v0.4.5 baseline.

v0.4.5

CCCC v0.4.5 Release Notes

v0.4.5 consolidates more of the everyday workflow into the Web UI, simplifies remote access handling, and hardens runtime startup and shutdown behavior across Windows and POSIX environments.

Highlights

1) Web Pet replaced the old desktop pet surface

The old standalone desktop pet implementation was removed and its useful behavior was moved into the Web UI.

Key improvements:

• the pet now lives directly inside the Web interface instead of requiring a separate desktop/Tauri surface
• reminder bubbles and panel actions are more interactive, including direct jump targets such as opening chat or the relevant task
• the pet panel now shows task progress and smarter hints instead of only generic reminders
• agent tabs can surface the last terminal output after an agent stops, which makes “what just happened?” easier to answer without reopening logs

2) Web access and reachability are clearer

v0.4.5 continues the Web-access cleanup started in the previous line and makes the remote-access story more coherent in practice.

Highlights:

• the Web Access panel is better aligned with real operator goals such as local-only access, LAN/private access, and externally exposed access
• supervised Web restart/apply flows are clearer from the main cccc session
• the Web health endpoint is now publicly reachable, which makes health checks and external probing simpler
• surrounding UI wording and styling were refined so the current access posture is easier to understand at a glance

3) Runtime lifecycle behavior was hardened on Windows and POSIX

This release includes several fixes in the startup and shutdown path that materially improve day-to-day reliability.

Important changes:

• Windows Codex MCP setup is more robust and now prefers a stable absolute cccc entrypoint instead of trusting weaker path assumptions
• stale or misleading Codex MCP entries are less likely to be treated as “already installed”
• supervised Web child shutdown handling was tightened so Ctrl+C and restart flows behave more predictably
• POSIX background Python startup now preserves the active virtualenv interpreter path instead of resolving it to the system Python and silently losing the environment

4) The runtime support surface is less fragile

Beyond startup mechanics, v0.4.5 reduces a few sharp edges in the runtime control plane.

This includes:

• fail-fast MCP startup checks are scoped more carefully so they do not over-block unrelated lifecycle flows
• IM bridge child-process startup paths now follow the same safer background-process rules as the daemon/Web stack
• cross-platform process handling was refactored and validated more thoroughly in tests

v0.4.4

CCCC v0.4.4 Release Notes

v0.4.4 is a small polish release over v0.4.3.
It focuses on making the settings experience clearer, reducing UI/config friction, and aligning safer defaults with actual operator intent.

Highlights

• Guidance is now the default first-open tab in group settings, matching the visible tab order instead of dropping users into Automation first.
• Settings terminology now more clearly separates built-in automation from user-authored rules and snippets.
• The Delivery panel was simplified around the only user-facing behavior that still matters there: whether successful PTY delivery should auto-advance the read cursor.
• The Web settings UI no longer exposes min_interval_seconds, while daemon/API compatibility for that low-level delivery throttle remains intact.
• Actor idle alerts now default to 0 (off) for new/default/reset paths, without silently changing existing group configs that already store a value.

v0.4.3

CCCC v0.4.3 Release Notes

v0.4.3 is a major refinement release over v0.4.2.
It tightens the core collaboration model, reduces prompt and control-plane drift, hardens Windows and runtime integration, and makes long-running group operation more predictable across Web, MCP, IM, and Group Space workflows.

Highlights

1) Prompt, help, and role guidance were re-layered

The guidance stack was simplified so stable startup rules, live runtime guidance, and actor-specific notes no longer compete with each other.

Key changes:

• the startup prompt is slimmer and more focused on durable operating rules
• live runtime guidance now belongs to cccc_help, so optional capability-specific instructions appear only when actually relevant
• actor role notes are now canonically stored in the group help document @actor blocks instead of leaking into working-state fields
• agent working stance and role guidance are now more clearly separated, which reduces confusion between long-term role intent and current execution context

2) Context and task authority semantics were hardened

Several core collaboration boundaries were tightened so the system behaves more predictably under real multi-actor usage.

This includes:

• task.restore now follows a clear archived-only precondition and matches the same authority model as the other task-mutating operations
• peers can no longer mutate arbitrary unassigned tasks; task control is limited to the actor actually responsible for the work
• actor-owned agent_state semantics are now aligned across docs, daemon behavior, MCP tooling, and Web expectations
• system-driven task-to-working-state synchronization remains in place where it materially reduces manual upkeep cost

3) Group Space and memory workflows became more coherent

v0.4.3 significantly improves the operational behavior of notebook-backed workflows.

Key improvements:

• work-lane and memory-lane status now track the current binding more accurately instead of leaking stale sync residue after unbind/rebind cycles
• NotebookLM-related runtime guidance is injected only when the relevant capability is actually active
• the login, bind, use, unbind, and disconnect flow is cleaner from both the daemon and Web state-model perspective
• memory and daily-memory coordination stays intentionally connected, but the surrounding guidance and runtime status are now clearer

4) Runtime support and Windows robustness were strengthened

This release continues the push toward a more disciplined and supportable runtime surface.

Highlights:

• Windows MCP reliability was hardened, including runtime-context resolution and stdio/encoding robustness
• the officially supported runtime surface was narrowed and clarified to the runtimes CCCC can set up and operate reliably
• standalone Web startup now follows the same local-first binding model as the main CLI entrypoint
• release verification was tightened to better match the project's claimed Linux, macOS, and Windows support surface

5) Operator-facing surfaces saw broad stabilization

A large amount of polish landed across the everyday control surfaces used by operators and agent teams.

Notable areas:

• user-scoped actor profiles now work end to end across daemon, Web, and MCP paths
• IM integration continued to improve, especially around DingTalk sender identity, revoke behavior, @ targeting, and streaming fallback behavior
• blueprint export/import portability was fixed so round-trips keep the intended portable fields
• Web settings, modal behavior, overflow handling, context presentation, and translation coverage were substantially cleaned up
• global browser surfaces were trimmed so scoped users see less irrelevant machine-global data by default

Validation Summary

The 0.4.3 line was stabilized through multiple release candidates and targeted regression work across the highest-risk areas, including:

• context and task authority rules
• role-notes source-of-truth handling
• Group Space bind/unbind status correctness
• Windows MCP stability
• scoped actor profiles and permission boundaries
• IM bridge revoke and delivery behavior
• blueprint round-trip portability

Upgrade Notes

From v0.4.2, this is still a drop-in minor upgrade for most deployments.
No explicit data migration step is required.

Recommended post-upgrade checks:

1. restart the daemon and Web once to ensure all runtime surfaces are on the new prompt/help/control-plane behavior
2. if you use custom help or prompt overrides, re-check your local overrides against the new guidance layering
3. if you use Group Space or NotebookLM workflows, verify current lane bindings and status after the upgrade
4. if you use scoped users, actor profiles, or remote/browser access, verify one non-admin path end to end

desktop-v0.0.3

Full Changelog: desktop-v0.0.2...desktop-v0.0.3