Changelog — Features

New Features

• Session Intelligence Digest: When Claude finishes a task and enters wait_for_instructions, the /loop watchdog evaluates the session risk score. Medium-risk sessions (score ≥16) receive an enriched digest card showing file heat map, test cycle sequence, bash failure rate, and a risk assessment. High-risk sessions (score ≥31) auto-trigger T4 QA verification.
• Digest Card Buttons: Medium-risk cards offer three actions: [▶ Continue] (resume session), [🔍 Run QA Check] (manually trigger T4 verification), and [⏹ End Session] (stop Claude). High-risk cards show [🔍 QA in Progress...] as T4 runs automatically.
• getDigestSnapshot() API: New method on SessionIntelligenceEngine returns a structured snapshot with risk score, file heat map (top 5 by edit count), test cycle sequence (last 10), bash health metrics, and scope drift detection.

Improvements

• Configurable Thresholds: Three new config fields control digest behavior: SESSION_DIGEST_ENABLED, SESSION_DIGEST_MIN_RISK (default 16), and SESSION_DIGEST_AUTO_QA_THRESHOLD (default 31). Startup validation warns when thresholds are inverted.
• TCVF Dependency Warning: Startup now warns when SESSION_DIGEST_ENABLED=true but TCVF_ENABLED=false — digests require TCVF intelligence data to compute risk scores.
• Idempotent Digest Delivery: Only one digest card per MCP wait cycle. The digestSentForWaitIds set prevents duplicates and is cleaned up in all 4 disposal paths.

Technical

• sessionIntelligence field added to GET /mcp/status response for external watchdog consumption.
• session_digest type added to POST /notify with threshold gating, idempotency, and per-waitId tracking.
• Idempotency marked after successful callback (not before try) to prevent poisoning on transient Telegram failures.
• 12 new tests covering snapshot generation, notify flow, idempotency, and threshold behavior.

New Features

• MCP Heartbeat Watchdog (Layer 2.5): An external /loop watchdog that runs in the developer's own Claude Code session and monitors the keep-alive connection every 15-20 minutes. When problems are detected, Telegram alert cards are sent directly to the user — not terminal output. Three alert types: bridge-down (🔴), no active MCP wait (🟡), and stale heartbeat ping (🟠).
• GET /mcp/status Endpoint: Rich health-check returning bridge liveness, MCP wait state, ping freshness, and configuration values. Used by the /loop watchdog and available for external monitoring.
• POST /notify Endpoint: Internal notification endpoint that accepts watchdog alert types and routes them to Telegram. 60-second throttle prevents alert storms. Validated against a type whitelist.
• Watchdog Telegram Cards: Three card templates with actionable buttons. [Restart Session] shuts down the PersistentCliBridge. [Check Status] shows current bridge state inline.

Improvements

• Liveness Ping Interval: A setInterval inside handleMcpWait() updates lastPingSentAt every 5 seconds. If the event loop hangs, the interval stops and /mcp/status reports growing lastPingAgeMs — signaling staleness.
• Configurable Endpoints: MCP_STATUS_ENDPOINT_ENABLED and NOTIFY_ENDPOINT_ENABLED config flags allow disabling either endpoint. WATCHDOG_STALE_PING_THRESHOLD_MS (default 30s) configures the stale ping detection threshold.

Technical

• Ping interval handle stored on PendingMcpWait interface for explicit cleanup in all 4 disposal paths (resolve, timeout, stale cleanup, shutdown).
• 16 new tests covering status responses, notify types, throttling, error handling, and edge cases.
• /loop command variants documented in CLAUDE.md for copy-paste usage.

New Features

• 9-Class Exploit Taxonomy: Embedded adversarial security intelligence directly into three existing CodePulse features — CommitReviewEngine, /review command, and T4 verification pipeline. Nine exploit classes detect vulnerabilities that were previously invisible: INJECTION, SECRETS, CODE_QUALITY, FAIL_OPEN, RACE_CONDITION, STATE_LEAK, BYPASS, PRIVILEGE_ESCALATION, and INPUT_VALIDATION. Zero additional API cost — the intelligence is baked into existing Haiku prompts.
• Exploit-Class Challenge Templates: T4 verification now generates targeted security challenges based on detected exploit classes. Critical classes (INJECTION, SECRETS, BYPASS) are prioritized over warning classes. Each challenge asks Claude to prove the vulnerability was actually addressed.
• Security Findings in GitHub PR Reviews: The /review command now includes structured security findings in GitHub PR review comments, with severity icons and fix suggestions.

Improvements

• Per-Project Exploit Class Isolation: In multi-project mode, exploit classes from one project cannot contaminate another project's T4 challenges. Each project has its own isolated exploit class storage.
• Single Source of Truth: VALID_EXPLOIT_CLASSES consolidated from 3 duplicated arrays into one constant, preventing future drift.
• Per-Exploit-Class Metrics: Dashboard stats endpoint now tracks finding counts per exploit class for trend visibility.
• TypeScript Clean Build: Resolved all 5 pre-existing TypeScript compilation errors. tsc --noEmit now passes with zero errors.

Technical

• 40+ new tests across 4 test files covering security findings parsing, exploit-class challenge injection, session intelligence storage, and commit review integration.
• COMMIT_REVIEW_DETAIL_ITEM template updated to show exploit class in expanded Details view.
• T4 verdict card now shows [EXPLOIT_CLASS] label on failed security challenges.
• GitHub markdown injection prevented with escapeMd() for message and fix fields.

New Features

• Built-in Auto-Updater: CodePulse now checks for updates automatically via the system tray menu. Click "Check for Updates" to download and install new versions silently. Every installer is signed with ed25519 (minisign) and verified before installation. This is the last version you need to install manually — all future updates arrive automatically.
• GitHub Actions CI/CD: Full release pipeline in the cloud. Push a v* tag and GitHub Actions builds the service exe, launcher exe, NSIS installer, signs for the auto-updater, uploads to Cloudflare R2, deploys the Worker, and creates a GitHub Release — all on a Windows runner with zero local resources needed.
• One-Command Release: release.ps1 -Version "X.Y.Z" bumps version in all 6 files, builds all components, signs, uploads, deploys, and tags in a single command.
• Selective Builds: The release pipeline detects what changed since the last release tag and only rebuilds affected components. Service-only changes skip the launcher build entirely, cutting most releases from 2 minutes to 10 seconds.

Improvements

• Version Bump Automation: All 6 version files (package.json, constants.ts, launcher package.json, tauri.conf.json, Cargo.toml, NSIS script) are bumped atomically by the release script. No more manual edits across multiple files.
• Auto-Updater Manifest: Each release generates and uploads an update.json manifest to Cloudflare R2, containing the version, download URL, and cryptographic signature. The launcher checks this endpoint on demand.
• Git Tagging: Release tags are created and pushed automatically as part of the pipeline, triggering the CI/CD workflow.

Technical

• Tauri v2 updater plugin with installMode: "quiet" (passes /S to the NSIS installer for silent upgrades).
• Updater public key embedded in tauri.conf.json; private key stored as GitHub Actions secret.
• Rust cache (Swatinem/rust-cache@v2) reduces CI build time from ~20 minutes to ~5-7 minutes on subsequent runs.

New Features

• License Tab: View your current license tier, key, and expiration directly in the dashboard. One-click upgrade to Premium.
• Help Tab: Quick-access links to documentation, support, and troubleshooting guides without leaving the app.
• Exit CodePulse: A dedicated button to cleanly stop the service and close the application in one action.

Installer Improvements

• Process Tree Cleanup: The installer and uninstaller now kill the full process tree (codepulse-service.exe, codepulse-panel.exe, CodePulse.exe) before installing or removing files, preventing file lock errors.
• Timeout Standardization: All installer timeouts normalized to 5 seconds for consistent behavior across different system speeds.
• Uninstaller File Locks: Fixed a bug where the uninstaller completed but left CodePulse.exe running, preventing manual file deletion until the process was killed.

Bug Fixes

• Fixed pricing display showing incorrect values in the installer's license activation screen.
• Fixed Telegram bot configuration wizard layout issues on smaller screens.
• Fixed 9 additional installer and launcher bugs discovered during end-to-end testing.

New Features

• The Pulse: Real-time activity tracking delivered to Telegram as concise one-line updates. See exactly which files Claude is reading, what commands it is running, and what tools it is using, without leaving your phone. Activity updates are batched intelligently to avoid notification flooding during high-frequency operations.
• Haiku Auto-Answer: Routine session queries ("what are you doing?", "status", "how far along?") are now answered by a fast Haiku model using the current session context, without interrupting Claude Code's workflow. Only direct instructions are forwarded to the active session.

Improvements

• Bidirectional Communication Reliability: Improved stdin write handling for long-running sessions. Messages are queued and delivered in order even when Claude Code is mid-operation. Added delivery confirmation in Telegram so you know your instruction reached the agent.
• Morning Briefing Formatting: Briefing messages now include per-project breakdowns when multiple projects were active overnight. Token costs are displayed with running monthly totals.
• Approval Card Context: Permission request cards now show the last 3 tool calls as context, so you can understand why Claude is requesting a particular operation without checking the full session.
• Hook Event Coverage: Added handlers for the newer Claude Code hook events including SubagentStart, SubagentStop, and ConfigChange. Subagent activity now appears in The Pulse feed.

Bug Fixes

• Fixed an issue where batch approval cards would not render correctly when more than 5 requests were grouped together.
• Fixed voice message transcription failing silently when the audio exceeded 60 seconds. Long voice messages are now split and transcribed in segments.
• Fixed session resume failing on Windows when the session ID contained certain special characters (related to Claude Code issue #3187).

Highlights

• Telegram Bot Integration: Full bidirectional communication between you and Claude Code
• Smart Auto-Approvals: Pattern-based auto-approval for trusted operations
• Batch Approval Cards: Multiple rapid-fire requests grouped into single cards
• Cost Tracking: Per-session and per-project token usage monitoring