v0.4.4

- Wire credential vault into main flows (dashboard save, CLI save, kernel boot) — API keys now stored in AES-256-GCM vault with dual-write to secrets.env for backward compat
- Fix cron channel delivery that was a no-op — Channel, LastChannel, and Webhook variants all deliver now
- Propagate cron delivery failures to scheduler (one-shot jobs not removed on failure)
- Add credential resolver (vault → dotenv → env var) to kernel for unified secret resolution
- Add remove_from_vault() to CredentialResolver
- Bump to v0.4.4

v0.4.3

Bug Fixes

• Open links in new tab (#612): External links in markdown agent responses now open in a new tab with target="_blank".
• Browser hand install (#611): Homebrew "already an App at" message now correctly recognized as success instead of failure.
• "FREE is not a valid model" (#610): Added "free", "openrouter/free", and "free-reasoning" aliases for OpenRouter free-tier models.
• WhatsApp drops media (#605): Gateway now handles images, voice notes, videos, documents, and stickers with descriptive placeholders instead of silently dropping them.
• WhatsApp sender metadata (#597): Sender identity (phone, name) now flows end-to-end from API → kernel → system prompt. Agents know who sent each message.
• Config overwrite warning (#578): Web dashboard shows a warning toast when saving an API key triggers an auto-provider-switch.
• Linux libssl error (#582): OpenSSL is now statically compiled via vendored feature — no runtime libssl dependency.

Enhancements

• Minimax global URL (#576): Default URL switched to global endpoint (api.minimax.io/v1). China users can override via [provider_urls] in config.toml.

v0.4.2

Bug Fixes

• LoopGuard poll detection (#603): Removed fragile cmd.len() < 50 heuristic. Poll detection is now purely keyword-based — long kubectl/docker commands are correctly identified.
• Custom model provider display (#581): Model switcher dropdown now shows provider:model format instead of just the display name.
• Telegram typing indicator (#571): Typing indicator now refreshes every 4 seconds continuously during LLM processing, instead of expiring after 5 seconds.
• "No agent selected" error (#569): Agents created via API are now immediately registered in the channel router's name cache.
• Tool calls denied by approval (#537): Denial message now includes guidance to use auto_approve = true in config.toml or --yolo flag.
• WhatsApp sender metadata (#597): MessageRequest and PromptContext now have sender_id/sender_name fields for identity-aware agents.
• LLM auth boot failure (#572): Already fixed in v0.4.0 (auto-detect fallback). Commented for users on older versions.

Enhancements

• NVIDIA NIM provider (#579): Added as OpenAI-compatible provider with 5 models (nemotron-70b, llama-3.1-405b/70b, mistral-large, nemotron-4-340b). Set NVIDIA_API_KEY to use.
• YOLO mode (#573): openfang start --yolo auto-approves all tool calls. Also configurable via auto_approve = true in [approval] section.
• Skill output persistence (#596): Tool/skill output cards in dashboard now default to expanded instead of collapsed, keeping results visible.

v0.4.1

Bug Fixes

• Memory recall loop (#583): build_memory_section() no longer tells the model to call memory_recall when memories are already injected into the prompt. Models now use provided memories directly.
• Raw errors in channels (#584): Channel bridge sanitizes LLM error messages before sending to users. Rate limits, auth errors, and JSON dumps are replaced with clean user-friendly messages.
• HAND.toml format (#588): Parser now accepts both flat root-level format and the documented [hand] table format.
• Token quota exceeded (#591): Pre-emptive quota-aware compaction triggers before LLM calls when session token count approaches remaining hourly quota headroom.
• log_level config (#594): log_level in config.toml now takes effect. Priority: RUST_LOG env var > config.toml log_level > default "info".
• Max iterations error (#599): Error message now includes guidance on configuring [autonomous] max_iterations in agent.toml.
• Config backup (#578): config.toml is backed up to config.toml.bak before any auto-rewrite (provider key save, config set/unset).

Enhancements

• Default model in Web UI (#593): Spawn wizard fetches default_provider/default_model from /api/status instead of hardcoding groq/llama-3.3-70b-versatile.

v0.4.0

v0.4.0 — Community Issue Batch

Fixes:
- Cron jobs can now run workflows directly by ID or name (#485)
- Auto-load workflow definitions from ~/.openfang/workflows/ on startup (#486)
- Matrix adapter: auto-accept invites, mention detection, DM/group detection, skip old messages (#565)
- Cross-channel default recipient via default_chat_id/default_channel_id config (#374)
- Telegram reply-to-message context forwarded to agents (#564)
- Configurable lifecycle_reactions flag per channel (#563)
- Telegram token auto-detection in bot_token_env field (#505)
- WhatsApp gateway ESM module fix (#511)
- Slack thread auto-response tracking (#560)
- Workflow CRUD API, CLI commands, and dashboard UI (#512)
- Dashboard username/password authentication with HMAC session tokens (#456)
- Added openrouter/hunter-alpha model (#568)

v0.3.49

v0.3.49 — Community Issue Batch #2

Fixes:
- WhatsApp Baileys makeWASocket error — ESM static imports (#511)
- Telegram bridge Unauthorized when raw token in config (#505)
- Slack thread auto-response without re-mentioning bot (#560)
- Workflow update/delete API, CLI, and dashboard (#512)
- Dashboard username/password login with HMAC sessions (#456)
- GLM-4.7 already in catalog, documented (#530)

v0.3.48

v0.3.48 — Community Issue Fixes

Bug Fixes

• Fix Chromium detection for Browser hand — now checks env vars, PATH, well-known install paths, and Playwright cache (#549)
• Fix Gemini 2.5 Flash empty responses — handle thinking model thought: true parts correctly (#550)
• Fix Twitter hand textbox not editable — API key inputs are now proper password fields (#551)
• Fix Slack threading — extract thread_ts, implement send_in_thread(), add was_mentioned metadata (#552)
• Fix EOF parse error classified as non-retryable — empty response bodies now retry as Overloaded (#535)
• Fix tool calls still showing as text — add 4 new recovery patterns: plugin blocks, Action/Action Input, bare name+JSON, tool_use tags (#537)
• Fix WhatsApp gateway silent disconnects — all disconnect reasons except loggedOut now auto-reconnect with backoff, auto-connect on startup if credentials exist (#555)
• Fix OPENFANG_API_KEY env var not picked up — works in both kernel and CLI as fallback (#557)

Features

• Add Qwen Code CLI as LLM provider with 3 models, auth detection, and full streaming support (#558)

Stats: 2,103 tests, 0 clippy warnings, 17 files changed

v0.3.47

Fix 11 Community Issues

Bug Fixes

#532 — Agent tool filtering — Only send tools declared in agent.toml to the LLM, not all available tools. Massively reduces token usage for agents with specific tool sets. Backwards compatible (empty tools list = all tools).

#531 — Streaming display bug — "streaming" text no longer leaks into chat responses. Fixed phase event handling in dashboard UI so tool-use loops don't show lifecycle signals as content.

#528 — Telegram image MIME detection — Added magic-byte detection (JPEG/PNG/GIF/WebP) so Telegram's application/octet-stream Content-Type no longer breaks vision. Three-tier detection: trusted image/* header → magic bytes → URL extension.

#527 — Custom provider misidentification — Explicit provider names in config are now preserved instead of being overridden by auto-detection. Fixes Tencent/custom base_url setups.

#506 — Gemini 3.x thoughtSignature — Captured at part level for both text and functionCall parts. Fixes INVALID_ARGUMENT: Function call is missing a thought_signature on Gemini 3.x thinking models.

#507 — Telegram group message drops — Added sender_chat fallback when from is absent, and populated was_mentioned metadata so GroupPolicy::MentionOnly works for Telegram groups. Debug logging on all dropped updates.

#519 — Trigger reassignment after restart — Triggers now survive agent restarts via take/restore mechanism, mirroring the existing cron job reassignment pattern.

#523 — Hand re-activation tool profile — tool_allowlist and profile are now correctly set from hand definition on re-activation, preventing tool surface drift.

#524 — Hand readiness API — Enriched with active, degraded, and per-requirement optional fields. Browser's chromium requirement marked optional since Playwright can auto-install it.

#515 — Claude Code agent permissions — Added skip_permissions config (default: true) so Claude Code agents work in daemon mode without blocking on terminal approval prompts.

#509 — Proactive channel_send — Added thread_id parameter for Telegram topic targeting and file_path for local file attachments with MIME detection.

Stats

• 27 files changed, +1730/-252 lines
• 2074 tests passing, 0 clippy warnings
• 14 crates, all clean

v0.3.46 — Community PR Batch

Community Contributions

11 PRs reviewed, labeled, commented, and implemented from scratch following our architecture. All PR authors credited.

Bug Fixes

• #438 — IME composition guard prevents Enter from sending during CJK input (@pandego)
• #433 — Default User-Agent: openfang/0.3.46 on all LLM drivers — fixes 403s from Moonshot/Qwen (@ozekimasaki)
• #417 / #392 — Default token quota changed to unlimited (was 1M/hour, caused immediate quota errors on fresh installs) (@f-liva, @cryptonahue)
• #410 — Safe string slicing in channel bridge (9 instances) + desktop server shutdown race condition (@hobostay)
• #413 / #275 — Embedding driver respects provider_urls config + auto-selects correct model per provider (@castorinop, @woodcoal)
• #464 — Wizard generates proper multi-line TOML strings for system_prompt with escaping (@citadelgrad)

New Models & Providers

• #419 / #480 / #439 — Added Z.AI Coding models (glm-5-coding, glm-4.7-coding), Kimi for Code (Anthropic-compatible), fixed Moonshot base URL, added kimi-k2.5-0711 alias (@shipdocs, @skeltavik, @modship)

Internal

• XML-attribute tool call recovery (Pattern 9) for Groq/Llama models that emit <function name="..." parameters="..." />
• 187 models, 40+ providers, 2040+ tests, 0 clippy warnings

Full Changelog: v0.3.45...v0.3.46

v0.3.45 — Trading Hand + Bug Fixes

New: Trading Hand (8th Bundled Hand)

Full autonomous trading agent built from extensive market research on what traders actually need in 2026.

Architecture

• HAND.toml (740 lines) — 12 configurable settings, 10 dashboard metrics, 470-line system prompt with 8-phase pipeline:

  1. State Recovery — restore position/context on restart
  2. Portfolio Setup — read config, validate risk parameters
  3. Market Intelligence Scan — gather data from free sources (Yahoo Finance, FRED, Fear & Greed Index)
  4. Multi-Factor Analysis — technical (RSI/MACD/Bollinger/VWAP/ATR), fundamental, sentiment, macro
  5. Adversarial Bull/Bear Debate — structured debate with entry zones, stop-loss, take-profit, R:R ratios
  6. Risk Management Gate — circuit breakers, position sizing caps, drawdown limits, correlation checks
  7. Trade Execution — three modes: analysis-only, paper trading, live via Alpaca API
  8. Analytics & Reporting — structured tables for dashboard metrics

• SKILL.md (937 lines) — Expert reference material:

  • RSI/MACD/Bollinger/VWAP/ATR formulas with interpretation guides
  • 22 candlestick pattern definitions
  • Position sizing + Kelly criterion + Value-at-Risk calculations
  • Full Alpaca API reference (discovered they have an official MCP server)
  • Free financial data sources catalog
  • Superforecasting calibration guide
  • Cognitive bias mitigations for trading decisions

Settings

• trading_mode (analysis/paper/live), risk_per_trade (default 2%), max_portfolio_pct (10%), watchlist, alpaca_api_key, preferred_timeframe, report_frequency, max_daily_trades, stop_loss_atr_multiplier, take_profit_atr_multiplier, circuit_breaker_drawdown, rebalance_interval

Live-Tested Behaviors

• Refuses to bypass risk management (100% portfolio / no stop-loss = rejected)
• Calculates position sizing correctly including cap violation detection
• Produces adversarial bull/bear debates with concrete price levels
• Generates structured Phase 7 reports with dashboard-ready tables
• Pause/resume/deactivate lifecycle works correctly

Bug Fixes

• #503 — Streaming <think> tag leak: Created StreamingThinkFilter that processes text deltas incrementally, buffering reasoning content so it never reaches the client during streaming. Handles partial tags split across chunks. 17 new tests.
• #504 — Cron jobs orphaned after agent deletion: kill_agent() now calls remove_agent_jobs() on the cron scheduler and persists the change to disk. 3 new tests.

Stats

• 2031 tests, 0 clippy warnings, 8 bundled hands, 184 models, 40 providers

Full Changelog: v0.3.44...v0.3.45