chore(master): release 0.8.0

[github-actions]

🤖 I have created a release beep boop

0.8.0 (2026-05-30)

Features

• [AutoRL-Bench] Update DeepSearchQA split and translate task instructions to English (#1368) (ffb9491)
• 15% monthly return target — infrastructure + daily signal resampling (ea0c94f)
• 1h London session momentum — +3.17%/month unlevered, -1.1% DD, RiskMgmt-safe (49c3e7f)
• 1h SMA10/30 signal integrated into RiskMgmt live trader (314a278)
• 30min factor combo bests 1h — +3.59%/month (+54% annual) (9c35dae)
• 9 additional daily strategies — ensembles, trailing stops, day filters (376622d)
• Add 'predix evaluate' command to CLI (da3bef6)
• Add 'predix top' command + explain factor evaluation results (f2d2c6c)
• Add 6 new CLI commands - all scripts integrated with local LLM (a712a3d)
• add a rag mcp in proposal (#1267) (dc7b732)
• add a web UI server (#1345) (1439548)
• Add advanced ML models (Transformer, TCN, PatchTST, CNN+LSTM) (e1e86e1)
• Add AI Strategy Builder (StrategyCoSTEER) - Closed Source (a5815bb)
• Add beautiful CLI welcome screen for GitHub README (e6e5b1a)
• Add CLI model selection (local vs OpenRouter) (5ab4db5)
• Add complete ML pipeline with graceful degradation (closed source) (5a3ee7e)
• add daily log rotation, llama health wait, factor auto-fixer, and README updates (d2388d6)
• Add factor code and description to saved results (a07b5f5)
• Add GitHub infrastructure, CI/CD pipelines, and examples (7fedccb)
• add improve_mode to MultiProcessEvolvingStrategy for selective task implementation (#1273) (03f22dc)
• Add improved local prompt with MultiIndex code examples (v3) (3f2398a)
• add Kronos CLI commands, expand tests, document in README (0fde3e1)
• add LLM-finetune scenario (#1314) (6e19c9e)
• Add model loader system (same as prompts) (19855ef)
• Add P5 ML Training Pipeline with LightGBM and 46 tests (59f150a)
• Add parallel run system with API key distribution (88577e2)
• Add RL Trading Agent system with 99 tests (faecbec)
• add runtime backtest verification (10 invariant checks in <1ms) + 489 tests + README docs (9e0a416)
• Add simple factor evaluator with direct IC/Sharpe computation (0d6537c)
• Add start_llama and start_loop CLI commands (4e32d4d)
• add stdout into workspace for easier debugging (#1236) (0daeb82)
• Add Trading Protection System with 4 protections + comprehensive tests (3cfb524)
• add user interaction in data science scenario (#1251) (6e09dc6)
• auto-mode live strategy — factors when fresh, SMA fallback (63abdc7)
• auto-post releases to Mastodon and X/Twitter via GitHub Actions (68c0921)
• Auto-start dashboard for fin_quant (3441604)
• Auto-start dashboard for fin_quant (52d2b89)
• backtest: add RiskMgmt-realistic backtest mode with leverage, daily/total loss limits and realistic EUR/USD costs (b76330f)
• backtest: add rolling walk-forward validation and Monte Carlo trade permutation test (0f26020)
• backtest: add walk-forward OOS validation to backtest_signal_riskmgmt (3d3866f)
• Backtesting Engine + Risk Management + Results Database (8339be2)
• Backtesting Engine + Risk Management + Results DB (4690b01)
• backtest: use backtest_signal_riskmgmt in strategy orchestrator and optuna optimizer (986eeeb)
• Beautiful CLI dashboard + corrected start command (c2932cb)
• Centralize all prompts in prompts/ directory (18416da)
• CLI Commands for strategy generation (P4 complete) (bad98b6)
• Complete P6-P9 implementation (73 tests) (c1c249d)
• continuous strategy generator (WF, MTF, stability, ML models, auto-ensemble) (d00426b)
• daily strategy generator — grid search SMA/EMA/RSI/MACD/BB (14/55 profitable) (fbcd0b6)
• Data Loader module with tests (P0 complete) (440aba5)
• Diverse factor selection + improved prompt v3 (e293f6c)
• enable walk-forward OOS validation by default in backtest_signal_riskmgmt (a6e6f35)
• EURUSD FX patches - prompts, factor spec, experiment settings (b6cf687)
• EURUSD model experiment setting + model simulator text patched (9a17b25)
• EURUSD Trading-Verbesserungen (Phase 2 & 3) (05c4e1b)
• EURUSD Trading-Verbesserungen implementiert (Phase 1) (b95bbf5)
• EURUSD walk-forward splits, bars terminology, README no $factor (0eae7d0)
• expand indicator library from 7 to 14 (22ac3c8)
• factor-coder: Add critical rules to prevent common factor implementation errors (bf25635)
• Fast mode - CoSTEER goes to backtest after 1 iteration (0b16f4f)
• fin_quant: auto-generate Kronos factor before loop start (ce13a37)
• Fix 1min data integration and centralize all prompts (f6f7b79)
• Fix realistic backtesting (Step 1+2) (84c1b5f)
• Full auto strategy generation in fin_quant loop (dd42d01)
• Full system integration - RL + Protections + Backtesting + CLI (1fda459)
• FX feedback loop, EURUSD ticker examples, bars terminology (781779a)
• FX Multi-Agent Validator (TradingAgents-inspired) - Session/Macro/Bull-Bear/Trader (cddfc53)
• Improve predix portfolio command with robust error handling (db1d4f9)
• Improved LLM prompt + Optuna integration (Step 3+5) (2af0006)
• init pydantic ai agent & context 7 mcp (#1240) (5ba5e83)
• Integrate critical features into fin_quant workflow (P0+P1) (eeb44a7)
• Integrate factor code/description saving into fin_quant process (3eaebeb)
• integrate Kronos foundation model into fin_quant R&D loop (dab2772)
• integrate Kronos-mini OHLCV foundation model (Option A + B) (ca2d3a2)
• Intelligent embedding chunking instead of truncation (2d0584b)
• inverse factor signal combos — top-3 gives +0.57%/month with -3.7% DD (f699733)
• live 1h London momentum strategy + multi-timeframe generator (bf79564)
• live price-action pipeline — Donchian+MACD majority-vote signals (de4494d)
• logging: write complete LLM prompts and responses to daily JSONL log (00ea268)
• mcp: cache with one-click toggle (#1269) (4f493c8)
• mcts policy based on trace scheduler (#1203) (ac6d8ed)
• migrate R&D loop to TA-Lib (17 indicators, 161 available) (a86c515)
• migrate to 1min EURUSD data (2020-2026) (b39f2b7)
• ML Training Pipeline with 46 tests (P5 complete) (9109613)
• model-track bias + daily/portfolio tools (ff46aa0)
• multi-asset data pipeline, daily strategy generator, ML pipeline (a317987)
• new R&D loop — indicator discovery with exploit/explore mechanics (efad52e)
• offline selector (#1231) (d4c5399)
• optimize strategy generator (cache OHLCV, min_sharpe 1.5, predix generate-strategies CLI) (963532f)
• optimizer: add max_positions parameter to Optuna search space (4ffa02d)
• Optuna Parameter Optimizer with 60 tests (P3 complete) (343f97d)
• Optuna-optimized RF ML pipeline for daily strategies (+0.61%/month) (c8b9683)
• PDF performance reports for strategies (reportlab) (5fd25b2)
• predix.py wrapper for dashboard support (757c66c)
• price-action strategy generator — no LLM, no factors, 38 profitable strategies (a099d0c)
• prioritize Kronos foundation model factors in strategy selection (0226e54)
• R&D loop fixes + new price-action research loop (5add57f)
• R&D loop v2 — LLM proposals, crossover mutation, WF filter, multi-instrument (10cc425)
• Realistic backtesting with OHLCV data (P5 continued) (8b5b8d9)
• Realistic backtesting with OHLCV data and spread costs (39ccdec)
• Redirect RD-Agent workspace to results/ directory (6875be6)
• rl: add AutoRL-Bench framework and benchmark integrations (#1348) (7cd64a2)
• run Kronos on CPU to avoid GPU conflict with llama-server (f2394dc)
• Save all factor results to results/factors/ (08e58fc)
• Save factor results immediately after each evaluation (98e3025)
• scripts: add full file logging to strategy generation and rebacktest scripts (e4ce0d2)
• show the summarized final difference between the final workspace and the base workspace (#1281) (35a7ae5)
• strategies: make OOS validation mandatory in strategy generator (710f5e6)
• Strategy Generator working with local LLM (P0-P4) (2262635)
• Strategy Orchestrator with 30 tests (P2 complete) (55ecfb8)
• Strategy performance reports, CLI docs, and README update (590984e)
• Strategy Worker module with 41 tests (P1 complete) (dbbce30)
• strategy: Continuous optimization with Optuna parameter injection (09cc725)
• Support 25+ parallel runs with resource warnings (b4dc2d5)
• support Kronos-small and Kronos-base models, auto-select GPU/CPU (f50b0f3)
• unified backtest engine, LLM error handling, strategy refactor (5c066c5)
• update README with latest paper acceptance to NeurIPS 2025 (#1252) (12969b4)
• zentrale data_config.yaml + apply_config.py für dynamische Datenkonfiguration (b7c1e4d)

Bug Fixes

• (to main) litellm's Timeout error is not picklable (#1294) (315850e)
• 15 bug fixes across orchestrator, runner, backtest, and infrastructure (7c88252)
• add a switch for ensemble_time_upper_bound and fix some bug in main (#1226) (fc18942)
• Add Bandit security scanning and fix critical vulnerabilities (ca09577)
• Add critical column name rules to factor generation prompt (bf9d50b)
• Add get_factor_count() to QuantTrace to prevent parallel run crashes (1d6efa7)
• add hypothesis to test deps and fix missing imports in deep tests (92a0ab8)
• add json format response fallback to prompt templates (#1246) (694afd8)
• add missing debug() method to RDAgentLog (04361ce)
• Add missing os import in factor_runner.py (18ccd1a)
• Add missing Panel import in predix evaluate command (706d887)
• add missing sys import and fix undefined acc_rate in factor eval (8e2729e)
• Add nosec comments for schema migration SQL in results_db.py (b8d632b)
• also catch ValueError in mean_variance for dimension mismatch (d0a1ff8)
• auto-fixer: add five new factor code fixes for groupby/apply errors (04900ad)
• auto-fixer: add four new factor code fixes for common runtime errors (0f103df)
• auto-fixer: add groupby([level=N,'date']) SyntaxError fix (bd3f2f7)
• auto-fixer: disable _fix_min_periods for intraday data (5a3a5b9)
• auto-fixer: fix chained groupby(level=N).groupby('date') pattern (084a2b5)
• auto-fixer: fix df.loc[instrument] DateParseError on MultiIndex frames (2e41a7d)
• auto-fixer: fix df['instrument'] KeyError on MultiIndex frames (5fadc9e)
• auto-fixer: fix two assignment-target bugs in instrument column fixers (afbef59)
• auto-fixer: preserve date dimension in groupby(['instrument','date']) fix (f64e4d9)
• auto-fixer: remove ddof from rolling() args, not only from std()/var() (07b3051)
• auto-fixer: replace zero $volume with price-range proxy for FX data (43a8e46)
• auto-fixer: strip spurious .reset_index() after .transform() calls (5d2c7d7)
• avoid triggering errors like "RuntimeError: dictionary changed s… (#1285) (b180543)
• backtest: replace broken MC permutation test with binomial win-rate test (6c2979d)
• bump axios 1.15.2→1.16.0, postcss 8.4.31→8.5.14 (Dependabot CVEs) (5de229c)
• case-insensitive assertion in test_add_column_idempotent (f78b040)
• change runner prompts (#1223) (be3433f)
• ci: fix closed-source asset check false positives in security workflow (cf985a3)
• ci: lazy import logger in predix.py and cli.py to avoid ImportError in test env (541c6bb)
• ci: remove CodeQL workflow (conflicts with default setup), drop duplicate lint job (62b6514)
• ci: remove env-print step to avoid leaking sensitive environment variables (#1299) (c067ea6)
• ci: set JAVA_TOOL_OPTIONS UTF-8 in Codacy workflow (c697349)
• CLI dashboard in separate terminal window (b72cca9)
• close log file handle, fix RiskMgmt equity double-count, remove bare except (20a5342)
• collect_info: parse package names safely from requirements constraints (#1313) (99a71bf)
• correct MaxDD to equity curve in strategy_builder; test: add 8 cross-validation tests for metric correctness (729af07)
• correct project root paths and subprocess handling in parallel runner and CLI (f2c1c01)
• correct Sharpe/MaxDD/WinRate in direct factor eval (was computing on raw factor, now on strategy returns) (373a254)
• deps: bump python-dotenv to >=1.2.2 (CVE symlink overwrite) (e6ce81e)
• deps: pin aiohttp>=3.13.4 to patch 4 CVEs (fceda7b)
• deps: relax aiohttp constraint to >=3.13.4 for litellm compatibility (92833b1)
• Disable ANSI color codes when not running in TTY (2e7652c)
• Disable Flask debug mode by default (Security Alert #2) (ab5fa78)
• Display litellm messages as info instead of warnings (2c89a35)
• dockerfile: install coreutils to resolve timeout command error (#1260) (35580cb)
• docs: update rdagent ui with correct params (#1249) (3b9ad11)
• Embedding Context Length Error (6d6c5ab)
• end-timestamp 23:45, weg, SZ-beispiele weg (6a9ccd5)
• enhance feedback handling in MultiProcessEvolvingStrategy for improved task evolution (#1274) (afb575c)
• Ensure backtest results save to DB and JSON files (9bb4b47)
• evaluator erkennt 15min als valid (nicht daily) (cf0f634)
• factors: detect and correct look-ahead bias in daily-constant factors (d48a8a9)
• factors: extend look-ahead rules to session factors and add intraday-factor guidance (64fcdad)
• filter NaN in max(), remove redundant ternary, handle non-finite vbt results (dcec524)
• fix chat_max_tokens calculation method to show true input_max_tokens (#1241) (7e99605)
• fix mcts (#1270) (5003aff)
• Fix parallel runner dashboard rendering error (8926a57)
• fix type annotation, remove unused parameter, improve import_class errors (3eb09ce)
• Forward-fill daily factors to 1-min frequency (dfed6d6)
• generate.py nutzt rdagent4qlib env für Qlib-Datenzugriff (b9007f7)
• Handle failed experiments in feedback step to prevent crashes (8a54ff4)
• handle mixed str and dict types in code_list (#1279) (32ecf92)
• Handle negative/zero values in performance report charts (1315638)
• Handle Qlib Docker backtest failures gracefully (SECURITY FIX) (557c581)
• Handle timeout exceptions safely in predix_full_eval.py (1132943)
• handle ValueError in stdout shrinking and refactor shrink logic (#1228) (6fc3877)
• Harden _safe_resolve to fix CodeQL alert #3 (28ea591)
• Harden path validation in Job Summary UI to fix CodeQL alert #17 (79bc526)
• Harden path validation to fix CodeQL alert #20 (87d1ce7)
• harmonize risk field names and case-insensitive DB column check (8b47d0a)
• Import pandas in predix portfolio_simple command (e4967e1)
• Improve path traversal prevention with dedicated helper function (8e00b89)
• increase retry count in hypothesis_gen decorator to 10 (#1230) (86ce4f1)
• Initialize EnvController in QuantTrace.init (cc1f44e)
• inject correct MultiIndex template into factor prompt (49004db)
• inject MultiIndex warning into factor interface prompt (YAML valide) (79e2915)
• kronos: lazy torch import to fix CI ModuleNotFoundError (8a33478)
• kronos: pass actual datetime Series to Kronos predictor timestamps (7422868)
• kronos: replace rdagent_logger with stdlib logging for CI compatibility (a8c6055)
• live 1h SMA uses minute_closes deque instead of stale HDF5 (46cc214)
• loop: compress old experiment history in proposal prompt to reduce context size (9fdac81)
• loop: prevent step_idx advance on unhandled exceptions + fix consecutive assistant messages (ba3421e)
• merge candidates (#1254) (46aad78)
• model/factor experiment filtering in Qlib proposals (#1257) (9e34b4e)
• move task cancellation to finally block and fix subprocess kill typo (#1234) (a984f69)
• optuna: fix inverted parameter range in Stage 2/3 when signal_bias is negative (6356743)
• Override webshop's Werkzeug dependency to fix CVE-2026-27199 (83e18e2)
• preserve null end_time when rendering dataset segments template (#1326) (6196ba3)
• prevent calendar index overflow when signal data ends early (#1324) (3dbd703)
• prevent JSON content from being added multiple times during retries (#1255) (31b19de)
• prevent LLM retry loop from consecutive assistant message corruption (a86666f)
• Prevent path injection in FT Job Summary UI (d95f509)
• Prevent path injection in RL Job Summary UI (a170f0a)
• Prevent path traversal in autorl_bench server.py (4cfec6c)
• Prevent path traversal in get_job_options() app.py (5bd5416)
• Prevent path traversal in RL UI app.py (848019d)
• Prevent path traversal in Streamlit UI app.py (9f8cf62)
• qlib: correct indentation in except blocks in quant_proposal and factor_runner (0dbe833)
• Refactor path validation to fix CodeQL alert #16 (2819423)
• refine task scheduling logic in MultiProcessEvolvingStrategy for… (#1275) (27d38af)
• relax WF default test (wf_oos_sharpe_mean not present when 0 windows) (8efb5d4)
• remove $factor from prompt, update example count to EURUSD (3adc5bf)
• remove all Chinese stock references, replace with EURUSD 1min FX (44eeb01)
• Remove API key from test_benchmark_api.py config (3ce366e)
• Remove API key logging from eurusd_llm.py (d73e3de)
• Remove API key parameter from generate_api_config() (9780e3a)
• Remove API key presence detection from logging (adba526)
• Remove clear-text storage of API key (CodeQL alert #8) (2f01c77)
• Remove hardcoded credentials from test_benchmark_api.py (c259a01)
• Rename loader.py to prompt_loader.py to fix module conflict (435e03b)
• replace hardcoded ChromeDriver path with webdriver-manager (#1271) (e3d2443)
• Resolve 88% empty backtest results + path fixes (f720f76)
• resolve dead code, shell injection risk, mutable defaults, and other bugs (952281a)
• Resolve FORWARD_BARS NameError in backtest script (e9e4817)
• Resolve security vulnerabilities (Dependabot + Code Scanning) (fe397c4)
• resolve unbound variable, logger shadowing, withdraw_loop edge case, and other bugs in main scripts (f48251d)
• restore KronosPredictor instantiation deleted during refactor (15f2c00)
• revert 2 commits (#1239) (2201a47)
• revert to v10 setting (#1220) (51f5bc9)
• security: nosec for B608/B701 false positives in UI and template code (0c4e411)
• security: Patch 5 CodeQL path injection and clear-text logging alerts (#22-#25, #9) (30bdd88)
• security: Patch 5 CodeQL path injection and weak hashing alerts (#25-#30) (e3a40de)
• security: Patch path injection and stack trace exposure (CodeQL #31, #27) (308e556)
• security: real fix for B110 (logging in factor_proposal.py #746) (81e92a5)
• security: real fix for B110 (logging in factor_runner.py #744) (a200194)
• security: real fix for B110 (logging in quant_proposal.py #741) (d8ce3ed)
• security: real fix for B110 (logging in quant_proposal.py #741) (0b95143)
• security: real fix for B404/B603 (sys.executable in factor_runner.py #745) (4f00fab)
• security: replace eval() with ast.literal_eval and add request timeouts (B307, B113) (d8d4091)
• security: replace eval() with ast.literal_eval in finetune validator (B307) (c7ada10)
• security: replace os.path.realpath with pathlib.resolve in safe_resolve_path to fix path-injection alerts (bc73123)
• security: replace relative_to() with realpath+startswith for CodeQL sanitization (2fd6e06)
• security: replace remaining assert statements with proper error handling (9e72998)
• security: replace shell=True subprocess calls with list args (B602) (1c16ac9)
• security: replace shell=True subprocess calls with list args in env.py (B602) (cad1c12)
• security: resolve all 30 Bandit security alerts (B301, B614, B104) (4577d6a)
• security: resolve CodeQL path-injection alerts in UI data loaders (4b6ddfa)
• security: resolve CodeQL path-injection and clear-text-logging alerts (811509d)
• security: Resolve GitHub Security Scan alerts (280cc29)
• security: resolve path-injection and add nosec for safe temp paths (B108, py/path-injection) (05a20f6)
• security: resolve path-injection, B701, B101, B112 Bandit alerts (d5f7cc3)
• security: revert broken read_pickle encoding arg in kaggle template (B301) (f2dde21)
• security: Upgrade vllm and transformers to patch 4 CVEs (dd675c7)
• security: validate SQL identifiers in _add_column_if_not_exists (B608) (d5e4717)
• security: whitelist-validate metric column in get_top_factors (B608) (204753e)
• set requires_documentation_search to None to disable feature in eval (#1245) (ee8c119)
• Skip already evaluated factors in predix_full_eval.py (573bff0)
• skip Kronos factor on GPUs < 20GB to avoid CUDA OOM (shared with llama-server) (b45f0b9)
• strategies: guard against None IC in acceptance check, disable slow wf_rolling (0cc2f86)
• strategies: handle None ic/sharpe/dd in rejected strategy log output (05dab63)
• strategy: Fix template variables, APIBackend import, and JSON extraction (520edbe)
• strategy: Re-evaluate Optuna-optimized strategies with full OHLCV backtest (c709f94)
• Switch to ThreadPoolExecutor for factor evaluation (8947089)
• sync release manifest to v1.4.3 (was diverged at 0.8.0) (c16aecc)
• Translate remaining German comment in eurusd_macro.py (6730ae4)
• Update LICENSE badge link from main to master branch (e79eff5)
• Update Werkzeug to 2.3.8 (latest secure 2.x version) (19b9d23)
• update WF test for new default (wf_rolling=True) (e5d626a)
• Use 96-bar forward returns in backtest (matching factor IC horizon) (a1f0ceb)
• Use num_api_keys instead of len(api_keys) for round-robin (17f68e6)
• weg, Timestamps mit Uhrzeit, kein SZ-Beispiel (e9f6ac4)

Performance Improvements

• kronos: batch GPU inference via predict_batch — 75x faster (bc1f3cf)
• kronos: batch GPU inference via predict_batch — 75x faster (9f6bc81)

Reverts

• remove automated release social workflow (ba62cf3)

Documentation

• Add ATTRIBUTION.md with clear usage guidelines (7701ba0)
• Add CLI welcome screenshot to README (fa6fa22)
• add closed-source test policy; remove closed-source test imports (69770b3)
• Add comprehensive CHANGELOG.md for v1.0.0 release (03cc28b)
• Add comprehensive CLI help and update README with quick start (cc116cf)
• Add comprehensive data setup guide to README (bbee683)
• Add comprehensive Git commit guidelines to QWEN.md (2d82325)
• Add conda requirement to README + fix predix CLI (a684c7a)
• Add CRITICAL rule - NEVER commit closed-source/private assets (6e24f7d)
• Add CRITICAL rule - NEVER commit trading strategies or JSON files (ef73a94)
• add documentation for Data Science configurable options (#1301) (d603d5a)
• add execution environment configuration guide (Docker vs Conda) (#1288) (27ed3d1)
• Add implementation summary (4fb80e8)
• Add live trading system documentation to QWEN.md (b9f7004)
• Add Microsoft RD-Agent acknowledgment to README (a48f0a9)
• add precise release trigger rules (5+ feats, 10+ fixes, 30+ commits, major feature, security) (afc5c30)
• Add professional badges to README header (8b28e30)
• Add results/ directory README for storage documentation (fd963a4)
• Add v2.0.0 release changelog (4d54edb)
• Clean changelog of closed-source performance metrics (9c08a50)
• Create changelog/ directory with v1.0.0.md release notes (d74e970)
• Final system completion - all 9 phases done (4e170e9)
• fix duplicate sections, add hardware requirements and data setup guide (7162113)
• fix script paths in README after rename (22c2b58)
• improve README badges, fix llama-server flags, clean up structure (dbfdd06)
• project status — what works / what doesn't (May 2026) (9c6a3bb)
• Remove 'Inspired by' comments and add comprehensive Acknowledgments (647be57)
• remove closed-source live trader reference from README (85fcb96)
• remove forex-specific language from README (d9e533a)
• Simplify README for git-clone-only installation (ec9cd9b)
• Translate all code comments to English (bb450f7)
• Translate data_config.yaml to English (1aca2dd)
• Translate server.py comments to English (40788b8)
• Translate server.py docstring to English (20caf6d)
• update license section from MIT to AGPL-3.0 (0f989d9)
• Update QWEN.md with complete 5-phase architecture and results (0cb61bb)
• Update QWEN.md with detailed Git history correction guide (9315fa8)
• Update QWEN.md with implementation guide (52fa35b)
• update README — Kronos-small, test depth, daemon setup, project structure (639e727)
• Update SECURITY.md and CONTRIBUTING.md (f2c7744)
• Update TODO.md with v1.0.0 completed items and future roadmap (b6d26bc)

Miscellaneous Chores

• release 0.8.0 (8c15238)

---

This PR was generated with Release Please. See documentation.