v1.5.0

1.5.0 (2026-06-26)

Features

• add voice background noise and randomized burst artifact injection (80258b8)
• address PR review comments on noise injection (7b8e84e)
• agents: add CUJ standardizer agent, refactor framework detector, and compile deliverables (49e5f55)
• allow customizing models for running and for evaluating evals (eda8f24)
• cli: add --overwrite flag to cxas pull (029edb4)
• cli: add --overwrite flag to cxas pull (4d14e96)
• cli: add --overwrite flag to cxas push (3d0287e)
• cli: add --overwrite flag to cxas push (7b4b24e)
• cli: add --timestamped flag to evals report (19e528d)
• cli: Add no-input flag for headless execution (408a564)
• cli: flag variable update attempts in llm-lint (e3bc802)
• core: add WebSocket timeout protection, close diagnostics, and support for citations and custom payloads (aff41c8)
• core: add WebSocket timeout protection, close diagnostics, and support for citations and custom payloads (ca29e81)
• cxas-cuj-report-generator: enforce explicit time confirmation turns in voice prompts (f3c360e)
• cxas-cuj-report-generator: enforce spelled-out verbal forms for times in voice responses (2f7ae2f)
• cxas-cuj-report-generator: implement batch grading, prompt optimizer, and TESTING manual (f822537)
• cxas-cuj-report-generator: integrate graph traversal rules, voice realism guidelines, and naturalness standards (3a0eecd)
• cxas-cuj-report-generator: mandate root-level call fields, generic fallback greetings, and sign-offs (5853b19)
• cxas-cuj-report-generator: mandate spelled-out forms for percentages, order IDs, and reward counts (b777c50)
• cxas-cuj-report-generator: require polite voice markers on every agent turn (7ae2c77)
• cxas-cuj-report-generator: standardize sign-off phrasing to Dining Service goodbye (3df284b)
• deployments: add traffic split support (5806bba)
• deployments: add traffic split support (ed10846)
• evals: add ability to timestamp eval reports (e695201)
• fix smaple names (2bf98d8)
• guardrails: add design guide docs and local create scaffolding (d3ef0c4)
• include global instructions and dynamic DIs to llm-lint (7ed70b3)
• ingestor: enforce first-turn description validation in append_turn.py (12487f9)
• lint: add I016 prose-state-machine rule (399d664)
• lint: add V100-V104 variable-reference rules (#291) (8bfc92d)
• linter: Add S007 linter rule to ensure sub agents only have one parent (b844aff)
• linter: flag variable update attempts in llm-lint (c4bc3a1)
• linter: Validate single-parent constraint for sub-agents (S007) (cfacdfb), closes #301
• llm-lint: expand semantic linter with red-teaming & robustness scenarios (2b1b988)
• llm-lint: expand semantic linter with red-teaming & robustness scenarios (9e7768a)
• Make generated local templates pass lint by default (97ceabd)
• make non-interactive and headless execution safe (#55) (c61f9ab)
• make use_tool_fakes as a flag when running evaluations (3138fcb)
• migration: always-on consolidation + grouping gate default (#231) (abec278)
• migration: emit tabbed HTML analysis report on every migration (#207) (85bebc1)
• migration: file-watch fallback for grouping gate (856248d)
• migration: Grouping Review tab in analysis report (read-only) (3458903)
• migration: Grouping Review tab in analysis report (read-only) (#227) (58c49da)
• migration: HTML grouping confirmation gate (opt-in) (7f2692d)
• migration: implement consolidated agents name-mapping throughout agent config (0c325c3)
• migration: local-first Phase 8 — skip per-flow CXAS deploys until post-consolidation (05cf6a4)
• move llm-lint from a skill to a package prompt and register as a cxas CLI subcommand (9f36128)
• prompts: add rules for quotes vs back-ticks and variable formatting to llm-lint (8d00356)
• report-generator: integrate export transcripts to JSON feature in HTML report UI (9e5b8ad)
• supervisor: implement ingestor supervisor and dynamic batch execution daemon (827bc5e)
• trace: add 'cxas trace search' for full-text conversation search (536fdb6), closes #236

Bug Fixes

• add background_noise_file nd additional args (1ea3e57)
• add background_noise_file nd additional args (3dd61b1)
• add pre-commit hook to block brand names (0b79d39)
• add pre-commit hook to block brand names (3f01d47)
• add unit tests (1925fc3)
• address final E501 line length errors in voice noise PR (a17c288)
• address lint failures and update unit test assertions (80a5468)
• clean up example colab (06d1079)
• clean up example colab (2c68e53)
• clear uv and venv ambiguity (013cafe)
• cli: drop unsupported format kwarg from evals report (ee058ba)
• cli: fix line too long in help text (fc3e1b3)
• cli: forward modality argument to run_evaluation in run_eval (f0f66d4)
• cli: forward modality argument to run_evaluation in run_eval (e288802)
• cli: resolve ruff line length and mkdocs strict nav warnings (aad1066)
• consolidate the detailed trace to populate the json for html ren… (8f66b86)
• consolidate the detailed trace to populate the json for html rendering (b3f965a)
• docs: add missing trace command to mkdocs navigation (df7a03a)
• docs: resolve strict link and anchor warnings in patterns and tutorials (d2ed4eb)
• enable tool fakes for cxas evals report and update docs (544ae40)
• eval cmd remove dead format flag (65cf240)
• eval-utils: Propagate credentials to internal Evaluations client (4054594)
• eval-utils: Propagate credentials to internal Evaluations client (c9ffa16)
• failing test due to merge conflict (30240bc)
• fix goal progress status on session end in SimulationEvals (79c2ca8)
• fix smaple names (c0a3c88)
• formatting (32ce5ee)
• gemini: log traceback using logger.exception instead of silently returning None (643ccd6)
• lint issue (5c4c7cd)
• linter: bypass scenario validation on golden/deterministic evaluations (c7629d8)
• linter: fix false positive V006 linter errors on deterministic Golden evaluations (339bf88)
• lint: update I014 to check for {current_date} instead of ${current_date} (13a203b)
• lock changelog edits (a885755)
• make use_tool_fakes as a flag when running evaluations (933edc9)
• migration: canonical-XML consolidation prompt + lint-driven retry (8bca323)
• migration: clean up unused imports and fix Gemini cache content format (c2f4f38)
• migration: resolve lint errors and pydantic Optional NameError (cd4627f)
• migration: resolve tool name truncation, standardize XML instructions, add LOCAL state (0312200)
• migration: resolve web review server blockers, TUI wiring gaps, and enable early boot dashboard (b1928b5)
• migration: restore docstring and inline comments in structural_consolidator (e21b407)
• prefer always using 'uv run' for 'cxas' commands. (835e63f)
• Print trace when logging exception error messages to prevent silent errors. (3adbb4c)
• prompts: lowercase <Agent> XML tags for consistency (52c4c2e)
• recover from bad truncation of cuj skill. (0719903)
• reformat files based on ruff check (478c7f8)
• remove duplicate agent response in turn evals (cff8c5d)
• ruff linter check (9b05314)
• skills: pass resource name instead of display name in sync-callb… (f904f76)
• tests: update mock app_name placeholder format to pass validation in test_eval_utils.py (3a75617)
• utils: add missing Any type annotation to kwargs in EvalUtils (cf8d9de)
• xml schema error (743100d)
• migration: always-on consolidation + grouping gate default (#231)

Performance Improvements

• cli: implement lazy imports for CLI subcommands to improve performance (18eeb31)
• cli: implement lazy imports for CLI subcommands to improve startup time (acdc8cd)
• migration: reduce pipeline latency with concurrency, local-first Stage 1, and prompt caching (13ec16d)

Reverts

• remove unrelated setup.sh change from cleanup commit (6d7df9c)
• undo changes to sync-callbacks.py (c9f543f)

Documentation

• add agentic development environment setup tutorial (ef1cc97)
• add agentic development environment setup tutorial (60478db)
• add type hints and docstrings for noise injection params in reporting (b671ada)
• cli: add llm-lint documentation and interactive help subcommand (1d0d936)
• cli: add llm-lint documentation and interactive help subcommand (e473984)
• cxas-cuj-report-generator: align testing documentation with new python evaluation pipeline (e38fad2)
• fix app-dir argument typo in linting guide (4bcf4bb)
• make mock tools it's own document and update refs (d61354f)
• update running-evals-cli reference and add tool fakes documentation (f3cb957)
• update running-evals-cli reference and add tool fakes documentation (d2a9120)

Miscellaneous Chores

• force release version to 1.5.0 (837a97b)