0.3.19

💥 BREAKING CHANGES

• due to 6c0f5aa - ✨ 引入 Judge 验收 Agent 替代 goal_scored 自证 (PR #224 by @HayWolf):

  GoalEvaluateResult.verdict no longer includes "complete"

  • docs: 📝 update and reorder README feature list
    Update the feature descriptions and reorder the bullet points in both
    README.md and README_zh.md to better reflect the current product
    capabilities and improve readability. Changes include:
  • Reordering features to highlight persistent goal management, real-time
    streaming, and extensibility earlier in the list
  • Updating descriptions for several features to be more accurate
  • Maintaining consistency between English and Chinese versions
  • Keeping the overall structure while improving flow
    These are documentation-only changes that do not affect functionality.
  • refactor(goal): ♻️ extract resolveGoalStatusKey for testability
  • Extract inline status key resolution into a pure exported function
    so the complete→verified (judgePassed) branch can be unit-tested
    without mounting the component
  • Add unit tests covering all status mappings and judgePassed variants
  • Add test for skipped verdict passthrough in goalEvaluate
  • refactor(subagent): 🔧 increase builtin default max delegation depth to 5
    Raise BUILTIN_DEFAULT_MAX_DELEGATION_DEPTH from 3 to 5 to match the
    existing GLOBAL_MAX_DELEGATION_DEPTH, allowing built-in subagents
    (explore/review) to be delegated to the same depth as custom profiles.
    Update delegation validation tests to reflect the new depth limits.
  • docs: 📝 remove obsolete design document
  • docs(judge): 📝 add size-first verification strategy and delegation guidelines
  • refactor(goal): ♻️ remove goal-level time_used_seconds in favor of run-level elapsed tracking

• due to 6bf6da9 - 🐛 converge orphaned subagents and account final turns for judge-completed goals (PR #226 by @HayWolf):

  内部 AgentSession.context_compression_state
  及其关联启发式 API 已移除,替换为
  AgentSession.last_observed_usage: Arc<StdMutex<Option<Usage>>>;
  前端 RunUsageDto 新增必填 contextSize,旧 totalTokens 保留
  为 wire-level 显示。任何外部消费方需更新到新字段。
  Refs: tiycore 0.2.10-rc.2 Usage::context_size()

• due to f05858c - ♻️ flatten update_plan input (PR #228 by @HayWolf):

  update_plan no longer accepts a nested plan
  object. Clients must pass all fields as top-level arguments.

• due to ba6a73c - ✨ replace self-attested goal completion with independent Judge subagent (PR #227 by @jorben):

  GoalEvaluateResult.verdict no longer includes "complete"

  • docs: 📝 update and reorder README feature list
    Update the feature descriptions and reorder the bullet points in both
    README.md and README_zh.md to better reflect the current product
    capabilities and improve readability. Changes include:
  • Reordering features to highlight persistent goal management, real-time
    streaming, and extensibility earlier in the list
  • Updating descriptions for several features to be more accurate
  • Maintaining consistency between English and Chinese versions
  • Keeping the overall structure while improving flow
    These are documentation-only changes that do not affect functionality.
  • refactor(goal): ♻️ extract resolveGoalStatusKey for testability
  • Extract inline status key resolution into a pure exported function
    so the complete→verified (judgePassed) branch can be unit-tested
    without mounting the component
  • Add unit tests covering all status mappings and judgePassed variants
  • Add test for skipped verdict passthrough in goalEvaluate
  • refactor(subagent): 🔧 increase builtin default max delegation depth to 5
    Raise BUILTIN_DEFAULT_MAX_DELEGATION_DEPTH from 3 to 5 to match the
    existing GLOBAL_MAX_DELEGATION_DEPTH, allowing built-in subagents
    (explore/review) to be delegated to the same depth as custom profiles.
    Update delegation validation tests to reflect the new depth limits.
  • docs: 📝 remove obsolete design document
  • docs(judge): 📝 add size-first verification strategy and delegation guidelines
  • refactor(goal): ♻️ remove goal-level time_used_seconds in favor of run-level elapsed tracking
  • feat(judge): ✨ redesign Judge evaluation for independence and completeness
  • fix(subagent): 🐛 make task field optional and fix UTF-8 safe truncation
  • Downgrade Judge prompt versions from 2 to 1 (likely a revert of unintended bump)
  • Change task field from required to optional in Judge tool schema, with updated description clarifying it is an optional note
  • Replace byte-based truncation with character-safe truncation to avoid panicking on multi-byte UTF-8 in process compliance summary
  • Simplify Judge request validation to only check input validity, discarding the parsed result used only for backward compatibility
  • Skip abandoned task boards when building summary to focus on relevant goal state
  • chore(deps): 🔧 align tiycore to 0.2.10-rc.2 and adopt Usage::context_size()
    Cherry-pick the master commit (a03d9ba) that bumps tiycore from 0.2.9
    to 0.2.10-rc.2 and unifies context_size semantics across
    RunUsageDto / frontend badge / auto-compression, removing the old
    initial_context_calibration heuristic path. No file conflict with
    the Judge work in this branch — the 25 files touched here do not
    overlap with the 6 Judge files resolved in the previous merge.
  • refactor(goal): ♻️ centralize status transitions to explicit commands and Judge verdicts
  • fix(agent): 🐛 fix timestamp slicing panic and add has_process_requirements tests
    Replace byte-index slicing with char-aware truncation to prevent
    panics on multi-byte UTF-8 boundaries in timestamp formatting.
    Add unit tests for has_process_requirements() covering English
    and CJK keywords, substring match behaviour, edge cases, and
    case-insensitive matching.
  • feat(compression): ✨ reserve 20% context window for auto-compression trigger
    Backend: replace fixed 16,384 token reserve with 20% of model context
    window (min floor 16,384). Small-window models keep the floor; GPT-4o
    class windows reserve ~25.6K, Claude-class ~40K, 1M-window ~200K.
    Frontend: add dashed threshold marker at 80% position in the thread
    header context pill so users can see when auto-compression will fire.
  • fix(run): 🐛 record elapsed running time when interrupting active runs
  • test: cover Judge summary builders and mapRunSummaryToContextUsage fallback
    Add four integration tests in agent_session_execution.rs for the
    Judge-prompt context builders (build_task_board_summary,
    build_process_compliance_summary) covering absent boards, active/abandoned
    board filtering, review-only helper filtering, status symbol mapping, and
    200-char input truncation.
    Add six unit tests in runtime-thread-surface-state.test.ts for
    mapRunSummaryToContextUsage covering null input, explicit contextSize
    precedence, fallback to per-bucket sum, and full-field passthrough.
    Addresses review feedback from PR #227 (round 4):

✨ New Features

• 00c6637 - ui: ✨ enable text selection in markdown preview and overlay (PR #221 by @HayWolf)
• 55e774b - subagent: ✨ Add nested subagent delegation with configurable depth limits (PR #223 by @HayWolf)
• 6c0f5aa - goal: ✨ 引入 Judge 验收 Agent 替代 goal_scored 自证 (PR #224 by @HayWolf)
• ba6a73c - judge: ✨ replace self-attested goal completion with independent Judge subagent (PR #227 by @jorben)

🐛 Bug Fixes

• 3690958 - core: 🐛 fix Windows cross-compilation type errors (PR #219 by @jorben)
• 6bf6da9 - core: 🐛 converge orphaned subagents and account final turns for judge-completed goals (PR #226 by @HayWolf)

♻️ Refactors

• 3a077c1 - thread: ♻️ track cumulative thread elapsed time across runs (PR #220 by @jorben)
• 96e7710 - prompt: ♻️ Overhaul prompt injection with modular layered architecture (PR #222 by @jorben)
• fe7fbfc - workbench: ♻️ remove runMode from frontend state management (PR #225 by @jorben)
• f05858c - core: ♻️ flatten update_plan input (PR #228 by @HayWolf)

0.3.19-rc.9

💥 BREAKING CHANGES

• due to 3b77dd1 - ♻️ remove mark_complete and complete verdict (commit by @jorben):

  GoalEvaluateResult.verdict no longer includes "complete"

• due to 6c0f5aa - ✨ 引入 Judge 验收 Agent 替代 goal_scored 自证 (PR #224 by @HayWolf):

  GoalEvaluateResult.verdict no longer includes "complete"

  • docs: 📝 update and reorder README feature list
    Update the feature descriptions and reorder the bullet points in both
    README.md and README_zh.md to better reflect the current product
    capabilities and improve readability. Changes include:
  • Reordering features to highlight persistent goal management, real-time
    streaming, and extensibility earlier in the list
  • Updating descriptions for several features to be more accurate
  • Maintaining consistency between English and Chinese versions
  • Keeping the overall structure while improving flow
    These are documentation-only changes that do not affect functionality.
  • refactor(goal): ♻️ extract resolveGoalStatusKey for testability
  • Extract inline status key resolution into a pure exported function
    so the complete→verified (judgePassed) branch can be unit-tested
    without mounting the component
  • Add unit tests covering all status mappings and judgePassed variants
  • Add test for skipped verdict passthrough in goalEvaluate
  • refactor(subagent): 🔧 increase builtin default max delegation depth to 5
    Raise BUILTIN_DEFAULT_MAX_DELEGATION_DEPTH from 3 to 5 to match the
    existing GLOBAL_MAX_DELEGATION_DEPTH, allowing built-in subagents
    (explore/review) to be delegated to the same depth as custom profiles.
    Update delegation validation tests to reflect the new depth limits.
  • docs: 📝 remove obsolete design document
  • docs(judge): 📝 add size-first verification strategy and delegation guidelines
  • refactor(goal): ♻️ remove goal-level time_used_seconds in favor of run-level elapsed tracking

  ---

• due to 6bf6da9 - 🐛 converge orphaned subagents and account final turns for judge-completed goals (PR #226 by @HayWolf):

  内部 AgentSession.context_compression_state
  及其关联启发式 API 已移除,替换为
  AgentSession.last_observed_usage: Arc<StdMutex<Option<Usage>>>;
  前端 RunUsageDto 新增必填 contextSize,旧 totalTokens 保留
  为 wire-level 显示。任何外部消费方需更新到新字段。
  Refs: tiycore 0.2.10-rc.2 Usage::context_size()

• due to f05858c - ♻️ flatten update_plan input (PR #228 by @HayWolf):

  update_plan no longer accepts a nested plan
  object. Clients must pass all fields as top-level arguments.

✨ New Features

• 00c6637 - ui: ✨ enable text selection in markdown preview and overlay (PR #221 by @HayWolf)
• 55e774b - subagent: ✨ Add nested subagent delegation with configurable depth limits (PR #223 by @HayWolf)
• d19a9e8 - goal: ✨ replace self-attestation goal_scored with independent Judge acceptance agent (commit by @jorben)
• 6c0f5aa - goal: ✨ 引入 Judge 验收 Agent 替代 goal_scored 自证 (PR #224 by @HayWolf)
• 4481759 - judge: ✨ redesign Judge evaluation for independence and completeness (commit by @jorben)
• 0cca885 - compression: ✨ reserve 20% context window for auto-compression trigger (commit by @jorben)

🐛 Bug Fixes

• 3690958 - core: 🐛 fix Windows cross-compilation type errors (PR #219 by @jorben)
• 0e8b153 - subagent: 🐛 make task field optional and fix UTF-8 safe truncation (commit by @jorben)
• 6bf6da9 - core: 🐛 converge orphaned subagents and account final turns for judge-completed goals (PR #226 by @HayWolf)
• f80d652 - agent: 🐛 fix timestamp slicing panic and add has_process_requirements tests (commit by @jorben)
• 73c7cb5 - run: 🐛 record elapsed running time when interrupting active runs (commit by @jorben)

♻️ Refactors

• 3a077c1 - thread: ♻️ track cumulative thread elapsed time across runs (PR #220 by @jorben)
• 96e7710 - prompt: ♻️ Overhaul prompt injection with modular layered architecture (PR #222 by @jorben)
• 3b77dd1 - goal: ♻️ remove mark_complete and complete verdict (commit by @jorben)
• e284fbe - goal: ♻️ extract resolveGoalStatusKey for testability (commit by @jorben)
• e8a58f2 - subagent: 🔧 increase builtin default max delegation depth to 5 (commit by @jorben)
• dc8fca0 - goal: ♻️ remove goal-level time_used_seconds in favor of run-level elapsed tracking (commit by @jorben)
• fe7fbfc - workbench: ♻️ remove runMode from frontend state management (PR #225 by @jorben)
• afd221e - goal: ♻️ centralize status transitions to explicit commands and Judge verdicts (commit by @jorben)
• f05858c - core: ♻️ flatten update_plan input (PR #228 by @HayWolf)

✅ Tests

• eb4b722 - cover Judge summary builders and mapRunSummaryToContextUsage fallback (commit by @jorben)

🔧 Chores

• 539005c - deps: 🔧 align tiycore to 0.2.10-rc.2 and adopt Usage::context_size() (commit by @jorben)

0.3.19-rc.8

💥 BREAKING CHANGES

• due to 3b77dd1 - ♻️ remove mark_complete and complete verdict (commit by @jorben):

  GoalEvaluateResult.verdict no longer includes "complete"

• due to 6c0f5aa - ✨ 引入 Judge 验收 Agent 替代 goal_scored 自证 (PR #224 by @HayWolf):

  GoalEvaluateResult.verdict no longer includes "complete"

  • docs: 📝 update and reorder README feature list
    Update the feature descriptions and reorder the bullet points in both
    README.md and README_zh.md to better reflect the current product
    capabilities and improve readability. Changes include:
  • Reordering features to highlight persistent goal management, real-time
    streaming, and extensibility earlier in the list
  • Updating descriptions for several features to be more accurate
  • Maintaining consistency between English and Chinese versions
  • Keeping the overall structure while improving flow
    These are documentation-only changes that do not affect functionality.
  • refactor(goal): ♻️ extract resolveGoalStatusKey for testability
  • Extract inline status key resolution into a pure exported function
    so the complete→verified (judgePassed) branch can be unit-tested
    without mounting the component
  • Add unit tests covering all status mappings and judgePassed variants
  • Add test for skipped verdict passthrough in goalEvaluate
  • refactor(subagent): 🔧 increase builtin default max delegation depth to 5
    Raise BUILTIN_DEFAULT_MAX_DELEGATION_DEPTH from 3 to 5 to match the
    existing GLOBAL_MAX_DELEGATION_DEPTH, allowing built-in subagents
    (explore/review) to be delegated to the same depth as custom profiles.
    Update delegation validation tests to reflect the new depth limits.
  • docs: 📝 remove obsolete design document
  • docs(judge): 📝 add size-first verification strategy and delegation guidelines
  • refactor(goal): ♻️ remove goal-level time_used_seconds in favor of run-level elapsed tracking

  ---

✨ New Features

• 00c6637 - ui: ✨ enable text selection in markdown preview and overlay (PR #221 by @HayWolf)
• 55e774b - subagent: ✨ Add nested subagent delegation with configurable depth limits (PR #223 by @HayWolf)
• d19a9e8 - goal: ✨ replace self-attestation goal_scored with independent Judge acceptance agent (commit by @jorben)
• 6c0f5aa - goal: ✨ 引入 Judge 验收 Agent 替代 goal_scored 自证 (PR #224 by @HayWolf)
• 4481759 - judge: ✨ redesign Judge evaluation for independence and completeness (commit by @jorben)
• 0cca885 - compression: ✨ reserve 20% context window for auto-compression trigger (commit by @jorben)

🐛 Bug Fixes

• 3690958 - core: 🐛 fix Windows cross-compilation type errors (PR #219 by @jorben)
• 0e8b153 - subagent: 🐛 make task field optional and fix UTF-8 safe truncation (commit by @jorben)
• f80d652 - agent: 🐛 fix timestamp slicing panic and add has_process_requirements tests (commit by @jorben)
• 73c7cb5 - run: 🐛 record elapsed running time when interrupting active runs (commit by @jorben)

♻️ Refactors

• 3a077c1 - thread: ♻️ track cumulative thread elapsed time across runs (PR #220 by @jorben)
• 96e7710 - prompt: ♻️ Overhaul prompt injection with modular layered architecture (PR #222 by @jorben)
• 3b77dd1 - goal: ♻️ remove mark_complete and complete verdict (commit by @jorben)
• e284fbe - goal: ♻️ extract resolveGoalStatusKey for testability (commit by @jorben)
• e8a58f2 - subagent: 🔧 increase builtin default max delegation depth to 5 (commit by @jorben)
• dc8fca0 - goal: ♻️ remove goal-level time_used_seconds in favor of run-level elapsed tracking (commit by @jorben)
• fe7fbfc - workbench: ♻️ remove runMode from frontend state management (PR #225 by @jorben)
• afd221e - goal: ♻️ centralize status transitions to explicit commands and Judge verdicts (commit by @jorben)

🔧 Chores

• 539005c - deps: 🔧 align tiycore to 0.2.10-rc.2 and adopt Usage::context_size() (commit by @jorben)

0.3.19-rc.7

💥 BREAKING CHANGES

• due to 3b77dd1 - ♻️ remove mark_complete and complete verdict (commit by @jorben):

  GoalEvaluateResult.verdict no longer includes "complete"

• due to 6c0f5aa - ✨ 引入 Judge 验收 Agent 替代 goal_scored 自证 (PR #224 by @HayWolf):

  GoalEvaluateResult.verdict no longer includes "complete"

  • docs: 📝 update and reorder README feature list
    Update the feature descriptions and reorder the bullet points in both
    README.md and README_zh.md to better reflect the current product
    capabilities and improve readability. Changes include:
  • Reordering features to highlight persistent goal management, real-time
    streaming, and extensibility earlier in the list
  • Updating descriptions for several features to be more accurate
  • Maintaining consistency between English and Chinese versions
  • Keeping the overall structure while improving flow
    These are documentation-only changes that do not affect functionality.
  • refactor(goal): ♻️ extract resolveGoalStatusKey for testability
  • Extract inline status key resolution into a pure exported function
    so the complete→verified (judgePassed) branch can be unit-tested
    without mounting the component
  • Add unit tests covering all status mappings and judgePassed variants
  • Add test for skipped verdict passthrough in goalEvaluate
  • refactor(subagent): 🔧 increase builtin default max delegation depth to 5
    Raise BUILTIN_DEFAULT_MAX_DELEGATION_DEPTH from 3 to 5 to match the
    existing GLOBAL_MAX_DELEGATION_DEPTH, allowing built-in subagents
    (explore/review) to be delegated to the same depth as custom profiles.
    Update delegation validation tests to reflect the new depth limits.
  • docs: 📝 remove obsolete design document
  • docs(judge): 📝 add size-first verification strategy and delegation guidelines
  • refactor(goal): ♻️ remove goal-level time_used_seconds in favor of run-level elapsed tracking

  ---

✨ New Features

• 00c6637 - ui: ✨ enable text selection in markdown preview and overlay (PR #221 by @HayWolf)
• 55e774b - subagent: ✨ Add nested subagent delegation with configurable depth limits (PR #223 by @HayWolf)
• d19a9e8 - goal: ✨ replace self-attestation goal_scored with independent Judge acceptance agent (commit by @jorben)
• 6c0f5aa - goal: ✨ 引入 Judge 验收 Agent 替代 goal_scored 自证 (PR #224 by @HayWolf)
• 4481759 - judge: ✨ redesign Judge evaluation for independence and completeness (commit by @jorben)
• 0cca885 - compression: ✨ reserve 20% context window for auto-compression trigger (commit by @jorben)

🐛 Bug Fixes

• 3690958 - core: 🐛 fix Windows cross-compilation type errors (PR #219 by @jorben)
• 0e8b153 - subagent: 🐛 make task field optional and fix UTF-8 safe truncation (commit by @jorben)
• f80d652 - agent: 🐛 fix timestamp slicing panic and add has_process_requirements tests (commit by @jorben)

♻️ Refactors

• 3a077c1 - thread: ♻️ track cumulative thread elapsed time across runs (PR #220 by @jorben)
• 96e7710 - prompt: ♻️ Overhaul prompt injection with modular layered architecture (PR #222 by @jorben)
• 3b77dd1 - goal: ♻️ remove mark_complete and complete verdict (commit by @jorben)
• e284fbe - goal: ♻️ extract resolveGoalStatusKey for testability (commit by @jorben)
• e8a58f2 - subagent: 🔧 increase builtin default max delegation depth to 5 (commit by @jorben)
• dc8fca0 - goal: ♻️ remove goal-level time_used_seconds in favor of run-level elapsed tracking (commit by @jorben)
• fe7fbfc - workbench: ♻️ remove runMode from frontend state management (PR #225 by @jorben)
• afd221e - goal: ♻️ centralize status transitions to explicit commands and Judge verdicts (commit by @jorben)

🔧 Chores

• 539005c - deps: 🔧 align tiycore to 0.2.10-rc.2 and adopt Usage::context_size() (commit by @jorben)

0.3.19-rc.6

💥 BREAKING CHANGES

• due to 3b77dd1 - ♻️ remove mark_complete and complete verdict (commit by @jorben):

  GoalEvaluateResult.verdict no longer includes "complete"

• due to 6c0f5aa - ✨ 引入 Judge 验收 Agent 替代 goal_scored 自证 (PR #224 by @HayWolf):

  GoalEvaluateResult.verdict no longer includes "complete"

  • docs: 📝 update and reorder README feature list
    Update the feature descriptions and reorder the bullet points in both
    README.md and README_zh.md to better reflect the current product
    capabilities and improve readability. Changes include:
  • Reordering features to highlight persistent goal management, real-time
    streaming, and extensibility earlier in the list
  • Updating descriptions for several features to be more accurate
  • Maintaining consistency between English and Chinese versions
  • Keeping the overall structure while improving flow
    These are documentation-only changes that do not affect functionality.
  • refactor(goal): ♻️ extract resolveGoalStatusKey for testability
  • Extract inline status key resolution into a pure exported function
    so the complete→verified (judgePassed) branch can be unit-tested
    without mounting the component
  • Add unit tests covering all status mappings and judgePassed variants
  • Add test for skipped verdict passthrough in goalEvaluate
  • refactor(subagent): 🔧 increase builtin default max delegation depth to 5
    Raise BUILTIN_DEFAULT_MAX_DELEGATION_DEPTH from 3 to 5 to match the
    existing GLOBAL_MAX_DELEGATION_DEPTH, allowing built-in subagents
    (explore/review) to be delegated to the same depth as custom profiles.
    Update delegation validation tests to reflect the new depth limits.
  • docs: 📝 remove obsolete design document
  • docs(judge): 📝 add size-first verification strategy and delegation guidelines
  • refactor(goal): ♻️ remove goal-level time_used_seconds in favor of run-level elapsed tracking

  ---

✨ New Features

• 00c6637 - ui: ✨ enable text selection in markdown preview and overlay (PR #221 by @HayWolf)
• 55e774b - subagent: ✨ Add nested subagent delegation with configurable depth limits (PR #223 by @HayWolf)
• d19a9e8 - goal: ✨ replace self-attestation goal_scored with independent Judge acceptance agent (commit by @jorben)
• 6c0f5aa - goal: ✨ 引入 Judge 验收 Agent 替代 goal_scored 自证 (PR #224 by @HayWolf)
• 4481759 - judge: ✨ redesign Judge evaluation for independence and completeness (commit by @jorben)

🐛 Bug Fixes

• 3690958 - core: 🐛 fix Windows cross-compilation type errors (PR #219 by @jorben)
• 0e8b153 - subagent: 🐛 make task field optional and fix UTF-8 safe truncation (commit by @jorben)

♻️ Refactors

• 3a077c1 - thread: ♻️ track cumulative thread elapsed time across runs (PR #220 by @jorben)
• 96e7710 - prompt: ♻️ Overhaul prompt injection with modular layered architecture (PR #222 by @jorben)
• 3b77dd1 - goal: ♻️ remove mark_complete and complete verdict (commit by @jorben)
• e284fbe - goal: ♻️ extract resolveGoalStatusKey for testability (commit by @jorben)
• e8a58f2 - subagent: 🔧 increase builtin default max delegation depth to 5 (commit by @jorben)
• dc8fca0 - goal: ♻️ remove goal-level time_used_seconds in favor of run-level elapsed tracking (commit by @jorben)
• fe7fbfc - workbench: ♻️ remove runMode from frontend state management (PR #225 by @jorben)

🔧 Chores

• 539005c - deps: 🔧 align tiycore to 0.2.10-rc.2 and adopt Usage::context_size() (commit by @jorben)

0.3.19-rc.5

💥 BREAKING CHANGES

• due to 3b77dd1 - ♻️ remove mark_complete and complete verdict (commit by @jorben):

  GoalEvaluateResult.verdict no longer includes "complete"

• due to 6c0f5aa - ✨ 引入 Judge 验收 Agent 替代 goal_scored 自证 (PR #224 by @HayWolf):

  GoalEvaluateResult.verdict no longer includes "complete"

  • docs: 📝 update and reorder README feature list
    Update the feature descriptions and reorder the bullet points in both
    README.md and README_zh.md to better reflect the current product
    capabilities and improve readability. Changes include:
  • Reordering features to highlight persistent goal management, real-time
    streaming, and extensibility earlier in the list
  • Updating descriptions for several features to be more accurate
  • Maintaining consistency between English and Chinese versions
  • Keeping the overall structure while improving flow
    These are documentation-only changes that do not affect functionality.
  • refactor(goal): ♻️ extract resolveGoalStatusKey for testability
  • Extract inline status key resolution into a pure exported function
    so the complete→verified (judgePassed) branch can be unit-tested
    without mounting the component
  • Add unit tests covering all status mappings and judgePassed variants
  • Add test for skipped verdict passthrough in goalEvaluate
  • refactor(subagent): 🔧 increase builtin default max delegation depth to 5
    Raise BUILTIN_DEFAULT_MAX_DELEGATION_DEPTH from 3 to 5 to match the
    existing GLOBAL_MAX_DELEGATION_DEPTH, allowing built-in subagents
    (explore/review) to be delegated to the same depth as custom profiles.
    Update delegation validation tests to reflect the new depth limits.
  • docs: 📝 remove obsolete design document
  • docs(judge): 📝 add size-first verification strategy and delegation guidelines
  • refactor(goal): ♻️ remove goal-level time_used_seconds in favor of run-level elapsed tracking

  ---

✨ New Features

• 00c6637 - ui: ✨ enable text selection in markdown preview and overlay (PR #221 by @HayWolf)
• 55e774b - subagent: ✨ Add nested subagent delegation with configurable depth limits (PR #223 by @HayWolf)
• d19a9e8 - goal: ✨ replace self-attestation goal_scored with independent Judge acceptance agent (commit by @jorben)
• 6c0f5aa - goal: ✨ 引入 Judge 验收 Agent 替代 goal_scored 自证 (PR #224 by @HayWolf)
• 4481759 - judge: ✨ redesign Judge evaluation for independence and completeness (commit by @jorben)

🐛 Bug Fixes

• 3690958 - core: 🐛 fix Windows cross-compilation type errors (PR #219 by @jorben)
• 0e8b153 - subagent: 🐛 make task field optional and fix UTF-8 safe truncation (commit by @jorben)

♻️ Refactors

• 3a077c1 - thread: ♻️ track cumulative thread elapsed time across runs (PR #220 by @jorben)
• 96e7710 - prompt: ♻️ Overhaul prompt injection with modular layered architecture (PR #222 by @jorben)
• 3b77dd1 - goal: ♻️ remove mark_complete and complete verdict (commit by @jorben)
• e284fbe - goal: ♻️ extract resolveGoalStatusKey for testability (commit by @jorben)
• e8a58f2 - subagent: 🔧 increase builtin default max delegation depth to 5 (commit by @jorben)
• dc8fca0 - goal: ♻️ remove goal-level time_used_seconds in favor of run-level elapsed tracking (commit by @jorben)
• fe7fbfc - workbench: ♻️ remove runMode from frontend state management (PR #225 by @jorben)

0.3.19-rc.4

💥 BREAKING CHANGES

• due to 6c0f5aa - ✨ 引入 Judge 验收 Agent 替代 goal_scored 自证 (PR #224 by @HayWolf):

  GoalEvaluateResult.verdict no longer includes "complete"

  • docs: 📝 update and reorder README feature list
    Update the feature descriptions and reorder the bullet points in both
    README.md and README_zh.md to better reflect the current product
    capabilities and improve readability. Changes include:
  • Reordering features to highlight persistent goal management, real-time
    streaming, and extensibility earlier in the list
  • Updating descriptions for several features to be more accurate
  • Maintaining consistency between English and Chinese versions
  • Keeping the overall structure while improving flow
    These are documentation-only changes that do not affect functionality.
  • refactor(goal): ♻️ extract resolveGoalStatusKey for testability
  • Extract inline status key resolution into a pure exported function
    so the complete→verified (judgePassed) branch can be unit-tested
    without mounting the component
  • Add unit tests covering all status mappings and judgePassed variants
  • Add test for skipped verdict passthrough in goalEvaluate
  • refactor(subagent): 🔧 increase builtin default max delegation depth to 5
    Raise BUILTIN_DEFAULT_MAX_DELEGATION_DEPTH from 3 to 5 to match the
    existing GLOBAL_MAX_DELEGATION_DEPTH, allowing built-in subagents
    (explore/review) to be delegated to the same depth as custom profiles.
    Update delegation validation tests to reflect the new depth limits.
  • docs: 📝 remove obsolete design document
  • docs(judge): 📝 add size-first verification strategy and delegation guidelines
  • refactor(goal): ♻️ remove goal-level time_used_seconds in favor of run-level elapsed tracking

  ---

✨ New Features

• 00c6637 - ui: ✨ enable text selection in markdown preview and overlay (PR #221 by @HayWolf)
• 55e774b - subagent: ✨ Add nested subagent delegation with configurable depth limits (PR #223 by @HayWolf)
• 6c0f5aa - goal: ✨ 引入 Judge 验收 Agent 替代 goal_scored 自证 (PR #224 by @HayWolf)

🐛 Bug Fixes

• 3690958 - core: 🐛 fix Windows cross-compilation type errors (PR #219 by @jorben)
• 5a168e9 - core: 🐛 converge orphaned subagents and account final turns for judge-completed goals (commit by @jorben)

♻️ Refactors

• 3a077c1 - thread: ♻️ track cumulative thread elapsed time across runs (PR #220 by @jorben)
• 96e7710 - prompt: ♻️ Overhaul prompt injection with modular layered architecture (PR #222 by @jorben)
• fe7fbfc - workbench: ♻️ remove runMode from frontend state management (PR #225 by @jorben)

0.3.19-rc.3

💥 BREAKING CHANGES

• due to 6c0f5aa - ✨ 引入 Judge 验收 Agent 替代 goal_scored 自证 (PR #224 by @HayWolf):

  GoalEvaluateResult.verdict no longer includes "complete"

  • docs: 📝 update and reorder README feature list
    Update the feature descriptions and reorder the bullet points in both
    README.md and README_zh.md to better reflect the current product
    capabilities and improve readability. Changes include:
  • Reordering features to highlight persistent goal management, real-time
    streaming, and extensibility earlier in the list
  • Updating descriptions for several features to be more accurate
  • Maintaining consistency between English and Chinese versions
  • Keeping the overall structure while improving flow
    These are documentation-only changes that do not affect functionality.
  • refactor(goal): ♻️ extract resolveGoalStatusKey for testability
  • Extract inline status key resolution into a pure exported function
    so the complete→verified (judgePassed) branch can be unit-tested
    without mounting the component
  • Add unit tests covering all status mappings and judgePassed variants
  • Add test for skipped verdict passthrough in goalEvaluate
  • refactor(subagent): 🔧 increase builtin default max delegation depth to 5
    Raise BUILTIN_DEFAULT_MAX_DELEGATION_DEPTH from 3 to 5 to match the
    existing GLOBAL_MAX_DELEGATION_DEPTH, allowing built-in subagents
    (explore/review) to be delegated to the same depth as custom profiles.
    Update delegation validation tests to reflect the new depth limits.
  • docs: 📝 remove obsolete design document
  • docs(judge): 📝 add size-first verification strategy and delegation guidelines
  • refactor(goal): ♻️ remove goal-level time_used_seconds in favor of run-level elapsed tracking

  ---

✨ New Features

• 00c6637 - ui: ✨ enable text selection in markdown preview and overlay (PR #221 by @HayWolf)
• 55e774b - subagent: ✨ Add nested subagent delegation with configurable depth limits (PR #223 by @HayWolf)
• 6c0f5aa - goal: ✨ 引入 Judge 验收 Agent 替代 goal_scored 自证 (PR #224 by @HayWolf)

🐛 Bug Fixes

• 3690958 - core: 🐛 fix Windows cross-compilation type errors (PR #219 by @jorben)

♻️ Refactors

• 3a077c1 - thread: ♻️ track cumulative thread elapsed time across runs (PR #220 by @jorben)
• 96e7710 - prompt: ♻️ Overhaul prompt injection with modular layered architecture (PR #222 by @jorben)
• fe7fbfc - workbench: ♻️ remove runMode from frontend state management (PR #225 by @jorben)

0.3.19-rc.2

💥 BREAKING CHANGES

• due to 3b77dd1 - ♻️ remove mark_complete and complete verdict (commit by @jorben):

  GoalEvaluateResult.verdict no longer includes "complete"

✨ New Features

• 00c6637 - ui: ✨ enable text selection in markdown preview and overlay (PR #221 by @HayWolf)
• 55e774b - subagent: ✨ Add nested subagent delegation with configurable depth limits (PR #223 by @HayWolf)
• d19a9e8 - goal: ✨ replace self-attestation goal_scored with independent Judge acceptance agent (commit by @jorben)

🐛 Bug Fixes

• 3690958 - core: 🐛 fix Windows cross-compilation type errors (PR #219 by @jorben)

♻️ Refactors

• 3a077c1 - thread: ♻️ track cumulative thread elapsed time across runs (PR #220 by @jorben)
• 96e7710 - prompt: ♻️ Overhaul prompt injection with modular layered architecture (PR #222 by @jorben)
• 3b77dd1 - goal: ♻️ remove mark_complete and complete verdict (commit by @jorben)
• e284fbe - goal: ♻️ extract resolveGoalStatusKey for testability (commit by @jorben)

0.3.19-rc.1

✨ New Features

• 00c6637 - ui: ✨ enable text selection in markdown preview and overlay (PR #221 by @HayWolf)

🐛 Bug Fixes

• 3690958 - core: 🐛 fix Windows cross-compilation type errors (PR #219 by @jorben)

♻️ Refactors

• 3a077c1 - thread: ♻️ track cumulative thread elapsed time across runs (PR #220 by @jorben)