| Age | Commit message (Collapse) | Author |
|---|
|
Model Ollama chat thinking separately from final content, preserve it only across assistant tool-call continuation, and keep private reasoning out of user results, session context, and logs.
Accept native boolean and low/medium/high/max think values, normalize YAML booleans, and serialize explicit overrides using the native top-level chat field.
Stop forcing think=false for structured planning, skill selection, and context summaries; corrected retries now retain the configured thinking mode.
Update the specification, design, audit report, and requirement traceability for OLL-14.
Add request/response, configuration, observability, retry, and tool-continuation coverage. Verified with 92 passing Agent.Core tests and a deepseek-v4-flash:cloud think:true MCP operational run.
|
|
Replace the uv-specific skill with a portable Python skill and rewrite the default user system prompt as a concise, structured Markdown execution policy.
Normalize a single fenced structured-JSON response, retry invalid skill selection with think disabled, validate selected skill output, and make coding plans keep editing and verification in one task.
Document the file_edit patch payload, expose that contract in the tool catalog, and convert malformed patch input into a retryable tool failure instead of terminating the agent task.
Update configuration and runtime tests for the Python skill, exact tool catalog, structured-output retry, and implementation-and-verification planning guidance.
Verified with 82 Agent.Core tests and an agent-mcp Python scheduling scenario with 49 passing unittest cases.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
persistence
AgentRuntime.ExecutePlannerTaskAsync:
- Add PlannerValidationException and FileNotFoundException to the tool
execution catch clause so that 'Completed tasks are immutable' and
'Approved path does not exist' errors are returned as tool results
instead of propagating as unhandled task failures.
- Treat task_update as a metadata tool: its failures no longer add to
unresolvedToolFailures, so the LLM is not forced into an infinite
retry loop when task_update receives invalid arguments.
- Skip throwing InvalidOperationException for RetryAllowed=false
failures originating from metadata tools (task_update), preventing
unnecessary replan cycles caused by graph bookkeeping errors.
- Improve the 'No tasks were executed' fallback message: when replan
was attempted but no tasks could execute, report that the sandbox
policy denied required operations.
PlannerService.PlanAsync:
- Persist fallback TaskGraph to session.TaskGraphs[taskId] in all
three fallback paths (ChatStructuredAsync exception, empty/null plan,
BuildTaskGraph exception) so that BeginTask's TryAdd does not create
an empty graph that shadows the fallback.
|
|
Two runtime bugs discovered during MCP integration testing:
1. PlannerService.BuildTaskGraph fallback: If the LLM-generated plan
contains invalid tasks (bad estimates, cycles, etc.), graph.AddTask
throws PlannerValidationException. Previously this propagated up and
caused "No tasks were executed." or "Planning failed" errors.
Fix: wrap BuildTaskGraph in try/catch, fall back to single-task
graph. Also handle graph.Count == 0 after filtering.
2. TaskGraphToolHandler.BeginTask conflict: PlanAsync stores the
planned TaskGraph in session.TaskGraphs[taskId] before RunAsync
calls BeginTaskAsync. BeginTask then tried TryAdd which failed
because the key already existed, throwing
"TaskGraph for '...' already exists in session".
Fix: use TryAdd without throwing on conflict — if PlanAsync already
created the graph, keep it; otherwise add a new empty one.
Test results: Core 61/61, Planner 10/10, Windows 41/41 (elevated).
MCP integration: agent_run/agent_status verified via HTTP transport.
ACL boundary: C:\Windows\System32 access correctly denied by sandbox.
ToolUseGuard: "Required external effect was not completed" fires
correctly when LLM does not produce verifiable external effect.
|
|
fixes
## P3: Session/Planning Foundation
### PlanAsync / RunAsync flow separation (Design §8.4)
- AgentRuntime.ExecuteAsync now follows a two-phase lifecycle:
1. Planning: generate Initial TaskGraph via Ollama structured output
2. Running: execute ready Tasks (dependencies satisfied) in
critical-path then creation order
- Sandbox Task Resource (BeginTask/EndTask) is applied at RunAsync
time, not PlanAsync time (Design constraint)
- QueuedTaskWorker transitions to Planning; ExecuteAsync transitions
to Running internally
### PlannerService (new: src/Agent.Core/Runtime/PlannerService.cs)
- PlanAsync: uses Ollama ChatStructuredAsync with JSON Schema to
generate a TaskGraph with per-Task requires_external_effect
- ReplanAsync: rebuilds TaskGraph after policy deny, preserving
completed tasks (Design §8.4)
- Fallback: single-task plan with conservative estimates when
structured output fails or returns empty
- Pure analysis tasks get RequiresExternalEffect=false with at
least 1 Task (Design constraint)
### PlanResult / PlanSchema (new: src/Agent.Core/Runtime/PlanResult.cs)
- JSON model for LLM structured output during Planning
- JSON Schema with tasks array: description, dependencies (by index),
budget_class, PERT estimates, requires_external_effect
### requires_external_effect integration (P2 + P3)
- Removed keyword heuristic RequiresExternalEffect() from AgentRuntime
- Removed tool-name-counting RequiredToolCalls() from AgentRuntime
- ToolUseGuard now receives PlannerTask.RequiresExternalEffect
(set by Planner during Planning, not by keyword matching)
- requires_external_effect is NOT always true; it is a per-Task
attribute determined by the Planner (Design constraint)
### RunAsync / ready Task execution
- SelectNextReadyTask: dependencies satisfied, not completed/failed,
critical path first then creation order
- Each PlannerTask executed via ExecutePlannerTaskAsync (LLM
chat-with-tools iteration loop)
- TaskGraph.AddUsage records per-Task token usage for CPM tracking
### Replan implementation
- Policy deny (InvalidOperationException with "denied by sandbox
policy") triggers ReplanAsync, up to max 3 replan attempts
- Failed task is marked Failed in TaskGraph before replan
- Registry transitions back to Running for replan iteration
## P3-A: AgentSession + TaskGraph ownership
### AgentSession expansion (src/Agent.Core/Sessions/AgentSession.cs)
- Added Summary, ExecutionResults, TaskGraphs
(ConcurrentDictionary<Guid, TaskGraph>)
- TaskGraph is per-MCP-Task (1 agent_run = 1 TaskGraph), NOT shared
per-Session (Design constraint)
- Added CompactConversation, CompactExecutionResults, SetSummary
methods for context summary compaction
### ExecutionResult (new: src/Agent.Core/Sessions/ExecutionResult.cs)
- Records tool execution results in session for context summary
- Fields: TaskId, ToolName, Success, Output
### SessionStore (src/Agent.Core/Sessions/SessionStore.cs)
- Added Sessions property for TaskGraphToolHandler to resolve graphs
by TaskId across sessions
### sessionId threading
- IInternalToolBackend.BeginTaskAsync signature changed to include
sessionId parameter
- InternalToolDispatcher, WindowsToolBackend, TaskGraphToolHandler
updated to thread sessionId through
- task_update schema includes requires_external_effect property
- McpHost and Program.cs pass SessionStore to TaskRegistry
## P3: Context Summary (Design §9.3)
- Context utilization = latest prompt_eval_count / num_ctx
(NOT cumulative InputTokens) (Design constraint)
- TryContextSummary: compacts old Conversation/ExecutionResults when
utilization exceeds 80% threshold
- AgentRuntimeSettings: added NumCtx, ContextSummaryThreshold,
ConversationKeepLastN, ExecutionResultsKeepLastN
- OllamaResult: added PromptEvalCount field
- OllamaClient: passes PromptEvalCount from OllamaChatResponse
## P3: ExecutionResults Session recording
- ExecutePlannerTaskAsync records each tool execution result via
session.AppendExecutionResult for context summary and audit
## Windows test fixes
### SandboxPolicyException catch (src/Agent.Windows/Tools/WindowsToolBackend.cs)
- ExecuteAsync now catches SandboxPolicyException and returns
ToolExecutionResult(false, ..., RetryAllowed: false) instead of
propagating the exception
- Fixes Dir_mkdir_outside_approved_root_is_denied and
File_edit_rename_rejects_outside_approved_root tests
### LoopbackExemption cleanup (tests/Agent.Windows.Tests/SecurityPolicyTests.cs)
- Recovery_after_crash: added pre-clean and try/finally to ensure
LoopbackExemption is always removed, even on assertion failure
- Independent_process_crash: added pre-clean to remove residual
loopback exemption from prior test failures
- Fixes 7 Independent_process_crash scenarios that were failing due
to LoopbackExemption residue from Recovery_after_crash
## Test updates (tests/Agent.Core.Tests/PromptAndRuntimeTests.cs)
- FakeOllamaClient implementations updated with ChatStructuredAsync
and ChatWithToolsAsync overrides to support Plan/Run flow
- RecordingOllamaClient: returns single-task plan JSON for
ChatStructuredAsync, tracks all call types
- ToolCallingOllamaClient: returns plan with
requires_external_effect=true for file edit tasks
- Test expectations updated for Plan+Run call counts and token
accounting (Plan tokens not added to registry usage)
## Documentation updates
- Design.md §7.7: requires_external_effect is set by Planner during
Planning, not keyword heuristic
- Design.md §8.4: Plan/Run phase separation, replan after policy deny
- Design.md §9.3: context utilization formula clarified
- ImplementationPlan.md §10.3: Plan/Run flow, replan, Context Summary
## Test results (all passing)
- Agent.Core.Tests: 61/61
- Agent.Planner.Tests: 10/10
- Agent.Windows.Tests (elevated): 41/41
- Build: 0 errors, 0 warnings
|
|
P5残件3項目を実装:
1. Ollama structured output (format param):
- OllamaChatRequestへFormat プロパティ追加 (JsonElement?)
- IOllamaClientへChatStructuredAsync メソッド追加
- OllamaClient.ChatCoreAsync へformat パラメータ追加
- ChatStructuredAsync はtoolsなし、format指定でJSON構造化出力を要求
2. AgentRuntime skill selection step:
- SelectSkillsAsync メソッド追加: メインループ前にOllamaへskill catalogを送信
- structured output で {"selected_skills": ["name"]} を取得
- ParseSelectedSkills: JSON解析、unknown skill名排除、重複排除、最大10件
- structured output非対応モデルはfallback空リスト
- 選択されたskillのInstructionsのみPromptContext.SelectedSkillsへ設定
- Progressive Disclosure Stage 2→3 が完了
3. Skill security/path validation:
- SelectSkillsAsync でsettings.Skillsからのみ選択（unknown name排除）
- SkillLoader でreparse point skip済み（既存実装）
- 選択数上限10件でDoS防止
- Skill load != permission grant 維持: allowed-toolsはSandbox permissionに影響しない
変更対象:
- OllamaModels.cs: OllamaChatRequest.Format プロパティ追加
- IOllamaClient.cs: ChatStructuredAsync メソッド追加
- OllamaClient.cs: ChatCoreAsync へformat パラメータ追加、ChatStructuredAsync 実装
- AgentRuntime.cs: SelectSkillsAsync + ParseSelectedSkills、メインループ前の選択ステップ
検証結果:
- Release build: 警告0、エラー0
- Core tests: 61/61 PASS、skip 0
- Planner tests: 10/10 PASS、skip 0
|
|
P1: Tool小改善
1. tailバイナリ判定 (TextFileDetector):
- file_search tailモードでtext/binary判定を追加
- 先頭4KBのみ読み、BOM確認(UTF-8/UTF-16 LE/BE)→UTF-8 strict byte検証
- NULバイトのみ判定不可(UTF-16でNULが正常出現するため)
- binaryファイルはToolValidationExceptionで拒否
- TextFileDetectorクラスへ判定ロジックを分離
2. file_edit rename機能:
- file_edit.operation=renameを追加(新規toolではない)
- new_path property追加、Write capability要求(source/destination双方)
- destination既存時は禁止(overwrite不可)
- cross-volume renameは不支持、Tool failureとして拒否
- FileRenameTransaction + RecoveryManager file.rename recovery追加
- crash recovery: destination hash == journal記録の場合のみ戻す
P5: Agent Skills open standard準拠
3. Skill形式をagentskills.io標準へ移行:
- legacy単一Markdown形式(skills/*.md)を廃止
- <skill-name>/SKILL.md標準directory形式のみ対応
- YAML frontmatter必須(name/description)、YamlDotNetで解析
- validation: name必須(1-64文字,lowercase英数字+hyphen,親dir名一致),
description必須(1-1024文字), malformed YAML reject, duplicate fatal
4. Progressive Disclosure:
- Stage 1 Discovery: name+descriptionのみをsystem messageへ(name+desc一覧)
- Stage 3 Instructions: 選択Skillの本文のみ注入
- PromptComposer: 全文埋め込みを廃止、カタログ形式へ変更
- PromptContext: Skills→AvailableSkills+SelectedSkillsへ分割
- 未選択Skill本文はpromptへ入らない
5. Internal Tool境界維持:
- skill_read等のInternal Tool追加なし
- Internal Toolは6群(file_search/file_read/file_edit/process_run/task_update/dir)のまま
- Skill選択・本文ロードはAgent Runtime/Prompt Context Managementの責務
6. AgentSkill data model (Agent.Core/Skills/AgentSkill.cs):
- RootPath, Name, Description, Instructions, License?, Compatibility?, Metadata?, AllowedTools?
- SkillLoader(Agent.App)がYamlDotNetでfrontmatter解析→AgentSkill構築
設計判断:
- renameはfile_edit operation拡張(新規toolではない)
- rmdir空dirのみ制約は維持
- Skill load != permission grant維持
- allowed-toolsはSandbox permissionとして解釈しない
- YamlDotNetはAgent.App側のみ使用(Agent.Coreへ依存追加なし)
変更対象:
- TextFileDetector.cs: 新規、text/binary判定
- WindowsToolBackend.cs: tail binary判定統合、rename case追加
- InternalToolCatalog.cs: file_edit operation enum に rename 追加、new_path property
- InternalToolValidator.cs: rename時new_path必須検証
- TransactionalFileEditor.cs: Rename() + FileRenameTransaction
- RecoveryManager.cs: file.rename recovery
- AgentSkill.cs: 新規data model
- SkillLoader.cs: 全面書き換え、YamlDotNet frontmatter解析、validation
- PromptComposer.cs: Progressive Disclosure、AvailableSkills+SelectedSkills
- AgentRuntimeSettings.cs: Skills型変更
- AgentRuntime.cs: SelectedSkills=[]で初期化
- Program.cs: SkillLoader戻り値型対応
- Specifications.md: FS-07 rename、Skill節Agent Skills standard準拠
- Design.md: §7.1 tail binary判定、§7.3 rename、AgentSkill model
- ImplementationPlan.md: Prompt順序更新、Skill標準準拠
テスト:
- SecurityPolicyTests.cs: tail binary拒否/UTF-8/UTF-16 text許可、rename正常/dest既存拒否/許可外拒否
- InternalToolTests.cs: rename validationテスト追加
- ConfigurationTests.cs: SkillLoader標準形式/missing frontmatter/name mismatch/duplicate tests
- PromptAndRuntimeTests.cs: PromptContext型変更対応、skill catalog検証
検証結果:
- Release build: 警告0、エラー0
- Core tests: 61/61 PASS、skip 0
- Planner tests: 10/10 PASS、skip 0
- Internal Tool 6群固定: 確認済み
|
|
Treat Policy Engine denials and UnauthorizedAccessException results as terminal tool failures by adding RetryAllowed metadata to ToolExecutionResult.
Stop the Agent loop immediately after recording the denied tool result, transition the Task to failed, and run normal Task resource cleanup instead of returning the same failure to the LLM for another iteration. Correctable validation and process failures retain the existing bounded retry behavior.
Expose RetryAllowed in llm.jsonl and document the fail-fast security invariant in Specifications, Design, and ImplementationPlan.
Tests: Agent.Core.Tests 50/50 passed with skip 0; Release build passed with 0 warnings and 0 errors. The full Windows suite remained environment-blocked outside an elevated token: 14 tests failed while creating/deriving the fixed AppContainer or creating symlinks; 11 passed and none were skipped.
Release: refreshed the win-x64 self-contained folder binaries, publish manifest, ZIP, and checksum while preserving the local agent.yaml. The clean ZIP contains no runtime logs or Task state.
|
|
Specifications、Design、ImplementationPlanの優先順位を整理し、単一Task実行モデル、typed option優先、設定可能なresource上限、local Ollamaを必須とするRelease Gateを文書化。
.NET 10/C# 14の5 production project、3 test project、E2E Clientを構築。typed YAML、en/ja locale、fixed/user prompt、stdioおよびloopback限定Streamable HTTP、agent_run/agent_status、Session、Ollama text/tool/Vision、TaskGraphとtoken accountingを実装。
Windows sandboxとしてfixed AppContainer、canonical/reparse検査、能力別ACL、path+SHA-256 executable approval、child-process restriction、Job Object、task journal、atomic file transaction、crash recoveryを実装。WFPのIPv4/IPv6 default denyとexact allow、dynamic session、temporary loopback exemption、管理者/BFE診断を追加。
Security/Recovery test、MCP/Ollama integration test、stdio/HTTP Operational E2E、Release Bundle生成・checksum・manifest・fresh extraction検査を追加。Requirement TraceabilityとPhase 0〜11の進捗、初回セットアップ可能なREADMEを整備。
Debug/Release/publish/objをrepository rootのbuild/へ集約し、旧project-local bin/objへの依存を除去。artifacts/とbuild/をGit管理外に設定し、clean checkoutでもsolution buildからE2E Clientまで生成可能にした。
|
