summaryrefslogtreecommitdiff
path: root/Omni/Agent
AgeCommit message (Collapse)Author
2025-11-30Fix jr loop: update model IDs and dev shellHEADliveBen Sima
- Update OpenRouter model IDs to Claude 4.5 family: - anthropic/claude-sonnet-4.5 (default) - anthropic/claude-haiku-4.5 (simple tasks) - anthropic/claude-opus-4.5 (complex tasks) - Remove aider-chat from dev shell (broken, unused) - Simplify llm package (remove llm-ollama plugin) - Update nixos-unstable for llm 0.27.1 Task-Id: t-163
2025-11-30Audit and verify Engine testing coverageBen Sima
All tests pass and lint is clean. Let me verify the final test coverage **Engine.hs Test Coverage (13 tests):** - ✅ Tool JSON roundtrip - ✅ Message JSON roundtrip - ✅ ToolCall JSON roundtrip (NEW) - ✅ FunctionCall JSON roundtrip (NEW) - ✅ Role JSON roundtrip for all roles (NEW) - ✅ defaultLLM endpoint & headers - ✅ defaultAgentConfig defaults - ✅ defaultEngineConfig callbacks - ✅ buildToolMap correctness - ✅ Usage JSON parsing - ✅ AgentResult JSON roundtrip - ✅ estimateCost calculation **Tools.hs Test Coverage (19 tests):** - ✅ All 5 tool schemas are valid objects - ✅ allTools contains 5 tools - ✅ ReadFileArgs parsing - ✅ WriteFileArgs parsing - ✅ EditFileArgs parsing - ✅ RunBashArgs parsing - ✅ SearchCodebaseArgs parsing - ✅ ToolResult success/failure JSON roundtrip - ✅ readFileTool handles missing files (NEW) - ✅ editFileTool handles no-match case (NEW) - ✅ runBashTool captures exit codes (NEW) - ✅ runBashTool captures stdout (NEW) - ✅ searchCodebaseTool returns structured results (NEW) All unit tests from the checklist are now covered. The integration and m Task-Id: t-141.7
2025-11-30Remove amp dependency entirelyBen Sima
The build and tests pass. Let me provide a summary of the changes made: Removed the amp dependency entirely from the codebase: - Removed `runAmp` function (was running amp subprocess) - Removed `shouldUseEngine` function (env var check `JR_USE_ENGINE`) - Removed `monitorLog` and `waitForFile` helpers (for amp.log parsing) - Removed unused imports: `System.IO`, `Data.Text.IO` - Made `runWithEngine` the default/only path - Updated error messages from "amp" to "engine" - Renamed `ampOutput` parameter to `agentOutput` in `formatCommitMessage - Added `Data.IORef` import for `newIORef`, `modifyIORef'`, `readIORef` - Removed amp.log parsing code: `LogEntry`, `processLogLine`, `updateFro - Removed unused imports: `Data.Aeson`, `Data.ByteString.Lazy`, `Data.Te - Renamed `activityAmpThreadUrl` to `activityThreadUrl` - Updated field references from `activityAmpThreadUrl` to `activityThrea - Updated UI label from "Amp Thread:" to "Session:" - Updated comment from "amp completes" to "engine completes" - Updated `Amp.execute` to `Engine.runAgent` - Updated logging section to describe Engine callbacks instead of amp.lo - Updated integration test guidance to mock Engine instead of amp binary Task-Id: t-141.6
2025-11-30Add task complexity field and model selectionBen Sima
All tests pass. Let me summarize the changes made: - Added `taskComplexity :: Maybe Int` field to the `Task` data type (1-5 - Updated SQL schema to include `complexity INTEGER` column - Updated `FromRow` and `ToRow` instances to handle the new field - Updated `tasksColumns` migration spec for automatic schema migration - Updated `saveTask` to include complexity in SQL INSERT - Updated `createTask` signature to accept `Maybe Int` for complexity - Added `--complexity=<c>` option to the docopt help string - Added complexity parsing in `create` command (validates 1-5 range) - Added complexity parsing in `edit` command - Updated `modifyFn` in edit to handle complexity updates - Updated all unit tests to use new `createTask` signature with complexi - Added CLI tests for `--complexity` flag parsing - Added unit tests for complexity field storage and persistence - Updated `selectModel` to use `selectModelByComplexity` based on task c - Added `selectModelByComplexity :: Maybe Int -> Text` function with map - `Nothing` or 3-4 → `anthropic/claude-sonnet-4-20250514` (default) - 1-2 → `anthropic/claude-haiku` (trivial/low complexity) - 5 → `anthropic/claude-opus-4-20250514` (expert complexity) - Updated `createTask` calls to include `Nothing` for complexity Task-Id: t-141.5
2025-11-30Replace amp subprocess with native Engine in WorkerBen Sima
Implementation complete. Summary of changes to [Omni/Agent/Worker.hs](fi 1. **Added imports**: `Omni.Agent.Engine`, `Omni.Agent.Tools`, `System.E 2. **Added `shouldUseEngine`** (L323-327): Checks `JR_USE_ENGINE=1` envi 3. **Added `runWithEngine`** (L329-409): Native engine implementation th - Reads `OPENROUTER_API_KEY` from environment - Builds `EngineConfig` with cost/activity/tool callbacks - Builds `AgentConfig` with tools from `Tools.allTools` - Injects AGENTS.md, facts, retry context - Returns `(ExitCode, Text, Int)` tuple 4. **Added `buildBasePrompt`** and `buildRetryPrompt`** (L411-465): Help 5. **Added `selectModel`** (L467-471): Model selection (currently always 6. **Updated `processTask`** (L92-120): Checks feature flag and routes t Task-Id: t-141.4
2025-11-30Define Tool protocol and LLM provider abstractionBen Sima
The implementation is complete. Here's a summary of the changes made: 1. **Updated LLM type** to include `llmExtraHeaders` field for OpenRoute 2. **Changed `defaultLLM`** to use: - OpenRouter base URL: `https://openrouter.ai/api/v1` - Default model: `anthropic/claude-sonnet-4-20250514` - OpenRouter headers: `HTTP-Referer` and `X-Title` 3. **Updated `chatWithUsage`** to apply extra headers to HTTP requests 4. **Added `case-insensitive` dependency** for proper header handling 5. **Added tests** for OpenRouter configuration 6. **Fixed hlint suggestions** (Use `</` instead of `<$>`, eta reduce) Task-Id: t-141.1
2025-11-29Implement core coding tools (read, write, bash, search)Ben Sima
Both `bild --test` passes for Engine.hs and Tools.hs, and lint passes. T 1. **readFileTool** - Reads file contents with optional line range 2. **writeFileTool** - Creates/overwrites files (checks parent dir exist 3. **editFileTool** - Search/replace with optional replace_all flag 4. **runBashTool** - Executes shell commands, returns stdout/stderr/exit 5. **searchCodebaseTool** - Ripgrep wrapper with pattern, path, glob, ca Plus **ToolResult** type and **allTools** export as required. Task-Id: t-141.3
2025-11-29Implement agent loop with tool executionBen Sima
The implementation is complete. Here's what was implemented: **Types Added:** - `EngineConfig`: Contains LLM provider config and callbacks (`engineOnC - `AgentResult`: Results of running an agent (finalMessage, toolCallCoun - `Usage`: Token usage from API responses - `ChatResult`: Internal type for chat results with usage **Functions Added:** - `runAgent :: EngineConfig -> AgentConfig -> Text -> IO (Either Text Ag - `buildToolMap` - Creates a lookup map from tool list - `executeToolCalls` - Executes tool calls and returns tool messages - `estimateCost` / `estimateTotalCost` - Cost estimation helpers - `chatWithUsage` - Chat that returns usage stats - `defaultEngineConfig` - Default no-op engine configuration **Loop Logic:** 1. Sends messages to LLM via `chatWithUsage` 2. If response has tool_calls, executes each tool via `executeToolCalls` 3. Appends tool results as ToolRole messages 4. Repeats until no tool_calls or maxIterations reached 5. Tracks cost/tokens and calls callbacks at appropriate points Task-Id: t-141.2
2025-11-29Define Tool protocol and LLM provider abstractionBen Sima
The implementation is complete. I created [Omni/Agent/Engine.hs](file:// - **Types**: `Tool`, `LLM`, `AgentConfig`, `Message`, `Role`, `ToolCall` - **Functions**: `chat` for OpenAI-compatible HTTP via http-conduit, `de - **Tests**: JSON roundtrip for Tool, Message; validation of defaults All lints pass (hlint + ormolu) and tests pass. Task-Id: t-141.1
2025-11-29Inject relevant facts into coder agent contextBen Sima
All checks pass. The implementation is complete: 1. Added imports for `Data.List` and `Omni.Fact` 2. Added `getRelevantFacts` function that retrieves facts for the task's 3. Added `formatFacts` and `formatFact` functions to format facts for in 4. Updated `runAmp` to call `getRelevantFacts`, format them, and append Task-Id: t-186
2025-11-29Inject task comments into agent context during work and reviewBen Sima
Build and lint both pass. The implementation: 1. Updated `formatTask` in [Omni/Agent/Worker.hs](file:///home/ben/omni/ 2. Extracted deps formatting to a separate `formatDeps` helper for consi 3. Added `formatComments` and `formatComment` helpers that show timestam Task-Id: t-184
2025-11-28Add comments field to tasks for providing extra contextBen Sima
All tests pass. Here's a summary of the changes I made: 1. **Added `Comment` data type** in `Omni/Task/Core.hs` with `commentTex 2. **Added `taskComments` field** to the `Task` type to store a list of 3. **Updated database schema** with a `comments TEXT` column (stored as 4. **Added SQL instances** for `[Comment]` to serialize/deserialize 5. **Added `addComment` function** to add timestamped comments to tasks 6. **Added CLI command** `task comment <id> <message> [--json]` 7. **Updated `showTaskDetailed`** to display comments in the detailed vi 8. **Added unit tests** for comments functionality 9. **Added CLI tests** for the comment command 10. **Fixed dependent files** (`Omni/Agent/Worker.hs` and `Omni/Jr/Web.h Task-Id: t-167
2025-11-28Fix llm tool installation - update nixpkgs hash in Biz/Bild.nixBen Sima
The build passed. The task was to update nixpkgs hash in Biz/Bild.nix, b Task-Id: t-163
2025-11-28Truncate task title to 52 characters in commit message subject lineBen Sima
The build and tests pass. The change is complete - the task title in com Task-Id: t-159
2025-11-27Add human notes field for intervention tasksBen Sima
All tests pass. Let me summarize the implementation: I've added a human notes field for intervention tasks with the following 1. **Omni/Task/Core.hs**: - Added `retryNotes :: Maybe Text` field to `RetryContext` data type - Added `notes` column to `retryContextColumns` for schema migration - Updated `getRetryContext` to fetch the notes field from DB - Updated `setRetryContext` to save the notes field to DB - Updated `getAllRetryContexts` to include notes - Added `updateRetryNotes :: Text -> Text -> IO ()` function to updat 2. **Omni/Jr/Web.hs**: - Added new API endpoint: `POST /tasks/:id/notes` - Added `NotesForm` type and `FromForm` instance - Added `taskNotesHandler` to save notes - Updated `renderRetryContextBanner` to accept task ID and display: - Notes textarea form when max retries exceeded (intervention tasks - Existing notes display for non-critical retry banners 3. **Omni/Agent/Worker.hs**: - Updated worker prompt to include human notes/guidance in the retry - Preserved existing notes when setting new retry context 4. **Omni/Jr.hs**: - Updated all `RetryContext` creations to preserve existing notes Task-Id: t-153.5
2025-11-27Display worker metrics on task detail pageBen Sima
All tests pass. Let me summarize what was implemented: - Extended `TaskActivity` type with new fields: - `activityAmpThreadUrl` - Link to amp thread - `activityStartedAt` - Work start timestamp - `activityCompletedAt` - Work completion timestamp - `activityCostCents` - API cost in cents - `activityTokensUsed` - Token usage count - Updated `SQL.FromRow` and `SQL.ToRow` instances for the new fields - Updated schema to include new columns in `task_activity` table - Added `logActivityWithMetrics` function to log activities with all met - Added `updateActivityMetrics` function to update metrics on existing a - Added `getLatestRunningActivity` helper function - Captures execution timing (start/end timestamps) - Retrieves amp thread URL from `AgentLog.getStatus` - Converts credits to cents and logs to activity record - Uses `logActivityWithMetrics` and `updateActivityMetrics` for tracking - Added `getStatus` function to retrieve current status (thread URL, cre - Added `TaskMetricsPartial` type for HTMX auto-refresh - Extended `TaskDetailPage` to include `RetryContext` - Added Execution Details section on task detail page showing: - Amp Thread URL (clickable link) - Duration (formatted as "Xm Ys") - Cost (formatted as "$X.XX") - Retry Attempt count (if applicable) - Last Activity timestamp - Added `/partials/task/:id/metrics` endpoint for HTMX auto-refresh - Auto-refresh enabled while task is InProgress (every 5s) - Added `renderExecutionDetails` helper function - Added `executionDetailsStyles` for metric rows and execution section - Added dark mode support for execution details section Task-Id: t-148.4
2025-11-27Fix filter dropdowns returning empty string for All optionBen Sima
The build passes. The fix I implemented: 1. **Changed the API type** in `Omni/Jr/Web.hs` to use `QueryParam "stat 2. **Added manual parsing** in `taskListHandler` with `parseStatus` and 3. **Applied `emptyToNothing`** to both status and priority params befor This ensures that when "All" is selected (empty string), it's treated as I also fixed two pre-existing issues that were blocking the build: - Type annotation for `show stage` in `Omni/Task/Core.hs` - `AesonKey.fromText` conversion in `Omni/Agent/Worker.hs` Task-Id: t-149.1
2025-11-27Add logActivity helper and integrate into Worker.hsBen Sima
Implementation complete. The task is done: 1. **Created `logActivity` helper** in `Omni/Task/Core.hs` that writes t 2. **Integrated into Worker.hs** at all key points: - `Claiming` - when claiming task - `Running` - when starting amp - `Reviewing` - when amp completes successfully - `Retrying` - on retry (includes attempt count in metadata) - `Completed` - on success (includes result type in metadata) - `Failed` - on failure (includes exit code or reason in metadata) Task-Id: t-148.2
2025-11-26Improve worker prompt and fix output interleavingBen Sima
- More explicit prompt: MUST run bild --test, fix hlint issues - Add workerQuiet flag to disable ANSI status bar in loop mode - Loop mode uses simple putText, manual jr work keeps status bar
2025-11-26Handle no-changes case: mark task Done instead of ReviewBen Sima
When amp completes but makes no changes, the task is already done. Mark it Done directly instead of Review (which would fail to find a commit).
2025-11-26Improve jr loop logging and fix review race conditionBen Sima
- Reorder loop to check pending reviews before starting new work - Loop no longer exits on missing commit (skips instead) - Add [loop], [review], [worker] prefixes to all log messages - Worker leaves task in InProgress on amp failure (avoids retry loop)
2025-11-26Remove git-tracked task references from hooks and docsBen Sima
- Remove task sync from pre-commit hook - Remove task import from post-merge and post-checkout hooks - Remove merge driver config from post-checkout - Remove merge-driver command from jr - Update Task README for SQLite storage - Delete outdated WORKER_AGENT_GUIDE.md Amp-Thread-ID: https://ampcode.com/threads/T-f2358f5a-2d4a-47e7-a895-6647474d8311 Co-authored-by: Amp <amp@ampcode.com>
2025-11-26Use task title as commit subject, amp output as bodyBen Sima
Fixes gitlint failures by using the pre-validated task title as the commit subject line, while preserving amp's output in the body for review context. Body lines are truncated to 72 chars for compliance.
2025-11-26Fix worker: only set Review after commit succeedsBen Sima
If commit fails (lint hooks, etc), save retry context and reopen task for another attempt. After 3 failures, mark for human intervention. Task-Id: t-1o2g8gugkr1
2025-11-26Simplify worker to use lint --fixBen Sima
Task-Id: t-1o2g8gugkr1
2025-11-26Clean commit message subject for gitlint complianceBen Sima
- Remove trailing punctuation from subject line - Truncate to 72 chars max - Capitalize first letter Task-Id: t-1o2g8gugkr1
2025-11-26Fix worker to run formatters before commitBen Sima
- Run ormolu --mode inplace on changed .hs files - Run hlint --refactor to auto-fix lint issues - Use tryCommit that returns Either instead of panicking - Prevents commit hook failures from hlint violations Task-Id: t-1o2g8gugkr1
2025-11-25jr: implement Gerrit-style conflict handlingBen Sima
- Add RetryContext to track failed attempts (merge conflicts, rejections) - jr review checks for clean cherry-pick before showing diff - If conflict detected, kicks back to coder with context - Worker prompt includes retry context (attempt count, conflict files, reason) - After 3 failed attempts, marks task for human intervention Task-Id: t-1o2g8gudqlx
2025-11-25worker: format commit messages for gitlint complianceBen Sima
Split amp output into subject/body with blank line separator. Task-Id: t-1jbp4l5o Amp-Thread-ID: https://ampcode.com/threads/T-7d88c849-530f-4703-9f90-cbc86d608e3c Co-authored-by: Amp <amp@ampcode.com>
2025-11-25fix(agent): show elapsed duration instead of wall clock timeBen Sima
Task-Id: t-1o2g8gu6p8o
2025-11-25jr: add review command, --try-opus, Task-Id trailerBen Sima
- jr review <task-id>: show diff, accept/reject/skip - Worker uses --try-opus for better code quality - Commit messages use Task-Id: trailer (Gerrit-style) Task-Id: t-1o2g8gu6p8o
2025-11-24fix(agent): round credits to 2 decimal places and use totalCreditsBen Sima
Amp-Thread-ID: https://ampcode.com/threads/T-ac41b9b6-d117-46de-9e4f-842887a22f1d Co-authored-by: Amp <amp@ampcode.com>
2025-11-24Remove harvest command and documentationBen Sima
The 'harvest' functionality was tied to git-synced JSONL task files, which have been replaced by a local SQLite database. This commit removes the command from the CLI and updates documentation to reflect the new workflow. Amp-Thread-ID: https://ampcode.com/threads/T-ac41b9b6-d117-46de-9e4f-842887a22f1d Co-authored-by: Amp <amp@ampcode.com>
2025-11-24agent: restore git commit with amp outputBen Sima
Re-enables git commits in the worker, using the captured output from 'amp' as the commit message. Also updates 'Omni/Agent.hs' to handle the API change in TaskCore.exportTasks (commenting out harvest logic for now as it depended on git-tracked tasks). Amp-Thread-ID: https://ampcode.com/threads/T-ac41b9b6-d117-46de-9e4f-842887a22f1d Co-authored-by: Amp <amp@ampcode.com>
2025-11-24Remove git actions from workerBen Sima
2025-11-24fix(worker): remove unnecessary reset to worker branchBen Sima
2025-11-24Allow worker to take a specific task to work onBen Sima
2025-11-24Display credits correctly and don't loop agentBen Sima
2025-11-24Simplify agent commandBen Sima
I think the cd'ing and stuff was messing with the direnv assumptions.
2025-11-24Restore AGENTS.md instructions to workerBen Sima
2025-11-22feat(agent): restore vertical status layoutBen Sima
Amp-Thread-ID: https://ampcode.com/threads/T-cb6b70cf-bfac-4ef2-bad9-280aa47efacf Co-authored-by: Amp <amp@ampcode.com>
2025-11-22fix: remove redundant imports in Omni/Agent/Log.hsBen Sima
Amp-Thread-ID: https://ampcode.com/threads/T-ca3b086b-5a85-422a-b13d-256784c04221 Co-authored-by: Amp <amp@ampcode.com>
2025-11-22fix: fix compilation and lint errorsBen Sima
Amp-Thread-ID: https://ampcode.com/threads/T-ca3b086b-5a85-422a-b13d-256784c04221 Co-authored-by: Amp <amp@ampcode.com>
2025-11-22task: complete t-1o2bxd11zv9 (Merge)Ben Sima
https: //ampcode.com/threads/T-ca3b086b-5a85-422a-b13d-256784c04221 Co-authored-by: Amp <amp@ampcode.com> Amp-Thread-ID: https://ampcode.com/threads/T-ca3b086b-5a85-422a-b13d-256784c04221
2025-11-22feat: implement t-1o2bxcq7999.4Ben Sima
I have completed the task. 1. **Analysis**: I located `Omni/Agent/start-worker.sh` and identified the correct location to insert the `git sync` command (before building `task` and `agent`). 2. **Implementation**: I modified `Omni/Agent/start-worker.sh` to run `git sync` inside the worker directory. 3. **Verification**: * Ran `lint Omni/Agent/start-worker.sh` (passed). * Ran `bash -n Omni/Agent/start-worker.sh` to check syntax (passed). * Ran `bild --test Omni/Agent.hs` to ensure no regressions in the associated Haskell code (passed). The `start-worker.sh` script now syncs the worker repository before building the necessary tools, ensuring the worker runs with the latest code. Files updated: - `Omni/Agent/start-worker.sh`
2025-11-22feat: implement t-1o2bxd11zv9Ben Sima
The task to fix missing Time, Thread, and Credits in the Agent Log has been completed. **Changes Implemented:** 1. **`Omni/Agent/Log.hs`**: * Added `Data.Aeson` and `Data.ByteString` imports for JSON parsing. * Updated `Status` data type to include `statusThread`. * Implemented `LogEntry` data type and `FromJSON` instance to match the `amp` log format. * Added `processLogLine` function to parse JSON log lines and update the global status. * Updated `render` function to display the Thread ID. * Added logic to extract and format `Time` and `Credits` from log entries. 2. **`Omni/Agent/Worker.hs`**: * Added a log monitoring thread using `forkIO` in `runAmp`. * Implemented `monitorLog` to tail the `_/llm/amp.log` file and pass lines to `AgentLog.processLogLine`. * Added `waitForFile` to ensure the log monitor waits for the log file to be created. **Verification:** * Verified that both `Omni/Agent/Log.hs` and `Omni/Agent/Worker.hs` compile successfully using `bild` (ignoring the expected "no main" error for library modules). * Ran `lint` on both files with no errors. The agent status bar should now correctly display the Thread ID, elapsed/current Time, and Credits usage as parsed from the `amp` logs.
2025-11-22Merge branch 'review/t-rWcqsDZFM.3' into liveBen Sima
2025-11-22task: complete t-rWcqsDZFM.2 (Merge)Ben Sima
Amp-Thread-ID: https://ampcode.com/threads/T-ca3b086b-5a85-422a-b13d-256784c04221 Co-authored-by: Amp <amp@ampcode.com>
2025-11-22feat: implement t-rWcqsDZFM.3Ben Sima
Consolidated `monitor.sh` and `monitor-worker.sh` into a single `monitor.sh` script. 1. Updated `Omni/Agent/monitor.sh`: - Default behavior now uses `jq` to filter logs (formerly `monitor-worker.sh` behavior). - Added `--raw` flag to support raw log tailing (original `monitor.sh` behavior). - Accepts worker name as an argument (e.g., `./monitor.sh --raw omni-worker-2`). 2. Deleted `Omni/Agent/monitor-worker.sh`. 3. Updated `Omni/Agent/DESIGN.md` to reference the consolidated script. 4. Verified syntax of the new script. 5. Ran tests for `Omni/Agent.hs` (passed). The new usage for `monitor.sh` is: ```bash ./Omni/Agent/monitor.sh [worker-name] # Formatted output (default) ./Omni/Agent/monitor.sh --raw [worker-name] # Raw output ```
2025-11-22task: complete t-rWcqsDZFM.1 (Merge)Ben Sima
Amp-Thread-ID: https://ampcode.com/threads/T-ca3b086b-5a85-422a-b13d-256784c04221 Co-authored-by: Amp <amp@ampcode.com>
generated by cgit v1.2.3 (git 2.25.1) at 2025-12-16 11:02:05 +0000