| Age | Commit message (Collapse) | Author |
|---|
|
Worked with Gemini and Opus to improve the system prompt with learnings from the
Amp prompt. Removed reference to Omni/Task/README.md because it is deprecated in
favor of `jr task`.
|
|
getReadyTasks now returns tasks sorted by:
1. Priority (P0 first, then P1, P2, etc.)
2. Creation time (oldest first within same priority)
This ensures high-priority items are always at the top of both
the CLI 'jr task ready' output and the web dashboard.
Task-Id: t-220
|
|
- Remove HumanTask from TaskType enum (now Epic | WorkTask only)
- Add NeedsHelp to Status enum for tasks requiring human guidance
- Update getReadyTasks to filter NeedsHelp instead of HumanTask
- Rename humanTasks to tasksNeedingHelp in HumanActionItems
- Add CLI parsing for needs-help status in list/update commands
- Add badge styling for NeedsHelp (amber/yellow theme)
- Update all status pattern matches in tree view and print functions
- Update tests to verify NeedsHelp exclusion from ready queue
Task-Id: t-210
|
|
- updateTaskStatusWithActor logs status_change events to agent_events
- Worker uses Junior actor for status changes - Jr review uses
System/Human actors appropriately - CLI task update uses Human actor
- Remove task_activity table schema (migrated to agent_events) -
addComment now inserts into agent_events with event_type='comment'
Task-Id: t-213
|
|
- Add 'actor' column to agent_events table (human/junior/system)
- Add System to CommentAuthor type (reused for actor) - Add SQL
FromField/ToField instances for CommentAuthor - Update insertAgentEvent
to accept actor parameter - Update all SELECT queries to include
actor column - Update Worker.hs to pass actor for all event types -
Guardrail events logged with System actor
Migration: ALTER TABLE adds column with default 'junior' for existing
rows.
Task-Id: t-213.1
|
|
Implement runtime guardrails in Engine.hs: - Cost budget limit (default
200 cents) - Token budget limit (default 1M tokens) - Duplicate tool
call detection (same tool called N times) - Test failure counting
(bild --test failures)
Add database-backed progress tracking: - Checkpoint events stored in
agent_events table - Progress summary retrieved on retry attempts -
Improved prompts emphasizing efficiency and autonomous operation
Worker.hs improvements: - Uses guardrails configuration - Reports
guardrail violations via callbacks - Better prompt structure for
autonomous operation
Task-Id: t-203
|
|
Comments now track whether they were made by a Human or by Junior
(the agent). The CommentAuthor type is stored in the database and
displayed in the web UI with styled badges.
Task-Id: t-201
|
|
Excellent! The implementation is complete and all tests pass. Let
me pro
I successfully implemented the task to show complexity in the task
detai
1. **File Modified**: `Omni/Task/Core.hs` 2. **Function**:
`showTaskDetailed` 3. **Change**: Added complexity display after the
Priority line (lines 1
```haskell case taskComplexity t of
Nothing -> pure () Just c -> putText ("Complexity: " <> T.pack
(show c) <> "/5")
```
This code: - Checks if the task has a complexity value set - If
`Nothing`, does nothing (no complexity line is shown) - If `Just c`,
displays "Complexity: X/5" where X is the complexity valu
- ✅ `bild --test Omni/Task.hs` passed successfully - ✅ `lint
Omni/Task/Core.hs` passed with no hlint warnings or errors - ✅ All
existing tests continue to pass
The implementation matches the exact specification provided in the task
Task-Id: t-196
|
|
- Add Omni/Agent/Event.hs with AgentEvent types
- Add agent_events table schema and CRUD functions to Core.hs
- Add new callbacks to Engine.hs: onAssistant, onToolResult, onComplete, onError
- Wire event logging into Worker.hs with session tracking
Events are now persisted to SQLite for each agent work session,
enabling visibility into agent reasoning and tool usage.
Task-Id: t-197.1
Task-Id: t-197.2
Task-Id: t-197.3
|
|
The fix is complete. I added the missing `complexity` column to the
`loa
```sql SELECT id, title, type, parent, namespace, status, priority,
complexity, ```
This matches the expected column order in the `FromRow Task`
instance at
Task-Id: t-195
|
|
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
|
|
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
|
|
All tests pass and lint is clean. The implementation is complete:
**Changes made:**
1. **Omni/Task/Core.hs:**
- Added `EpicForReview` data type to hold epic with progress info -
Added `HumanActionItems` data type to group all three categories -
Added `getHumanActionItems` function that returns:
- `failedTasks`: Tasks with retry_attempt >= 3 - `epicsInReview`:
Epics where all children are Done (and has at le - `humanTasks`:
HumanTask type tasks in Open status
2. **Omni/Jr/Web.hs:**
- Updated `InterventionPage` data type to use `HumanActionItems`
- Updated `interventionHandler` to call `getHumanActionItems` -
Rewrote `ToHtml InterventionPage` to show 3 sections with headers -
Added `renderEpicReviewCard` for epic review cards with "Approve &
- Renamed navbar link from "Intervention" to "Human Action"
Task-Id: t-193.5
|
|
All tests pass. The implementation is complete:
**Summary of changes:**
1. **Omni/Task/Core.hs** - Added helper functions:
- `getBlockingImpact`: Counts how many tasks are transitively
blocked - `getTransitiveDependents`: Gets all tasks that depend
on a task (di - `dependsOnTask`: Helper to check if a task depends
on a given ID wi
2. **Omni/Jr/Web.hs** - Updated blocked page:
- Changed `BlockedPage` type to include blocking impact:
`[(TaskCore. - Updated `blockedHandler` to compute blocking impact
and sort by it - Added `renderBlockedTaskCard` to display tasks with
their blocking - Updated the info message to explain the sorting
3. **Omni/Jr/Web/Style.hs** - Added CSS:
- `.blocking-impact` badge style (light mode) - `.blocking-impact`
dark mode style
Task-Id: t-189
|
|
The build and tests pass with no errors. The time range filter
feature f
**Implementation summary:** - Route accepts
`?range=today|week|month|all` query param - `TimeRange` type with
`Today`, `Week`, `Month`, `AllTime` variants - `homeHandler` filters
both tasks and activities by time range - Toggle buttons rendered
with `timeFilterBtn` helper - Full CSS styling in `timeFilterStyles`
with dark mode support - Default selection: "All Time"
Task-Id: t-180
|
|
The implementation is complete. The build passed with `bild --test
Omni/
**Summary of changes:**
1. **Omni/Task/Core.hs**: Added `getGlobalAggregatedMetrics ::
IO Aggreg
2. **Omni/Jr/Web.hs**:
- Updated `HomePage` data type to include `AggregatedMetrics`
paramet - Updated `homeHandler` to fetch global metrics via
`getGlobalAggrega - Updated `ToHtml HomePage` instance to add
two new cards: "Cost" (fo - Added helper functions `metricCard`,
`formatCost`, and `formatDurat
3. **Omni/Jr/Web/Style.hs**: Added `badge-neutral` CSS styling
(gray bor
Task-Id: t-179
|
|
|
|
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
|
|
All tests pass. The changes are complete:
**Summary of changes:** 1. **Omni/Task/Core.hs**: Changed
`taskDescription` from `Maybe Text` to 2. **Omni/Task.hs**:
Made `--description` required on CLI `create` (pani
3. **Omni/Task/RaceTest.hs**: Updated test to provide descriptions
Task-Id: t-165
|
|
The build passed. The task was to update nixpkgs hash in Biz/Bild.nix,
b
Task-Id: t-163
|
|
This allows Servant's QueryParam Maybe to treat Left as "parameter not
provided", so the 'All' filter option (which sends empty string value)
now works correctly instead of causing an "Invalid priority" error.
Task-Id: t-146
|
|
All changes are in place. The build and tests pass. The implementation
i
1. **Added `Draft` to Status enum** - First in sequence: `Draft |
Open | 2. **Excluded Draft from getReadyTasks** - Uses `taskStatus
t `elem` [Op 3. **CLI support** - `task update <id> draft` works,
`task list --status 4. **Display coloring** - Draft shows in gray
with `[.]` indicator in tr 5. **TaskStats** - Added `draftTasks`
field and display in stats output 6. **Tests** - Added unit test for
draft exclusion from ready tasks and
Task-Id: t-166
|
|
The Omni/Fact.hs module is complete with CRUD operations:
- **createFact**: Create a new fact with project, content, related
files - **getFact**: Retrieve a fact by ID - **getAllFacts**: Get all
facts from the database - **getFactsByProject**: Get facts filtered by
project - **getFactsByFile**: Get facts related to a specific file -
**updateFact**: Update an existing fact's content, related files,
and - **deleteFact**: Delete a fact by ID
The module properly re-exports the `Fact` data type from
`Omni.Task.Core
Task-Id: t-158.2
|
|
Tasks that have failed 3 or more times need human intervention and
should not appear in the ready queue. This prevents infinite retry
loops.
Task-Id: t-164 Amp-Thread-ID:
https://ampcode.com/threads/T-4c8bc88f-f8f9-4921-96e5-3b68552c0bc0
Co-authored-by: Amp <amp@ampcode.com>
|
|
Both tests pass. The change converts the task detail display from:
``` Task: t-123
Title: Some title ```
To the inline format:
``` Title: Some title (ID: t-123) ```
Task-Id: t-156.1
|
|
|
|
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
|
|
All tests pass. The implementation adds:
1. **`runMigrations`** - Called at the end of `initTaskDb` to run
migrat 2. **`migrateTable`** - Compares expected columns against
existing colum 3. **`getTableColumns`** - Uses `PRAGMA table_info` to
get existing colu 4. **`addColumn`** - Runs `ALTER TABLE ADD COLUMN`
for missing columns 5. **Column definitions** - Lists of expected
columns for `task_activity
When new columns are added to the schema in the future, you just
add the
Task-Id: t-152.3
|
|
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
|
|
The build passes with no errors. The implementation was already
in place
Task-Id: t-149.6
|
|
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
|
|
All builds pass. Here's a summary of the changes I made:
**Omni/Task/Core.hs:** - Added `getActivitiesForTask` function to
query task_activity table for
**Omni/Jr/Web.hs:** - Added `Data.Time` import for timestamp formatting
- Updated `TaskDetailPage` type to include `[TaskCore.TaskActivity]` -
Updated `taskDetailHandler` to fetch activities for the task - Added
activity timeline rendering in `toHtml` instance for InProgress -
Added helper functions: `renderActivity`, `stageClass`, `stageIcon`, `
**Omni/Jr/Web/Style.hs:** - Added `activityTimelineStyles`
function with vertical timeline CSS - Added stage-specific colors
(claiming=blue, running=yellow, reviewing= - Added dark mode styles
for the activity timeline
Task-Id: t-148.3
|
|
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
|
|
All components are in place: - `ActivityStage` enum with stages:
Claiming, Running, Reviewing, Retryi - `TaskActivity` data type with
all required fields - JSON instances (ToJSON/FromJSON) - SQLite
instances (FromField/ToField for ActivityStage, FromRow/ToRow f -
`task_activity` table in `initTaskDb`
Build passes with no errors.
Task-Id: t-148.1
|
|
- FromHttpApiData instances return Left for empty strings (Servant
treats as missing param for QueryParam Maybe)
- getTasksDbPath now uses ~/.local/share/jr/jr.db via XDG - Remove
standalone task binary output - Add tests for parseQueryParam on
Priority/Status
Task-Id: t-145, t-146 Amp-Thread-ID:
https://ampcode.com/threads/T-2ad5310f-b7f5-451d-ad9b-35aa17c58774
Co-authored-by: Amp <amp@ampcode.com>
|
|
All tests pass. The implementation is complete:
**Summary of changes:** 1. Removed sqids dependency from
`Omni/Task/Core.hs`, `Omni/Task.hs`, an 2. Changed `generateId` in
`Omni/Task/Core.hs` to produce simple sequent 3. Removed the now-unused
`sqidsOptions` configuration and `Web.Sqids` i
Task-Id: t-1o2g8gu9y2z
|
|
- Document _/ directory structure in AGENTS.md - Change test database
path from .tasks/ to _/tmp/ - Update all references in tests and docs
|
|
|
|
Tests were polluting production database because TASK_DB_PATH
took precedence over TASK_TEST_MODE. Now test mode always uses
.tasks/tasks-test.db regardless of TASK_DB_PATH setting.
|
|
The build passes. Let me also verify that the filter functionality
is co
1. **API endpoint with query params** (lines 46-49): ✅ Already
has `Quer 2. **Handler** (lines 776-781): ✅ Already receives
and applies filters 3. **Filter form in HTML** (lines 295-330):
✅ Already has form with drop 4. **Filter logic** (lines 787-807):
✅ Already applies AND-combined filt
The implementation is complete and the hlint suggestions have been
addre
Task-Id: t-1o2g8gugkr1.8
|
|
- 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>
|
|
Tasks are now stored in SQLite at ~/.cache/omni/tasks/tasks.db.
No need to sync to git anymore. Deleted 51 test cruft tasks.
|
|
- 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
|
|
8-char lowercase IDs using sqids with sequential counter.
Task-Id: t-1o2g8gu9y2z Amp-Thread-ID:
https://ampcode.com/threads/T-7d88c849-530f-4703-9f90-cbc86d608e3c
Co-authored-by: Amp <amp@ampcode.com>
|
|
Re-introduces MVar locking in Task Core to prevent race conditions
during Read-Modify-Write cycles (e.g. ID generation). Updates tests
to use isolated SQLite databases instead of the production DB or
JSONL files. Removes legacy test artifacts.
Amp-Thread-ID:
https://ampcode.com/threads/T-ac41b9b6-d117-46de-9e4f-842887a22f1d
Co-authored-by: Amp <amp@ampcode.com>
|
|
Removes .tasks/tasks.jsonl and replaces it with a local SQLite database
(.tasks/tasks.db). Adds --db flag to CLI. Removes sync command.
Amp-Thread-ID:
https://ampcode.com/threads/T-ac41b9b6-d117-46de-9e4f-842887a22f1d
Co-authored-by: Amp <amp@ampcode.com>
|
|
Amp-Thread-ID:
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
Co-authored-by: Amp <amp@ampcode.com>
|
|
|
