Git/GitIdentity/Port/WriteAccess and Claude CLI/Version/Auth/PermissionModeAuto
checks plus the ExecutableResolver they depend on were built in two sibling
task branches that hadn't landed on main yet. Vendored the finished files in
from those branches (same content, verified building + tests green) so the
SystemCheckPage task has something to consume.
EnsureExists blindly seeded ~/.todo-app/prompts/*.md with the bundled
default and never revisited it, so any file created by opening the
Files settings tab shadowed every later default change permanently
(SuggestImprovement/AskUser sections never reached real runs since
2026-06-04). PromptFiles now hashes what a file was seeded/saved with
in prompts/.defaults.json: Classify() tells missing/current-default/
known-past-default/edited apart, ReconcileStaleDefaults() drops files
that only ever matched a superseded default, and real edits are left
alone and surfaced in the Files tab with a diff + reset-to-default
action. QuarantineOrphans() moves stale-named leftovers (agent.md,
planning.md) into prompts/_orphans instead of silently deleting them.
Wired as a Worker startup sweep (PromptFileRecovery) alongside the
existing OrphanRecovery/AttachmentOrphanRecovery services.
## Kontext: Limits sind Fenster, nicht Summen
Die Runs laufen ueber das Claude-Abo. Limits greifen pro 5h-Fenster und pro 7 Tage. Nicht die Wochensumme tut weh, sondern dass ein Agent-Burst ein Fenster leerraeumt, in dem Mika selbst interaktiv arbeiten will.
## Messgrundlage (alle Transcripts unter ~/.claude/projects)
Agent-Runs sind ueber die ganze Historie nur **18,4 %** des Account-Verbrauch
ClaudeDo-Task: 87105f5e-c4f4-4af4-ae60-89cd2e153e3c
task_runs.tokens_in only ever held the API's uncached "input_tokens" field
(off by a factor of ~400,000 on a resumed session), and tokens_out summed
only the last result event instead of the whole session. TaskRunner now
reads each run's cache-read/cache-write/input/output totals from the
session transcript via a new ITranscriptUsageReader.ReadSessionTotalsAsync,
storing the delta against prior runs on the same session so a --resume
doesn't double-count. New task_runs.cache_read_tokens/cache_write_tokens
columns; the Session tab now shows the raw total (what actually counts
against the 5h/7d usage limit) with a breakdown tooltip.
Runaway sessions were the single biggest cost driver: model_presets was
never persisted (stayed code-only), default_max_turns shipped at 100, and
ResolveMaxTurns had no upper bound, so a task/list override could run
hundreds of turns unchecked.
- TaskRunner.ResolveMaxTurns now clamps the resolved value to
AppSettings.MaxTurnsCeiling (new column, default 80) and logs a warning
with task id / requested / effective value when it clamps.
- default_max_turns default lowered from 100 to 40 (entity, EF config,
and the seeded row via the new AddMaxTurnsCeiling migration).
- AppSettingsRepository.GetAsync backfills model_presets with the
shipping defaults on first read instead of leaving the column null.
- Settings > General's per-model preset table and the task/list agent
editor now show a hint when a set max-turns value exceeds the ceiling.
Adds a "Reading efficiently" section to SystemDefault covering
locate-before-read (Grep/Glob), targeted reads (offset/limit), avoiding
re-reads, and using an exploration subagent as a context firewall for
orientation questions. Based on measurement across 144 real sessions
showing context resend (Read especially) dominates token cost.
Persists the merge commit SHA on WorktreeEntity for every successful
single-task and unit merge, and adds a TaskMergeService.RevertMergeAsync
+ revert_merge MCP tool that undoes a merged task's merge via
`git revert -m 1` (never reset/rewrite, since the target checkout is
shared). Rejects cleanly when there's no recorded SHA, the repo is
mid-merge/mid-revert, or the target has foreign uncommitted changes;
a conflicting revert aborts immediately. Also exposes the new
mergeCommit field via get_task_worktree.
Planning sessions could already steer a subtask's model but not its turn
budget, so a visibly large subtask would still die at the global default
turn limit. maxTurns is optional (default null = inherit list/global
default, matching model); 0/negative values are rejected as invalid input,
consistent with the existing model-alias validation.
Per-list optional VerifyCommand (list_config.verify_command) runs via
VerifyCommandRunner in the list's working dir right after a successful
merge/continue-merge, before the task is allowed to reach Done. A
non-zero exit or timeout leaves the merge in place but keeps the task
out of Done and reports StatusVerifyFailed with an output excerpt
through MergeResultDto/review_task; no command configured behaves
exactly as before. Merges against the same repo are now serialized
per working dir so a running verify can't be interrupted by a second
merge landing mid-build. Adds the field to the List Settings modal
(en/de localized) and covers success/failure/timeout in
TaskMergeServiceTests + VerifyCommandRunnerTests.
Give an autonomous reviewer a non-destructive merge-tree preview
(status/conflicts/changedFileCount/behind) for a task's worktree branch,
plus a file-overlap check across a batch of tasks so same-file collisions
between sibling branches are visible before merging. MergeHelperDefault's
Phase 4 now calls preview_merge_set before merging a batch.
Phase 2 can now propose splitting a bundled/blocked task via add_task/add_subtask
instead of forcing it into one description. Phase 3 reports each task's effective
max-turns and asks before queuing a substantial task with a low value. Phase 4
checks Phase 2's file lists for cross-task collisions and may reorder merges with
a stated reason instead of always following brief order.
Replaces the list handler's Start-Sleep + blind get_task poll (Phase 3
of the merge-helper prompt) with a blocking MCP tool that returns as
soon as a task leaves Queued/Running, or times out. Implemented as an
async DB poll (short-lived DbContext, 500ms delay, no held connection)
rather than hooking HubBroadcaster, keeping the existing broadcast
callers untouched. timeoutSeconds is clamped server-side to 170s, under
the list handler's 200s MCP_TOOL_TIMEOUT.
Phase 0 forced a batch_get_tasks full-fetch across every task just to see
descriptions, which blew past the client's token limit on larger lists.
brief.md lives on disk and has no such limit, so descriptions now render
there directly (fenced with an extended backtick run, indented under the
list bullet, so embedded headings/lists/code fences can't break the task
list's own structure). Phase 0 now treats the brief as the primary source
and only falls back to batch_get_tasks for fields it doesn't carry.
Adds AppSettings.UsageGateFiveHourPct/UsageGateSevenDayPct (defaults
80/90, clamped 0..100 in UpdateAsync) and a nullable TaskRunEntity.Model
column, laying the data foundation for the usage monitor. No worker/UI
changes.
"Let Claude handle it" now creates one ClaudeDo task per run to host the
ConPTY session (Idle/IsManual, never queued) instead of an untracked
ad-hoc tile, so the run has a real title, diff, and review outcome.
Since the handler merges its own changes straight into the list's
working dir, the task never gets a WorktreeEntity; its review range
lives as new HandlerBaseCommit/HandlerHeadCommit columns on TaskEntity
instead, reusing the existing commit-range diff machinery and keeping
it out of the worktrees overview entirely.
A full model id like claude-sonnet-4-6 in list_config.model never matched any
ModelPresets row (only bare aliases did), so every run under it landed on the
hardcoded 30-turn/DefaultLevel fallback instead of the sonnet preset row -
this is what killed two autonomous tasks at the 30-turn limit.
ModelRegistry.TryNormalizeAlias (non-throwing: exact match, then substring
match against a full model id) lets ModelPresets.For resolve a full model id
to its alias's preset row. For a model that still doesn't resolve, the
hardcoded 30 is replaced by a caller-supplied fallbackMaxTurns, and TaskRunner
now passes AppSettings.DefaultMaxTurns there - so that setting has a real
effect instead of being dead, matching the direction already noted in
docs/open.md.
Phase 1 previously asked the user to confirm the absence of duplicates
even when no candidate pair was found. The handler now decides that
itself and moves straight to Phase 2; per-pair questions remain when
at least one candidate exists.
Dragging a task row onto a user list in the Lists island now reassigns it
to that list. The task drag holds the pointer capture, so the release is
resolved geometrically (new case between the Mission Control and reorder
cases) instead of going through the Lists island's own DragDrop path,
which never sees a DragEventArgs during a task drag.
TaskRepository.MoveToListAsync reassigns the task plus every descendant
(a child must never sit in a different list than its parent) and appends
the task at the end of the target list. Guards: running tasks and tasks
holding an Active/Kept worktree are rejected to the footer error strip;
a move that changes repo asks for confirmation naming both repos.
The source repo is read from the task's own list rather than the island's
current list, which is a smart/virtual list with no working dir of its own
whenever one of those is shown.
ClaudeDo never passed --effort, so every session inherited whatever effortLevel
the user's Claude Code config happened to carry. Settings -> General now holds one
row per model alias (haiku medium/20, sonnet high/30, opus high/40, fable high/25)
supplying the global effort and turn defaults; list- and task-level max-turns
overrides still win, and the agent editor's inherited badge follows the model.
--effort is applied to autonomous runs and to every ConPTY spec (task session,
planning start/resume, ad-hoc, list handler). The model itself is deliberately not
forced on interactive sessions. The single global 'Max turns' field is replaced by
the table, and 'fable' joins ModelRegistry.Aliases.
The migration also adds the is_manual columns used by the next commit.
HasChangesAsync counted untracked files, so a stray file in the shared
target working dir (e.g. left by a concurrent session) blocked merge
preflights even though nothing tracked changed. Add an includeUntracked
overload defaulting to true, and pass includeUntracked: false only from
the two target-working-tree merge preflights (TaskMergeService.MergeAsync,
PlanningMergeOrchestrator.StartAsync). Auto-commit and the worktree
cleanup data-loss guard keep counting untracked files, since those
callers need to know about them.
- GitService.MergeFfOnlyAsync had no callers anywhere in code; removed.
- AgentMcpTools moved out of LifecycleMcpTools.cs into External/AgentMcpTools.cs (no behavior change).
- Worker CLAUDE.md described ZitadelAuthProvider as a Phase 2 stub; it's fully implemented (OIDC discovery + refresh-token flow), updated both mentions.
A running task can call mcp__claudedo_run__AskUser(question) to block (up to 3
min) on a human answer. PendingQuestionRegistry holds the pending question +
TaskCompletionSource; the tool broadcasts TaskQuestionAsked, awaits the answer
(WorkerHub.AnswerTaskQuestion resolves it), and returns it as the tool result —
or a 'proceed on your judgment' fallback on timeout. The run stays Running
throughout (no status/schema change). ClaudeProcess raises MCP_TOOL_TIMEOUT so
the 60s HTTP-MCP cap doesn't kill the wait; the run MCP is now wired for every
task, not just standalone ones. System prompt updated to reconcile 'unattended'.
Data/Worker/Ui CLAUDE.md + docs/open.md updated for TaskAttachmentEntity,
AttachmentStore, AttachmentMcpTools, AttachmentOrphanRecovery, the run-prompt
injection, and the detail-pane drag-and-drop UI (incl. a manual verification
item).
AttachmentMcpTools exposes add_task_attachment (text or base64),
list_task_attachments, and remove_task_attachment on the external MCP
endpoint, so an agent can prepare reference files (plans, scripts) on a task
that will run later. Re-attaching the same name overwrites; add/remove refuse
on a running task.
TaskRunner appends attached files (absolute paths) to the run prompt as the
read-only Reference files section. Task and list deletes now remove the
on-disk attachment dir eagerly, and a startup AttachmentOrphanRecovery sweep
drops any attachments/<taskId>/ whose task no longer exists (covers list
cascade and planning-discard paths).
TaskAttachmentEntity (+config, cascade FK), TaskAttachmentRepository, and an
AttachmentStore that writes files under ~/.todo-app/attachments/<taskId>/ with
a path-traversal guard and a 5 MB cap. TaskPromptComposer gains an optional
read-only 'Reference files' section. Migration AddTaskAttachments.
GetConflictsAsync/GetMergeConflicts (+ MergeConflicts/ConflictFileContent/ConflictFileDto/ConflictHunkDto DTOs and the now-orphaned GitService.ShowStageAsync) were superseded by the segment-based GetMergeConflictDocuments path and had no production callers. Removes the IWorkerClient member, both test fakes, the lingering test, and updates the Worker/Ui/Data CLAUDE.md surface notes.
Replace the whole-file conflict model with line-level hunks, the
foundation for the full in-app merge editor.
- ConflictMarkerParser: parses git conflict markers (incl. diff3 base)
into ordered stable/conflict MergeSegments; exact round-trip + Compose
- GitService.MergeNoFfAsync passes -c merge.conflictStyle=diff3 so the
working tree carries the merge base in conflict markers
- TaskMergeService.GetConflictDocumentsAsync: reads each conflicted file,
parses into segments, flags binary files
- hub GetMergeConflictDocuments + DTOs (MergeConflictDocumentsDto/
ConflictDocumentDto/MergeSegmentDto), IWorkerClient + both fakes
- tests: 8 parser unit tests + a real-git integration test asserting
line-level hunks with a diff3 base
Optional, opt-in (online_inbox.enabled, default false → zero network).
Worker-side reconcile loop: pull web-created tasks down as Idle, push the
list catalog and the Idle backlog mirror up. Auth behind IOnlineAuthProvider
(StaticTokenAuthProvider default; ZitadelAuthProvider stubbed for Phase 2).
DPAPI refresh-token store. 35 tests, no real network/Zitadel/Claude.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
AddTask, planning CreateChildTask, and SuggestImprovement now accept an
optional alias-validated model (haiku/sonnet/opus; blank = inherit) so the
model is chosen at creation time instead of a follow-up set_task_config call.
The planning, system, and improvement prompts instruct Claude to pick the
cheapest capable model (haiku < sonnet < opus).
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
mika kuns