memberUsage was already populated for CLI members (from the result event)
and Anthropic-API members (via the tool loop), but it was never written to
the panel_member_done SSE event or the persisted content JSON, so the
frontend had no token data to render.
Add the token fields (input/output/cacheRead/cacheCreation) to both the
SSE event and the persisted JSON, and render them via a shared
buildPanelMemberMeta helper used by both the live stream and history, so
the badge survives F5. OpenAI members (no per-turn tokens), error members,
and pre-existing history without token fields fall through to no badge.
The badge is display-only; aggregation into the worker/chain total via
seedUsage is unchanged, so there is no double counting and no DB migration.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Two bugs surfaced when driving the composite toggle (off→plan→fusion→moa)
in an all-CLI setup (no API keys):
1. MoA ran only 1 round instead of the configured 2. cycleCompositeMode
fired the multiModelMode PATCH un-serialized and sendMessage did not
await it, so a message sent right after toggling loaded the session
before 'moa' was committed → the backend read the prior 'fusion' value
→ 1 round. Persisted totalLayers in the DB confirmed fusion (1) for all
post-toggle chains. Serialize mode PATCHes into a promise chain (last
click wins, in order) and await it in sendMessage/sendMessageDirect.
2. A read-only panel member could still write files. ClaudeCliService
hard-coded --permission-mode acceptEdits, which auto-accepts Write/Edit
regardless of --allowed-tools, so a member running with planMode=true
(tools limited to Read/Glob/Grep) could still call write_file. Use
'plan' when planMode is set; this also closes the same latent hole for
regular plan-mode users on the shared CLI path.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
The panel agents card wrapped its agent chips in a display:flex container;
render them in a plain div so they flow naturally with the surrounding
layout instead of being forced onto one flex row.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Replace the separate panel_usage SSE event + frontend accumulator with
server-side seeding of the worker's usage object. Both the done-event and
FinalizeChain read from the same usage, so panel (Fusion/MoA) member tokens
now flow into the live badge AND the DB as a single source of truth — the
badge no longer drops to the worker-only value after F5.
- RunPanel takes a TokenUsage usageSink; accumulates member costs after the
Task.WhenAll barrier (single-threaded, no lock)
- ChatEndpoint passes panelUsage as seedUsage to all three worker paths
- StreamChat / StreamChatViaCli / OpenAI StreamChat fold seedUsage into usage
at creation time, so every exit path persists it
- OpenAI done-events extended with cacheCreation/cacheRead fields for live
consistency when seeded by Anthropic members
- chat.js: remove redundant _panelUsage / _addPanelUsage / panel_usage
- TODO.md: mark the live-only v1 boundary closed, note the new mechanism
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
The composer had two separate mode buttons (plan + panel). Fold them into a
single #planModeBtn that cycles through every operating mode in one place:
Off -> Plan -> Fusion -> MoA -> Off. Cleaner UI, one affordance instead of two.
Plan stays transient (reset on session switch, never persisted) while
Fusion/MoA persist to the session via apiUpdateSession({multiModelMode}) and
are read server-side from ctx.MultiModelMode. The compat var _planModeActive
is kept in sync (true iff mode === 'plan') so sendMessage and modals.js read
it unchanged. No text label — icon + tint only.
- index.html: drop the separate panel button, reuse #planModeBtn
- chat.css: unified states (plan/fusion/moa tints) on #planModeBtn
- chat.js: cycleCompositeMode / initCompositeMode / _renderCompositeBtn
replace the split plan/panel functions
- chat-page.js: single wiring block, init from session.multiModelMode
- ARCHITECTURE_QUICK.md: document the unified toggle
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Panel member token usage was tracked but discarded, so the cost badge only
ever showed the worker's tokens — misleading for MoA where the real cost is
roughly rounds x agents. Collect each member's usage and add it to the badge.
Each member fills its own TokenUsage in parallel (Anthropic loop via the
existing memberUsage, CLI via the now-captured CliChatResult return value;
OpenAI members stay null, nachruestbar). RunPanel sums them after the
Task.WhenAll barrier — single-threaded, so no lock or Interlocked needed —
across all MoA rounds and emits a panel_usage SSE event before panel_done.
The frontend adds those tokens onto the worker totals in the done handler so
the badge reflects the full chain cost.
- SseHelper: add TokenUsage.Add()
- AnthropicService.Panel.cs: PanelMemberResult.Usage, accumulate per round
after the barrier, emit panel_usage; RunPanelMemberViaCli returns usage
- chat.js: _panelUsage state, panel_usage case, add to worker tokens on done,
reset on stream start
- TODO.md: check off the member-token item
v1 limit: live badge only — FinalizeChain still persists worker tokens, so a
reload shows worker-only cost.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Previously only the final proposer layer was persisted, so after a reload
the intermediate MoA rounds and their "Runde k/N" dividers were gone — the
history showed only the last refined round, not the full live view. Persist
every proposer round instead, tagging each member's JSON transcript with
its layer index, and rebuild the round structure on reload.
- AnthropicService.Panel.cs: persist every round unconditionally; drop the
now-dead persist parameter and isFinalLayer local; write layer/totalLayers
into the transcript; iteration = layer*100+index+1 so DB rows are
layer-aware (no UNIQUE constraint on chain_id/iteration, id-based ordering)
- history.js: group panel bubbles by layer on reload and insert the
"Runde k / N" divider on round change for MoA (totalLayers > 1), matching
the live startPanelLayer view; back-compat for old format (default layer 1)
- TODO.md: check off the MoA persistence item
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Three related panel-member improvements:
Tool-box streaming fix: correlate tool boxes by tool ID instead of a
single pointer (fixes orphaned spinners and empty boxes when a member
calls multiple tools in one message), forward CLI ToolEnd to capture the
tool input (command/path), normalize tool names, clean up orphaned
spinners on finalize, and add a blinking cursor during text streaming.
Image/screenshot support: CLI panel members now extract image refs from
the last user message (like the worker) and drop them as temp files
readable via the Read tool, so members can see screenshots and file
attachments instead of being blind on image-based questions.
Reload persistence: each member persists a structured JSON transcript
({name, model, segments:[text|tool]}) instead of plain text, so a reload
restores text AND tool boxes interleaved exactly like live. history.js
renders the transcript and keeps back-compat for the old [Panel: Name]
plaintext format.
- AnthropicService.Agents.cs: NonStreamingLoopCallbacks.TranscriptSink,
loop collects text/tool segments, tool input added to combined event
- AnthropicService.Panel.cs: CLI member ID-correlation + ToolEnd input +
image refs + transcript; RunPanelMember persists one JSON transcript
- stream-ui.js: tool boxes keyed by ID, name normalization, cursor,
orphaned-spinner cleanup
- history.js: render JSON transcript with tool boxes, plaintext fallback
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Extend the panel engine with a layer loop: Fusion is one proposer round,
MoA runs N rounds where each round after the first sees the previous
round's responses via <previous_layer_responses> and refines its answer.
Only the final round is persisted; intermediate rounds are live-only.
Rounds are clamped to 1-5.
- SessionRecord + migration: moa_layers column (default 2)
- RunPanel: layer loop with per-member cloned message injection
- CloneForMember / BuildPreviousLayerBlock helpers for member isolation
- SSE: panel_layer_start / panel_layer_done events
- Frontend: layer_index composite keying, round dividers, MoA option
- Docs: ARCHITECTURE + ARCHITECTURE_QUICK updated
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Panel members now stream token-by-token and show tool uses in real time
(like the session agent) instead of delivering text only at completion.
The key constraint is byte-level safety: N members flushing SSE frames
concurrently on the shared HttpResponse would interleave and corrupt the
stream, so a SemaphoreSlim gate serializes the writes (not the model work).
- SseHelper.TryWriteSse takes an optional write-lock (default null, backward
compatible)
- NonStreamingLoopCallbacks carries SseGate + MemberIndex; _text/_tool/_error
events are tagged with the member index (review/finalizer stay at -1, no gate)
- CLI members forward TextDelta/ToolStart/ToolResult live instead of
discarding everything but the final text
- Anthropic-API members stream per tool-round via the loop callbacks; OpenAI
members fall back to collected text at panel_member_done
- Frontend demuxes by member index into per-bubble interleaved text/tool
rendering
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Panel agents answer the user prompt in parallel (read-only, non-streaming);
their responses are merged into the worker's last user message as a
<panel_responses> block, and the session agent synthesizes one final
streamed answer. The RunPanel engine is built layer-ready for future MoA.
- New session fields: multi_model_mode (off/fusion), panel_agent_ids (CSV)
with idempotent column migration
- New partial Services/AnthropicService.Panel.cs holding the RunPanel engine
- Provider-agnostic members: Anthropic RunNonStreamingToolLoop / OpenAI
CompleteText / CLI plan-mode; all forced read-only, persisted with Tag=panel
- SSE events: panel_start, panel_member_start, panel_member_done, panel_done
- Frontend: multi-agent picker, live panel bubbles, history rendering
- Graceful degradation: panel errors fall back to worker-only
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Previously a session could only be reassigned to another user via a
manual DB UPDATE. This adds it to the session edit UI for every owner of
a session (not just admins) - the ownership check in HandleUpdate
(existing.UserId == userId) already guarantees the caller owns the
session, so handing over one's own session is safe.
Backend:
- ProfileEndpoint: new GET /api/users returning a minimal user directory
(userId/username/displayName only) for any logged-in user. The
admin-gated /api/admin/users stays the source for sensitive fields
(defaultPath/canUseCli/isAdmin).
- SessionEndpoint.HandleUpdate: validate the target user exists (400 if
not) and pass allowUserReassign: true to UpdateSession.
- DatabaseService.UpdateSession: new allowUserReassign flag; only then is
a non-empty userId applied as user_id (empty/null is ignored - a
session must always have an owner).
Frontend:
- index.html: hidden #sessionOwnerRow with a user picker card in the
session edit form (existing sessions only).
- cards.js: buildUserCard helper for the picker.
- session-page.js: initSessionUserPicker loads users via apiGetUsers(),
preselects the current owner, and on an actual owner change asks for
confirmation (irreversible - the session leaves the user's own list).
- api.js: apiGetUsers() -> /api/users.
- ARCHITECTURE.md: document /api/users.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Pasted screenshots all share the same filename (e.g. "image.png"), so the
placeholder substitution in _renderUserTextContent resolved every
placeholder to the FIRST matching inline image via find() - showing the
first image N times. Data itself was always correct (DB/agent received
all images; a refresh rendered them properly).
Match images consumingly (findIndex + splice on a copy) instead: labels
and inlineImages are built in the same order, so same-named images now
map one-to-one. Also fix the same latent issue in the legacy attachment
path in history.js (_autoLoadImageAttachments), keeping the shift()
fallback.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Shorten the streaming-mode input placeholder from
"💬 Einwurf an die laufende Arbeit… (Enter)" to a terse "Einwurf...".
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
When the chat is opened while a chain is already streaming, the recovery
poll (_streamingPollInterval) is started. Its forced pollHistory(true)
renders the DB messages while the live SSE bubbles render them too — the
live bubbles never advance lastKnownMessageId, so the poll re-fetches the
same assistant message and renders a second bubble.
Make live SSE and the recovery poll mutually exclusive:
- Stop a lingering recovery poll at the start of a real live stream so the
SSE renders alone.
- Re-ensure the regular (isStreaming-guarded) history polling idempotently
in the finally block, so it is not left off after entering a running chain.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Let the user inject a message into a running chain instead of only being
able to abort it. While a chain streams, typing + Enter sends the text to
a new /api/chat/steer endpoint; it is drained at the next iteration
boundary, wrapped with a hint so the model actively classifies it
("complements the task -> keep working" vs. "changes course -> adjust"),
and stored as a Type="steer" user message so it survives reload.
Shared infrastructure (provider-agnostic):
- SteeringQueue: out-of-band queue keyed by sessionId, mirrored from
StreamingTracker (Enqueue/Drain/Clear).
- Program.cs registers it as a singleton and passes it to AnthropicService.
- ChatEndpoint: POST /api/chat/steer enqueues only while IsStreaming,
Clear() in the finally.
- ChatService.BuildHistoryFromDb groups Type="steer" so no two
consecutive user turns are produced on re-chat.
- Frontend api.js/chat.js/bubbles.js/history.js + chat.css render the
optimistic steer bubble and the steer_injected SSE event; Enter during
a stream sends a steer instead of being blocked.
Anthropic API path:
- Drain point B (tool boundary, merged into the tool_result user turn)
and C (turn end -> inject + continue instead of finalize).
Claude CLI path (kill-and-restart):
- The agentic loop runs inside the claude child, so true mid-turn inject
is impossible. On a pending steer the child is killed at the next tool
boundary, progress is rebuilt from the DB as a <work_in_progress>
transcript, and the CLI is restarted with the steer appended.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Snapshot the agent's effort onto the chain (like model) so it survives
reload, archive and shared chains, then show it in the chain-end meta line.
- ChainRecord.Effort + chains.effort column (TryAddColumn migration).
- CreateChain INSERT carries the value.
- ChatService snapshots agent.Effort at chain creation, but only for Claude
models – OpenAI providers store '' so there is no misleading badge.
- Anthropic streaming + CLI done-events include effort for the live path.
- chat.js buildMetaBadges renders "Effort: <level>" after the model badge,
only when a value is set.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Opus 4.5+ and Sonnet 4.6+ support a new "effort" knob that controls how
much budget the model spends on thinking and tool calls. Plumb it through
end to end so each agent can pick its own level.
Storage & shape:
- New TEXT column agents.effort (default '') added via TryAddColumn.
- AgentRecord.Effort + INSERT/UPDATE in DatabaseService.Agents.cs.
- ChatContext.Effort + SubAgentContext.Effort so the value travels with the
request alongside model and tool settings.
Agent editor:
- Effort dropdown above git-commit behavior in the agent form (low/medium/
high/xhigh/max plus empty = "use default"). Always visible; on OpenAI
providers the value is sent but silently ignored.
- agent-page.js load/save and AgentEndpoint create/update wired up.
Anthropic API path:
- StreamChat and RunNonStreamingToolLoop add output_config: { effort } when
effort is set and not "high" – empty/null/"high" means "omit and let the
API pick its default".
- Sub-agents (preparer/review/finalizer) get the parameter through
RunAgentChat so each step uses its own agent's effort.
Anthropic CLI path:
- ClaudeCliService.ChatStreamingAsync takes an effort parameter and exports
CLAUDE_CODE_EFFORT_LEVEL on the spawned process. Env-var beats the
--effort flag because it also covers "max" and "ultracode".
- StreamChatViaCli, ChatNonStreamingViaCli, RunSubAgentViaCli, and the
ChatEndpoint anthropic branches all hand the value through.
ARCHITECTURE.md / ARCHITECTURE_QUICK.md updated with the new field.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
MiniMax-M2.7 stoppt häufig nach Action-Ankündigung ohne Tool-Call (z.B. "Lass mich X machen:" → stop).
Auto-Continue erkennt das per Heuristik und injiziert automatisch "Continue." als User-Message (max 3×).
MiniMax-Sampling: temperature=1.0, top_p=0.95 (offizielle Empfehlung für agentic Performance).
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
- Auto-Context (Embedding-Suche) für OpenAI-Provider aktiviert: BuildAutoContextAsync
auf internal static refactored und in StreamChat + ChatNonStreaming integriert
- Tool-Results mit Role="tool" (OpenAI-Konvention) werden in BuildHistoryFromDb
jetzt korrekt erkannt (vorher nur Role="user"/Anthropic)
- Payload-Preview zeigt für OpenAI-Provider echtes API-Format (function-Wrapper,
tool_choice:"auto", max_tokens, stream_options, extra_body)
- Tool-Input (Argumente) wird im SSE tool_end-Event mitgesendet (fehlte im OpenAI-Pfad)
- Leere Bubbles durch Whitespace-only Text nach </think>-Extraktion behoben
(Trim in DB-Save, BuildHistoryFromDb und Frontend-Guard)
- History-Toggle-Bug: var→const in for-Loop (Block-Scoping für Closures),
tool_result-Matching per data-tool-call-id statt blindes letztes Element
- Non-Streaming max_tokens für MiniMax auf 32768 + extra_body.reasoning_split
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Pfade werden auf Windows nativ mit Backslashes zurückgegeben statt zu Forward-Slashes konvertiert. Navigation von Laufwerk (C:) zurück zur Laufwerksliste ermöglicht.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Remote-Verbindungen erkennen jetzt das OS des Clients und passen die Tool-Description
dynamisch an (PowerShell für Windows, Bash für Linux). Neues remote.sh Script für
Linux/macOS-Clients mit embedded Python WebSocket-Client.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
- recalled_context-Header verstärkt (klare Nutzungs-Anweisung statt passivem Hinweis)
- SSE-Event 'auto_context' ans Frontend senden für Live-Anzeige
- Auto-Context als Message (type=auto_context) in DB speichern
- Aufklappbare Auto-Context-Box im Chat-Stream und History-Rendering
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Neues Server-Setting NvidiaApiKey – wenn gesetzt, wird direkt
integrate.api.nvidia.com verwendet statt g4f.space Proxy.
Thinking-Modelle (kimi-k2, qwq, deepseek-r1) erhalten automatisch
chat_template_kwargs und reasoning-Output wird als klappbare
Denkprozess-Bubble im Chat angezeigt.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
- Neue Felder CanCreateAgents und CanUseCli im UserRecord (Default: true)
- DB-Migration mit Abwärtskompatibilität (bestehende User behalten alle Rechte)
- Admin-UI: Checkboxen für beide Berechtigungen pro User
- AgentEndpoint: Prüfung auf CanCreateAgents beim Erstellen
- ChatEndpoint: CLI-Fallback nur wenn CanUseCli erlaubt
- Frontend: Neuer-Agent-Button und Agent-Page bei fehlender Berechtigung gesperrt
- Chat: Proaktive Warnung wenn kein API-Key und keine CLI-Berechtigung
- Bug Fix: is_public fehlte im Agent-INSERT (Public Agents erst nach erneutem Speichern sichtbar)
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Sessions können jetzt einen Unity MCP-Server (URL + Token) konfigurieren.
Die CLI erhält automatisch die MCP-Config mit korrektem Transport-Typ
(URL-basierte Erkennung: /sse → SSE, sonst HTTP für streamableHttp).
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
TodoWrite → todo_write Mapping in Backend und Frontend ergänzt.
Todo-Liste wird jetzt aus dem Input-Array gebaut statt aus dem
Result, da die CLI nur einen generischen Erfolgstext zurückgibt.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
- Long-Poll durch Short-Poll ersetzt (MCP-Server pollt jede Sekunde statt einer blockierenden HTTP-Anfrage)
- Expliziter Lambda-Rückgabetyp Task<IResult> für ASP.NET Minimal API Endpoints (behebt 200 empty body Bug)
- Freitext-Option bei Choice-Buttons ("Eigene Antwort…") für freie User-Eingabe
- Stop während ask_user_choice markiert Chain als awaiting_user_choice statt stopped (Kontext bleibt erhalten)
- ask_user_choice System-Prompt-Instruktion breiter formuliert (Quiz, Multiple-Choice etc.)
- Text wird jetzt immer in DB gespeichert, auch bei ask_user_choice
- Key-Check Model auf claude-haiku-4-5 geändert
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
MCP-Server erweitert um ask_user_choice (Long-Poll), memory_read, memory_write
und memory_list Tools. MCP-Config wird jetzt immer generiert (nicht nur bei
Remote-Verbindung). InternalEndpoint um PendingChoices + choice-respond Endpoint
ergänzt. Frontend differenziert CLI-Modus (choice-respond API) vs. API-Modus.
Gesamter :::ASK_USER_CHOICE::: Text-Marker-Mechanismus aus ClaudeCliService,
AnthropicService, markdown.js und stream-ui.js entfernt.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
- Python MCP-Server (stdio, JSON-RPC 2.0) für remote_execute via Claude CLI
- Interner API-Endpoint /api/internal/remote-execute mit Token-Auth
- MCP-Config wird automatisch generiert wenn Remote-Verbindung vorhanden
- Auth-Middleware: /api/internal/ von Auth ausgenommen
- Frontend: :::ASK_USER_CHOICE::: Blöcke als interaktive Buttons rendern
- Streaming: Unvollständige Choice-Blöcke werden während des Streams versteckt
- tool-ui.js: MCP-Tool-Namen generisch normalisieren (mcp__server__tool → tool)
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Result-Div wird nicht mehr leer erstellt bei tool_use – erst wenn
tatsächlich ein Result vorliegt. Header wird nachträglich clickable
gemacht wenn das Result später eintrifft.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
- Tool-Namen/Inputs von CLI-Konvention auf gott-Konvention mappen (Edit→edit_file, file_path→path etc.)
- Text vor Tool-Use in DB flushen für korrekte Reihenfolge (statt alles am Ende als Blob)
- lineBuffer in ClaudeCliService vor Tool-Start und bei Text-Block-Ende flushen
- ToolResult-Events parsen und in DB speichern (CLI sendet diese als type:"user" Messages)
- Errors in DB speichern und als SSE-Event senden
- Bild-Attachments als Temp-Dateien für CLI bereitstellen (Read-Tool kann sie lesen)
- Frontend: tool_result Handler, Tool-Name-Normalisierung, appendToolResult()
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
- sp-loading: Flexbox-Layout statt text-align center
- Remote-Modal: Powershell-Befehl immer sichtbar (nicht nur bei leerer Liste)
- remote-card-content: Padding ergänzt
- Neuer Endpoint GET /api/sessions/{id}/payload-preview
Gibt den exakten Anthropic-API-Payload als JSON zurück (read-only)
- Chat-Menü: 'Payload anzeigen' öffnet Modal mit formatiertem JSON
- Reminder-Logik umgebaut: halbes Intervall (15) vor Ende,
dann volle Intervalle (30) rückwärts statt von vorne gezählt
- CSS: Payload-Modal Styling, kleine Variable-Fixes
- <hint> wird an jede User-Nachricht angehängt wenn Plan-Modus aktiv
- Erinnert Agent an Einschränkungen: keine Dateiänderungen, keine Shell-Befehle (außer read-only), keine Commits
- Analog zum bestehenden cat -n Hint
