* feat(ui): scoped graph nodes per ticker + MockEngine for LLM-free UI testing
## Summary
Adds a MockEngine that streams scripted agent events with zero real LLM calls,
enabling full UI testing (graph, terminal, drawer, metrics) without API keys or
network. Also fixes the ReactFlow graph so that each ticker/identifier gets its
own visual node — previously an auto run with 5 tickers collapsed all pipelines
into the same node IDs, overwriting each other.
## Changes
- **MockEngine** (`agent_os/backend/services/mock_engine.py`): new class that
generates realistic scripted events for pipeline, scan, and auto run types.
Supports configurable speed divisor (1× realistic → 10× instant). Auto mock
accepts a `tickers` list for multi-ticker runs.
- **POST /api/run/mock** (`runs.py`): new endpoint wiring MockEngine into the
BackgroundTasks + store pattern identical to real run endpoints.
- **WebSocket routing** (`websocket.py`): added `mock` run-type branch so the
WS executor path also dispatches to MockEngine when the background task hasn't
started yet.
- **LangGraphEngine** (`langgraph_engine.py`): added `_run_identifiers` dict to
track ticker/MARKET/portfolio_id per run; all emitted events now carry an
`identifier` field so the frontend can scope them.
- **AgentGraph.tsx**: ReactFlow nodes now keyed by `node_id:identifier` (e.g.
`news_analyst:AAPL`, `news_analyst:NVDA`). Edges scoped to same identifier.
`onNodeClick` passes raw `node_id` + `identifier` separately so the event
drawer can filter without parsing the scoped key.
- **Dashboard.tsx**: Mock button + type/speed controls added. `openNodeDetail`
accepts identifier; `NodeEventsDetail` filters by both `node_id` and
`identifier`. Comma-separated ticker input for mock auto runs (e.g.
`AAPL,NVDA,TSLA`).
- **useAgentStream.ts**: `AgentEvent` interface extended with `identifier?`
field.
## Decision Context
- Scoped node ID format chosen as `node_id:identifier` (colon separator) rather
than embedding identifier in the agent display name — keeps node labels clean
and identifier visible as a coloured badge, not label text.
- Raw `node_id` and `identifier` stored separately in `node.data` so the drawer
filtering (`events.filter(e => e.node_id === nodeId && e.identifier === id)`)
does not need to parse/split the scoped key.
- Parent edges are scoped to the same identifier as the child, assuming intra-
ticker chains. Cross-run topology edges (e.g. scan → pipeline) are implicit
via log events, not ReactFlow edges.
- MockEngine uses `asyncio.sleep` with a speed divisor — higher speed values
give faster replays for rapid iteration during UI development.
## Considerations for Future Agents
- Re-run button on graph nodes already uses `identifier` to dispatch
`startRun('pipeline', { ticker: identifier })` or `startRun('scan')` — no
further changes needed for per-node re-runs to be correctly scoped.
- The `_run_identifiers` dict in LangGraphEngine is keyed by `run_id`; it is
cleaned up after each run. If parallel runs are ever supported per engine
instance, this dict handles them correctly already.
- For run_auto, each sub-run (scan, per-ticker pipeline) calls its own
`run_scan`/`run_pipeline` which sets `_run_identifiers[run_id]`. The outer
`run_auto` does not set it — this is intentional.
- `uv.lock` changes reflect dependency tree after Chainlit removal in the
previous commit; no new runtime dependencies were added by this PR.
---
🤖 Commit Agent | Session: mock-engine + scoped-graph-nodes
* feat(graph): two-phase column layout — scan top, ticker columns below
## Summary
Redesigns the ReactFlow graph layout engine so scan nodes form a centred funnel
at the top and each ticker gets its own vertical column below, matching the
agreed design. Ticker header cards (bold ticker symbol + pulse dot + progress
counter) act as column anchors; agent cards stack beneath each one. Fan-out
dashed edges connect macro_synthesis → each ticker header.
## Changes
- SCAN phase: geopolitical/market-movers/sector scanners placed on the same
horizontal row at x = [0, COL_WIDTH, 2×COL_WIDTH] (aligns with first 3
ticker columns); industry_deep_dive and macro_synthesis centered below.
- TICKER columns: new identifiers get a TickerHeaderNode at tickerStartY;
agent nodes stack beneath using column-based parent tracking
(header → agent0 → agent1 → …) independent of evt.parent_node_id.
- TickerHeaderNode: wide card, bold ticker symbol, animated pulse status dot,
completedCount/agentCount counter updated live as results arrive.
- Tool nodes (node_id starts with "tool_") skipped from graph — visible in
terminal/drawer, not cluttering the column layout.
- Portfolio nodes centred below all ticker columns.
- Layout state extracted into LayoutState ref + freshLayout() for clean resets.
- Node labels use toLabel() (snake_case → Title Case).
- Metrics row shows total tokens (in+out) instead of just latency.
## Decision Context
- Column-based parent edges chosen over evt.parent_node_id because mock engine
emits parent_node_id="start" for all agents; column ordering is reliable.
- Scan phase X positions reuse COL_WIDTH so phase-1 scanners visually align
above first three ticker columns — no arbitrary magic numbers.
- Tool nodes removed from graph (not hidden) — they add noise to column layout
with no actionable meaning; the drawer already shows them per node.
## Considerations for Future Agents
- identifierLastNode tracks scoped ID of previous agent per ticker column —
used for sequential edge chaining; do not remove without replacing edge logic.
- tickerStartY is set once on first ticker arrival; subsequent tickers share
the same Y baseline — only colCount and identifierAgentRow differ per ticker.
- TickerHeaderNode clicks pass node_id='header' + identifier to onNodeClick;
Dashboard NodeEventsDetail filters all events by identifier when node_id is
'header' (shows the full ticker run timeline in the drawer).
---
🤖 Commit Agent | Session: two-phase column graph layout
- ReportStore.clear_portfolio_stage(date, portfolio_id): deletes pm_decision
(.json + .md) and execution_result files for a given date/portfolio
- DELETE /api/run/portfolio-stage endpoint: calls clear_portfolio_stage
and returns list of deleted files
- Dashboard: 'Reset Decision' button calls the endpoint, then user can
run Auto to re-run Phase 3 from scratch while skipping Phase 1 & 2
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Adds a 'Force re-run' checkbox that passes force=True to the backend,
bypassing all date-based skip checks (scan, pipeline, portfolio, execution).
Also fixes auto run: ticker is not required (scan discovers tickers),
portfolio_id is the correct required field instead.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
The scan summary never contained a 'prices' key, so trade execution always
ran with an empty prices dict. Now prices are fetched via yfinance:
- run_trade_execution: fetches prices for all tickers in the PM decision
(sells/buys/holds) when prices arg is empty
- run_auto resume path: fetches prices for decision tickers instead of
reading from scan data
- run_portfolio: fetches prices for current holdings + scan candidates
before invoking the portfolio graph
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
TRADINGAGENTS_REPORTS_DIR now controls where all reports land (scans,
analysis, portfolio artifacts). Both report_paths.REPORTS_ROOT and
ReportStore.data_dir read from the same env var so the entire
reports/daily/{date}/... tree is rooted at one configurable location.
PORTFOLIO_DATA_DIR still works as a portfolio-specific override.
Falls back to "reports" (relative to CWD) when neither is set.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
PortfolioRepository expects its own portfolio config (with data_dir),
not DEFAULT_CONFIG. Passing config=self.config caused a KeyError because
DEFAULT_CONFIG has no data_dir key. Removing the argument lets the
repository call get_portfolio_config() which provides the correct defaults.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
- Extend run_portfolio to save Holding Reviews, Risk Metrics, PM Decision,
and Execution Result from final state
- Add run_trade_execution method for resuming trade execution from a saved
PM decision without re-running the full portfolio graph
- Update run_auto skip logic to check for execution result (not just decision)
and resume from saved decision when available
- Gitignore uv.lock and untrack it from version control
Co-Authored-By: Oz <oz-agent@warp.dev>
Added comprehensive unit tests for `fundamentals_analyst`, `market_analyst`,
`social_media_analyst`, and `news_analyst` to verify that they correctly
handle recursive tool calling via `run_tool_loop`. A MockLLM was created
to simulate a two-turn conversation (tool call request followed by a final
report generation) to ensure the `.invoke()` bug does not regress. Added
missing `build_instrument_context` imports to those agents to prevent
NameErrors.
Co-authored-by: aguzererler <6199053+aguzererler@users.noreply.github.com>
This commit updates the `fundamentals_analyst`, `market_analyst`,
`social_media_analyst`, and `news_analyst` files to use `run_tool_loop`
instead of `.invoke()`. Using `.invoke()` resulted in the LLM execution
stopping immediately upon a tool call request without executing the tool,
returning an empty report or raw JSON. The `run_tool_loop` function
ensures tools are executed recursively and the final text content is
returned.
Co-authored-by: aguzererler <6199053+aguzererler@users.noreply.github.com>
- Wrap each event-type branch (LLM start/end, tool start/end) in try/except
to prevent a single unexpected object shape from crashing the streaming loop
- Add _safe_dict() helper to guard response_metadata and usage_metadata
access — some providers return non-dict types (bound methods, etc.)
- Fix potential_text extraction: check for None AND callable before using
- Ensure all event IDs use .get() with fallback to prevent KeyError
- Fix test file: remove hardcoded /Users/Ahmet/ path, add edge-case tests
for non-dict metadata, tool events, and unknown event types
- All 725 unit tests pass, TypeScript compiles clean
Co-authored-by: aguzererler <6199053+aguzererler@users.noreply.github.com>
Agent-Logs-Url: https://github.com/aguzererler/TradingAgents/sessions/fe6575b5-c03b-4037-bd98-a94303ae8313
1. Run buttons: only the triggered button shows spinner, others disabled
2. Backend: enhanced prompt extraction with multiple fallback paths
(data.messages, data.input.messages, data.input, data.kwargs.messages)
and raw dump fallback; improved response extraction for edge cases
3. Portfolio viewer: new PortfolioViewer component with holdings table,
trade history, and summary tabs; portfolio dropdown with auto-load;
Wallet sidebar icon now navigates to portfolio page
4. Parameter inputs: collapsible panel with date/ticker/portfolio_id;
validation prevents running without required fields per run type
Co-authored-by: aguzererler <6199053+aguzererler@users.noreply.github.com>
Agent-Logs-Url: https://github.com/aguzererler/TradingAgents/sessions/ffa268c8-e97c-4335-9bce-19bba583bea9
Backend:
- Extract full prompt from all LLM messages (not just first)
- Add prompt/response fields to streamed event payloads
- Improve model name extraction with multiple fallback strategies
- Add run_portfolio and run_auto streaming methods
- Wire portfolio/auto in websocket router
- New tool_result event type for tool completion
Frontend:
- Add full event detail modal with tabs (Prompt, Response, Summary, Metrics)
- Show actual prompt content in drawer instead of "Prompting unknown..."
- Add Scan, Pipeline, Portfolio, Auto buttons to control panel
- Fix node animation: completed nodes never revert to running
- Handle tool_result type for marking tool nodes as done
- Drawer events have "Full Detail →" button to open modal
Co-authored-by: aguzererler <6199053+aguzererler@users.noreply.github.com>
Agent-Logs-Url: https://github.com/aguzererler/TradingAgents/sessions/7997c579-ab7e-4071-afd0-18703a8e5618
The agent_os/, agent_os/backend/, agent_os/backend/routes/, and
agent_os/backend/services/ directories were missing __init__.py,
causing `from agent_os.backend.routes import ...` to fail with
ModuleNotFoundError when running `python agent_os/backend/main.py`.
Co-authored-by: aguzererler <6199053+aguzererler@users.noreply.github.com>
Agent-Logs-Url: https://github.com/aguzererler/TradingAgents/sessions/4b002166-5cc2-4a75-aa01-14d7b5d8d8bc
1. Terminal: remove inline prompts/full text; show short summary per event;
click any event to open detail drawer with full request/response/model/metrics
2. Fix node "thinking" animation: shimmer only when status=running;
on_chat_model_end (result) transitions node to completed, animation stops
3. Link nodes to events: clicking a graph node opens the drawer showing
all events for that node (prompts, tool calls, results)
4. Upgrade Vite 5→8.0.1, @vitejs/plugin-react→5.2.0;
update tsconfig moduleResolution to "bundler" for Vite 8 compat
Co-authored-by: aguzererler <6199053+aguzererler@users.noreply.github.com>
Agent-Logs-Url: https://github.com/aguzererler/TradingAgents/sessions/93c31c35-9509-4254-96fd-6f47aad07927
ahmet guzererler
copilot-swe-agent[bot]
google-labs-jules[bot]