yf176 commited on
Commit ·
038d10f
1
Parent(s): 0887bee
docs: define V8 agent contracts storage ACL and UI
Browse files- docs/polyhedraV8.0.md +628 -137
docs/polyhedraV8.0.md
CHANGED
|
@@ -153,144 +153,259 @@ Permissions apply within the active session and the agent's effective ticker
|
|
| 153 |
scope. Unlisted artifacts are inaccessible through the runtime file interface.
|
| 154 |
All entries are filenames or filename templates relative to the session folder,
|
| 155 |
including subdirectories. They are not logical artifact identifiers.
|
| 156 |
-
`{ticker}` resolves only to tickers in the agent's effective scope
|
| 157 |
-
|
| 158 |
-
for delta comparisons. Listing returns only filenames allowed by `list`;
|
| 159 |
reading their contents separately requires `read` permission.
|
| 160 |
|
| 161 |
#### ACL Table
|
| 162 |
|
| 163 |
-
|
| 164 |
-
|
| 165 |
-
enforcement
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 166 |
|
| 167 |
| Agent | `read` | `create` | `edit` | `list` |
|
| 168 |
|---|---|---|---|---|
|
| 169 |
-
| `DataFetcher` | `[quant/
|
| 170 |
-
| `OptionsFlowWatcher` | `[]` | `[quant/
|
| 171 |
-
| `TrendAnalyst` | `[quant/
|
| 172 |
-
| `SentimentAnalyst` | `[quant/
|
| 173 |
-
| `MarketEventWatcher` | `[quant/
|
| 174 |
-
| `MacroContextWatcher` | `[quant/
|
| 175 |
-
| `UnusualEventDetector` | `[quant/
|
| 176 |
-
| `EventRouter` | `[quant/
|
| 177 |
-
| `BTCAnalyst` | `[quant/
|
| 178 |
-
| `SPYAnalyst` | `[quant/
|
| 179 |
-
| `QQQAnalyst` | `[quant/
|
| 180 |
-
| `GLDAnalyst` | `[quant/
|
| 181 |
-
| `QuantResearcher` | `[quant/
|
| 182 |
-
| `Backtester` | `[quant/
|
| 183 |
-
| `RiskAnalyst` | `[quant/
|
| 184 |
-
| `QuantStrategist` | `[quant/
|
| 185 |
-
| `Publisher` | `[quant/
|
| 186 |
-
| `VizAgent` | `[quant/raw/{ticker}
|
| 187 |
-
| `PortfolioMonitor` | `[]` | `[quant/
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 188 |
|
| 189 |
#### Baseline File Permissions
|
| 190 |
|
| 191 |
-
|
| 192 |
-
|
| 193 |
-
|
| 194 |
-
|
| 195 |
-
|
| 196 |
-
|
| 197 |
|
| 198 |
| Agent | Additional `read` | Additional `list` |
|
| 199 |
|---|---|---|
|
| 200 |
-
| `DataFetcher` | `[quant/
|
| 201 |
-
| `OptionsFlowWatcher` | `[quant/
|
| 202 |
-
| `TrendAnalyst` | `[quant/
|
| 203 |
-
| `SentimentAnalyst` | `[quant/
|
| 204 |
-
| `MarketEventWatcher` | `[quant/
|
| 205 |
-
| `MacroContextWatcher` | `[quant/
|
| 206 |
-
| `UnusualEventDetector` | `[quant/
|
| 207 |
-
| `EventRouter` | `[quant/
|
| 208 |
-
| `BTCAnalyst` | `[quant/
|
| 209 |
-
| `SPYAnalyst` | `[quant/
|
| 210 |
-
| `QQQAnalyst` | `[quant/
|
| 211 |
-
| `GLDAnalyst` | `[quant/
|
| 212 |
-
| `QuantResearcher` | `[quant/
|
| 213 |
-
| `Backtester` | `[quant/
|
| 214 |
-
| `RiskAnalyst` | `[quant/
|
| 215 |
-
| `QuantStrategist` | `[quant/
|
| 216 |
-
| `Publisher` | `[quant/
|
| 217 |
| `VizAgent` | `[]` | `[]` |
|
| 218 |
| `PortfolioMonitor` | `[]` | `[]` |
|
| 219 |
|
| 220 |
#### Permission Boundaries
|
| 221 |
|
| 222 |
-
-
|
| 223 |
-
|
| 224 |
-
|
| 225 |
-
|
| 226 |
-
|
| 227 |
-
-
|
| 228 |
-
|
| 229 |
-
|
| 230 |
-
|
| 231 |
-
-
|
| 232 |
-
|
| 233 |
-
|
| 234 |
-
- The
|
| 235 |
-
|
| 236 |
-
|
| 237 |
-
|
| 238 |
-
|
| 239 |
-
|
| 240 |
-
|
| 241 |
-
|
| 242 |
-
|
| 243 |
-
|
| 244 |
-
|
| 245 |
-
|
| 246 |
-
|
| 247 |
-
|
| 248 |
-
|
| 249 |
-
|
| 250 |
-
|
|
|
|
| 251 |
|
| 252 |
#### File Content Reference
|
| 253 |
|
| 254 |
-
|
| 255 |
-
|
| 256 |
-
|
| 257 |
-
guarantee that a provider or agent successfully produced it in every run.
|
| 258 |
|
| 259 |
-
|
|
| 260 |
-
|---|---|---|
|
| 261 |
-
| `quant/
|
| 262 |
-
| `quant/
|
| 263 |
-
| `quant/
|
| 264 |
-
| `quant/
|
| 265 |
-
| `quant/
|
| 266 |
-
| `quant/
|
| 267 |
-
| `quant/
|
| 268 |
-
| `quant/
|
| 269 |
-
| `quant/
|
| 270 |
-
| `quant/
|
| 271 |
-
| `quant/
|
| 272 |
-
| `quant/
|
| 273 |
-
| `quant/
|
| 274 |
-
| `quant/
|
| 275 |
-
| `quant/
|
| 276 |
-
| `quant/
|
| 277 |
-
| `quant/
|
| 278 |
-
| `quant/
|
| 279 |
-
| `quant/
|
| 280 |
-
| `quant/
|
| 281 |
-
| `quant/
|
| 282 |
-
| `quant/
|
| 283 |
-
| `quant/viz/
|
| 284 |
-
| `quant/
|
| 285 |
-
| `quant/
|
| 286 |
-
| `quant/
|
| 287 |
-
| `quant/
|
| 288 |
-
| `
|
| 289 |
-
| `
|
| 290 |
-
| `
|
| 291 |
-
|
| 292 |
-
|
| 293 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 294 |
|
| 295 |
### Typed Artifact Schemas
|
| 296 |
|
|
@@ -303,8 +418,295 @@ data-quality metadata must be respected when consuming these files.
|
|
| 303 |
its ACL.
|
| 304 |
- Human-readable markdown may remain as a rendered artifact, but markdown
|
| 305 |
conventions alone are not the V8.0 machine contract.
|
| 306 |
-
- Artifact
|
| 307 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 308 |
|
| 309 |
### Runtime And Product Boundaries
|
| 310 |
|
|
@@ -328,15 +730,100 @@ data-quality metadata must be respected when consuming these files.
|
|
| 328 |
|
| 329 |
### UI Visibility
|
| 330 |
|
| 331 |
-
The
|
|
|
|
|
|
|
|
|
|
| 332 |
|
| 333 |
-
|
| 334 |
-
|
| 335 |
-
|
| 336 |
-
|
|
|
|
|
|
|
|
|
|
| 337 |
|
| 338 |
-
|
| 339 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 340 |
|
| 341 |
---
|
| 342 |
|
|
@@ -432,13 +919,16 @@ applicable ticker scope.
|
|
| 432 |
|
| 433 |
---
|
| 434 |
|
| 435 |
-
##
|
| 436 |
|
| 437 |
-
The Routing Table and
|
| 438 |
-
|
| 439 |
-
|
| 440 |
-
|
| 441 |
-
|
|
|
|
|
|
|
|
|
|
| 442 |
|
| 443 |
---
|
| 444 |
|
|
@@ -453,9 +943,10 @@ implemented.
|
|
| 453 |
- [x] Define the complete Routing Table at the agent-dependency and scope level.
|
| 454 |
- [x] Draft filename-based ACL rows and file-content references for all quant agents.
|
| 455 |
- [x] Record baseline snapshot read permissions for session-delta context.
|
| 456 |
-
- [
|
| 457 |
-
- [
|
| 458 |
-
- [
|
| 459 |
-
- [
|
| 460 |
-
- [
|
| 461 |
-
- [
|
|
|
|
|
|
| 153 |
scope. Unlisted artifacts are inaccessible through the runtime file interface.
|
| 154 |
All entries are filenames or filename templates relative to the session folder,
|
| 155 |
including subdirectories. They are not logical artifact identifiers.
|
| 156 |
+
`{ticker}` resolves only to tickers in the agent's effective scope. Run IDs
|
| 157 |
+
resolve to the current run or the explicitly selected read-only source run. Listing returns only filenames allowed by `list`;
|
|
|
|
| 158 |
reading their contents separately requires `read` permission.
|
| 159 |
|
| 160 |
#### ACL Table
|
| 161 |
|
| 162 |
+
This is the V8.0 filename contract for all 19 registered quant agents.
|
| 163 |
+
It supersedes the earlier date-based draft. It is a PRD specification;
|
| 164 |
+
runtime enforcement has not been implemented.
|
| 165 |
+
|
| 166 |
+
Every entry below is a complete session-relative filename template.
|
| 167 |
+
`{run_id}` is the runtime-selected current run. For a separate visualization
|
| 168 |
+
request, read entries bind to its selected source run and create/edit entries
|
| 169 |
+
bind to the visualization run; these bindings are fixed before activation.
|
| 170 |
+
A required dependency must be present; optional reads confer no scheduling
|
| 171 |
+
dependency. Missing optional files remain explicit gaps.
|
| 172 |
|
| 173 |
| Agent | `read` | `create` | `edit` | `list` |
|
| 174 |
|---|---|---|---|---|
|
| 175 |
+
| `DataFetcher` | `[quant/runs/{run_id}/data_fetch.json, quant/runs/{run_id}/raw/{ticker}.json]` | `[quant/runs/{run_id}/data_fetch.json, quant/runs/{run_id}/data_fetch.md, quant/runs/{run_id}/raw/{ticker}.json, quant/runs/{run_id}/raw/{ticker}_summary.md]` | `[quant/runs/{run_id}/data_fetch.json, quant/runs/{run_id}/data_fetch.md, quant/runs/{run_id}/raw/{ticker}.json, quant/runs/{run_id}/raw/{ticker}_summary.md]` | `[quant/runs/{run_id}/raw/{ticker}.json]` |
|
| 176 |
+
| `OptionsFlowWatcher` | `[]` | `[quant/runs/{run_id}/options_flow.json, quant/runs/{run_id}/options_flow.md]` | `[quant/runs/{run_id}/options_flow.json, quant/runs/{run_id}/options_flow.md]` | `[]` |
|
| 177 |
+
| `TrendAnalyst` | `[quant/runs/{run_id}/data_fetch.json, quant/runs/{run_id}/raw/{ticker}.json]` | `[quant/runs/{run_id}/trend_analysis.json, quant/runs/{run_id}/trend_analysis.md]` | `[quant/runs/{run_id}/trend_analysis.json, quant/runs/{run_id}/trend_analysis.md]` | `[quant/runs/{run_id}/raw/{ticker}.json]` |
|
| 178 |
+
| `SentimentAnalyst` | `[quant/runs/{run_id}/data_fetch.json, quant/runs/{run_id}/raw/{ticker}.json, quant/runs/{run_id}/trend_analysis.json]` | `[quant/runs/{run_id}/sentiment_analysis.json, quant/runs/{run_id}/sentiment_analysis.md]` | `[quant/runs/{run_id}/sentiment_analysis.json, quant/runs/{run_id}/sentiment_analysis.md]` | `[quant/runs/{run_id}/raw/{ticker}.json]` |
|
| 179 |
+
| `MarketEventWatcher` | `[quant/runs/{run_id}/data_fetch.json, quant/runs/{run_id}/raw/{ticker}.json, quant/runs/{run_id}/trend_analysis.json]` | `[quant/runs/{run_id}/market_events.json, quant/runs/{run_id}/market_events.md]` | `[quant/runs/{run_id}/market_events.json, quant/runs/{run_id}/market_events.md]` | `[quant/runs/{run_id}/raw/{ticker}.json]` |
|
| 180 |
+
| `MacroContextWatcher` | `[quant/runs/{run_id}/market_events.json, quant/runs/{run_id}/options_flow.json]` | `[quant/runs/{run_id}/macro_context.json, quant/runs/{run_id}/macro_context.md]` | `[quant/runs/{run_id}/macro_context.json, quant/runs/{run_id}/macro_context.md]` | `[]` |
|
| 181 |
+
| `UnusualEventDetector` | `[quant/runs/{run_id}/market_events.json, quant/runs/{run_id}/options_flow.json, quant/runs/{run_id}/macro_context.json]` | `[quant/runs/{run_id}/unusual_events.json, quant/runs/{run_id}/unusual_events.md]` | `[quant/runs/{run_id}/unusual_events.json, quant/runs/{run_id}/unusual_events.md]` | `[]` |
|
| 182 |
+
| `EventRouter` | `[quant/runs/{run_id}/unusual_events.json, quant/runs/{run_id}/market_events.json, quant/runs/{run_id}/options_flow.json]` | `[quant/runs/{run_id}/event_route.json, quant/runs/{run_id}/event_route.md]` | `[quant/runs/{run_id}/event_route.json, quant/runs/{run_id}/event_route.md]` | `[]` |
|
| 183 |
+
| `BTCAnalyst` | `[quant/runs/{run_id}/trend_analysis.json, quant/runs/{run_id}/event_route.json, quant/runs/{run_id}/market_events.json, quant/runs/{run_id}/macro_context.json, quant/runs/{run_id}/unusual_events.json, quant/runs/{run_id}/sentiment_analysis.json]` | `[quant/runs/{run_id}/btc_analysis.json, quant/runs/{run_id}/btc_analysis.md]` | `[quant/runs/{run_id}/btc_analysis.json, quant/runs/{run_id}/btc_analysis.md]` | `[]` |
|
| 184 |
+
| `SPYAnalyst` | `[quant/runs/{run_id}/trend_analysis.json, quant/runs/{run_id}/event_route.json, quant/runs/{run_id}/market_events.json, quant/runs/{run_id}/options_flow.json, quant/runs/{run_id}/macro_context.json, quant/runs/{run_id}/unusual_events.json, quant/runs/{run_id}/sentiment_analysis.json]` | `[quant/runs/{run_id}/spy_analysis.json, quant/runs/{run_id}/spy_analysis.md]` | `[quant/runs/{run_id}/spy_analysis.json, quant/runs/{run_id}/spy_analysis.md]` | `[]` |
|
| 185 |
+
| `QQQAnalyst` | `[quant/runs/{run_id}/trend_analysis.json, quant/runs/{run_id}/event_route.json, quant/runs/{run_id}/market_events.json, quant/runs/{run_id}/options_flow.json, quant/runs/{run_id}/macro_context.json, quant/runs/{run_id}/unusual_events.json, quant/runs/{run_id}/sentiment_analysis.json]` | `[quant/runs/{run_id}/qqq_analysis.json, quant/runs/{run_id}/qqq_analysis.md]` | `[quant/runs/{run_id}/qqq_analysis.json, quant/runs/{run_id}/qqq_analysis.md]` | `[]` |
|
| 186 |
+
| `GLDAnalyst` | `[quant/runs/{run_id}/trend_analysis.json, quant/runs/{run_id}/event_route.json, quant/runs/{run_id}/market_events.json, quant/runs/{run_id}/options_flow.json, quant/runs/{run_id}/macro_context.json, quant/runs/{run_id}/unusual_events.json, quant/runs/{run_id}/sentiment_analysis.json]` | `[quant/runs/{run_id}/gld_analysis.json, quant/runs/{run_id}/gld_analysis.md]` | `[quant/runs/{run_id}/gld_analysis.json, quant/runs/{run_id}/gld_analysis.md]` | `[]` |
|
| 187 |
+
| `QuantResearcher` | `[quant/runs/{run_id}/trend_analysis.json, quant/runs/{run_id}/sentiment_analysis.json, quant/runs/{run_id}/asset_analysis.json, quant/runs/{run_id}/macro_context.json, quant/runs/{run_id}/unusual_events.json]` | `[quant/runs/{run_id}/signals.json, quant/runs/{run_id}/signals.md]` | `[quant/runs/{run_id}/signals.json, quant/runs/{run_id}/signals.md]` | `[]` |
|
| 188 |
+
| `Backtester` | `[quant/runs/{run_id}/signals.json, quant/runs/{run_id}/raw/{ticker}.json]` | `[quant/runs/{run_id}/backtest_results.json, quant/runs/{run_id}/backtest_results.md]` | `[quant/runs/{run_id}/backtest_results.json, quant/runs/{run_id}/backtest_results.md]` | `[quant/runs/{run_id}/raw/{ticker}.json]` |
|
| 189 |
+
| `RiskAnalyst` | `[quant/runs/{run_id}/backtest_results.json, quant/runs/{run_id}/trend_analysis.json, quant/runs/{run_id}/asset_analysis.json, quant/runs/{run_id}/macro_context.json]` | `[quant/runs/{run_id}/risk_assessment.json, quant/runs/{run_id}/risk_assessment.md]` | `[quant/runs/{run_id}/risk_assessment.json, quant/runs/{run_id}/risk_assessment.md]` | `[]` |
|
| 190 |
+
| `QuantStrategist` | `[quant/runs/{run_id}/risk_assessment.json, quant/runs/{run_id}/backtest_results.json, quant/runs/{run_id}/sentiment_analysis.json, quant/runs/{run_id}/signals.json, quant/runs/{run_id}/asset_analysis.json, quant/runs/{run_id}/macro_context.json, quant/strategist_performance.json]` | `[quant/runs/{run_id}/trade_proposals.json, quant/runs/{run_id}/trade_proposals.md, quant/strategist_performance.json]` | `[quant/runs/{run_id}/trade_proposals.json, quant/runs/{run_id}/trade_proposals.md, quant/strategist_performance.json]` | `[]` |
|
| 191 |
+
| `Publisher` | `[quant/runs/{run_id}/trade_proposals.json, quant/runs/{run_id}/trend_analysis.json, quant/runs/{run_id}/sentiment_analysis.json, quant/runs/{run_id}/risk_assessment.json, quant/runs/{run_id}/asset_analysis.json, quant/runs/{run_id}/macro_context.json]` | `[quant/runs/{run_id}/post.json, quant/runs/{run_id}/post.md]` | `[quant/runs/{run_id}/post.json, quant/runs/{run_id}/post.md]` | `[]` |
|
| 192 |
+
| `VizAgent` | `[quant/runs/{run_id}/raw/{ticker}.json, quant/runs/{run_id}/backtest_results.json, quant/runs/{run_id}/risk_assessment.json]` | `[quant/runs/{run_id}/visualizations.json, quant/runs/{run_id}/visualizations.md, quant/runs/{run_id}/viz/candlestick_{ticker}.png, quant/runs/{run_id}/viz/rsi_macd_{ticker}.png, quant/runs/{run_id}/viz/backtest.png, quant/runs/{run_id}/viz/risk_heatmap.png, quant/runs/{run_id}/viz/portfolio_pnl.png]` | `[quant/runs/{run_id}/visualizations.json, quant/runs/{run_id}/visualizations.md, quant/runs/{run_id}/viz/candlestick_{ticker}.png, quant/runs/{run_id}/viz/rsi_macd_{ticker}.png, quant/runs/{run_id}/viz/backtest.png, quant/runs/{run_id}/viz/risk_heatmap.png, quant/runs/{run_id}/viz/portfolio_pnl.png]` | `[quant/runs/{run_id}/raw/{ticker}.json]` |
|
| 193 |
+
| `PortfolioMonitor` | `[]` | `[quant/runs/{run_id}/portfolio_log.json, quant/runs/{run_id}/portfolio_log.md]` | `[quant/runs/{run_id}/portfolio_log.json, quant/runs/{run_id}/portfolio_log.md]` | `[]` |
|
| 194 |
+
|
| 195 |
+
`edit` is limited to the owning agent's unpublished outputs during its current
|
| 196 |
+
activation. After valid outputs are published and dependency completion is
|
| 197 |
+
recorded, those files are read-only. Later runs use different paths.
|
| 198 |
+
The session-level performance file is the explicit exception described below.
|
| 199 |
|
| 200 |
#### Baseline File Permissions
|
| 201 |
|
| 202 |
+
The following lists extend current-run permissions for session-delta context.
|
| 203 |
+
`{baseline_run_id}` is the prior completed YOLO run selected by the runtime
|
| 204 |
+
before activation. It cannot equal the current run ID or name a different
|
| 205 |
+
session. Each entry grants read-only access; no baseline file is editable.
|
| 206 |
+
These lists include prior outputs needed to perform the already specified
|
| 207 |
+
per-agent delta comparison.
|
| 208 |
|
| 209 |
| Agent | Additional `read` | Additional `list` |
|
| 210 |
|---|---|---|
|
| 211 |
+
| `DataFetcher` | `[quant/runs/{baseline_run_id}/raw/{ticker}.json]` | `[quant/runs/{baseline_run_id}/raw/{ticker}.json]` |
|
| 212 |
+
| `OptionsFlowWatcher` | `[quant/runs/{baseline_run_id}/options_flow.json, quant/runs/{baseline_run_id}/risk_assessment.json, quant/runs/{baseline_run_id}/trade_proposals.json, quant/runs/{baseline_run_id}/post.json]` | `[]` |
|
| 213 |
+
| `TrendAnalyst` | `[quant/runs/{baseline_run_id}/trend_analysis.json, quant/runs/{baseline_run_id}/post.json]` | `[]` |
|
| 214 |
+
| `SentimentAnalyst` | `[quant/runs/{baseline_run_id}/sentiment_analysis.json, quant/runs/{baseline_run_id}/trend_analysis.json, quant/runs/{baseline_run_id}/signals.json, quant/runs/{baseline_run_id}/post.json]` | `[]` |
|
| 215 |
+
| `MarketEventWatcher` | `[quant/runs/{baseline_run_id}/market_events.json, quant/runs/{baseline_run_id}/trend_analysis.json, quant/runs/{baseline_run_id}/signals.json, quant/runs/{baseline_run_id}/risk_assessment.json, quant/runs/{baseline_run_id}/trade_proposals.json, quant/runs/{baseline_run_id}/post.json]` | `[]` |
|
| 216 |
+
| `MacroContextWatcher` | `[quant/runs/{baseline_run_id}/macro_context.json, quant/runs/{baseline_run_id}/trend_analysis.json, quant/runs/{baseline_run_id}/signals.json, quant/runs/{baseline_run_id}/risk_assessment.json, quant/runs/{baseline_run_id}/trade_proposals.json, quant/runs/{baseline_run_id}/post.json]` | `[]` |
|
| 217 |
+
| `UnusualEventDetector` | `[quant/runs/{baseline_run_id}/unusual_events.json, quant/runs/{baseline_run_id}/signals.json, quant/runs/{baseline_run_id}/risk_assessment.json, quant/runs/{baseline_run_id}/trade_proposals.json, quant/runs/{baseline_run_id}/post.json]` | `[]` |
|
| 218 |
+
| `EventRouter` | `[quant/runs/{baseline_run_id}/event_route.json, quant/runs/{baseline_run_id}/risk_assessment.json, quant/runs/{baseline_run_id}/trade_proposals.json, quant/runs/{baseline_run_id}/post.json]` | `[]` |
|
| 219 |
+
| `BTCAnalyst` | `[quant/runs/{baseline_run_id}/btc_analysis.json, quant/runs/{baseline_run_id}/trend_analysis.json, quant/runs/{baseline_run_id}/signals.json, quant/runs/{baseline_run_id}/risk_assessment.json, quant/runs/{baseline_run_id}/trade_proposals.json, quant/runs/{baseline_run_id}/post.json]` | `[]` |
|
| 220 |
+
| `SPYAnalyst` | `[quant/runs/{baseline_run_id}/spy_analysis.json, quant/runs/{baseline_run_id}/trend_analysis.json, quant/runs/{baseline_run_id}/signals.json, quant/runs/{baseline_run_id}/risk_assessment.json, quant/runs/{baseline_run_id}/trade_proposals.json, quant/runs/{baseline_run_id}/post.json]` | `[]` |
|
| 221 |
+
| `QQQAnalyst` | `[quant/runs/{baseline_run_id}/qqq_analysis.json, quant/runs/{baseline_run_id}/trend_analysis.json, quant/runs/{baseline_run_id}/signals.json, quant/runs/{baseline_run_id}/risk_assessment.json, quant/runs/{baseline_run_id}/trade_proposals.json, quant/runs/{baseline_run_id}/post.json]` | `[]` |
|
| 222 |
+
| `GLDAnalyst` | `[quant/runs/{baseline_run_id}/gld_analysis.json, quant/runs/{baseline_run_id}/trend_analysis.json, quant/runs/{baseline_run_id}/signals.json, quant/runs/{baseline_run_id}/risk_assessment.json, quant/runs/{baseline_run_id}/trade_proposals.json, quant/runs/{baseline_run_id}/post.json]` | `[]` |
|
| 223 |
+
| `QuantResearcher` | `[quant/runs/{baseline_run_id}/signals.json, quant/runs/{baseline_run_id}/backtest_results.json, quant/runs/{baseline_run_id}/risk_assessment.json, quant/runs/{baseline_run_id}/trade_proposals.json, quant/runs/{baseline_run_id}/post.json]` | `[]` |
|
| 224 |
+
| `Backtester` | `[quant/runs/{baseline_run_id}/signals.json, quant/runs/{baseline_run_id}/backtest_results.json, quant/runs/{baseline_run_id}/risk_assessment.json, quant/runs/{baseline_run_id}/trade_proposals.json]` | `[]` |
|
| 225 |
+
| `RiskAnalyst` | `[quant/runs/{baseline_run_id}/backtest_results.json, quant/runs/{baseline_run_id}/risk_assessment.json, quant/runs/{baseline_run_id}/trade_proposals.json, quant/runs/{baseline_run_id}/post.json]` | `[]` |
|
| 226 |
+
| `QuantStrategist` | `[quant/runs/{baseline_run_id}/signals.json, quant/runs/{baseline_run_id}/backtest_results.json, quant/runs/{baseline_run_id}/risk_assessment.json, quant/runs/{baseline_run_id}/trade_proposals.json, quant/runs/{baseline_run_id}/post.json]` | `[]` |
|
| 227 |
+
| `Publisher` | `[quant/runs/{baseline_run_id}/trade_proposals.json, quant/runs/{baseline_run_id}/post.json, quant/runs/{baseline_run_id}/risk_assessment.json]` | `[]` |
|
| 228 |
| `VizAgent` | `[]` | `[]` |
|
| 229 |
| `PortfolioMonitor` | `[]` | `[]` |
|
| 230 |
|
| 231 |
#### Permission Boundaries
|
| 232 |
|
| 233 |
+
- The runtime resolves filenames and effective ticker scope before supplying
|
| 234 |
+
an agent's input. Providers, prompt builders, renderers, and RAG use the same
|
| 235 |
+
permissions when acting on behalf of that agent.
|
| 236 |
+
- `read` permits only fields declared by the input schema. `list` exposes
|
| 237 |
+
filenames only. A returned filename grants no implicit content access.
|
| 238 |
+
- Optional inputs are captured when an agent activates. An optional producer
|
| 239 |
+
completing later does not change that activation's input. Prior evidence
|
| 240 |
+
is supplied as baseline context with its original run and timestamps.
|
| 241 |
+
- `DataFetcher` does not read trend output to choose the next agent.
|
| 242 |
+
- The four asset analysts write only their individual artifacts. The runtime
|
| 243 |
+
assembles `AssetAnalysisCollection` from their published outputs and writes
|
| 244 |
+
the aggregate. Consumers receive only records overlapping their own scope.
|
| 245 |
+
- The trusted performance tracker, acting for `QuantStrategist`, is the only
|
| 246 |
+
writer of `quant/strategist_performance.json`. LLM votes cannot edit weights.
|
| 247 |
+
Each run's strategy output retains the weights actually used and the
|
| 248 |
+
resulting updates; replay does not substitute the latest session weights.
|
| 249 |
+
- Session state, conversation logs, run records, RAG indexes, input snapshots,
|
| 250 |
+
traces, and evidence ledgers are runtime-owned. Agent inputs may receive
|
| 251 |
+
selected typed state fields, never unrestricted state or thread contents.
|
| 252 |
+
Provider credentials remain in the configured service layer and are not
|
| 253 |
+
artifact contents.
|
| 254 |
+
- Snapshotting an input or building an aggregate does not grant broader read
|
| 255 |
+
access. The original producer, artifact identity, record references, and
|
| 256 |
+
ticker restrictions remain attached to the data.
|
| 257 |
+
- The tables grant no access to arbitrary older runs. Explicit baseline
|
| 258 |
+
references and a visualization's selected source run are the exceptions.
|
| 259 |
+
Session RAG retrieval is filtered to those same permitted files.
|
| 260 |
+
- JSON filenames in both tables must match the declared producer schema.
|
| 261 |
+
Markdown renderings remain available to people through replay and downloads;
|
| 262 |
+
they are not automatically added to an agent's read permissions.
|
| 263 |
|
| 264 |
#### File Content Reference
|
| 265 |
|
| 266 |
+
All paths are relative to the existing session folder. Each JSON/Markdown
|
| 267 |
+
pair below lists two explicit files: JSON contains the typed output, and
|
| 268 |
+
Markdown renders the same agent-owned content for the product and download.
|
|
|
|
| 269 |
|
| 270 |
+
| Filenames | Owner | Content |
|
| 271 |
+
|---|---|---|
|
| 272 |
+
| `quant/runs/{run_id}/data_fetch.json`, `quant/runs/{run_id}/data_fetch.md` | `DataFetcher` | DataFetcherOutput run manifest with availability, one ticker result per requested ticker, issues, and references to per-ticker data. |
|
| 273 |
+
| `quant/runs/{run_id}/options_flow.json`, `quant/runs/{run_id}/options_flow.md` | `OptionsFlowWatcher` | OptionsFlowWatcherOutput including sampled contracts, provider capabilities, context, flow candidates, supported unusual-flow claims, and sampling limits. |
|
| 274 |
+
| `quant/runs/{run_id}/trend_analysis.json`, `quant/runs/{run_id}/trend_analysis.md` | `TrendAnalyst` | TrendAnalystOutput with technical findings, evidence, and per-ticker delta. |
|
| 275 |
+
| `quant/runs/{run_id}/sentiment_analysis.json`, `quant/runs/{run_id}/sentiment_analysis.md` | `SentimentAnalyst` | SentimentAnalystOutput with source coverage, themes, earnings where applicable, sentiment, and uncertainty. |
|
| 276 |
+
| `quant/runs/{run_id}/market_events.json`, `quant/runs/{run_id}/market_events.md` | `MarketEventWatcher` | MarketEventWatcherOutput with observed data changes and already available news/catalysts; no invented external feed. |
|
| 277 |
+
| `quant/runs/{run_id}/macro_context.json`, `quant/runs/{run_id}/macro_context.md` | `MacroContextWatcher` | MacroContextWatcherOutput with the main line, weighted drivers, contradictions, and affected tickers. |
|
| 278 |
+
| `quant/runs/{run_id}/unusual_events.json`, `quant/runs/{run_id}/unusual_events.md` | `UnusualEventDetector` | UnusualEventDetectorOutput with meaningful events, suppression reasons, and monitoring conditions. |
|
| 279 |
+
| `quant/runs/{run_id}/event_route.json`, `quant/runs/{run_id}/event_route.md` | `EventRouter` | EventRouterOutput assigning event evidence to in-scope tickers without changing activation. |
|
| 280 |
+
| `quant/runs/{run_id}/btc_analysis.json`, `quant/runs/{run_id}/btc_analysis.md` | `BTCAnalyst` | BTCAnalystOutput for BTC only. |
|
| 281 |
+
| `quant/runs/{run_id}/spy_analysis.json`, `quant/runs/{run_id}/spy_analysis.md` | `SPYAnalyst` | SPYAnalystOutput for SPY only. |
|
| 282 |
+
| `quant/runs/{run_id}/qqq_analysis.json`, `quant/runs/{run_id}/qqq_analysis.md` | `QQQAnalyst` | QQQAnalystOutput for QQQ only. |
|
| 283 |
+
| `quant/runs/{run_id}/gld_analysis.json`, `quant/runs/{run_id}/gld_analysis.md` | `GLDAnalyst` | GLDAnalystOutput for GLD only. |
|
| 284 |
+
| `quant/runs/{run_id}/signals.json`, `quant/runs/{run_id}/signals.md` | `QuantResearcher` | QuantResearcherOutput with signal hypotheses, priorities, evidence, and lifecycle changes. |
|
| 285 |
+
| `quant/runs/{run_id}/backtest_results.json`, `quant/runs/{run_id}/backtest_results.md` | `Backtester` | BacktesterOutput with method, signal results, executed metrics when available, and limitations. |
|
| 286 |
+
| `quant/runs/{run_id}/risk_assessment.json`, `quant/runs/{run_id}/risk_assessment.md` | `RiskAnalyst` | RiskAnalystOutput with signal verdicts, portfolio risk, scenarios, and mitigations. |
|
| 287 |
+
| `quant/runs/{run_id}/trade_proposals.json`, `quant/runs/{run_id}/trade_proposals.md` | `QuantStrategist` | QuantStrategistOutput with proposals or no-trade/watch conclusions, votes, trusted weights, and prior proposal updates. |
|
| 288 |
+
| `quant/runs/{run_id}/post.json`, `quant/runs/{run_id}/post.md` | `Publisher` | PublisherOutput with Finley's readable result and proposal or no-proposal explanation. |
|
| 289 |
+
| `quant/runs/{run_id}/visualizations.json`, `quant/runs/{run_id}/visualizations.md` | `VizAgent` | VizAgentOutput manifest with chart references, sources, caption, and errors. |
|
| 290 |
+
| `quant/runs/{run_id}/portfolio_log.json`, `quant/runs/{run_id}/portfolio_log.md` | `PortfolioMonitor` | PortfolioMonitorOutput with position checks, quote provenance, thresholds, and alerts for one monitoring run. |
|
| 291 |
+
| `quant/runs/{run_id}/raw/{ticker}.json`, `quant/runs/{run_id}/raw/{ticker}_summary.md` | `DataFetcher` | MarketDataArtifact and its readable summary: normalized OHLCV, computed indicators, news, earnings, timestamps, and component quality. |
|
| 292 |
+
| `quant/runs/{run_id}/asset_analysis.json`, `quant/runs/{run_id}/asset_analysis.md` | Runtime aggregate | AssetAnalysisCollection preserving each analyst's producer and source reference. No additional analysis is generated. |
|
| 293 |
+
| `quant/runs/{run_id}/viz/candlestick_{ticker}.png` | `VizAgent` | Price candles, volume, and a moving-average overlay from validated data. |
|
| 294 |
+
| `quant/runs/{run_id}/viz/rsi_macd_{ticker}.png` | `VizAgent` | RSI and MACD plots from typed indicator series. |
|
| 295 |
+
| `quant/runs/{run_id}/viz/backtest.png` | `VizAgent` | Backtest metrics, with the source method clearly identified. |
|
| 296 |
+
| `quant/runs/{run_id}/viz/risk_heatmap.png` | `VizAgent` | Typed risk verdicts rendered as a risk-rating chart. |
|
| 297 |
+
| `quant/runs/{run_id}/viz/portfolio_pnl.png` | `VizAgent` | Existing position-size and entry-price visualization; its filename does not establish calculated P&L. |
|
| 298 |
+
| `quant/runs/{run_id}/inputs/{agent}.json` | Runtime | Exact ACL-filtered typed input used for an activation, including selected state, dependency identities, and baseline references; excludes secrets. `{agent}` is an exact registered name. |
|
| 299 |
+
| `yolo_runs/{run_id}.json` | Runtime | Existing replay record, extended with fixed routing plan, baseline run ID, artifact inventory, actual statuses, and resolved ACL/input references. Support runs carry their execution context and are excluded from the YOLO baseline selection. |
|
| 300 |
+
| `quant/evidence_ledger_{run_id}.json`, `quant/evidence_ledger_{run_id}.md` | Runtime | Existing evidence ledger filenames; records evidence actually used, excluded, or missing for that run. |
|
| 301 |
+
| `quant/strategist_performance.json` | Trusted tracker for `QuantStrategist` | Session-scoped current weights, vote history, and explainable changes. |
|
| 302 |
+
| `session.json`, `research_state.json`, `thread.jsonl`, `trace.jsonl` | Runtime | Existing session metadata, state, conversation, and append-only trace. Events and run references identify the relevant execution. |
|
| 303 |
+
|
| 304 |
+
Historical runs have the same layout with their own concrete run IDs. They
|
| 305 |
+
are read-only; this does not require a duplicate directory of baseline copies.
|
| 306 |
+
|
| 307 |
+
### Artifact Storage
|
| 308 |
+
|
| 309 |
+
#### Layout And Ownership
|
| 310 |
+
|
| 311 |
+
V8.0 keeps the existing session folder and introduces one directory per run:
|
| 312 |
+
|
| 313 |
+
```text
|
| 314 |
+
<session>/
|
| 315 |
+
session.json
|
| 316 |
+
research_state.json
|
| 317 |
+
thread.jsonl
|
| 318 |
+
trace.jsonl
|
| 319 |
+
yolo_runs/
|
| 320 |
+
<run_id>.json
|
| 321 |
+
quant/
|
| 322 |
+
strategist_performance.json
|
| 323 |
+
evidence_ledger_<run_id>.json
|
| 324 |
+
evidence_ledger_<run_id>.md
|
| 325 |
+
runs/
|
| 326 |
+
<run_id>/
|
| 327 |
+
inputs/
|
| 328 |
+
DataFetcher.json
|
| 329 |
+
TrendAnalyst.json
|
| 330 |
+
... other active registered agents ...
|
| 331 |
+
data_fetch.json
|
| 332 |
+
data_fetch.md
|
| 333 |
+
raw/
|
| 334 |
+
SPY.json
|
| 335 |
+
SPY_summary.md
|
| 336 |
+
trend_analysis.json
|
| 337 |
+
trend_analysis.md
|
| 338 |
+
... other published agent outputs from File Content Reference ...
|
| 339 |
+
```
|
| 340 |
+
|
| 341 |
+
The ellipses explain the layout; they are not ACL wildcard grants.
|
| 342 |
+
The same storage convention applies to quant analysis for every supported
|
| 343 |
+
market. Support executions have their own run IDs and execution contexts.
|
| 344 |
+
|
| 345 |
+
#### Publication And Versioning
|
| 346 |
+
|
| 347 |
+
1. A run ID is unique within its session, including multiple starts on the
|
| 348 |
+
same day. Dates belong in artifact content; a date alone is not an output
|
| 349 |
+
identity.
|
| 350 |
+
2. Inputs are resolved and recorded before activation. JSON is parsed and
|
| 351 |
+
validated before publication. Dependencies see only complete published
|
| 352 |
+
JSON files, never partial writes.
|
| 353 |
+
3. Before publication, an agent may edit only its own listed outputs. After
|
| 354 |
+
publication, the output identity and contents remain fixed. A rerun creates
|
| 355 |
+
a new run ID; it never replaces a prior completed result.
|
| 356 |
+
4. The runtime records schema version, producer, run ID, and exact path in
|
| 357 |
+
each artifact reference. Each JSON schema defines its own version;
|
| 358 |
+
Markdown and PNG references identify their format and source JSON artifact
|
| 359 |
+
instead of pretending the rendering implements a typed JSON schema.
|
| 360 |
+
5. The typed JSON is authoritative. Markdown is derived from its declared
|
| 361 |
+
narrative and structured fields. A rendering failure is recorded separately
|
| 362 |
+
from analysis availability and cannot erase an already valid JSON result.
|
| 363 |
+
6. Missing providers or inputs produce explicit typed gaps when possible.
|
| 364 |
+
An activation that cannot produce a valid output is recorded as failed;
|
| 365 |
+
no success artifact or no-trade decision is fabricated.
|
| 366 |
+
7. The runtime aggregate is published only after the active contributing
|
| 367 |
+
analysts reach their recorded terminal state. It preserves unavailable
|
| 368 |
+
entries and producer failures; absent results are never silently counted
|
| 369 |
+
as completed analyses.
|
| 370 |
+
8. Session-state updates and performance changes use the existing runtime
|
| 371 |
+
coordination. The per-run input and output snapshots retain the state
|
| 372 |
+
actually consumed or produced so later updates cannot rewrite replay.
|
| 373 |
+
|
| 374 |
+
#### Baseline And Replay
|
| 375 |
+
|
| 376 |
+
- The first run without a usable completed baseline performs baseline YOLO.
|
| 377 |
+
Subsequent runs select the latest completed eligible YOLO run in this
|
| 378 |
+
session. The selected baseline ID is fixed before activation.
|
| 379 |
+
- Each agent uses only the prior filenames listed in its baseline ACL.
|
| 380 |
+
A newly added ticker without prior coverage is explicitly not compared.
|
| 381 |
+
A failed or incomplete run remains available for review but does not replace
|
| 382 |
+
the last eligible baseline.
|
| 383 |
+
- Prior JSON is consumed only when its schema is supported. Existing
|
| 384 |
+
date-named Markdown and `quant/yolo_baselines/` snapshots remain available
|
| 385 |
+
in historical downloads and replay. They are not silently promoted to
|
| 386 |
+
typed inputs. A session with only legacy artifacts starts a new typed
|
| 387 |
+
baseline while retaining its existing session and paper-position state.
|
| 388 |
+
- The replay record and its artifact inventory identify one run exactly.
|
| 389 |
+
Replay must not search for the latest date-named file or substitute current
|
| 390 |
+
strategy weights, current state, or another run's Finley output.
|
| 391 |
+
- Saved files preserve the recorded result. This remains display replay;
|
| 392 |
+
deterministic LLM re-execution and historical simulation are separate
|
| 393 |
+
product capabilities.
|
| 394 |
+
|
| 395 |
+
#### Downloads And Retention
|
| 396 |
+
|
| 397 |
+
The existing recursive session export includes all run directories, input
|
| 398 |
+
snapshots, typed outputs, renderings, charts, baseline sources, replay records,
|
| 399 |
+
traces, and available evidence ledgers. The selected run record identifies
|
| 400 |
+
which artifacts belong to the viewed run when the package contains multiple
|
| 401 |
+
runs. Download remains available for completed, blocked, and failed runs.
|
| 402 |
+
|
| 403 |
+
The runtime does not delete prior runs on a later YOLO invocation or ordinary
|
| 404 |
+
process restart. Retention lasts as long as the underlying session storage
|
| 405 |
+
exists. This specification does not claim durability after replacement of
|
| 406 |
+
ephemeral deployment storage or introduce an external storage service.
|
| 407 |
+
The evidence ledger remains included in the package; it is not made a primary
|
| 408 |
+
UI panel by this storage change.
|
| 409 |
|
| 410 |
### Typed Artifact Schemas
|
| 411 |
|
|
|
|
| 418 |
its ACL.
|
| 419 |
- Human-readable markdown may remain as a rendered artifact, but markdown
|
| 420 |
conventions alone are not the V8.0 machine contract.
|
| 421 |
+
- Artifact paths and publication rules follow the Artifact Storage section.
|
| 422 |
+
|
| 423 |
+
#### `DataFetcher` Typed Contract
|
| 424 |
+
|
| 425 |
+
`DataFetcher` is a root agent. It fetches, normalizes, validates, and organizes
|
| 426 |
+
market data for its effective ticker scope. It does not interpret market
|
| 427 |
+
direction and does not select the next workflow agent.
|
| 428 |
+
|
| 429 |
+
##### Input: `DataFetcherInput`
|
| 430 |
+
|
| 431 |
+
| Field | Type | Required | Meaning |
|
| 432 |
+
|---|---|---|---|
|
| 433 |
+
| `run_id` | `string` | Yes | Identifier of the current YOLO run. |
|
| 434 |
+
| `session_id` | `string` | Yes | Identifier of the owning session context. |
|
| 435 |
+
| `run_mode` | `BASELINE \| DELTA` | Yes | Whether this is the first session run or a later session-delta run. |
|
| 436 |
+
| `as_of` | `datetime` | Yes | Data-fetch cutoff supplied by the runtime. |
|
| 437 |
+
| `ticker_scope` | `list[string]` | Yes | Non-empty runtime-approved effective ticker scope. |
|
| 438 |
+
| `baseline_refs` | `map[string, ArtifactRef]` | Delta only | Prior market-data artifact reference for each ticker when available. An absent reference is an explicit missing baseline, not an instruction to search unrestricted session files. |
|
| 439 |
+
|
| 440 |
+
`DataFetcher` has no required upstream agent artifact. Session and run fields
|
| 441 |
+
are runtime inputs rather than session-folder read permissions.
|
| 442 |
+
|
| 443 |
+
##### Output: `DataFetcherOutput`
|
| 444 |
+
|
| 445 |
+
The agent produces one run manifest with one result for every requested ticker.
|
| 446 |
+
|
| 447 |
+
| Field | Type | Required | Meaning |
|
| 448 |
+
|---|---|---|---|
|
| 449 |
+
| `schema_version` | `string` | Yes | Version of this output contract. |
|
| 450 |
+
| `run_id` | `string` | Yes | Run identifier copied from the validated input. |
|
| 451 |
+
| `session_id` | `string` | Yes | Session identifier copied from the validated input. |
|
| 452 |
+
| `producer` | literal `DataFetcher` | Yes | Exact registered producer name. |
|
| 453 |
+
| `completed_at` | `datetime` | Yes | Time at which the fetch manifest was completed. |
|
| 454 |
+
| `overall_status` | `COMPLETE \| PARTIAL \| UNAVAILABLE` | Yes | Aggregate availability across the requested ticker scope. |
|
| 455 |
+
| `ticker_results` | `list[TickerFetchResult]` | Yes | Exactly one result for every ticker in `ticker_scope`. |
|
| 456 |
+
|
| 457 |
+
`TickerFetchResult` contains:
|
| 458 |
+
|
| 459 |
+
| Field | Type | Required | Meaning |
|
| 460 |
+
|---|---|---|---|
|
| 461 |
+
| `ticker` | `string` | Yes | Ticker from the effective scope. The value is never decorated with status markers such as `*`. |
|
| 462 |
+
| `status` | `COMPLETE \| PARTIAL \| UNAVAILABLE` | Yes | Availability of the ticker's requested market data. |
|
| 463 |
+
| `market_data_ref` | `ArtifactRef` | When data exists | Reference to the typed per-ticker `MarketDataArtifact`. |
|
| 464 |
+
| `summary_ref` | `ArtifactRef` | When rendered | Reference to the human-readable markdown rendering. |
|
| 465 |
+
| `available_components` | `list[MarketDataComponent]` | Yes | Components that contain usable records. |
|
| 466 |
+
| `unavailable_components` | `list[MarketDataComponent]` | Yes | Requested components with no usable records. |
|
| 467 |
+
| `errors` | `list[DataIssue]` | Yes | Provider, normalization, and quality problems; empty on clean completion. |
|
| 468 |
+
|
| 469 |
+
`MarketDataComponent` is one of `OHLCV`, `INDICATORS`, `NEWS`, or `EARNINGS`.
|
| 470 |
+
An ETF without an applicable earnings component records earnings as not
|
| 471 |
+
applicable rather than treating it as a provider failure.
|
| 472 |
+
|
| 473 |
+
##### Per-Ticker Artifact: `MarketDataArtifact`
|
| 474 |
+
|
| 475 |
+
| Field | Type | Required | Meaning |
|
| 476 |
+
|---|---|---|---|
|
| 477 |
+
| `schema_version` | `string` | Yes | Version of the market-data artifact contract. |
|
| 478 |
+
| `run_id` | `string` | Yes | Producing run. |
|
| 479 |
+
| `producer` | literal `DataFetcher` | Yes | Exact registered producer name. |
|
| 480 |
+
| `ticker` | `string` | Yes | Single ticker represented by this artifact. |
|
| 481 |
+
| `retrieved_at` | `datetime` | Yes | Time at which Polyhedra obtained the data. |
|
| 482 |
+
| `market_date` | `date` | When available | Latest valid market date represented by price data. |
|
| 483 |
+
| `status` | `COMPLETE \| PARTIAL \| UNAVAILABLE` | Yes | Overall per-ticker data availability. |
|
| 484 |
+
| `ohlcv` | `list[OHLCVBar]` | Yes | Validated daily price and volume records, ordered by date. |
|
| 485 |
+
| `indicators` | `TechnicalIndicatorSeries` | Yes | SMA-20, EMA-20, RSI-14, and MACD series computed from valid OHLCV records. |
|
| 486 |
+
| `news` | `list[NewsRecord]` | Yes | Available company or market news records. |
|
| 487 |
+
| `earnings` | `list[EarningsRecord]` | Yes | Available earnings records; empty when unavailable or not applicable. |
|
| 488 |
+
| `provenance` | `list[ComponentProvenance]` | Yes | Provider, retrieval time, source observation time, freshness, and availability for each component. |
|
| 489 |
+
| `quality_issues` | `list[DataIssue]` | Yes | Excluded rows, missing fields, stale components, rate limits, and provider errors. |
|
| 490 |
+
| `baseline_ref` | `ArtifactRef` | Delta only | Runtime-approved prior market-data artifact when available. |
|
| 491 |
+
|
| 492 |
+
The nested record types preserve numeric values and timestamps structurally:
|
| 493 |
+
|
| 494 |
+
| Type | Required content |
|
| 495 |
+
|---|---|
|
| 496 |
+
| `ArtifactRef` | Session-relative filename, schema version, producer, and artifact identifier. |
|
| 497 |
+
| `OHLCVBar` | Market date, open, high, low, close, optional adjusted close, and volume. |
|
| 498 |
+
| `TechnicalIndicatorSeries` | Dated SMA-20, EMA-20, RSI-14, and MACD values, including MACD signal and histogram. |
|
| 499 |
+
| `NewsRecord` | Published time, headline, source, URL when available, and provider sentiment fields when available. |
|
| 500 |
+
| `EarningsRecord` | Fiscal period, actual EPS, estimated EPS, surprise, and surprise percentage when available. |
|
| 501 |
+
| `ComponentProvenance` | Component, provider, retrieval time, source observation time when available, `FRESH \| STALE \| UNKNOWN` freshness, and `AVAILABLE \| UNAVAILABLE \| NOT_APPLICABLE` availability. |
|
| 502 |
+
| `DataIssue` | Component, stable issue code, message, and affected record or date references when available. |
|
| 503 |
+
|
| 504 |
+
`COMPLETE`, `PARTIAL`, and `UNAVAILABLE` describe data availability, not agent
|
| 505 |
+
execution. A schema-valid `UNAVAILABLE` result is an explicit data-gap artifact
|
| 506 |
+
that downstream agents consume. An agent execution failure means no valid
|
| 507 |
+
`DataFetcherOutput` was produced and is tracked separately by the runtime.
|
| 508 |
+
|
| 509 |
+
The existing `next_role` field is removed from the V8.0 contract because the
|
| 510 |
+
Routing Table owns activation. The per-ticker artifact is stored at
|
| 511 |
+
`quant/runs/{run_id}/raw/{ticker}.json`; its downloadable rendering is
|
| 512 |
+
`quant/runs/{run_id}/raw/{ticker}_summary.md`. The manifest is
|
| 513 |
+
`quant/runs/{run_id}/data_fetch.json`.
|
| 514 |
+
|
| 515 |
+
#### Common Typed Envelope
|
| 516 |
+
|
| 517 |
+
The remaining quant agents use a common runtime envelope so routing, scope,
|
| 518 |
+
provenance, and data gaps are represented consistently without becoming part
|
| 519 |
+
of every agent-specific reasoning payload.
|
| 520 |
+
|
| 521 |
+
`AgentInput[Dependencies, Context]` contains:
|
| 522 |
+
|
| 523 |
+
| Field | Type | Required | Meaning |
|
| 524 |
+
|---|---|---|---|
|
| 525 |
+
| `run_id` | `string` | Yes | Current run identifier. |
|
| 526 |
+
| `session_id` | `string` | Yes | Owning session identifier. |
|
| 527 |
+
| `run_mode` | `BASELINE \| DELTA` | Yes | Current session execution mode. |
|
| 528 |
+
| `as_of` | `datetime` | Yes | Runtime cutoff for available evidence. |
|
| 529 |
+
| `ticker_scope` | `list[string]` | Yes | Agent's frozen effective ticker scope. |
|
| 530 |
+
| `dependencies` | agent-specific typed object | Yes | Schema-valid outputs from required Routing Table dependencies. |
|
| 531 |
+
| `optional_context` | agent-specific typed object | Yes | ACL-approved optional artifacts; absent fields remain absent rather than being replaced with invented values. |
|
| 532 |
+
| `baseline_refs` | `list[ArtifactRef]` | Delta only | Runtime-selected prior artifacts permitted for this agent. |
|
| 533 |
+
|
| 534 |
+
For each agent, the Baseline File Permissions table enumerates the complete
|
| 535 |
+
set of permitted prior artifact types, including its own earlier output for
|
| 536 |
+
delta comparison. References resolve to the corresponding typed schemas;
|
| 537 |
+
optional-context summaries below do not expand or replace that filename list.
|
| 538 |
+
|
| 539 |
+
`AgentArtifact[Payload]` contains:
|
| 540 |
+
|
| 541 |
+
| Field | Type | Required | Meaning |
|
| 542 |
+
|---|---|---|---|
|
| 543 |
+
| `schema_version` | `string` | Yes | Version of the concrete agent schema. |
|
| 544 |
+
| `artifact_id` | `string` | Yes | Stable identity of this artifact within the session. |
|
| 545 |
+
| `run_id` | `string` | Yes | Producing run. |
|
| 546 |
+
| `session_id` | `string` | Yes | Owning session. |
|
| 547 |
+
| `producer` | registered agent-name literal | Yes | Exact producer from the Routing Table. |
|
| 548 |
+
| `ticker_scope` | `list[string]` | Yes | Scope actually represented by the payload. |
|
| 549 |
+
| `created_at` | `datetime` | Yes | Artifact creation time. |
|
| 550 |
+
| `status` | `COMPLETE \| PARTIAL \| UNAVAILABLE` | Yes | Availability of the agent result. |
|
| 551 |
+
| `input_refs` | `list[ArtifactRef]` | Yes | Exact current-run artifacts used. |
|
| 552 |
+
| `baseline_refs` | `list[ArtifactRef]` | Yes | Exact prior artifacts used; empty in baseline mode or when unavailable. |
|
| 553 |
+
| `data_gaps` | `list[DataIssue]` | Yes | Missing, stale, excluded, or invalid evidence. |
|
| 554 |
+
| `payload` | agent-specific typed object | Yes | Agent-owned result defined below. |
|
| 555 |
+
| `render_ref` | `ArtifactRef` | When rendered | Human-readable markdown rendering for UI and run-package use. |
|
| 556 |
+
|
| 557 |
+
The runtime validates that `ticker_scope` is a subset of the agent's frozen
|
| 558 |
+
effective scope and filters every referenced multi-ticker artifact to that
|
| 559 |
+
scope before prompt construction. A filename permission never grants access to
|
| 560 |
+
out-of-scope ticker records.
|
| 561 |
+
|
| 562 |
+
Common enums used below are:
|
| 563 |
+
|
| 564 |
+
```text
|
| 565 |
+
ConfidenceLevel = HIGH | MEDIUM | LOW | UNKNOWN
|
| 566 |
+
Direction = BULLISH | BEARISH | NEUTRAL | MIXED | UNKNOWN
|
| 567 |
+
DeltaState = NEW | CHANGED | UNCHANGED | RESOLVED | INVALIDATED | NOT_COMPARED
|
| 568 |
+
AnalysisOutcome = NO_TRADE | WATCH_FOR_CONFIRMATION | PAPER_TRADE_SUGGESTION | ROUTE_TO_HUMAN
|
| 569 |
+
RiskVerdict = ACCEPTABLE | ELEVATED | REJECT
|
| 570 |
+
```
|
| 571 |
+
|
| 572 |
+
#### `OptionsFlowWatcher` Typed Contract
|
| 573 |
+
|
| 574 |
+
`OptionsFlowWatcherInput` uses the common input envelope with no required agent
|
| 575 |
+
dependency. Its agent-specific input contains the `OPTIONS` ticker scope, a
|
| 576 |
+
provider fetch cutoff, and optional prior `OptionsFlowWatcherOutput` references
|
| 577 |
+
for delta comparison.
|
| 578 |
+
|
| 579 |
+
`OptionsFlowWatcherOutput` uses `OptionsFlowPayload`:
|
| 580 |
+
|
| 581 |
+
| Field | Type | Required | Meaning |
|
| 582 |
+
|---|---|---|---|
|
| 583 |
+
| `ticker_results` | `list[OptionsTickerResult]` | Yes | Exactly one result per in-scope SPY, QQQ, or GLD ticker. |
|
| 584 |
+
| `sampling_policy` | `OptionsSamplingPolicy` | Yes | Expiration and per-side contract limits applied by the provider adapter. |
|
| 585 |
+
|
| 586 |
+
Each `OptionsTickerResult` contains `ticker`, availability status, provider,
|
| 587 |
+
retrieval time, checked expirations, normalized `OptionContract` records,
|
| 588 |
+
`OptionsMarketContext`, zero or more `FlowCandidate` records, zero or more
|
| 589 |
+
`UnusualOptionFlow` records, provider capability flags, `DeltaState`, and data
|
| 590 |
+
issues. `OptionContract` preserves contract symbol, expiration, strike, option
|
| 591 |
+
type, bid, ask, last, volume, open interest, implied volatility, provider, and
|
| 592 |
+
delay or entitlement notes.
|
| 593 |
+
|
| 594 |
+
`OptionsMarketContext`, `FlowCandidate`, and `UnusualOptionFlow` remain separate
|
| 595 |
+
types. A flow candidate records the exact volume, open-interest, IV, or ratio
|
| 596 |
+
rule that selected it and is non-directional by default. `UnusualOptionFlow`
|
| 597 |
+
requires supporting trade-side, sweep/block, opening/closing, premium, or
|
| 598 |
+
validated-classifier evidence. Missing capabilities produce an empty unusual
|
| 599 |
+
flow list, not an inferred claim.
|
| 600 |
+
|
| 601 |
+
#### Analysis Agent Contracts
|
| 602 |
+
|
| 603 |
+
The following table defines each remaining analysis agent's concrete input and
|
| 604 |
+
payload type. All inputs and outputs are wrapped by the common envelopes.
|
| 605 |
+
Required dependency fields correspond exactly to the Routing Table after
|
| 606 |
+
effective-scope pruning.
|
| 607 |
+
|
| 608 |
+
| Agent and schema | Required dependency outputs | Optional typed context | Output payload fields |
|
| 609 |
+
|---|---|---|---|
|
| 610 |
+
| `TrendAnalyst`: `TrendAnalystInput` -> `TrendAnalystOutput` | `DataFetcherOutput` plus referenced `MarketDataArtifact` records | Prior `TrendAnalystOutput` in delta mode | `ticker_analyses: list[TrendAnalysis]`; each record has ticker, price direction, magnitude and duration, support/resistance levels, volume assessment, SMA/EMA state, RSI state, MACD state, confidence, evidence references, `DeltaState`, and data gaps. No recommendation or next role. |
|
| 611 |
+
| `SentimentAnalyst`: `SentimentAnalystInput` -> `SentimentAnalystOutput` | Scope-filtered `DataFetcherOutput` and market-data news/earnings records | Current `TrendAnalystOutput`; prior sentiment, signal, and Finley artifacts in delta mode | `ticker_analyses: list[SentimentAnalysis]`; each record has ticker, source coverage, article count, scored/unscored counts, aggregate sentiment, themes with evidence references, earnings sentiment when applicable, optional trend alignment, incremental-signal-value flag, confidence, `DeltaState`, and data gaps. Thin or mostly unscored news is insufficient evidence, not neutral sentiment. |
|
| 612 |
+
| `MarketEventWatcher`: `MarketEventWatcherInput` -> `MarketEventWatcherOutput` | Scope-filtered `DataFetcherOutput` and `MarketDataArtifact` records | Current `TrendAnalystOutput`; approved baseline event context | `ticker_contexts: list[MarketEventContext]`; each record has ticker, observed market-data changes, relevant news/catalyst records already present in DataFetcher evidence, source references, checked time, `DeltaState`, and data gaps. `external_event_feed_status` explicitly records `NOT_CONFIGURED` unless an approved provider exists. This agent does not invent a separate live event feed. |
|
| 613 |
+
| `MacroContextWatcher`: `MacroContextWatcherInput` -> `MacroContextWatcherOutput` | `MarketEventWatcherOutput` and scope-overlapping `OptionsFlowWatcherOutput` | Approved baseline trend, signal, risk, trade-state, and Finley artifacts | `main_line`, `drivers: list[MacroDriver]`, affected tickers, confidence, uncertainties, contradictions, `DeltaState`, and data gaps. Each driver has a numeric relevance weight, evidence references, and affected tickers. `main_line` may be `UNCLEAR`. No trade decision. |
|
| 614 |
+
| `UnusualEventDetector`: `UnusualEventDetectorInput` -> `UnusualEventDetectorOutput` | `MarketEventWatcherOutput`, `MacroContextWatcherOutput`, and scope-overlapping `OptionsFlowWatcherOutput` | Approved baseline signal, risk, trade-state, and Finley artifacts | `meaningful_events: list[EventCandidate]`, `suppressed_events: list[SuppressedEvent]`, and `monitoring_conditions`. Each candidate has event ID, type, affected tickers, significance, confidence, evidence references, missing evidence, and `DeltaState`. Each suppressed event records its reason: stale, duplicate, unchanged, low significance, contradicted, or unsupported. |
|
| 615 |
+
| `EventRouter`: `EventRouterInput` -> `EventRouterOutput` | `UnusualEventDetectorOutput` | Current market-event and options evidence plus approved baseline risk, trade-state, and Finley artifacts | `assignments: list[EventAssignment]` and `unassigned_event_ids`. Each assignment has event ID, ticker, relevance, evidence references, and rationale. It assigns evidence only to tickers already in effective scope; it cannot activate agents, emit next roles, or expand ticker scope. |
|
| 616 |
+
|
| 617 |
+
#### Specialized Asset Analyst Contracts
|
| 618 |
+
|
| 619 |
+
`BTCAnalyst`, `SPYAnalyst`, `QQQAnalyst`, and `GLDAnalyst` share one payload
|
| 620 |
+
shape but retain separate concrete schemas and exact producer literals:
|
| 621 |
+
|
| 622 |
+
```text
|
| 623 |
+
BTCAnalystInput -> BTCAnalystOutput
|
| 624 |
+
SPYAnalystInput -> SPYAnalystOutput
|
| 625 |
+
QQQAnalystInput -> QQQAnalystOutput
|
| 626 |
+
GLDAnalystInput -> GLDAnalystOutput
|
| 627 |
+
```
|
| 628 |
+
|
| 629 |
+
Each required input contains the scope-filtered `TrendAnalystOutput` and
|
| 630 |
+
`EventRouterOutput`. Optional typed context may include `MarketEventWatcherOutput`,
|
| 631 |
+
scope-applicable `OptionsFlowWatcherOutput`, `MacroContextWatcherOutput`,
|
| 632 |
+
`UnusualEventDetectorOutput`, `SentimentAnalystOutput` when available, and the
|
| 633 |
+
agent's approved baseline references.
|
| 634 |
+
|
| 635 |
+
Each output payload contains one `AssetAnalysis` with:
|
| 636 |
+
|
| 637 |
+
| Field | Type | Required | Meaning |
|
| 638 |
+
|---|---|---|---|
|
| 639 |
+
| `ticker` | fixed ticker literal | Yes | Must equal the analyst's registered symbol. |
|
| 640 |
+
| `what_matters_now` | `string` | Yes | Concise current interpretation grounded in evidence. |
|
| 641 |
+
| `signals` | `list[WeightedSignal]` | Yes | Evidence-backed signals with weight, confidence, direction, and references. |
|
| 642 |
+
| `cross_market_evidence` | `list[CrossMarketObservation]` | Yes | Confirmations or contradictions; empty when unsupported. |
|
| 643 |
+
| `setup` | `SetupHypothesis` | When supported | Setup thesis, confirmation conditions, and invalidation conditions. |
|
| 644 |
+
| `outcome` | `AnalysisOutcome` | Yes | Exactly one PRD-approved outcome. |
|
| 645 |
+
| `trade_suggestion` | `PaperTradeSuggestion` | Only for `PAPER_TRADE_SUGGESTION` | Direction, entry condition and level, target, stop, confirmation, invalidation, and human-approval requirement. |
|
| 646 |
+
| `confidence` | `ConfidenceLevel` | Yes | Confidence in the overall outcome. |
|
| 647 |
+
| `delta_state` | `DeltaState` | Yes | Relationship to the approved prior analysis. |
|
| 648 |
+
| `evidence_refs` | `list[EvidenceRef]` | Yes | Evidence actually used. |
|
| 649 |
+
| `data_gaps` | `list[DataIssue]` | Yes | Missing or unusable evidence. |
|
| 650 |
+
|
| 651 |
+
`trade_suggestion` is forbidden for all other outcomes. Its ticker is derived
|
| 652 |
+
from `AssetAnalysis.ticker` and cannot carry a contradictory symbols list.
|
| 653 |
+
|
| 654 |
+
Each specialized analyst creates only its own typed per-ticker artifact and
|
| 655 |
+
markdown rendering. It does not create or append to a shared asset-analysis
|
| 656 |
+
file. The runtime constructs a read-only `AssetAnalysisCollection` from
|
| 657 |
+
schema-valid active analyst outputs for downstream agents. This removes
|
| 658 |
+
parallel shared-file writes and preserves producer ownership.
|
| 659 |
+
|
| 660 |
+
#### Research, Validation, And Decision Contracts
|
| 661 |
+
|
| 662 |
+
| Agent and schema | Required dependency outputs | Optional typed context | Output payload fields |
|
| 663 |
+
|---|---|---|---|
|
| 664 |
+
| `QuantResearcher`: `QuantResearcherInput` -> `QuantResearcherOutput` | Scope-applicable `TrendAnalystOutput`, `SentimentAnalystOutput`, and/or `AssetAnalysisCollection` according to the active Routing Table | `MacroContextWatcherOutput`, `UnusualEventDetectorOutput`, prior signals, backtests, risk, trade state, and Finley output | `signals: list[SignalHypothesis]`, prioritized signal IDs, synthesis, `DeltaState`, and data gaps. Each signal has stable ID, ticker, thesis, direction, entry and exit conditions, confidence, assumptions, falsification conditions, evidence references, and delta state. The list may be empty when evidence supports no signal. |
|
| 665 |
+
| `Backtester`: `BacktesterInput` -> `BacktesterOutput` | `QuantResearcherOutput` | Scope-filtered `MarketDataArtifact` records and prior signal/backtest/risk/trade-state artifacts | `results: list[BacktestResult]`, method, tested window, assumptions, limitations, and data gaps. Each result has signal ID, ticker, observations, occurrences, win rate, average return, cumulative return, maximum drawdown, Sharpe ratio when calculable, and `SUFFICIENT \| WEAK \| NOT_TESTABLE` evidence strength. `method` must distinguish `HISTORICAL_SIMULATION` from `LLM_ASSESSMENT`; only executed calculations may claim simulation metrics. |
|
| 666 |
+
| `RiskAnalyst`: `RiskAnalystInput` -> `RiskAnalystOutput` | `BacktesterOutput` | Current trend, asset-analysis collection, macro context, scope-filtered paper portfolio state, and approved baseline artifacts | `signal_assessments: list[SignalRiskAssessment]`, portfolio heat, concentration assessment, correlation assessment, maximum-loss estimate when calculable, stress scenarios, overall risk summary, and data gaps. Each signal assessment has signal ID, `RiskVerdict`, rationale, suggested paper position limit, and required mitigation. |
|
| 667 |
+
| `QuantStrategist`: `QuantStrategistInput` -> `QuantStrategistOutput` | `RiskAnalystOutput` | Signals, backtests, sentiment, asset analyses, macro context, prior trade state, and runtime-owned committee performance | final `outcome: AnalysisOutcome`, `proposals: list[PaperTradeProposal]`, no-trade/watch rationale, exclusions, committee votes, runtime-owned weights, weighted aggregation, proposal lifecycle updates, evidence references, and data gaps. At most three proposals are allowed; `REJECT` signals cannot become proposals. |
|
| 668 |
+
|
| 669 |
+
`PaperTradeProposal` contains proposal ID, one ticker, direction, entry
|
| 670 |
+
condition and level, target, stop, time horizon, confidence, source signal IDs,
|
| 671 |
+
risk verdict, mitigation when elevated, confirmation and invalidation
|
| 672 |
+
conditions, rationale, and explicit human-approval requirement. Empty proposals
|
| 673 |
+
with `NO_TRADE` or `WATCH_FOR_CONFIRMATION` are valid strategy outcomes.
|
| 674 |
+
|
| 675 |
+
Committee votes contain member ID, vote, confidence, thesis, cited evidence,
|
| 676 |
+
and proposal impact. Trusted weight and aggregation fields are attached by the
|
| 677 |
+
runtime performance tool; LLM output cannot set or modify them.
|
| 678 |
+
|
| 679 |
+
#### Product And Support Agent Contracts
|
| 680 |
+
|
| 681 |
+
| Agent and schema | Required dependency outputs | Optional typed context | Output payload fields |
|
| 682 |
+
|---|---|---|---|
|
| 683 |
+
| `Publisher`: `PublisherInput` -> `PublisherOutput` | `QuantStrategistOutput` | Scope-filtered trend, sentiment, risk, asset-analysis, macro, and approved baseline Finley artifacts | `headline`, `market_summary`, `what_to_watch`, displayed proposal IDs, `no_proposal_reason`, disclaimer, approximate word count, Slack-ready rendering, `DeltaState`, evidence references, and data gaps. `no_proposal_reason` is exactly `DATA_LOSS`, `AGENT_PENDING`, `TRUE_NO_TRADE`, or `WATCH_FOR_CONFIRMATION` when proposals are empty. No next-role or human workflow node is emitted. |
|
| 684 |
+
| `VizAgent`: `VizAgentInput` -> `VizAgentOutput` | None; this is an on-demand execution context | Runtime-selected, ACL-approved market-data, backtest, risk, or portfolio artifacts required by the requested chart | requested chart type, `charts: list[ChartArtifact]`, caption, and errors. Each chart records chart type, optional ticker, image reference, and exact source artifact references. A chart is unavailable when its typed source fields are absent; markdown regex parsing is not the V8 machine path. |
|
| 685 |
+
| `PortfolioMonitor`: `PortfolioMonitorInput` -> `PortfolioMonitorOutput` | None; this is a separately initialized monitoring context | Runtime-supplied open paper positions, alert thresholds, pause state, market-hours state, and quote-provider configuration | checked time, `position_checks: list[PositionCheck]`, `alerts: list[PortfolioAlert]`, quote provenance, and data gaps. Each check records position ID, ticker, direction, entry, current price when available, percentage move, and threshold states. This agent never closes a position. Runtime applies the validated last-monitor timestamp and publishes alerts. |
|
| 686 |
+
|
| 687 |
+
#### Schema Ownership And Validation Rules
|
| 688 |
+
|
| 689 |
+
1. Every agent owns only the payload it produces. Renderers and runtime
|
| 690 |
+
aggregators may transform a valid payload but cannot add agent reasoning.
|
| 691 |
+
2. Required dependency outputs are passed directly from the active Routing
|
| 692 |
+
Table plan. Agents do not search the session folder to discover upstream
|
| 693 |
+
producers.
|
| 694 |
+
3. Optional and baseline artifacts are selected by the runtime through the
|
| 695 |
+
agent ACL and declared input schema.
|
| 696 |
+
4. A schema-valid `PARTIAL` or `UNAVAILABLE` artifact carries explicit data
|
| 697 |
+
gaps and can satisfy dependency completion. Missing or malformed output is
|
| 698 |
+
an execution failure, not a no-trade conclusion.
|
| 699 |
+
5. Ticker-bearing records must be inside the producer's effective scope.
|
| 700 |
+
References to records outside that scope are rejected before prompt
|
| 701 |
+
construction.
|
| 702 |
+
6. Numeric unknowns are `null`; they are never represented as `N/A`, zero, or
|
| 703 |
+
prose inside machine artifacts.
|
| 704 |
+
7. LLM prose is retained only in declared narrative fields. Enum values,
|
| 705 |
+
numbers, identifiers, evidence references, and decision fields must parse
|
| 706 |
+
and validate before publication or downstream use.
|
| 707 |
+
8. Markdown and PNG files are product/download renderings. Typed JSON artifacts
|
| 708 |
+
are the inter-agent contract. Exact paths and owners are enumerated in
|
| 709 |
+
the File Content Reference and filename ACL tables.
|
| 710 |
|
| 711 |
### Runtime And Product Boundaries
|
| 712 |
|
|
|
|
| 730 |
|
| 731 |
### UI Visibility
|
| 732 |
|
| 733 |
+
The existing YOLO console remains the product entry point. Session selection,
|
| 734 |
+
ticker entry, baseline/delta runs, prior-run replay, options context, Finley
|
| 735 |
+
output, and package downloads remain available. The UI reads the same run
|
| 736 |
+
state used by Slack and the coordinator.
|
| 737 |
|
| 738 |
+
#### Run Views
|
| 739 |
+
|
| 740 |
+
| View | Content | Interaction |
|
| 741 |
+
|---|---|---|
|
| 742 |
+
| Run | Run ID, session, frozen tickers, baseline/delta label, execution progress, diagnostics, options context, and Finley's result. | Default view. Start YOLO, run again within the selected session, select a prior run, or download the existing session package. |
|
| 743 |
+
| Routing Table | Active agent rows with exact names, scope enum, effective tickers, required dependencies as a list, execution state, result availability, and waiting/failure detail. | Select an agent to inspect its inputs and outputs. Show the full registered table only through an explicit view toggle; inactive entries carry their exclusion reason. |
|
| 744 |
+
| Permissions | Per-agent read/create/edit/list filename lists, current-run bindings, selected baseline bindings, and publication state. | Select an agent; switch between declared filename templates and resolved paths. Read-only inspection; no ACL editing or agent activation controls. |
|
| 745 |
|
| 746 |
+
Session and run selection remain shared across all three views. Selecting a
|
| 747 |
+
different tab does not start a run or change its scope. `VizAgent` and
|
| 748 |
+
`PortfolioMonitor` are absent from the normal active YOLO table; the full
|
| 749 |
+
registry view identifies their separate execution contexts.
|
| 750 |
+
|
| 751 |
+
#### Progress And Result State
|
| 752 |
+
|
| 753 |
+
| Agent execution state | Display behavior |
|
| 754 |
+
|---|---|
|
| 755 |
+
| Waiting | Name the required producers whose outputs are not yet published for the overlapping ticker scope. |
|
| 756 |
+
| Running | Show every concurrently running agent, its actual start time, and elapsed time. |
|
| 757 |
+
| Completed | A valid output was published. Display its separate COMPLETE, PARTIAL, or UNAVAILABLE result status. |
|
| 758 |
+
| Failed | Show the named agent and recorded execution or schema-validation error. Preserve available earlier results. |
|
| 759 |
+
| Blocked | Name the failed or missing required dependency that prevents activation. Do not present this as a market recommendation. |
|
| 760 |
+
| Inactive | Visible only in the full registry view; explain empty effective scope or different execution context. |
|
| 761 |
+
|
| 762 |
+
Execution state comes from runtime activation and publication records. The UI
|
| 763 |
+
must not infer completion from message counts, a Markdown file's existence,
|
| 764 |
+
or the position of an agent in a linear array. A quiet LLM request can still
|
| 765 |
+
be running; a refresh/network error reports connection state without changing
|
| 766 |
+
the recorded agent result.
|
| 767 |
+
|
| 768 |
+
The run view shows completed/active counts and all current agent names. It
|
| 769 |
+
does not render a sequential arrow chain that implies parallel agents ran
|
| 770 |
+
one after another. Unavailable options evidence remains a visible data gap,
|
| 771 |
+
even when OptionsFlowWatcher completed its fetch/report operation.
|
| 772 |
+
|
| 773 |
+
#### Agent Details And Permissions
|
| 774 |
+
|
| 775 |
+
The selected agent detail contains effective tickers, dependency states,
|
| 776 |
+
start/end times, exact current and baseline input references, output identity,
|
| 777 |
+
schema version, result availability, and actionable failure detail when any.
|
| 778 |
+
Long paths wrap without hiding the agent name or permission column.
|
| 779 |
+
|
| 780 |
+
Permissions show what the agent may access, while input/output references
|
| 781 |
+
show what it actually consumed or produced. `[]` is displayed as None.
|
| 782 |
+
Baseline paths and published output paths are labelled read-only even when
|
| 783 |
+
the template permits editing during the owning activation. Runtime-owned
|
| 784 |
+
aggregate, state, replay, and ledger files retain their distinct ownership;
|
| 785 |
+
they are never shown as extra agent nodes.
|
| 786 |
+
|
| 787 |
+
File details are metadata supplied by the existing session/run payloads.
|
| 788 |
+
The download action continues to provide the available intermediate files;
|
| 789 |
+
this UI change does not add arbitrary server-file browsing or a new endpoint.
|
| 790 |
+
|
| 791 |
+
#### Finley And Diagnostics
|
| 792 |
+
|
| 793 |
+
Finley's readable market result remains primary. Routing summaries, JSON,
|
| 794 |
+
and artifact paths do not replace it. Before Publisher runs, the page shows
|
| 795 |
+
progress rather than placing progress text under a completed Finley result.
|
| 796 |
+
|
| 797 |
+
No-proposal output distinguishes missing evidence, analysis still pending or
|
| 798 |
+
failed, an actual NO_TRADE conclusion, and WATCH_FOR_CONFIRMATION. A provider
|
| 799 |
+
gap may coexist with a valid strategy conclusion; the UI displays both and
|
| 800 |
+
does not infer data loss solely from an empty proposal list. LLM/provider
|
| 801 |
+
failures name the affected agent and evidence component using recorded
|
| 802 |
+
diagnostics. A missing final result is never manufactured as NO_TRADE.
|
| 803 |
+
|
| 804 |
+
The existing options context remains available. Evidence ledgers stay in the
|
| 805 |
+
download package, and the distilled committee expansion remains halted under
|
| 806 |
+
the inherited V7.1 decision.
|
| 807 |
+
|
| 808 |
+
#### Replay And Responsive Behavior
|
| 809 |
+
|
| 810 |
+
- Prior-run views use their recorded routing plan, permission bindings,
|
| 811 |
+
statuses, inputs, outputs, and strategy weights. A later live run cannot
|
| 812 |
+
overwrite the selected replay view during polling.
|
| 813 |
+
- Legacy replay lacking routing/ACL snapshots displays that information as
|
| 814 |
+
unavailable for that recorded version. It does not attach today's contract
|
| 815 |
+
to the old run or execute agents to fill the gap.
|
| 816 |
+
- The existing session package is downloadable from every run state. The
|
| 817 |
+
selected run ID is visible so its files can be located inside the package.
|
| 818 |
+
- Desktop uses compact tables. On narrow screens, routing and permission
|
| 819 |
+
tables scroll within their view; agent details and long filenames wrap.
|
| 820 |
+
Controls remain keyboard accessible and status is communicated by text as
|
| 821 |
+
well as color. Refresh preserves selection and scroll position.
|
| 822 |
+
- A new/empty session shows the ticker entry and Run YOLO action. Loading,
|
| 823 |
+
absent replay, failed refresh, and empty options states have distinct labels.
|
| 824 |
+
- UI acceptance covers a mobile viewport of 390 x 844 and a desktop viewport
|
| 825 |
+
of 1440 x 900, including long paths, mixed tickers, parallel running rows,
|
| 826 |
+
failed dependencies, and a replay view while another run is active.
|
| 827 |
|
| 828 |
---
|
| 829 |
|
|
|
|
| 919 |
|
| 920 |
---
|
| 921 |
|
| 922 |
+
## Design Status
|
| 923 |
|
| 924 |
+
The Routing Table and typed input/output contracts now cover all registered
|
| 925 |
+
quant agents. Specialized asset ownership and schema-level ticker filtering
|
| 926 |
+
are settled. Run-based storage, filename ACLs, and UI presentation are defined.
|
| 927 |
+
The implementation and verification sequence is in
|
| 928 |
+
[V8.0_IMPLEMENTATION_PLAN.md](V8.0_IMPLEMENTATION_PLAN.md).
|
| 929 |
+
These are design specifications. Checked definition items below mean that the
|
| 930 |
+
PRD section is written; implementation checkboxes in the plan remain open until
|
| 931 |
+
the corresponding behavior is implemented and verified.
|
| 932 |
|
| 933 |
---
|
| 934 |
|
|
|
|
| 943 |
- [x] Define the complete Routing Table at the agent-dependency and scope level.
|
| 944 |
- [x] Draft filename-based ACL rows and file-content references for all quant agents.
|
| 945 |
- [x] Record baseline snapshot read permissions for session-delta context.
|
| 946 |
+
- [x] Define the `DataFetcher` typed input and output artifact contract.
|
| 947 |
+
- [x] Finalize shared-file ownership and scope-filtered access with typed schemas.
|
| 948 |
+
- [x] Define the filename ACL for each quant agent against the typed artifact layout.
|
| 949 |
+
- [x] Define typed input and output artifact schemas for each quant agent.
|
| 950 |
+
- [x] Define artifact storage, publication, baseline references, replay, and downloads.
|
| 951 |
+
- [x] Define UI presentation for dependency and ACL state.
|
| 952 |
+
- [x] Write the V8.0 implementation and verification plan.
|