Spaces:
Running
Running
File size: 11,043 Bytes
25c3a8b 3bacbf8 25c3a8b 3bacbf8 25c3a8b |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 |
"""Orchestrator - the agent loop connecting Search and Judge."""
import asyncio
from collections.abc import AsyncGenerator
from typing import Any, Protocol
import structlog
from src.utils.models import (
AgentEvent,
Evidence,
JudgeAssessment,
OrchestratorConfig,
SearchResult,
)
logger = structlog.get_logger()
class SearchHandlerProtocol(Protocol):
"""Protocol for search handler."""
async def execute(self, query: str, max_results_per_tool: int = 10) -> SearchResult: ...
class JudgeHandlerProtocol(Protocol):
"""Protocol for judge handler."""
async def assess(self, question: str, evidence: list[Evidence]) -> JudgeAssessment: ...
class Orchestrator:
"""
The agent orchestrator - runs the Search -> Judge -> Loop cycle.
This is a generator-based design that yields events for real-time UI updates.
"""
def __init__(
self,
search_handler: SearchHandlerProtocol,
judge_handler: JudgeHandlerProtocol,
config: OrchestratorConfig | None = None,
):
"""
Initialize the orchestrator.
Args:
search_handler: Handler for executing searches
judge_handler: Handler for assessing evidence
config: Optional configuration (uses defaults if not provided)
"""
self.search = search_handler
self.judge = judge_handler
self.config = config or OrchestratorConfig()
self.history: list[dict[str, Any]] = []
async def run(self, query: str) -> AsyncGenerator[AgentEvent, None]:
"""
Run the agent loop for a query.
Yields AgentEvent objects for each step, allowing real-time UI updates.
Args:
query: The user's research question
Yields:
AgentEvent objects for each step of the process
"""
logger.info("Starting orchestrator", query=query)
yield AgentEvent(
type="started",
message=f"Starting research for: {query}",
iteration=0,
)
all_evidence: list[Evidence] = []
current_queries = [query]
iteration = 0
while iteration < self.config.max_iterations:
iteration += 1
logger.info("Iteration", iteration=iteration, queries=current_queries)
# === SEARCH PHASE ===
yield AgentEvent(
type="searching",
message=f"Searching for: {', '.join(current_queries[:3])}...",
iteration=iteration,
)
try:
# Execute searches for all current queries
search_tasks = [
self.search.execute(q, self.config.max_results_per_tool)
for q in current_queries[:3] # Limit to 3 queries per iteration
]
search_results = await asyncio.gather(*search_tasks, return_exceptions=True)
# Collect evidence from successful searches
new_evidence: list[Evidence] = []
errors: list[str] = []
for q, result in zip(current_queries[:3], search_results, strict=False):
if isinstance(result, Exception):
errors.append(f"Search for '{q}' failed: {result!s}")
elif isinstance(result, SearchResult):
new_evidence.extend(result.evidence)
errors.extend(result.errors)
else:
# Should not happen with return_exceptions=True but safe fallback
errors.append(f"Unknown result type for '{q}': {type(result)}")
# Deduplicate evidence by URL
seen_urls = {e.citation.url for e in all_evidence}
unique_new = [e for e in new_evidence if e.citation.url not in seen_urls]
all_evidence.extend(unique_new)
yield AgentEvent(
type="search_complete",
message=f"Found {len(unique_new)} new sources ({len(all_evidence)} total)",
data={
"new_count": len(unique_new),
"total_count": len(all_evidence),
},
iteration=iteration,
)
if errors:
logger.warning("Search errors", errors=errors)
except Exception as e:
logger.error("Search phase failed", error=str(e))
yield AgentEvent(
type="error",
message=f"Search failed: {e!s}",
iteration=iteration,
)
continue
# === JUDGE PHASE ===
yield AgentEvent(
type="judging",
message=f"Evaluating {len(all_evidence)} sources...",
iteration=iteration,
)
try:
assessment = await self.judge.assess(query, all_evidence)
yield AgentEvent(
type="judge_complete",
message=(
f"Assessment: {assessment.recommendation} "
f"(confidence: {assessment.confidence:.0%})"
),
data={
"sufficient": assessment.sufficient,
"confidence": assessment.confidence,
"mechanism_score": assessment.details.mechanism_score,
"clinical_score": assessment.details.clinical_evidence_score,
},
iteration=iteration,
)
# Record this iteration in history
self.history.append(
{
"iteration": iteration,
"queries": current_queries,
"evidence_count": len(all_evidence),
"assessment": assessment.model_dump(),
}
)
# === DECISION PHASE ===
if assessment.sufficient and assessment.recommendation == "synthesize":
yield AgentEvent(
type="synthesizing",
message="Evidence sufficient! Preparing synthesis...",
iteration=iteration,
)
# Generate final response
final_response = self._generate_synthesis(query, all_evidence, assessment)
yield AgentEvent(
type="complete",
message=final_response,
data={
"evidence_count": len(all_evidence),
"iterations": iteration,
"drug_candidates": assessment.details.drug_candidates,
"key_findings": assessment.details.key_findings,
},
iteration=iteration,
)
return
else:
# Need more evidence - prepare next queries
current_queries = assessment.next_search_queries or [
f"{query} mechanism of action",
f"{query} clinical evidence",
]
yield AgentEvent(
type="looping",
message=(
f"Need more evidence. "
f"Next searches: {', '.join(current_queries[:2])}..."
),
data={"next_queries": current_queries},
iteration=iteration,
)
except Exception as e:
logger.error("Judge phase failed", error=str(e))
yield AgentEvent(
type="error",
message=f"Assessment failed: {e!s}",
iteration=iteration,
)
continue
# Max iterations reached
yield AgentEvent(
type="complete",
message=self._generate_partial_synthesis(query, all_evidence),
data={
"evidence_count": len(all_evidence),
"iterations": iteration,
"max_reached": True,
},
iteration=iteration,
)
def _generate_synthesis(
self,
query: str,
evidence: list[Evidence],
assessment: JudgeAssessment,
) -> str:
"""
Generate the final synthesis response.
Args:
query: The original question
evidence: All collected evidence
assessment: The final assessment
Returns:
Formatted synthesis as markdown
"""
drug_list = (
"\n".join([f"- **{d}**" for d in assessment.details.drug_candidates])
or "- No specific candidates identified"
)
findings_list = (
"\n".join([f"- {f}" for f in assessment.details.key_findings]) or "- See evidence below"
)
citations = "\n".join(
[
f"{i + 1}. [{e.citation.title}]({e.citation.url}) "
f"({e.citation.source.upper()}, {e.citation.date})"
for i, e in enumerate(evidence[:10]) # Limit to 10 citations
]
)
return f"""## Drug Repurposing Analysis
### Question
{query}
### Drug Candidates
{drug_list}
### Key Findings
{findings_list}
### Assessment
- **Mechanism Score**: {assessment.details.mechanism_score}/10
- **Clinical Evidence Score**: {assessment.details.clinical_evidence_score}/10
- **Confidence**: {assessment.confidence:.0%}
### Reasoning
{assessment.reasoning}
### Citations ({len(evidence)} sources)
{citations}
---
*Analysis based on {len(evidence)} sources across {len(self.history)} iterations.*
"""
def _generate_partial_synthesis(
self,
query: str,
evidence: list[Evidence],
) -> str:
"""
Generate a partial synthesis when max iterations reached.
Args:
query: The original question
evidence: All collected evidence
Returns:
Formatted partial synthesis as markdown
"""
citations = "\n".join(
[
f"{i + 1}. [{e.citation.title}]({e.citation.url}) ({e.citation.source.upper()})"
for i, e in enumerate(evidence[:10])
]
)
return f"""## Partial Analysis (Max Iterations Reached)
### Question
{query}
### Status
Maximum search iterations reached. The evidence gathered may be incomplete.
### Evidence Collected
Found {len(evidence)} sources. Consider refining your query for more specific results.
### Citations
{citations}
---
*Consider searching with more specific terms or drug names.*
"""
|