feat: add evidence-bound RNA-seq result reports

2026-08-09 01:37:00 +08:00
parent 7399b0bf14
commit 65f79207f0
4 changed files with 3620 additions and 2 deletions
@@ -6911,6 +6911,10 @@ class ExecuteRequest(BaseModel):
    speciesCode: str = ""
    rnaseqPrefix: str = ""
    rnaseqOutputPrefix: str = ""
+    rnaseqScopeId: str = ""
+    rnaseqExpectedStages: List[str] = Field(default_factory=list)
+    rnaseqReportAction: str = "generate"
+    rnaseqReportUseModel: bool = True
    # RNA-seq QC 参数
    rnaseqDataMode: str = "upload"
    rnaseqDataPath: str = ""
@@ -7794,6 +7798,10 @@ def run_stage_sync(task_id: str, stage: str, job_id: str, params: dict):
            wgcna_powers=params.get("wgcnaPowers", "1,2,3,4,5,6,7,8,9,10,12,14,16,18,20"),
            candidate_max_deg_proteins=params.get("candidateMaxDegProteins", 500),
            candidate_run_interproscan=params.get("candidateRunInterproscan", "auto"),
+            rnaseq_scope_id=params.get("rnaseqScopeId", ""),
+            rnaseq_expected_stages=params.get("rnaseqExpectedStages") or params.get("expectedStages") or [],
+            rnaseq_report_action=params.get("rnaseqReportAction", "generate"),
+            rnaseq_report_use_model=_bool_param("rnaseqReportUseModel", "report_use_model", default=True),
            # PPI参数
            ppi_species=params.get("ppiSpecies") or params.get("ppi_species") or "auto",
            normalization_species_label=params.get("normalizationSpeciesLabel") or params.get("normalization_species_label") or "",
@@ -12093,6 +12101,10 @@ async def execute_stage(req: ExecuteRequest):
        "wgcnaPowers": getattr(req, 'wgcnaPowers', "1,2,3,4,5,6,7,8,9,10,12,14,16,18,20"),
        "candidateMaxDegProteins": getattr(req, 'candidateMaxDegProteins', 500),
        "candidateRunInterproscan": getattr(req, 'candidateRunInterproscan', "auto"),
+        "rnaseqScopeId": getattr(req, 'rnaseqScopeId', ""),
+        "rnaseqExpectedStages": getattr(req, 'rnaseqExpectedStages', []),
+        "rnaseqReportAction": getattr(req, 'rnaseqReportAction', "generate"),
+        "rnaseqReportUseModel": getattr(req, 'rnaseqReportUseModel', True),
        "ncbiQuery": getattr(req, 'ncbiQuery', ''),
        "ncbiGeneIds": getattr(req, 'ncbiGeneIds', ''),
        "ncbiMode": getattr(req, 'ncbiMode', 'gene'),
@@ -13679,6 +13691,7 @@ async def get_results(
        "rnaseq_fgsea": {"images": [], "files": [], "elapsed_time": 0},
        "rnaseq_wgcna": {"images": [], "files": [], "elapsed_time": 0},
        "rnaseq_candidate_family": {"images": [], "files": [], "elapsed_time": 0},
+        "rnaseq_report": {"images": [], "files": [], "elapsed_time": 0},
        "genome_prepare": {"images": [], "files": [], "elapsed_time": 0},
        "prepare_organize": {"images": [], "files": [], "elapsed_time": 0},
        "prepare_normalize_gff": {"images": [], "files": [], "elapsed_time": 0},
@@ -13780,6 +13793,7 @@ async def get_results(
        "rnaseq_fgsea",
        "rnaseq_wgcna",
        "rnaseq_candidate_family",
+        "rnaseq_report",
        "expression",
    }
    RNASEQ_FILE_TOKENS = (
@@ -14801,6 +14815,7 @@ async def get_results(
                "genome_prepare": ["genome_prepare", "species_config"],
                "msa_region_plot": ["msa_region", "region.tsv", "conservation_profile"],
                "subfamily_confirm": ["subfamily_confirm", "confirmed_subfamily"],
+                "rnaseq_report": ["rnaseq_report"],
                "rnaseq_fgsea": ["rnaseq_fgsea", "fgsea"],
                "rnaseq_go_enrich": ["rnaseq_go_enrich", ".go_enrich", "_go_"],
                "rnaseq_kegg_enrich": ["rnaseq_kegg_enrich", ".kegg_enrich", "_kegg_", "kegg_pathway", "kegg_pathview"],
@@ -16029,6 +16044,7 @@ def parse_natural_language(message: str) -> dict:
        "rnaseq_align": ["rnaseq比对", "rna比对", "hisat2", "比对"],
        "rnaseq_quant": ["rnaseq定量", "rna定量", "stringtie", "定量"],
        "rnaseq_sample_qc": ["样本质量", "样本检测", "sample qc", "sample quality", "pca", "样本相关性"],
+        "rnaseq_report": ["rnaseq结果报告", "rna-seq结果报告", "转录组结果报告", "rnaseq报告"],
        "rnaseq_wgcna": ["wgcna", "共表达", "加权共表达", "模块性状", "module trait"],
        "rnaseq_de": ["rnaseq差异", "rna差异", "差异表达", "de分析"],
        "rnaseq_fgsea": ["fgsea", "gsea", "基因集富集", "排序富集"],
@@ -16838,7 +16854,10 @@ async def _run_agent_chat(
        )
        router_context_terms = dict(terms)

-    from gfa_core.mas.utils.intent_parser import parse_sequence_extract_request
+    from gfa_core.mas.utils.intent_parser import (
+        deterministic_agent_chat_intent,
+        parse_sequence_extract_request,
+    )

    utility_params = parse_sequence_extract_request(request.message)
    if utility_params:
@@ -16884,6 +16903,58 @@ async def _run_agent_chat(
            "session_id": session_id,
        }

+    deterministic_intent = deterministic_agent_chat_intent(
+        request.message,
+        rnaseq_context=any(
+            str(stage).startswith("rnaseq_") for stage in completed_stages
+        ),
+    )
+    if deterministic_intent is not None:
+        report_action = str(
+            (deterministic_intent.get("params") or {}).get("rnaseqReportAction")
+            or "generate"
+        )
+        report_message = (
+            "已识别为打开 RNA-seq 结果报告。"
+            if report_action == "open"
+            else "已识别为生成 RNA-seq 结果报告。"
+        )
+        report_intent = {
+            **deterministic_intent,
+            "stage": "rnaseq_report",
+            "primary_stage": "rnaseq_report",
+            "taskType": "analysis",
+            "task_kind": "analysis",
+            "job_id": request.job_id,
+            "workspace": (
+                str(PROJECT_ROOT / "workspace" / request.job_id)
+                if request.job_id
+                else ""
+            ),
+            "message": report_message,
+        }
+        if conversation_turn is not None:
+            active_store.finish_turn(
+                conversation_turn,
+                assistant_message=report_message,
+                interaction_kind="independent",
+                action="propose_analysis",
+                intent=report_intent,
+            )
+        return {
+            "success": True,
+            "status": "ok",
+            "action": "propose_analysis",
+            "intent": report_intent,
+            "sources": [],
+            "tool_trace": [],
+            "mode": "analysis",
+            "completed_stages": completed_stages,
+            "model_used": "rule",
+            "session_id": session_id,
+            "handoff_request": request.message,
+        }
+
    global llm_manager
    active_llm_manager = llm_manager
    if active_llm_manager is None:
@@ -20012,6 +20083,63 @@ async def agent_plan(request: AgentPlanRequest):
            request.intent["params"] = dict(request.intent.get("params") or {})
            _apply_reconciled_species_to_intent(request.intent, plan_role_resolution)
        query_lower_for_context = (request.message or "").lower()
+        result_report_query = (
+            "结果报告" in query_lower_for_context
+            and any(action in query_lower_for_context for action in ["生成", "打开"])
+        )
+        if result_report_query:
+            from gfa_core.rnaseq_evidence import is_rnaseq_evidence_stage, manifest_identity_value
+
+            current_intent = dict(request.intent or {})
+            current_params = dict(current_intent.get("params") or {})
+            current_stages = [str(stage) for stage in (current_intent.get("stages") or [])]
+            explicit_rnaseq_report = any(
+                marker in query_lower_for_context
+                for marker in ["rnaseq", "rna-seq", "rna seq", "转录组"]
+            )
+            rnaseq_context = any(is_rnaseq_evidence_stage(stage) for stage in current_stages)
+            latest_rnaseq_manifest = None
+            if request.job_id:
+                report_final_dir = WORKSPACE_ROOT / request.job_id / "final"
+                report_prefix = _nonempty_prefix(request.prefix or current_intent.get("prefix") or current_params.get("prefix"))
+                report_pattern = f"{report_prefix}.*.manifest.json" if report_prefix else "*.manifest.json"
+                candidates = []
+                for candidate in report_final_dir.glob(report_pattern) if report_final_dir.exists() else []:
+                    try:
+                        payload = json.loads(candidate.read_text(encoding="utf-8"))
+                    except Exception:
+                        continue
+                    if (
+                        is_rnaseq_evidence_stage(str(payload.get("stage") or ""))
+                        and str(payload.get("status") or "") in {"success", "partial_success"}
+                    ):
+                        candidates.append((candidate.stat().st_mtime, candidate, payload))
+                if candidates:
+                    _mtime, _path, latest_rnaseq_manifest = max(candidates, key=lambda item: item[0])
+                    rnaseq_context = True
+            if explicit_rnaseq_report or rnaseq_context:
+                current_params["rnaseqReportAction"] = "open" if "打开" in query_lower_for_context else "generate"
+                if latest_rnaseq_manifest:
+                    current_params.setdefault(
+                        "rnaseqScopeId",
+                        manifest_identity_value(latest_rnaseq_manifest, "rnaseq_scope_id"),
+                    )
+                report_prefix = _nonempty_prefix(
+                    request.prefix
+                    or current_intent.get("prefix")
+                    or current_params.get("prefix")
+                    or (latest_rnaseq_manifest or {}).get("prefix")
+                )
+                request.intent = {
+                    **current_intent,
+                    "stages": ["rnaseq_report"],
+                    "primary_stage": "rnaseq_report",
+                    "task_type": "report",
+                    "task_kind": "pipeline",
+                    "prefix": report_prefix,
+                    "params": {**current_params, "prefix": report_prefix},
+                    "confidence": 0.99,
+                }
        subfamily_confirm_query_for_context = any(
            kw in query_lower_for_context
            for kw in ["确认亚家族", "亚家族确认", "确认亚家族标签", "人工确认亚家族", "subfamily confirm", "confirmed subfamily"]
@@ -20907,7 +21035,10 @@ async def agent_plan(request: AgentPlanRequest):
                            "manifest_path": str(status.manifest_path) if status.manifest_path else "",
                            "missing_count": len(status.missing_artifacts or []) + len(status.errors or []),
                        }
-                        if status.completed:
+                        # Report requests are actions, not a request to skip an
+                        # already completed computation. The CLI decides whether
+                        # an "open" request can reuse the fresh snapshot.
+                        if status.completed and stage_id != "rnaseq_report":
                            completed_rnaseq_stages.append(stage_id)
                        else:
                            remaining_rnaseq_stages.append(stage_id)
@@ -20923,6 +21054,7 @@ async def agent_plan(request: AgentPlanRequest):
                        "rnaseq_fgsea": "RNA-seq fgsea",
                        "rnaseq_wgcna": "RNA-seq WGCNA",
                        "rnaseq_candidate_family": "RNA-seq Candidate Family",
+                        "rnaseq_report": "RNA-seq Result Report",
                    }
                    plan_prefix = effective_plan_prefix or request.prefix or incoming_intent.get("prefix", "")
                    final_dir_for_rnaseq = PROJECT_ROOT / "workspace" / request.job_id / "final"
@@ -20942,6 +21074,7 @@ async def agent_plan(request: AgentPlanRequest):
                        "rnaseq_fgsea": ["rnaseq_de"],
                        "rnaseq_wgcna": ["rnaseq_sample_qc"],
                        "rnaseq_candidate_family": ["rnaseq_de", "rnaseq_go_enrich", "rnaseq_kegg_enrich", "rnaseq_fgsea"],
+                        "rnaseq_report": [],
                    }
                    if (
                        "rnaseq_fgsea" in remaining_rnaseq_stages
@@ -20965,6 +21098,7 @@ async def agent_plan(request: AgentPlanRequest):
                        "rnaseq_fgsea": 10,
                        "rnaseq_wgcna": 20,
                        "rnaseq_candidate_family": 10,
+                        "rnaseq_report": 2,
                    }
                    stages_detail = []
                    for order, stage_id in enumerate(remaining_rnaseq_stages, start=1):
@@ -87,6 +87,7 @@ STAGE_KEYWORDS = {
    "rnaseq_kegg_enrich": ["rnaseq kegg", "rnaseq_kegg", "rna kegg", "kegg富集", "kegg分析", "kegg", "富集分析", "enrich"],
    "rnaseq_enrich": ["富集分析", "enrich", "go分析", "kegg", "clusterprofiler"],
    "rnaseq_candidate_family": ["候选家族", "候选基因家族", "家族排名", "tf注释", "tf family", "tffamily", "pfam注释", "deg注释", "差异基因注释", "差异基因家族", "candidate family"],
+    "rnaseq_report": ["rnaseq结果报告", "rna-seq结果报告", "转录组结果报告", "rnaseq报告", "rna-seq报告"],
    "ncbi_fetch_sequences": ["ncbi下载", "ncbi序列", "下载序列", "下载蛋白", "获取蛋白", "下载protein", "下载cds", "protein和cds", "蛋白和cds", "基因list", "gene list", "gene_list", "id列表", ".ids"],
 }

@@ -256,6 +257,7 @@ RNASEQ_STAGES = {
    "rnaseq_kegg_enrich",
    "rnaseq_enrich",
    "rnaseq_candidate_family",
+    "rnaseq_report",
 }

 # 物种关键词映射
@@ -732,6 +734,10 @@ def parse_intent_from_query(query: str) -> Dict:
        "clarify_type": result.get("clarify_type"),
        "message": result.get("message")
    }
+    if parsed["primary_stage"] == "rnaseq_report":
+        parsed["params"] = {
+            "rnaseqReportAction": "open" if "打开" in query_lower else "generate"
+        }
    if ncbi_params:
        parsed["params"] = ncbi_params
        parsed["prefix"] = ncbi_params.get("prefix", "")
@@ -781,6 +787,43 @@ def parse_intent_from_query(query: str) -> Dict:
    return parsed


+def deterministic_agent_chat_intent(
+    query: str,
+    *,
+    rnaseq_context: bool = False,
+) -> Optional[Dict]:
+    """Return explicit chat intents that must not depend on the Router model."""
+    intent = parse_intent_from_query(query)
+    if intent.get("stages") == ["rnaseq_report"]:
+        return intent
+    query_lower = str(query or "").lower()
+    query_without_space = re.sub(r"\s+", "", query_lower)
+    is_generic_report_action = (
+        rnaseq_context
+        and "结果报告" in query_without_space
+        and any(action in query_without_space for action in ("生成", "打开"))
+    )
+    if is_generic_report_action:
+        return {
+            "gene_family": "",
+            "species": "",
+            "stages": ["rnaseq_report"],
+            "primary_stage": "rnaseq_report",
+            "task_type": "report",
+            "task_kind": "pipeline",
+            "confidence": 0.99,
+            "need_clarify": False,
+            "clarify_type": None,
+            "message": None,
+            "params": {
+                "rnaseqReportAction": (
+                    "open" if "打开" in query_without_space else "generate"
+                )
+            },
+        }
+    return None
+
+
 def parse_msa_region_plot_request(query: str) -> Dict:
    """Extract parameters for drawing a selected MSA alignment region."""
    text = str(query or "").strip()
@@ -1367,6 +1410,12 @@ def _extract_stages(query: str, query_lower: str) -> List[str]:
        stages.append("gwas_fmt")
    matched_keywords = []  # 记录匹配到的关键词长度，用于优先级判断
    has_rnaseq_marker = any(marker in query_lower for marker in RNASEQ_MARKERS)
+    requests_result_report = any(
+        keyword in query_lower
+        for keyword in ["生成结果报告", "打开结果报告", "结果报告", "生成报告", "打开报告"]
+    )
+    if has_rnaseq_marker and requests_result_report:
+        return ["rnaseq_report"]
    extraction_context = any(kw in query_lower for kw in ["提取", "extract", "gffread", "筛选", "subseq"])
    explicit_gene_family_context = any(kw in query_lower for kw in ["基因家族", "家族表达", "表达量", "热图", "heatmap"])
    curated_member_context = (