dbagent-cli 0.9.1__tar.gz → 0.9.3__tar.gz

{dbagent_cli-0.9.1 → dbagent_cli-0.9.3}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: dbagent-cli
-Version: 0.9.1
+Version: 0.9.3
 Summary: Enterprise AI Database Copilot, Schema Graph Introspector & Autonomous Recovery Agent (CLI)
 Author: Santhosh Gupta
 Requires-Python: >=3.9

{dbagent_cli-0.9.1 → dbagent_cli-0.9.3}/dbagent/__init__.py

@@ -2,5 +2,5 @@
 DB-Agent: Universal Database Introspection and Script Generation AI Agent (CLI).
 """
 
-__version__ = "0.9.1"
+__version__ = "0.9.3"
 __author__ = "Santhosh Gupta"

{dbagent_cli-0.9.1 → dbagent_cli-0.9.3}/dbagent/agent/conversation.py

@@ -54,9 +54,13 @@ class ConversationContext:
         if len(self.turns) > self.max_history:
             self.turns.pop(0)
 
-        if tables and not is_chat:
+        if tables:
             self.active_tables.update(t.lower() for t in tables)
 
+    def get_active_tables(self) -> List[str]:
+        """Returns currently active database table names discussed in this session."""
+        return list(self.active_tables)
+
     def get_last_turn(self) -> Optional[ConversationTurn]:
         if self.turns:
             return self.turns[-1]

{dbagent_cli-0.9.1 → dbagent_cli-0.9.3}/dbagent/agent/generator.py

@@ -106,6 +106,11 @@ Provide ready-to-run, dialect-accurate SQL JOIN queries answering the user's spe
 
 ### 4. 💡 Architectural Insights & Best Practices
 Mention indexing recommendations, cascade rules, or performance considerations for these join paths.
+
+### 🛑 Critical Operational Directives:
+1. NEVER ask passive questions like "Would you like me to inspect tables?" or "Should I run a query?". Always proactively inspect and deliver the full architectural blueprint immediately.
+2. NEVER give generic textbook definitions. Always ground every explanation in the real database schema provided above.
+3. Always include ALL 4 sections (Diagram, Theoretical Breakdown, SQL Queries, and Insights).
 """
 
 
@@ -142,37 +147,56 @@ class ScriptGenerator:
         prompt_lower = user_prompt.lower().strip()
         clean_prompt = prompt_lower.rstrip(".!?,:;~ ")
 
-        # Chat / Conversational indicators (greetings, feedback, praise, acknowledgements)
-        chat_triggers = [
-            "hello", "hi", "hey", "howdy", "greetings", "good morning", "good evening", "good afternoon",
-            "who are you", "what can you do", "what are you", "help me", "how to use",
-            "what is this", "tell me about this database", "how does this work",
-            "can you help", "thanks", "thank you", "thx", "bye", "goodbye", "see ya",
-            "good", "great", "nice", "cool", "awesome", "perfect", "ok", "okay",
-            "yes", "no", "sure", "got it", "understood", "nice work", "well done",
-            "sounds good", "looks good", "alright", "super", "neat", "excellent",
-            "amazing", "wonderful", "cool thanks", "great thanks", "thanks a lot",
-        ]
-        for trig in chat_triggers:
-            if clean_prompt == trig or prompt_lower.startswith(f"{trig} ") or prompt_lower.startswith(f"{trig},") or prompt_lower.startswith(f"{trig}!"):
-                return "chat"
-
-        # Architecture / Relationship / Linkage / Analysis indicators
+        # 1. Architecture / Relationship / Linkage / Analysis indicators (Highest Priority)
         analysis_keywords = [
             "linkage architecture", "linkage", "architecture", "relationship between",
             "how are", "how is", "how were", "how they were related", "how were they related",
-            "how they were mapped", "how to map", "mapped to", "er diagram", "diagram of",
+            "how they were mapped", "how to map", "where they mapped", "where is it mapped",
+            "how they were assigned", "how are they assigned", "how will be linked", "how is it linked",
+            "mapped to", "mapped with", "er diagram", "diagram of",
             "data model", "explain relationship", "explain schema", "schema analysis",
             "analyze the database", "analyze database", "table relationship",
             "foreign key relationship", "how are tables related", "which sites in",
             "how to know that which", "how to know which", "mapping architecture",
             "entity relationship", "theoritical information", "theoretical information",
+            "check with my previous context", "check with previous context", "previous context",
+            "complete architecture", "scope architecture", "tenant level to user level",
+            "tenant level", "user level",
+            "tables that were linked", "tables linked with", "linked with", "links of",
+            "related tables", "related tebales", "table mappings", "related tables mappings",
+            "related tebales mappings", "not correct", "not right", "check all the tables",
+            "mappings also", "find all mappings", "check links", "check mappings",
         ]
         for kw in analysis_keywords:
             if kw in prompt_lower:
                 return "analysis"
 
-        # DDL indicators
+        # Contextual clarification for analysis (e.g. "i mean ivis_scope", "i mean table_x")
+        if re.search(r'\bi mean\b', prompt_lower) and not re.search(r'\b(insert|update|delete|drop)\b', prompt_lower):
+            return "analysis"
+
+        # 2. Pure Greeting / Feedback / Help triggers (Only when not asking a technical question)
+        pure_chat_greetings = ["hello", "hi", "hey", "howdy", "greetings", "good morning", "good evening", "good afternoon"]
+        pure_chat_feedback = [
+            "thanks", "thank you", "thx", "bye", "goodbye", "see ya",
+            "good", "great", "nice", "cool", "awesome", "perfect", "ok", "okay",
+            "yes", "no", "sure", "got it", "understood", "nice work", "well done",
+            "sounds good", "looks good", "alright", "super", "neat", "excellent",
+            "amazing", "wonderful", "cool thanks", "great thanks", "thanks a lot",
+        ]
+        pure_chat_help = [
+            "who are you", "what can you do", "what are you", "help me", "how to use",
+            "what is this", "tell me about this database", "how does this work", "can you help",
+        ]
+
+        if clean_prompt in pure_chat_greetings or clean_prompt in pure_chat_feedback or clean_prompt in pure_chat_help:
+            return "chat"
+
+        for trig in pure_chat_greetings + pure_chat_help:
+            if prompt_lower.startswith(f"{trig} ") or prompt_lower.startswith(f"{trig},") or prompt_lower.startswith(f"{trig}!"):
+                return "chat"
+
+        # 3. DDL indicators
         ddl_keywords = [
             "create table", "alter table", "drop table", "add column",
             "remove column", "rename column", "rename table", "modify column",
@@ -182,7 +206,7 @@ class ScriptGenerator:
             if kw in prompt_lower:
                 return "ddl"
 
-        # Write indicators (word-boundary matching to avoid false positives like "show dataset")
+        # 4. Write indicators (word-boundary matching to avoid false positives like "show dataset")
         write_phrases = [
             "insert", "add record", "add row", "add new",
             "update", "delete", "drop record",
@@ -191,14 +215,10 @@ class ScriptGenerator:
         for kw in write_phrases:
             if kw in prompt_lower:
                 return "write"
-        # Single-word write verbs need word boundary to avoid false positives
-        # e.g. "set" should not match "dataset", "change" should not match "show changes"
-        import re as _re
         write_verbs = ["set", "change", "modify", "remove"]
         for verb in write_verbs:
-            if _re.search(r'\b' + verb + r'\b', prompt_lower):
-                # Exclude when preceded by 'show', 'list', 'display', 'view', 'get'
-                read_context = _re.search(r'\b(?:show|list|display|view|get|count)\b.*\b' + verb, prompt_lower)
+            if re.search(r'\b' + verb + r'\b', prompt_lower):
+                read_context = re.search(r'\b(?:show|list|display|view|get|count)\b.*\b' + verb, prompt_lower)
                 if not read_context:
                     return "write"
 

{dbagent_cli-0.9.1 → dbagent_cli-0.9.3}/dbagent/agent/pipeline.py

@@ -157,17 +157,40 @@ class QueryPipeline:
                 max_tables=8,
             )
 
-        # 2. Targeted on-demand table introspection (~50ms instead of 5000ms for full scan)
+        # 2. Targeted on-demand table introspection with automatic junction expansion
         target_names = list(set(exact + fuzzy))
         if target_names:
+            try:
+                all_table_names = self.connector.get_table_names()
+                stems = set()
+                for t in target_names:
+                    unprefixed = re.sub(r'^(?:ivis_|tbl_|table_|app_)', '', t.lower())
+                    unprefixed = re.sub(r'(?:s|es)$', '', unprefixed)
+                    if len(unprefixed) >= 3:
+                        stems.add(unprefixed)
+
+                for t in all_table_names:
+                    t_lower = t.lower()
+                    if t in target_names:
+                        continue
+                    is_map = any(m in t_lower for m in ["_map", "mapping", "_rel", "_junction", "_link", "_access", "_config"])
+                    matches_stem = any(s in t_lower for s in stems)
+                    if (is_map and matches_stem) or sum(1 for s in stems if s in t_lower) >= 2:
+                        if t not in target_names:
+                            target_names.append(t)
+                    if len(target_names) >= 12:
+                        break
+            except Exception:
+                pass
+
             targeted = self.connector.inspect_schema(table_names=target_names, include_samples=True, max_samples=2)
             retriever = ContextRetriever(targeted)
-            return retriever.retrieve_context(user_prompt, exact_tables=exact, fuzzy_tables=fuzzy, max_tables=8)
+            return retriever.retrieve_context(user_prompt, exact_tables=exact, fuzzy_tables=fuzzy, max_tables=12)
 
         # 3. Fallback: inspect targeted
-        targeted = self.connector.inspect_targeted(user_prompt, max_tables=8, include_samples=True)
+        targeted = self.connector.inspect_targeted(user_prompt, max_tables=12, include_samples=True)
         retriever = ContextRetriever(targeted)
-        return retriever.retrieve_context(user_prompt, exact_tables=exact, fuzzy_tables=fuzzy, max_tables=8)
+        return retriever.retrieve_context(user_prompt, exact_tables=exact, fuzzy_tables=fuzzy, max_tables=12)
 
     def run(self, user_prompt: str, force: bool = False, bypass_cache: bool = False) -> PipelineResult:
         """
@@ -214,6 +237,12 @@ class QueryPipeline:
                 except Exception:
                     exact, fuzzy = [], []
 
+                # Inherit active tables from conversation context if follow-up prompt doesn't name tables explicitly
+                if not exact and not fuzzy:
+                    inherited = self.conversation.get_active_tables()
+                    if inherited:
+                        exact = inherited[:4]
+
                 sub_schema, join_steps = self._get_fast_schema_context(user_prompt, exact, fuzzy)
                 result.schema = sub_schema
                 result.join_steps = join_steps
@@ -244,7 +273,13 @@ class QueryPipeline:
                 result.was_executed = True
                 result.query_type = "analysis"
                 result.execution_time_ms = (time.time() - t_start) * 1000
-                self.conversation.add_turn(user_prompt=user_prompt, sql="", assistant_response=result.message, is_chat=True)
+                self.conversation.add_turn(
+                    user_prompt=user_prompt,
+                    sql="",
+                    assistant_response=result.message,
+                    tables=exact + fuzzy,
+                    is_chat=True,
+                )
                 return result
             except Exception as e:
                 result.error = f"Architecture analysis failed: {str(e)}"

{dbagent_cli-0.9.1 → dbagent_cli-0.9.3}/dbagent/connectors/base.py

@@ -44,14 +44,42 @@ class BaseConnector(ABC):
 
     def resolve_tables(self, user_prompt: str) -> Tuple[List[str], List[str]]:
         """
-        Resolve which tables the user is referring to.
+        Resolve which tables the user is referring to with prefix stripping, pluralization handling, and fuzzy matching.
         Returns (exact_matches, fuzzy_matches).
-        Default implementation uses get_table_names with simple substring matching.
         """
+        import re
         all_tables = self.get_table_names()
         prompt_lower = user_prompt.lower()
-        exact = [t for t in all_tables if t.lower() in prompt_lower]
-        return exact, []
+        exact = []
+        fuzzy = []
+
+        tokens = set(re.findall(r'\b[a-zA-Z0-9_]+\b', prompt_lower))
+
+        for t in all_tables:
+            t_lower = t.lower()
+            # 1. Exact full table name in prompt
+            if re.search(r'\b' + re.escape(t_lower) + r'\b', prompt_lower):
+                exact.append(t)
+                continue
+
+            # 2. Match without common prefixes (e.g. "ivis_scope" -> "scope", "scopes")
+            unprefixed = re.sub(r'^(?:ivis_|tbl_|table_|app_)', '', t_lower)
+            if unprefixed and len(unprefixed) >= 3:
+                if (unprefixed in tokens or 
+                    f"{unprefixed}s" in tokens or 
+                    f"{unprefixed}es" in tokens or 
+                    re.search(r'\b' + re.escape(unprefixed) + r'(?:s|es)?\b', prompt_lower)):
+                    if t not in exact:
+                        exact.append(t)
+                        continue
+
+            # 3. Fuzzy partial match
+            for tok in tokens:
+                if len(tok) >= 4 and (tok in t_lower or t_lower in tok):
+                    if t not in exact and t not in fuzzy:
+                        fuzzy.append(t)
+
+        return exact, fuzzy
 
     def refresh_cache(self) -> None:
         """Invalidate any cached metadata. Override in subclasses."""

{dbagent_cli-0.9.1 → dbagent_cli-0.9.3}/dbagent_cli.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: dbagent-cli
-Version: 0.9.1
+Version: 0.9.3
 Summary: Enterprise AI Database Copilot, Schema Graph Introspector & Autonomous Recovery Agent (CLI)
 Author: Santhosh Gupta
 Requires-Python: >=3.9

{dbagent_cli-0.9.1 → dbagent_cli-0.9.3}/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "dbagent-cli"
-version = "0.9.1"
+version = "0.9.3"
 description = "Enterprise AI Database Copilot, Schema Graph Introspector & Autonomous Recovery Agent (CLI)"
 readme = "README.md"
 requires-python = ">=3.9"