frontend/app/chat/_types/types.ts (1)

40-84: 📐 Maintainability & Code Quality | 🔵 Trivial | ⚡ Quick win

Consider extracting a shared metadata type to reduce 4x field duplication.

embedding_model, parser, page, score, chunk_size, chunk_overlap are each declared four times (top-level, data, data.metadata, metadata). This mirrors the fallback chain in chunk-popup.tsx's getMetadataValue, so the shape duplication is functionally intentional, but keeping the field list in sync across four spots increases the chance of drift when new metadata fields are added.

♻️ Suggested refactor

+interface ChunkMetadataFields {
+  embedding_model?: string;
+  parser?: string;
+  page?: number | string;
+  score?: number | string;
+  chunk_size?: number | string;
+  chunk_overlap?: number | string;
+}
+
 export interface ToolCallResult {
   text_key?: string;
   data?: {
     file_path?: string;
     text?: string;
-    page?: number | string;
-    score?: number | string;
-    embedding_model?: string;
-    parser?: string;
-    chunk_size?: number | string;
-    chunk_overlap?: number | string;
-    metadata?: {
-      embedding_model?: string;
-      parser?: string;
-      page?: number | string;
-      score?: number | string;
-      chunk_size?: number | string;
-      chunk_overlap?: number | string;
-      [key: string]: unknown;
-    };
+    metadata?: ChunkMetadataFields & { [key: string]: unknown };
+    [key: string]: unknown;
+  } & ChunkMetadataFields;
+  default_value?: string;
+  chunk_id?: string;
+  id?: string;
+  filename?: string;
+  source_url?: string | null;
+  text?: string;
+  metadata?: ChunkMetadataFields & { [key: string]: unknown };
+  [key: string]: unknown;
+}

🤖 Prompt for AI Agents

Verify each finding against current code. Fix only still-valid issues, skip the
rest with a brief reason, keep changes minimal, and validate.

In `@frontend/app/chat/_types/types.ts` around lines 40 - 84, The ToolCallResult
shape repeats the same metadata fields in four places, which makes future
updates easy to drift. Extract a shared metadata type for the common fields used
by chunk-popup.tsx’s getMetadataValue fallback chain, then reuse it for
ToolCallResult’s top-level, data, data.metadata, and metadata properties. Keep
the overall structure the same, but centralize the repeated field list so new
metadata fields only need to be added once.

src/services/langflow_file_service.py (1)

476-478: 📐 Maintainability & Code Quality | 🔵 Trivial | ⚡ Quick win

Centralize parser label strings to avoid drift.

"Docling Serve 1.20.0" and "URL Ingester" are hardcoded here, while processors.py defines DOCLING_PARSER_LABEL/TEXT_PARSER_LABEL constants for the same values, and chat_service.py also hardcodes "URL Ingester" in two places. Consider moving these labels into a shared module (e.g. alongside the existing constants in processors.py, or a new constants.py) and importing them everywhere they're used, so a future rename/version bump doesn't require hunting down every literal.

Also applies to: 648-650

🤖 Prompt for AI Agents

Verify each finding against current code. Fix only still-valid issues, skip the
rest with a brief reason, keep changes minimal, and validate.

In `@src/services/langflow_file_service.py` around lines 476 - 478, The parser
labels are duplicated as hardcoded strings, so centralize them in a shared
constant location and reuse those symbols everywhere. Move or reuse the existing
DOCLING_PARSER_LABEL and TEXT_PARSER_LABEL definitions from processors.py, and
replace the inline “Docling Serve 1.20.0” and “URL Ingester” literals in
langflow_file_service.py and chat_service.py with imports from that shared
source. Keep the naming consistent across the related parser/service methods so
future version or label changes only need one update.

src/services/chat_service.py (1)

107-128: 📐 Maintainability & Code Quality | 🔵 Trivial | ⚡ Quick win

Duplicated DocumentIndexContext/ingest-token construction across langflow_chat and upload_context_chat.

Both methods build an almost identical URL-ingest DocumentIndexContext (now with the added parser/chunk_size/chunk_overlap fields) and mint a token the same way. Extracting a small helper (e.g. _build_url_ingest_token(...)) would prevent the two call sites from drifting as more fields are added.

Also applies to: 524-545

🤖 Prompt for AI Agents

Verify each finding against current code. Fix only still-valid issues, skip the
rest with a brief reason, keep changes minimal, and validate.

In `@src/services/chat_service.py` around lines 107 - 128, The URL-ingest
`DocumentIndexContext` and token minting logic is duplicated in `langflow_chat`
and `upload_context_chat`, so extract it into a shared helper such as
`_build_url_ingest_token(...)` or a small builder used by both methods. Move the
repeated `DocumentIndexContext` construction in `chat_service.py` into that
helper, including the new `parser`, `chunk_size`, and `chunk_overlap` fields,
and have both call sites reuse it to keep the two paths in sync.

src/agent.py (1)

37-37: 📐 Maintainability & Code Quality | 🔵 Trivial | ⚖️ Poor tradeoff

System prompt duplicated verbatim across three files.

The identical prompt string (with the new citation rule) is hardcoded in src/agent.py (line 37), src/config/config_manager.py (AgentConfig.system_prompt), and frontend/lib/constants.ts (DEFAULT_AGENT_SETTINGS.system_prompt). Any future change to citation formatting or tool instructions must be kept in sync across all three, which is error-prone.

Consider deriving agent.py's in-memory default from config_manager.AgentConfig.system_prompt (single backend source of truth), and having the frontend fetch it from settings rather than hardcoding a copy.

🤖 Prompt for AI Agents

Verify each finding against current code. Fix only still-valid issues, skip the
rest with a brief reason, keep changes minimal, and validate.

In `@src/agent.py` at line 37, The system prompt text is duplicated across
multiple places, so changes to tool instructions or citation formatting will
drift out of sync. Make `src/agent.py` use the single backend source of truth
from `AgentConfig.system_prompt` in `src/config/config_manager.py`, and remove
the hardcoded frontend copy in `DEFAULT_AGENT_SETTINGS.system_prompt` by loading
it from settings instead. Keep the prompt content centralized and referenced by
`agent.py`, `AgentConfig`, and `DEFAULT_AGENT_SETTINGS` so there is only one
canonical prompt to update.

frontend/app/chat/_components/chunk-popup.tsx (1)

63-71: 🗄️ Data Integrity & Integration | 🔵 Trivial | ⚡ Quick win

Hardcoded fabricated parser version as fallback.

When no parser metadata is present, this falls back to a hardcoded, specific-sounding version string "Docling Serve 1.20.0" rather than a generic label. Unlike formatSplitConfig, which correctly falls back to actual settings values, this presents a guessed, potentially stale/incorrect version as if it were factual data.

♻️ Proposed fix

   const fileExt = filename.split(".").pop()?.toLowerCase() || "";
   if (fileExt === "txt" || fileExt === "md") return "Text Parser";
-  return "Docling Serve 1.20.0";
+  return "Docling Serve";

✅ Autofix completed

src/api/settings/models.py (1)

81-86: 📐 Maintainability & Code Quality | 🔵 Trivial | 💤 Low value

Validator silently drops malformed result payloads.

ignore_non_list_result converts any non-list, non-None result value to None without logging, so malformed onboarding payloads fail silently instead of surfacing an error. Given src/**/*.py should use get_logger for diagnostics rather than staying silent, consider logging a warning when discarding an unexpected shape.

🤖 Prompt for AI Agents

Verify each finding against current code. Fix only still-valid issues, skip the
rest with a brief reason, keep changes minimal, and validate.

In `@src/api/settings/models.py` around lines 81 - 86, The ignore_non_list_result
validator in the settings model is silently discarding unexpected result
payloads by turning any non-list, non-None value into None. Update this
validator to use get_logger and emit a warning whenever it drops a malformed
result shape, while still preserving the current fallback behavior. Keep the
change localized to the validator on the result field so onboarding payload
issues are visible in diagnostics instead of failing silently.

frontend/app/onboarding/_components/onboarding-content.tsx (1)

59-68: 📐 Maintainability & Code Quality | 🔵 Trivial | ⚡ Quick win

Duplicate hasNestedResults type guard.

This is byte-for-byte identical to hasNestedResults in frontend/app/chat/_components/assistant-message.tsx (Lines 59-68 per the graph context). Consider extracting to a shared module (e.g. alongside ToolCallResult/FunctionCall types or a small citation-utils.ts) to avoid drift between the two copies.

🤖 Prompt for AI Agents

Verify each finding against current code. Fix only still-valid issues, skip the
rest with a brief reason, keep changes minimal, and validate.

In `@frontend/app/onboarding/_components/onboarding-content.tsx` around lines 59 -
68, The hasNestedResults type guard is duplicated in onboarding-content.tsx and
assistant-message.tsx, so move this logic into a shared helper module and import
it from both places to prevent drift. Keep the existing hasNestedResults
behavior unchanged, but centralize it near the related
ToolCallResult/FunctionCall types or in a small shared utility file. Update both
onboarding-content and AssistantMessage to use the shared implementation instead
of maintaining two copies.

Fix all unresolved CodeRabbit comments on this PR:

• Push a commit to this branch (recommended)
• Create a new PR with the fixes