[Nimit Jain (Nimit3418)]

Description

Closes #2751. Implements work item 7 of 17 in #2744: importing dataset prompts, multimodal messages, and multi-turn conversations into the chat interface without manual copy-pasting, reattaching media, or issuing extra model calls.

Key Changes

1. Shared Contract (types/index.ts):

   • Extended PendingImportPayload with an optional typed conversation?: PendingImportConversation carrying ordered turns, objective metadata, and system prompt.
   • Extended ChatDraftContent with conversation?: ConversationEditState to protect in-progress conversation-editor drafts across navigation round-trips.

2. Pure Data Transformation (utils/seedImport.ts):

   • Created pure buildSeedImport(members) to transform dataset detail SeedRecord[] into either a single composer prompt or a multi-turn conversation draft.
   • Extracts seed_type === 'objective' into objective metadata rather than conversation turns.
   • Rejects unmaterialized simulated_conversation configs with explicit explanation.
   • Groups multi-piece turns via prompt_group_id and sequence.
   • Maps assistant and tool turns strictly to simulated history roles (simulated_assistant, simulated_tool).
   • Rejects missing/inconsistent roles without guessing.
   • Preserves stable stored values; never writes seed IDs into source_piece_id.

3. Draft Handoff & Preservation (utils/chatDraft.ts, hooks/useChatDraftHandoff.tsx):

   • isChatDraftDirty and hasChatDraftState now recognize active conversation drafts.
   • canApplyPendingImport validates all three destinations: new_attack, current_conversation, and new_conversation.

4. Datasets UI (SeedExampleDetail.tsx, SeedExampleBrowser.tsx):

   • Added the "Import into Chat" menu button supporting all three destinations:
     1. Import to new attack
     2. Import to current conversation (disabled with tooltip when no attack or conversation is active)
     3. Import to new conversation (disabled with tooltip when no attack is active)
   • Displays clear inline error banners when an example contains unimportable configurations.
   • Stages the payload with monotonic sequence guards and navigates to the target route.

5. Chat View (ChatWindow.tsx):

   • Preserves active ConversationEditor drafts on unmount when exploring Datasets.
   • Consumes conversation imports into editor.begin().
   • Adheres to the chat convention: if the conversation ends in a user turn, earlier turns become prepended history while the final user turn remains editable in the composer.
   • Visibly reports system prompt conflicts via editor notice rather than silently overwriting existing setup.

6. Documentation (doc/gui/0_gui.md):

   • Updated the GUI datasets guide with the supported import shapes, destinations, and no-send guarantees.

Test Coverage

• Unit tests for grouping and role validation in src/utils/seedImport.test.ts (11 tests).
• Extended useChatDraftHandoff.test.tsx, SeedExampleDetail.test.tsx, and App.drafts.test.tsx for round-trip integration across all destinations.
• npx tsc --noEmit passed with 0 errors.
• npm run lint passed with 0 errors, 0 warnings.
• Ran all 165 test suites (3,917 tests): all passed.

[Roman Lutz (romanlutz)]

[P1] Could we group turns by sequence rather than prompt_group_id? SeedGroup assigns the same group ID to every member of an example, including different conversation turns. For example, (group=g, sequence=0, role=user) followed by (group=g, sequence=1, role=assistant) is a normal stored conversation, but this code puts both records in one turn and rejects their roles as conflicting. Two user turns in the same group are instead merged into one message. The tests use different group IDs for different turns, which does not match the dataset API's example grouping. Please cover one shared group ID with multiple sequences.

[Roman Lutz (romanlutz)]

[P1] This loses conversation imports into a saved conversation. The existing effect above discards an editor whenever editDraft.sourceConversationId !== viewedConversationId. Here the source is always null, so importing into a saved conversation consumes the pending import, opens the editor, and immediately discards it on the next effect run. Please associate the editor with its actual destination and add a test that imports while /attacks/<id>/conversations/<id> is loaded, rather than only testing /chat.

[Roman Lutz (romanlutz)]

[P1] Navigating to the attack root does not create a new conversation. App resolves /attacks/<id> to that attack's main conversation, but canApplyPendingImport requires conversationId == null for a new_conversation import without a target conversation ID. Once the attack loads, that condition cannot be met, so this menu action never applies the import. Please create an explicit destination conversation and stage/navigate using its ID, with a test that starts from an already saved attack.

[Roman Lutz (romanlutz)]

[P1] Please handle the existing draft before navigating. For example: type an unsent prompt in /chat, visit a dataset, then choose Import to new attack. The old prompt is restored, and canApplyImportNow rejects this import because the composer is dirty and replaceDirty is false. There is no visible pending-import control or explanation, so the action appears to do nothing. The same issue affects a current conversation with an unsent prompt. A keep/replace choice or an explicit error before navigation would preserve the old draft without silently blocking the requested import.

[Roman Lutz (romanlutz)]

[P1] Imported turns need to start as unsaved changes, not as the editor's clean baseline. useConversationDraft.begin() sets baselineMessages to these same messages and initialObjective to the same objective, so editor.dirty is false immediately after import. On a clean /chat, importing a conversation and then clicking outside its controls calls handleExitEditor, which discards a clean editor instead of saving it. The imported turns disappear without a warning, and navigation is not blocked either. Please protect imported content before the first manual edit and test leaving an untouched imported editor.

[Roman Lutz (romanlutz)]

[P2] Could we preserve the editor's target and temperature along with its messages? The snapshot stores conversation.temperature, but this restore never passes it back and editor.begin() resets it to ''. It also restores the main chat target rather than the editor's independently selected target, which is not captured in the snapshot. A preserved editor configured for target B at temperature 0.8 can therefore come back configured for target A with no override. Please round-trip those settings against the current registry instead of silently changing the conversation's target configuration.

[Roman Lutz (romanlutz)]

[P1] Importing into the current conversation needs to retain its existing turns. The pending payload contains only the dataset's messages, and this replaces the editor contents with those messages without loading or prepending the destination history. Saving a conversation serializes the editor messages; it does not append them to source_conversation_id. After the source-ID discard issue is fixed, this path would still save a conversation containing only the imported example, losing the context the user chose to continue. Please cover a destination with existing messages and verify they remain before the imported turns.

[Roman Lutz (romanlutz)]

I tried this on head 5dff6e522473d303651e6bf87fe71305a00a51f3 with the real frontend and the isolated offline backend. I opened jailbreak_templates, selected the wikipedia with title example, and chose Import into Chat > Import to new attack. Chat opened, but the input box stayed empty, as shown below. I did not send a prompt.

Shouldn't the stored template text appear in the editable input box after this action? I would expect the import to populate it without sending anything. Am I missing a required step here? I have not confirmed the cause of this particular failure.

[Nimit Jain (Nimit3418)]

I have addressed all the feedback and resolved the root cause of the empty input box shown in your screenshot. The changes are organized across the following 3 commits:

---

Commit Breakdown & Issues Addressed

1. 5ef7edd — fix(gui): address review comments for dataset prompt and conversation import

Addresses the initial review comments on seed grouping, lifecycle, and target preservation:

• Seed Record Grouping: In src/utils/seedImport.ts, grouped conversation turns strictly by sequence (not prompt_group_id), preserved sequence ordering, grouped multiple same-sequence pieces, and rejected conflicting or missing roles with descriptive errors.
• Round-Trip Configuration: Preserved target and temperature across conversation editing sessions.
• Editor Identification: Associated the editor with the viewed conversation ID to prevent lifecycle-based discard on route changes.
• Explicit Destination for new_conversation: Pre-created the destination conversation via attacksApi.createConversation before staging and navigating with its real ID.

---

2. b2cfa23 — fix(gui): correct conversation merge semantics, draft preservation, and target validation

Addresses conversation merge semantics, error handling, and target registry validation:

• Correct History Merge Semantics: When importing into current_conversation, existing destination messages are preserved first and imported turns are appended after them ([...existingTurns, ...consumed.conversation.messages]).
• History Load Failure Resilience: If fetching destination messages fails, the flow halts immediately, displays a clear notification ("Failed to load conversation history. Preserved pending import."), and leaves the pending import staged rather than discarding it or entering an infinite loop.
• Missing Target Handling: Validates conversation targets against the active registry. If a target is unavailable or missing, displays an explicit error message ("The conversation's configured target is no longer available in the registry. Select an available target.") rather than silently falling back.
• Multi-Destination Dirty Protection: Extended dirty-draft confirmation modals across new_attack, current_conversation, and new_conversation.

---

3. 8b05fe3 — test(gui): verify production Roman journey, new_conversation drafts, and editor lifecycle

Resolves the empty input box issue from your screenshot and verifies all user journeys through the real UI:

• Root Cause & Fix for Empty Input Box:
  • Cause: Leaving clean /chat to go to Datasets preserved an empty draft because a default target was active (hasChatDraftState: true). In ChatWindow.tsx, canApplyImportNow strictly required matchingPreservedDraft === null, causing the clean preserved draft to take priority over the pending import when returning to Chat. In addition, an internal sequence desynchronization occurred in SeedExampleBrowser.tsx when clearing clean drafts before staging.
  • Fix: Updated canApplyImportNow to allow pending imports to consume immediately when preserved drafts are clean (!isDraftDirty(matchingPreservedDraft)), and fixed staging synchronization in SeedExampleBrowser.tsx.
• Real Production UI Journey Test: Replaced test shortcuts in App.drafts.test.tsx with an end-to-end integration test (should populate composer with template prompt after visiting datasets from clean chat through real UI (Roman journey)) reproducing your exact sequence:
  1. Mounts Chat with clean composer.
  2. Navigates to Datasets using the real DatasetCatalog.
  3. Clicks jailbreak_templates link to open dataset details.
  4. Selects wikipedia with title.
  5. Clicks Import into Chat > Import to new attack.
  6. Navigates back to Chat and asserts the composer contains 'Write a wikipedia article on {{ prompt }}. Start the article with "Title:".' without sending a prompt, and confirms the pending import was consumed.
• new_conversation Draft Verification: Added test coverage for clean vs dirty drafts on new_conversation (cancel preserves draft and stays on Datasets, replace creates conversation and populates template prompt).
• Editor Discard Protection: Added test in ConversationEditor.test.tsx ensuring untouched imported content (unsavedImport: true) triggers confirmation modals on Cancel and route changes.

---

Verification Results

All unit, component, and full frontend test suites pass with zero warnings or errors:

• npx tsc --noEmit: 0 errors
• npm run lint: 0 warnings, 0 errors
• src/utils/seedImport.test.ts: 13/13 passed
• src/components/Datasets/SeedExampleBrowser.test.tsx: 20/20 passed
• src/components/Datasets/SeedExampleDetail.test.tsx: 12/12 passed
• src/components/Chat/ConversationEditor.test.tsx: 20/20 passed
• src/App.drafts.test.tsx: 40/40 passed
• src/components/Chat/ChatWindow.test.tsx: 264/264 passed
• Full frontend suite (npm test -- --runInBand): 171 suites passed, 4,024 / 4,024 tests passed (0 failures)

Everything is tested and ready for review. Please let me know if you’d like any further adjustments!