Context
Narrova lets you build with intent by combining three kinds of Context. Each one carries a different layer of story memory, so responses stay sharp, relevant, and true to your current objective.
Context types at a glance
- Story Context keeps broad material that applies across many ideas: world lore, character bios, visual references, tone guides, research notes. Think of it as your shared universe bible.
- Storyform Context holds the structured pieces of a single Dramatica Storyform: Throughline workpads, signpost explorations, encoded beats, thematic breakdowns. It is the “structured spine” for one story.
- Conversation Context is temporary and narrow. Upload files here only when you need short-lived reference for the current chat.
TIP
A Story can have many Storyforms. Use Story Context when something should be true for every version, and Storyform Context when the material belongs exclusively to one specific structure.
Solo and team workflows
If you are working one Storyform inside one story, Storyform Context will usually be the most useful place to stay. Put the cast pressure, locations, scene notes, encoded Storypoints, draft material, and Storybeat work there so Narrova can keep answering from the structure you are actively developing.
Use Story Context when the material is bigger than one Storyform: worldbuilding, shared continuity, recurring locations, series rules, tone guides, research, character histories, and anything you keep repeating across conversations or Storyforms. It is also helpful when you are not sure about the Storyform yet and want Narrova to keep the larger creative frame in view while you explore.
For development teams, Story Context becomes the shared story-world layer. A series team might keep the franchise bible, world rules, character canon, and season-level continuity in Story Context, while separate episode teams work in separate Storyform Contexts. Each episode can technically contain more than one Storyform, but most episodes are cleaner with one complete Storyform unless the runtime or format gives the story enough room to carry multiple complete structures.
The working mental model
The simplest way to stay oriented in Narrova is this:
- Context is memory.
- Conversation is workspace.
That means Narrova works best when you let Story and Storyform hold the durable knowledge, while each conversation stays focused on the job directly in front of you.
What belongs where
- Use Story Context for broad canon: character bios, world rules, tone references, research, visual inspiration, and notes that should stay true across multiple versions of the story.
- Use Storyform Context for structure-specific canon: Throughlines, Signposts, encoded beats, thematic notes, Player mapping, and transcripts that belong to one specific Dramatica Storyform.
- Use the live Conversation for directives, decisions, and the current task. Think of it as a work session, not your project's permanent memory.
Worldbuilding and codex files
Many writers use a “codex” file as a personal world bible: history, factions, magic systems, character biographies, continuity rules, visual references, voice notes, and prior-story events. Narrova can use those files well, but the file’s location matters.
Put worldbuilding files in Story Context when they describe the larger creative universe. This includes setting rules, recurring locations, character histories, metaphysics, research, cultural references, and continuity that should apply across more than one Storyform.
Put current-structure files in Storyform Context when they belong to one exact Dramatica structure. This includes the selected Main Character, Influence Character, Protagonist, Antagonist, Throughline work, Storypoints, Signpost plans, Storybeat notes, and draft pages for that Storyform.
IMPORTANT
Uploaded files are reference material. The current Storyform, current Perspective selections, and your latest explicit instruction are the authority for the story you are developing right now. If an older character dossier says “Risha is the Main Character,” but the current Storyform says “Walburga is the Main Character,” Narrova should follow the current Storyform.
If you are writing a series, organize prior events as history, not as instructions to repeat them. A file named Prior Events - Season One.md tells Narrova what happened before. A file named Current Storyform - Episode Two.md tells Narrova what structure it should help develop now.
Writing use: Keep broad canon in Story Context, keep current structural decisions in Storyform Context, and use the current conversation to say what you want Narrova to do next.
Role-neutral character notes
Character documents travel better when they describe the person before assigning a Dramatica role. A durable character file can say what the character wants, fears, hides, knows, believes, and does under pressure. The Storyform can then decide whether that character is functioning as Main Character, Influence Character, Protagonist, Antagonist, or another Player in the current structure.
Use role-specific language only when the file belongs to that Storyform. For example:
- Story Context:
Walburga - Character Dossier.md - Storyform Context:
Walburga as Main Character - Current Storyform.md - Story Context:
Series Timeline - Prior Events.md - Storyform Context:
Episode Two Signposts and Storybeats.md
TIP
If a character changes function from one story to another, keep their biography in Story Context and put the role assignment in Storyform Context. That keeps Narrova from treating an old role as permanent canon.
IMPORTANT
If you treat one conversation like a writing partner that should remember everything forever, the thread eventually gets crowded. That is when you start to see lower Narrative Efficiency, more compaction, slower replies, and less predictable behavior.
A better way to work
Start a new conversation whenever the objective changes, even if you are still working inside the same Storyform.
For example, during Encoding you might use:
- one conversation for Objective Story Players
- one for Main Character pressure
- one for Influence Character pressure
- one for Relationship Story tension
- one for a specific Storybeat or Signpost cluster
This does not break continuity as long as those conversations stay attached to the same Storyform Context. The Storyform carries the structural spine forward, so the new conversation does not need to inherit the entire old thread to stay aligned.
TIP
When a conversation produces something worth keeping, save it as a Note or upload the transcript into Story or Storyform Context. Then start fresh. This preserves the insight without forcing the next thread to carry all the old chat history.
Navigating contexts
- Open the Stories menu in the top navigation to jump straight to the Stories index (Story Context) or the Storyforms index (Storyform Context).
- Use the Context and Sources control just above the input area to manage what Narrova listens to in the current conversation.
Context button
The Context button shows whether contextual sources are active. When it is lit, Narrova is drawing from one or more sources beyond the raw conversation. Tap it to open the context sheet; tap again to turn every source off if you want a clean slate.
Quick-add menu (+)
The + button beside the input is a shortcut for managing context without leaving the chat. Open it to:
- Add Files – upload supporting files straight into the active Story or Storyform.
- Add Context – create or switch to a Story/Storyform context for this conversation.
- Next Story Context – quickly jump to the next Story context in your workspace.
TIP
The + menu mirrors the same actions available elsewhere in the Context Manager, giving you a faster, in-place way to keep Narrova aligned with the right materials.
Narrova Context Window
The Narrova Context Window meter sits above the input and shows how much conversation context is being used.
- The percentage is a live estimate of context usage in this thread.
- As usage rises, Narrova may recommend starting a new conversation or moving the transcript into Story or Storyform Context.
Tap the meter to open the control panel for response shaping controls:
- Thinking level options (Quick, Light, Balanced, Deliberate, Frontier)
- Response verbosity options (Concise, Normal, Detailed)
Use this panel to match response depth to your current task instead of manually overloading a thread.
Sources switcher
Inside the sheet, choose Story or Storyform (or both) under the Sources heading. This is the fastest way to point the conversation at the right material without leaving the page.
IMPORTANT
Only two sources can be active at once. Mix and match Story, Storyform, and Conversation context however you like, but stay within that limit. If you need more references, upload them as documents to the appropriate Story or Storyform so they remain available without consuming another slot.
When to use the switches
- Story only: brainstorming lore, tone, or character arcs that apply to every version of the story.
- Storyform only: drilling into structural details—Drivers, Signposts, or encoded beats—for one specific Dramatica model.
- Story + Storyform: balancing thematic intent with the expression you already designed; perfect for polishing scenes while keeping the structure honest.
Context icons
You can always see which sources are active by glancing at the icons beside the Sources control:
- 📖 Story – Story Context is on.
- ⚛️ Storyform – Storyform Context is on.
- 💬 Conversation – at least one file has been uploaded directly into this conversation, so it now carries its own context bundle.
TIP
Conversation context appears automatically the moment you attach a file to the chat. Remove the file to drop back to Story and Storyform only.
Uploading documents
Uploading turns a document into usable Context. Narrova stores the file in the chosen Context, splits it into retrieval-friendly passages, and makes it available through the Sources modal so you can control when it is visible.
For Story Context and Storyform Context, limits are based more on the overall document footprint than on the number of files.
- Dramatica: 2 GB document storage
- Dramatica Plus: 10 GB
- Dramatica Pro: 20 GB
That is why file count by itself is not a very useful measure. A few large drafts may matter more than many small notes, and many small files can work perfectly well if the overall Context stays coherent and intentional.
What uploading means
- Story Context upload adds a document that can support every Storyform in that Story.
- Storyform Context upload adds a document that supports only that specific Storyform.
- Conversation Context upload attaches a file directly to the current chat for short-lived reference.
When uploading worldbuilding or codex files, use the optional Document intent field when it is available:
- World bible for broad setting, metaphysics, rules, factions, history, and series canon.
- Character profile for role-neutral character dossiers.
- Timeline snapshot for current chronology or continuity state.
- Prior story/events for events that already happened and should be treated as background unless you ask Narrova to continue them.
- Style guide for voice, format, expression, prose preferences, or translation notes.
- Other for reference material that does not fit the above.
TIP
The intent label helps you manage the file and gives Narrova a cleaner hint about how to use it. It does not override your current Storyform or your latest instruction.
IMPORTANT
For comic books and graphic novels, upload through the Story or Storyform document managers (not conversation-only upload) so Narrova can run comic-script processing and keep the resulting -comic-script.md artifact as durable context.
NOTE
Uploading is not just storage. Narrova extracts text, chunks it into passages, and indexes it so answers can cite the most relevant parts.
Upload lifecycle
- Uploading – the file is transferring. You can keep chatting, but the file is not yet searchable.
- Uploaded – the file is stored. Narrova starts preparing it for retrieval.
- Indexing – text is extracted and split into passages. Once indexing finishes, the document is fully available for responses.
TIP
If answers do not reflect a newly added file, wait for Indexing to finish and try again.
Managing visibility in the Sources modal
Use the Context and Sources control above the input to open the Sources modal. In Story and Storyform Context, each document includes a visibility toggle:
- On means the file can be retrieved for the current conversation.
- Off means the file stays stored but will be ignored until you re-enable it.
This lets you swap drafts, focus on a single reference, or temporarily silence a file without removing it.
Why Conversation Context has no visibility toggles
Conversation Context is intentionally simple: files attached to a chat are either present or removed. There are no per-file toggles because the expectation is that everything attached to the conversation is always available while the chat is active.
If you need fine-grained control, move the file into Story or Storyform Context and manage it through the Sources modal instead.
Compaction in Conversation Context
Compaction keeps long conversations writable by replacing heavy prior context with a condensed version Narrova can continue from.
It does not erase your visible conversation history. It compresses active model context so Narrova can keep delivering focused, high-signal responses.
See Narrative Efficiency for the meter and controls that signal when compaction is useful.
Manual compaction
Run manual compaction with /compact in chat.
- Best when you want to keep the current thread but reclaim headroom right now.
- Narrova compacts from the active response-chain anchor in the current conversation.
- After compaction completes, Narrative Efficiency updates immediately with an estimated post-compaction value.
Automatic compaction
Automatic compaction runs when the thread reaches the hard context threshold.
- Before that threshold, Narrova can show a soft warning that compaction is recommended.
- At the hard limit, Narrova starts compaction automatically so the conversation can continue without a hard creative stop.
- The compaction notice in-thread marks running and completed states.
What compaction changes (before vs after)
Before compaction
After compaction
In both columns, your current prompt stays the same. What changes is the memory stack above it:
- Before: raw, full conversation history.
- After: a compact narrative snapshot that preserves what matters most for continuation.
IMPORTANT
Compaction is a continuity tool, not a replacement for good Context hygiene. Keep chats goal-focused, move durable material into Story or Storyform Context, and start new threads when objectives change.
Working inside a Story
Opening a Story reveals everything linked to that project.
Documents
Upload files you want Narrova to consider for every Storyform in that Story—casting sheets, location research, tone guides. Rename or remove documents anytime.
IMPORTANT
Avoid mixing multiple drafts in the same Context. When you upload a PDF, Narrova splits it into many small passages for fast retrieval. If you upload Draft A, Draft B, and Draft C into one Context, those passages are pooled together. When you ask a question, Narrova pulls the most relevant passages regardless of draft, which can blend versions or resurrect older lines. The clean workflow is to keep separate Contexts for major rewrites, so every answer stays aligned with the right draft.
IMPORTANT
Document retention: files in Story Context or Storyform Context remain available for 30 days after their last access. Viewing them or having Narrova use them resets the timer. If nothing touches a file for 30 days, it is cleared; when you return after that window, simply re-upload the document into the same Context Manager to continue.
Conversations
Every conversation that references this Story appears here. Click a title to reopen it, favorite frequent threads, or use the overflow menu for more actions (see below).
Storyforms
Attach new Storyforms, set one as primary, or detach and reuse it elsewhere. You can still find every Storyform in the global index even if it is not currently attached to a Story.
IMPORTANT
Deleting a Story or Storyform does not delete conversations. Only the association is removed. Delete conversations separately if you no longer need them.
Working inside a Storyform
A Storyform page focuses on the structure itself. Store encoded beats, progression notes, documents, and conversations that belong exclusively to this interpretation of the story. When you validate or adjust the Storyform, those updates guide every conversation that references it.
TIP
If you have a Storyform, store draft documents there so every request benefits from the Storyform automatically. You can remove older drafts if they are no longer useful, or temporarily hide them so their passages are not retrieved.
NOTE
Story Context and Storyform Context are separate on purpose. Think like a TV series: character bios, settings, and worldbuilding live in Story Context, while individual episode drafts and their notes live in Storyform Context.
Conversation actions menu
The conversation overflow menu (⋯) exposes tools that help you keep context tidy.
Branch conversation
Use Branch conversation when you want to test a different creative path without disturbing the original thread. Branching duplicates the conversation up to the selected completed response, then opens a new conversation from that point. The original stays intact, and the branch gives you a clean place to make a different choice.
This is especially useful during Story development when Narrova asks you to choose between meaningful structural alternatives. For example, if Narrova asks whether the story should end in Success or Failure, branch at that response and try both. One conversation can explore the Success version, while the other explores the Failure version, letting you compare how each Outcome lines up with the Storyform, Throughlines, Storypoints, and Storytelling pressure.
To branch:
- Find the completed Narrova response where the alternate path begins.
- Click Branch conversation on that response.
- Confirm with Create branch.
- Continue from the new conversation that opens.
The branch carries forward the same Story Context and Storyform Context, so Narrova still understands the Story and Storyform you were developing. Conversation files attached to the original thread also remain available to the branch. The Narrative Context Package workspace is not duplicated into a separate notebook object; if you want long-term material from either path to become official context, save it deliberately with Notes or Upload into Context.
Each conversation keeps links to its related branch. The original conversation shows where it branched to, and the branched conversation shows where it came from. Use those links to move back and forth when comparing versions.
TIP
Branch before you make the choice you want to test. That gives each version a clean record: one thread for Success, one for Failure; one thread for a Change Main Character, one for Steadfast; one thread for keeping a Relationship together, one for letting it break.
IMPORTANT
Branching is for exploration, not automatic canon. Decide which branch earns a place in the project, then save the useful result into Story or Storyform Context so future conversations inherit the decision intentionally.
Writing use: when a structural decision could take the story in two honest directions, branch the conversation and let each version prove itself through Storyform alignment, character pressure, and scene consequences.
Move to Context
Use this when the conversation belongs somewhere else. Maybe you brainstormed under the wrong Story, created a new Storyform you’d rather use, or want to explore the same idea in a clean space. The Move dialog lets you review current attachments and select a new Story or Storyform without dismissing the modal. Once moved, the conversation immediately benefits from documents and structure that live in the new destination.
TIP
Move first, then continue the discussion. The assistant will start drawing from the new Story or Storyform as soon as you switch context.
Upload into Context
Upload into Context saves the entire transcript as a Markdown document inside the current Story or Storyform. Narrova does not archive chats automatically—you choose what becomes long-term memory. When you trigger the upload, the conversation is stored as a document whose name matches the conversation title, so you can reference or reopen it later.
NOTE
Treat this as a one-click “download and re-upload.” Once the conversation earns a place in the canon, upload it and it becomes part of the official context alongside your other documents.
Keeping context manageable
Large chats are tempting, but smaller purposeful conversations stay cleaner, faster, and easier to steer. Let the Storyform carry continuity across sessions, and store durable knowledge as documents instead of leaving critical decisions buried in chat scrollback.
- Collect and label documents for each Story and Storyform. Short focused files (2–10k tokens) are easier for the model to retrieve accurately.
- Start a new conversation for each objective: locking Domains, testing a Relationship Throughline, exploring alternate Outcomes.
- Upload when finished. If a chat uncovers insights worth keeping, archive it with Upload into Context so future requests can build on it.
- Move conversations when focus shifts to a different Story or Storyform so Narrova always writes from the right foundation.
Be deliberate about where information lives, and Narrova stays responsive while each response reflects the latest living version of your story world.