Files
notarius/docs/roadmap/future.md

163 lines
7.9 KiB
Markdown
Raw Normal View History

# Future Work
Current Notarius behavior is documented in the canonical README, CLI,
configuration, operations, internal, and integration docs. This backlog records
2026-11-22 09:51:45 +00:00
proposed extensions to that implementation. Items below are ordered roughly by
value and specificity, not as committed release dates.
## Near-Term D&D Pipeline
### Evaluate Spell Extraction And Normalization
- Evaluate extraction, normalization, and correction quality against a
human-reviewed transcript set, comparing retained baselines with the native path.
- Maintain a small set of human-reviewed transcripts and outputs for prompt,
validator, and normalizer development. Treat model-quality review as an
iterative human evaluation aid, not a deterministic correctness gate.
2026-07-26 13:53:38 +00:00
### Evaluate The Shared D&D Scene Plan
- Reassess whether one shared scene plan provides enough context for NPC,
spell, combat, interaction, and scene-description lanes after real-world use.
Add more complex chunking only in response to demonstrated failures.
## Shared Normalization And Quality Work
The implemented source-backed core and initial D&D registry adoption are
described by [Module Internals](../internal/modules.md#semantic-reconciliation)
and
[D&D Module Internals](../internal/dnd.md#semantic-registry-reconciliation).
2026-08-25 19:11:30 +00:00
The sections below keep broader extensions deferred.
### Large-Collection Semantic Reconciliation
- Evaluate deterministic candidate blocking only after representative registry
inputs exceed practical single-request capacity. Blocking should use cheap,
explainable signals to form plausible comparison sets while
preserving the possibility that a duplicate appears outside a lexical name
match.
- Define correctness for candidates that appear in more than one block,
conflicting canonical selections, transitive identity across blocks, retry
isolation, and deterministic final ordering before implementation.
- Prefer a reconciliation graph or union plan with explicit conflict checks
over arbitrary fixed-size slices. Never silently treat a batch boundary as
evidence that two candidates are distinct.
- Record per-request bounds, block provenance, model calls, discarded
proposals, and final group derivation well enough to audit a collapse.
### Operator-Selected Semantic Policies
- Consider a dedicated semantic-policy selection option for a typed
reconciliation module when a concrete operator workflow needs more than the
2026-11-22 09:51:45 +00:00
[native prompt replacement](../config.md#promptkit-profiles).
- Use native prompt IDs and sources while retaining typed interpretation and
deterministic safety rules. Define any additional configuration and domain
compatibility checks from that workflow; do not recreate asset registration,
prompt fingerprints, or checkpoint dependency tracking.
2026-11-22 09:51:45 +00:00
- Reuse the [accepted-artifact cache policy](../operations.md#accepted-result-cache-and-recovery)
when evaluating policy changes and the need for explicit refresh.
### Broader Reconciliation Inputs And Module Selection
- Revisit alternate context providers when a concrete non-source-backed entity
collection needs semantic reconciliation. Any extension must preserve the
same request-local identity, deterministic proposal validation, provenance,
and typed application guarantees.
- Consider a selectable generic normalizer only if Notarius gains a real
domain-neutral typed artifact contract that can safely support it. Do not
weaken exact artifact registration or introduce reflection-based arbitrary
JSON mutation merely to expose a universal module key.
### Validation And Review
- Add domain validators and production default chains alongside each new D&D
artifact.
- Add production LLM-backed validators only when a concrete review policy
benefits from model judgment and deterministic checks are insufficient.
- Consider additional validator diagnostic views only if a concrete need remains
2026-11-22 09:51:45 +00:00
with the existing [native observations and debug capture](../internal/llm.md#native-evidence-and-sensitive-data).
- Existing typed resolution already checks validator target, artifact kind,
and exact Go-type compatibility. Add further semantic suitability metadata
only if a deployment needs a contract beyond those implemented checks.
- Add media-type validators when non-JSON artifact representations are
introduced.
## Further Reference Evolution
- Make prior-run artifacts easier to bind as references without changing the
existing module-facing reference-item contract.
- Existing registry/catalog consumers already parse and validate typed contextual
projections. Consider a framework-level parsed-reference facility only when
concrete consumers need shared behavior beyond those module-owned resolvers.
- Add per-slot or per-chunk inclusion policies so large references are not
repeated in every prompt unnecessarily.
- Add token budgeting and model context-window management for reference
content.
- Add reference caching, preprocessing, summarization, embedding, or retrieval
only when reference size and observed model behavior justify them.
- Extend generated references to prior-run artifacts or derived summaries only
after same-run ordered handoffs establish the required provenance and
lifecycle semantics.
## Design Considerations To Revisit
These concerns are relevant to ordered artifact dependencies but are not
committed near-term features.
### Cross-artifact identity links
Evaluate whether downstream D&D artifacts should retain canonical NPC IDs from
the generated NPC reference in addition to normalized display names. Any such
contract must define player-character, unknown-actor, missing-NPC, and
superseded-identity behavior before implementation. Deterministic validation
may confirm that a linked ID exists in the consumed NPC artifact, but the link
must never substitute for transcript evidence that the downstream event
occurred.
### Artifact contract evolution
Define compatibility and migration policy before generated-reference chains
must span multiple schema versions or long-lived historical artifacts. The
policy should address stable identifier semantics, when an older artifact may
be decoded or adapted, and when consumers need regenerated artifacts. For cached
2026-11-22 09:51:45 +00:00
artifacts, use the [current reuse policy](../operations.md#accepted-result-cache-and-recovery)
and explicit refresh where needed. Do not add a general migration framework
until an actual contract change requires one.
### Artifact-family-oriented physical packaging
[ADR-0004](../adr/0004-package-modules-by-domain.md) currently groups production
extensions by domain and then by pipeline stage. After artifact-family
ownership terminology is established and more families span extraction,
normalization, validation, codecs, references, and assets, reassess whether a
feature-first physical layout would improve navigation and reduce scattered
changes enough to justify a repository-wide package migration. Any change must
address Go dependency cycles, registrar ownership, stable public module keys,
and supersession of the affected ADR-0004 decision. Conceptual artifact-family
ownership does not by itself require this move.
## Blue-Sky Platform And Operations
These ideas are intentionally less specified. Promote one into an earlier
section only after a concrete workflow, contract, and priority emerge.
### Platform Extensions
- Additional input adapters, such as Markdown or note-export formats.
- Additional output encoders.
- Broader workflow composition only when a concrete need justifies revisiting
the fixed-shape pipeline decision; ready cross-lane completion already runs concurrently.
- Batching or specialized context-window controls for LLM-backed validators.
### Distribution And Operations
- Packaged release artifacts for alpha distribution.
- Optional generated example-output fixtures with a regeneration procedure.
- Additional diagnostics or reporting views.
### Workspace And Storage
2026-07-16 22:31:14 -05:00
- Remote workspace storage.
- Workspace garbage collection and archival policies.
- Cross-machine sharing of accepted-artifact cache entries.