docs(jfm): establish traceable manuscript planning baseline

Track the research dossiers, section freezes, supporting manuscript materials, and round-aware agent controls so future drafting decisions can be reviewed across both repository mirrors. Co-authored-by: Cursor <cursoragent@cursor.com>
2026-08-10 18:51:53 +08:00
parent 140eea4d25
commit 0ade812864
143 changed files with 37165 additions and 1 deletions
@@ -0,0 +1,30 @@
+---
+description: DynamisLab JFM research, decision, and drafting workflow
+alwaysApply: true
+---
+
+# JFM Research and Manuscript Workflow
+
+## Round-aware operating mode
+- Identify the active round and output before work. R1 indexes evidence; R2 designs the manuscript; R3 builds section dossiers; R4 settles author-facing arguments, ownership, displays and section freezes; R5 drafts prose only from frozen R4 packets and authorities.
+- Keep evidence states distinct: `mapped` is not `read`; `read` is not independently verified or artifact-audited. Use a compact ledger (`read`, `mapped`, `not-covered`, `external-inaccessible`) proportional to the round; do not let governance overwhelm argument/design.
+- In R4/5 prioritize the section question, bounded answer, paragraph jobs, display logic, ownership, interfaces, author choices and manuscript value. Do not recreate R1 inventories or rediscover the project.
+
+## Continuation and context
+- When prior decisions matter, continuation agents begin with targeted Nowledge `memory_search`; use thread recall for exact prior discussion. Then verify every operative decision against current repository authorities. Memory aids discovery/history and never overrides authorities, manifests, code/configuration or immutable artifacts.
+- Before launching section agents, the coordinator creates a minimum context packet containing: exact controlling reads; accepted author feedback; available material/artifact inventory with readiness; requested output decision; exclusions; target length/section share; paragraph jobs; concrete display layout; ownership; and exact questions. Agents stay within that packet and perform only targeted authority checks.
+- Cadence after the initial architecture: present two detailed section packets together; receive author feedback; launch two tightly scoped continuation agents in parallel; then perform a coordinator second audit before either section is frozen or handed to R5.
+
+## Tool routing and execution safety
+- Nowledge: decisions, preferences and discussion history. Undermind: external literature only, after `get_orientation` and `list_workspaces`; literature cannot establish internal results. Repository read/search tools: internal evidence, authorities, code, manifests and artifacts.
+- For read-only derivations or scripts, discover the designated conda environment from current repository authority or environment listings and record it; never guess an environment. Do not run CFD, training, artifact generation or expensive analysis unless explicitly authorized.
+
+## Evidence and claim boundaries
+- Trace claims to current authorities and preserve solver, geometry/configuration, Reynolds convention, case/seed/role, comparator, metric/estimand, ROI/window and artifact. Keep internal Legacy and modern V5 chains separate; use physical configuration names in manuscript prose.
+- Use case-specific periodic, transient and steady metrics. Distinguish sourced fact, bounded observation, interpretation, historical/negative result and open question; report gaps and conflicts without inventing citations or numbers.
+- Image work inventories existing data/scripts before proposing panels; inventory is not panel readiness. Label existing derivations, independent checks and new conjectures separately.
+
+## Fixed scientific cautions
+- Bound positive SR to Kármán/cloaking. Illusion SR is historical/negative; CCD is descriptive/noncausal and uses `action-correlated correction-field modes`; OID is claim-free; steady results are contextual; experiment is qualitative/provenance-gated.
+- Kan99b K2 retains the authority's exact overall `partial pass`. Its opposite mean-lift sign is explained by the CFD coordinate/force-direction convention, not unresolved physics or suspected wrong rotation; do not call the sign unresolved.
+- Never promote claims across chains, alter evidence packages/archive/history, or inflate solver qualification into controller or mechanism validation.
@@ -0,0 +1,13 @@
+---
+description: Round-3 section dossier workflow; superseded for Round 4/5
+globs: docs/JFM_WYQ/ROUND3_BOTTOM_UP/**/*.md
+alwaysApply: false
+---
+
+# Round-3 Section Dossiers
+- This rule applies only to Round 3. Round 4/5 follow `jfm-research-workflow.mdc` and their current coordinator controls; do not carry Round-3 dossier density into section design or prose drafting.
+- Read the R2 freeze/style guide, relevant R1 dossiers and current authorities. Deliver an author-readable paragraph map plus a compact claim/evidence ledger; record `read`, `mapped`, `not-covered` and `external-inaccessible` without treating reading as verification.
+- Include the section question and bounded answer, paragraph jobs, transitions, display/equation roles, imports/exports, caveats, conflicts, non-claims and blockers. Preserve chain, role, comparator, metric, ROI/window and artifact boundaries.
+- Authority-led artifact deferral is acceptable unless the missing artifact is needed to resolve a conflict, bind an exact role/comparator/window, or substantiate a proposed number or panel.
+- First-pass agents cannot self-declare ready. The coordinator classifies systematic versus module-specific defects, repairs controls first when systematic, requests targeted revision, and performs a second audit.
+- Near-colliding results must be classified as `same estimand`, `related diagnostic` or `different estimand`; prohibit arithmetic pooling and replication/validation/agreement/triangulation wording without exact authority.