conductor/rune
1
2 Fork 1
Code Issues 38 Pull Requests 32 Actions 7 Packages Projects Releases 564 Wiki Activity

P0 Epic: Research Runtime Correctness (RSC0-9) #257

New Issue
Closed
opened 2026-09-08 14:55:11 +01:00 by conductor · 8 comments
conductor commented 2026-09-08 14:55:11 +01:00
Owner
Copy link
Copy source

Research Runtime P0 — SUPERSEDED DESIGN NOTICE (2026-09-08)

The RSC0–RSC9 stage design is superseded by the canonical Research-to-Build Pipeline (handoff 2026-09-08). This epic remains the single parent for research-runtime work; its child DAG is being amended to RP0–RP14.

Key design changes:

  • Gitea issue replaces DEFINE — the issue is the authoritative statement of intent; no cognitive DEFINE stage.
  • Unified OUTWARD — one natural MiMo research task; OUTWARD_DISCOVERY/OUTWARD_READING split is retired.
  • Gitea owns stage eligibility — Rune executes exactly one authorized stage per StageReady event; no self-walking loops.
  • Runner placement enforced — Pi = Gitea/storage/control plane only; desktop = heavy runner (MiMo, research, coding, heavy tests).
  • Cleanup as explicit child — RP11 safe retirement of superseded ResearchProcess attempts; old authorities must not be able to quietly run.

Canonical pipeline: ISSUE → INWARD → OUTWARD → APPLICABILITY → optional INNOVATION → ADVERSARIAL → SYNTHESIS → QUALIFY → PROCEED/REFINE → IMPLEMENT → VERIFY.

Historical RSC status (superseded, preserved for evidence)

IMPLEMENTED (deterministic tests proven)

  • RSC0: Red reproduction recorded (foreground slept 300s×N while child mimo was productive)
  • RSC1: ResearchTaskTree — canonical state, persisted, round synced on load
  • RSC2: Dynamic stage prompt compiler — 8 templates, process capsule included
  • RSC3: Bounded one-stage MiMo executor — one invocation per stage
  • RSC4: Structured artifact generation — receipt + URLs + paths + disposition
  • RSC5: OUTWARD router — academic/software/web classification
  • RSC6: INNOVATION/SYNTHESIS causality — derived_from required, anti-decorative-research
  • RSC7: MORE_RESEARCH targeted branching — tree transitions to minimal stage set

INTEGRATION PROVEN (deterministic)

  • 15 pipeline tests green (8-stage chain, MORE_RESEARCH targeted branch, cross-workspace persistence, evidence handoff, retry)
  • Fake-MiMo harness runs in <1 second (replaces 20-minute real MiMo for plumbing bugs)

ACCEPTANCE PENDING

  • RSC8: TUI live observability — ResearchStatusLabel added, needs real MiMo event streaming proof
  • RSC9: Unattended e2e acceptance — dispatch ready, tree persistence to master implemented, awaiting clean run

BLOCKED

  • #258 State Awareness — BLOCKED by this P0
  • #259 Scaffolding — BLOCKED by this P0 and State Awareness

KNOWN LIMITATIONS

  • Task tree persistence via master contents API is TEMPORARY_RESEARCH_STATE_BACKEND
  • Evidence-gate regex tuning: agent prose must match gate regexes (iterative)
  • No dedicated search MCP — DDG HTML is fallback
  • p1_03 test-order pollution under Python 3.14 (fixed, but monitor)
## Research Runtime P0 — SUPERSEDED DESIGN NOTICE (2026-09-08) The RSC0–RSC9 stage design is **superseded by the canonical Research-to-Build Pipeline** (handoff 2026-09-08). This epic remains the single parent for research-runtime work; its child DAG is being amended to RP0–RP14. Key design changes: - **Gitea issue replaces DEFINE** — the issue is the authoritative statement of intent; no cognitive DEFINE stage. - **Unified OUTWARD** — one natural MiMo research task; OUTWARD_DISCOVERY/OUTWARD_READING split is retired. - **Gitea owns stage eligibility** — Rune executes exactly one authorized stage per StageReady event; no self-walking loops. - **Runner placement enforced** — Pi = Gitea/storage/control plane only; desktop = heavy runner (MiMo, research, coding, heavy tests). - **Cleanup as explicit child** — RP11 safe retirement of superseded ResearchProcess attempts; old authorities must not be able to quietly run. Canonical pipeline: ISSUE → INWARD → OUTWARD → APPLICABILITY → optional INNOVATION → ADVERSARIAL → SYNTHESIS → QUALIFY → PROCEED/REFINE → IMPLEMENT → VERIFY. --- ## Historical RSC status (superseded, preserved for evidence) ### IMPLEMENTED (deterministic tests proven) - RSC0: Red reproduction recorded (foreground slept 300s×N while child mimo was productive) - RSC1: ResearchTaskTree — canonical state, persisted, round synced on load - RSC2: Dynamic stage prompt compiler — 8 templates, process capsule included - RSC3: Bounded one-stage MiMo executor — one invocation per stage - RSC4: Structured artifact generation — receipt + URLs + paths + disposition - RSC5: OUTWARD router — academic/software/web classification - RSC6: INNOVATION/SYNTHESIS causality — derived_from required, anti-decorative-research - RSC7: MORE_RESEARCH targeted branching — tree transitions to minimal stage set ### INTEGRATION PROVEN (deterministic) - 15 pipeline tests green (8-stage chain, MORE_RESEARCH targeted branch, cross-workspace persistence, evidence handoff, retry) - Fake-MiMo harness runs in <1 second (replaces 20-minute real MiMo for plumbing bugs) ### ACCEPTANCE PENDING - RSC8: TUI live observability — ResearchStatusLabel added, needs real MiMo event streaming proof - RSC9: Unattended e2e acceptance — dispatch ready, tree persistence to master implemented, awaiting clean run ### BLOCKED - #258 State Awareness — BLOCKED by this P0 - #259 Scaffolding — BLOCKED by this P0 and State Awareness ### KNOWN LIMITATIONS - Task tree persistence via master contents API is TEMPORARY_RESEARCH_STATE_BACKEND - Evidence-gate regex tuning: agent prose must match gate regexes (iterative) - No dedicated search MCP — DDG HTML is fallback - p1_03 test-order pollution under Python 3.14 (fixed, but monitor)
gitea-actions Bot commented 2026-09-08 14:55:15 +01:00
Copy link
Copy source

⚠️ Priority gate: this issue has no priority. Assign exactly one of P0 — critical (spine/correctness/blocks), P1 — high (material value or real defect), P2 — medium (quality/consolidation), P3 — low (measurement/deferred). An issue without a priority is not filed.

⚠️ **Priority gate:** this issue has no priority. Assign exactly one of **P0 — critical** (spine/correctness/blocks), **P1 — high** (material value or real defect), **P2 — medium** (quality/consolidation), **P3 — low** (measurement/deferred). An issue without a priority is not filed.
gitea-actions Bot commented 2026-09-08 18:25:00 +01:00
Copy link
Copy source

⚠️ Priority gate: this issue has no priority. Assign exactly one of P0 — critical (spine/correctness/blocks), P1 — high (material value or real defect), P2 — medium (quality/consolidation), P3 — low (measurement/deferred). An issue without a priority is not filed.

⚠️ **Priority gate:** this issue has no priority. Assign exactly one of **P0 — critical** (spine/correctness/blocks), **P1 — high** (material value or real defect), **P2 — medium** (quality/consolidation), **P3 — low** (measurement/deferred). An issue without a priority is not filed.
gitea-actions Bot added the bugcustodianinfrastructureperception labels 2026-09-08 18:25:05 +01:00
conductor commented 2026-09-08 21:21:29 +01:00
Author
Owner
Copy link
Copy source

R1-R2 IMPLEMENTED — DETERMINISTIC DEFINE/INWARD PROVEN

DEFINE: <1s deterministic. INWARD context: 0.03s deterministic. MiMo only for bounded inspection.

METHODOLOGY STAGE ≠ MANDATORY LLM CALL.

**R1-R2 IMPLEMENTED — DETERMINISTIC DEFINE/INWARD PROVEN** DEFINE: <1s deterministic. INWARD context: 0.03s deterministic. MiMo only for bounded inspection. METHODOLOGY STAGE ≠ MANDATORY LLM CALL.
gitea-actions Bot commented 2026-09-08 23:35:28 +01:00
Copy link
Copy source

⚠️ Priority gate: this issue has no priority. Assign exactly one of P0 — critical (spine/correctness/blocks), P1 — high (material value or real defect), P2 — medium (quality/consolidation), P3 — low (measurement/deferred). An issue without a priority is not filed.

⚠️ **Priority gate:** this issue has no priority. Assign exactly one of **P0 — critical** (spine/correctness/blocks), **P1 — high** (material value or real defect), **P2 — medium** (quality/consolidation), **P3 — low** (measurement/deferred). An issue without a priority is not filed.
conductor commented 2026-09-08 23:37:37 +01:00
Author
Owner
Copy link
Copy source

DAG amended 2026-09-08: children #264–#277 (RP1–RP14) created under this epic. RP0 executed: issue #263 superseded+closed with evidence-preservation note; research-pending trigger labels removed from #245/#254/#255/#256/#260/#261/#262. Obsolete OUTWARD run research-263-r1 stopped; evidence preserved at /mnt/workdrive/research-stage/research/issue-263/.

DAG amended 2026-09-08: children #264–#277 (RP1–RP14) created under this epic. RP0 executed: issue #263 superseded+closed with evidence-preservation note; research-pending trigger labels removed from #245/#254/#255/#256/#260/#261/#262. Obsolete OUTWARD run research-263-r1 stopped; evidence preserved at /mnt/workdrive/research-stage/research/issue-263/.
conductor commented 2026-09-09 01:03:37 +01:00
Author
Owner
Copy link
Copy source

Epic amended per pipeline correction 2026-09-09 (a553fb1, no duplicate issues):

  • #269 ADVERSARIAL: disposition contract + targeted refinement routes recorded
  • #270 SYNTHESIS: readiness invariant (survivor required before READY)
  • #271 QUALIFY: narrowed to implementation-readiness + exceptional reopen
  • DAG edges now encode: ADVERSARIAL survivor→SYNTHESIS; evidence-deficiency→OUTWARD→APPLICABILITY→(INNOVATION)→ADVERSARIAL; applicability-deficiency→APPLICABILITY→ADVERSARIAL; innovation-warranted→INNOVATION→ADVERSARIAL; QUALIFY synthesis-deficiency→SYNTHESIS→QUALIFY
  • No generic MORE_RESEARCH stage created
  • #161 current transition: disposition SURVIVES_WITH_MITIGATIONS → #270 SYNTHESIS READY (no OUTWARD rerun — defects were implementation hazards with viable mitigations)
**Epic amended per pipeline correction 2026-09-09** (a553fb1, no duplicate issues): - #269 ADVERSARIAL: disposition contract + targeted refinement routes recorded - #270 SYNTHESIS: readiness invariant (survivor required before READY) - #271 QUALIFY: narrowed to implementation-readiness + exceptional reopen - DAG edges now encode: ADVERSARIAL survivor→SYNTHESIS; evidence-deficiency→OUTWARD→APPLICABILITY→(INNOVATION)→ADVERSARIAL; applicability-deficiency→APPLICABILITY→ADVERSARIAL; innovation-warranted→INNOVATION→ADVERSARIAL; QUALIFY synthesis-deficiency→SYNTHESIS→QUALIFY - No generic MORE_RESEARCH stage created - #161 current transition: disposition SURVIVES_WITH_MITIGATIONS → #270 SYNTHESIS READY (no OUTWARD rerun — defects were implementation hazards with viable mitigations)
conductor commented 2026-09-09 14:05:22 +01:00
Author
Owner
Copy link
Copy source

RP0–RP14 COMPLETE — pipeline PROVISIONALLY_RATIFIED 2026-09-09. All children #264–#277 closed with evidence. Two real issues (#161, #163) traversed the full canonical path; #161 implemented and merged (v0.56.0). Ratification report amended (~/Desktop/RUNE_RESEARCHPROCESS_RATIFICATION_REPORT.md). Known limitations + follow-ups (#282 ledger, timing persistence, Gitea merge-API repair) recorded in the report, separated from ratification.

**RP0–RP14 COMPLETE — pipeline PROVISIONALLY_RATIFIED 2026-09-09.** All children #264–#277 closed with evidence. Two real issues (#161, #163) traversed the full canonical path; #161 implemented and merged (v0.56.0). Ratification report amended (~/Desktop/RUNE_RESEARCHPROCESS_RATIFICATION_REPORT.md). Known limitations + follow-ups (#282 ledger, timing persistence, Gitea merge-API repair) recorded in the report, separated from ratification.
conductor commented 2026-09-09 14:22:21 +01:00
Author
Owner
Copy link
Copy source

CLOSED as completed historical evidence — RP0–RP14 all executed and ratified (PROVISIONALLY_RATIFIED 2026-09-09). Successor epic: #284 (Adaptive Development Pipeline + Ratification Limitation Closure). This epic is preserved as canonical evidence of the research pipeline that was proven; it is not reopened.

**CLOSED as completed historical evidence** — RP0–RP14 all executed and ratified (PROVISIONALLY_RATIFIED 2026-09-09). Successor epic: #284 (Adaptive Development Pipeline + Ratification Limitation Closure). This epic is preserved as canonical evidence of the research pipeline that was proven; it is not reopened.
Sign in to join this conversation.
No Branch/Tag Specified
Labels
Clear labels
P0 — critical
Spine/core correctness or blocks other work — do first
 P1 — high
Material user value or real defect (money, bugs, next-stage dep)
 P2 — medium
Quality/consolidation improvement
 P3 — low
Measurement / benchmark / deferred policy
 blocked
Dependencies open
 bug
Confirmed defect or regression
 custodian
epic
Rune v1 course-correction issue graph
 feature
New capability or improvement
 governance
growth
identity
in-progress
Currently being worked on by Rune
 incomplete
Incomplete work — draft PR with ledger, awaiting resume
 infrastructure
life
memory
memory-atlas
Memory Research Atlas child domain
 needs-testing
Needs manual testing with dumbed-down steps before close
 perception
ready
Order satisfied - Rune may start
 release-drift
research
Research jobs — spikes, watchlists, evidence work
 rune
rune
 scaffolding
scaffolding
 spine,correction
spine,correction
 spine,deferred
spine,deferred
 spine,resolved
spine,resolved
 strangler,burn,endgame,deferred
strangler,burn,endgame,deferred
 strangler,burn,endgame,inventory,epic
strangler,burn,endgame,inventory,epic
 tui
tui
 tui,epic
tui,epic
 tui,openspec
tui,openspec
 v1-course-correction
Rune v1 course-correction issue graph
No labels bug custodian infrastructure perception
Milestone
No items
No Milestone
Projects
Clear projects
No projects
Assignees
Clear assignees
conductor
No Assignees
2 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: conductor/rune#257