|
2 | 2 | {"id":"why-1hf","title":"temp parent blocked repro epic","status":"closed","priority":4,"issue_type":"epic","created_at":"2026-03-11T11:45:10.437063092Z","created_by":"quangdang","updated_at":"2026-03-15T05:16:45.241188248Z","closed_at":"2026-03-15T05:16:45.241145491Z","close_reason":"Temporary repro epic no longer needed","source_repo":".","compaction_level":0,"original_size":0,"dependencies":[{"issue_id":"why-1hf","depends_on_id":"why-sca","type":"blocks","created_at":"2026-03-11T11:45:25.488093790Z","created_by":"quangdang","metadata":"{}","thread_id":""}]} |
3 | 3 | {"id":"why-25o","title":"Add representative large-history benchmark fixtures for cold-path validation","description":"Create benchmark-oriented fixture repos and/or generators that approximate the performance targets described in PLAN.md section 11, including larger commit histories (for example ~1000-commit archaeology fixtures) and scanner-scalability scenarios. Use them to validate cold-cache latency and repo-wide scan targets rather than only tiny correctness fixtures with 2-3 commits.","status":"closed","priority":2,"issue_type":"task","created_at":"2026-03-13T17:24:39.937829749Z","created_by":"quangdang","updated_at":"2026-03-13T17:49:15.675418813Z","closed_at":"2026-03-13T17:49:15.675022349Z","close_reason":"Added benchmark-only fixture scaling and fixed archaeology benchmark target wiring","source_repo":".","compaction_level":0,"original_size":0} |
4 | 4 | {"id":"why-29z","title":"Benchmark coupling and outage performance","status":"closed","priority":3,"issue_type":"task","created_at":"2026-03-31T15:04:47.074853587Z","created_by":"quangdang","updated_at":"2026-03-31T15:12:53.200972486Z","closed_at":"2026-03-31T15:12:53.200930041Z","close_reason":"Completed","source_repo":".","compaction_level":0,"original_size":0} |
5 | | -{"id":"why-2ky","title":"Adopt Claude Code investigation-runtime patterns in why","description":"Adopt Claude Code's strongest multi-surface investigation patterns in why: shared question-engine ownership, markdown-defined investigation workflows, and bounded result/policy handling for expensive git + LLM operations.","design":"Keep this epic focused on multi-surface investigation quality: a shared question engine, named investigation workflows, and bounded policy-aware handling for expensive git plus model operations.","acceptance_criteria":"Child beads cover engine extraction, workflow loading, and bounded or policy-aware output behavior. The epic stays tightly tied to history-investigation use cases.","notes":"Copy the runtime discipline, not the product-specific surface area.","status":"open","priority":1,"issue_type":"epic","created_at":"2026-03-31T16:34:21.250561562Z","created_by":"Codex","updated_at":"2026-03-31T16:42:07.575816255Z","source_repo":".","compaction_level":0,"original_size":0,"labels":["architecture","claude-code-port","investigation"]} |
| 5 | +{"id":"why-2ky","title":"Adopt Claude Code investigation-runtime patterns in why","description":"Adopt Claude Code's strongest multi-surface investigation patterns in why: shared question-engine ownership, markdown-defined investigation workflows, and bounded result/policy handling for expensive git + LLM operations.","design":"Keep this epic focused on multi-surface investigation quality: a shared question engine, named investigation workflows, and bounded policy-aware handling for expensive git plus model operations.","acceptance_criteria":"Child beads cover engine extraction, workflow loading, and bounded or policy-aware output behavior. The epic stays tightly tied to history-investigation use cases.","notes":"Copy the runtime discipline, not the product-specific surface area.","status":"closed","priority":1,"issue_type":"epic","created_at":"2026-03-31T16:34:21.250561562Z","created_by":"Codex","updated_at":"2026-04-01T07:02:52.068663122Z","closed_at":"2026-04-01T07:02:52.068629522Z","close_reason":"Completed shared question engine extraction, bounded policy gating, and markdown workflow loading surfaces for why.","source_repo":".","compaction_level":0,"original_size":0,"labels":["architecture","claude-code-port","investigation"]} |
6 | 6 | {"id":"why-2ky.1","title":"Extract a shared question engine for why","description":"Extract a shared why question engine that owns history-target normalization, evidence gathering, prompt assembly, model invocation, and result shaping so CLI and future MCP/web surfaces share one investigative core.","design":"Extract a shared question engine that owns target normalization, git evidence collection policy, prompt assembly, model invocation, and bounded result shaping so CLI and future MCP or web surfaces share one investigative core.","acceptance_criteria":"At least two why-facing surfaces can share the question engine boundary, or the engine is clearly transport-neutral and covered by tests. Evidence and result shaping no longer live only in the CLI path. Tests cover engine behavior directly.","notes":"This bead is high leverage because the product thesis already separates evidence gathering from presentation.","status":"closed","priority":1,"issue_type":"task","created_at":"2026-03-31T16:34:21.928038332Z","created_by":"Codex","updated_at":"2026-04-01T06:22:19.556317528Z","closed_at":"2026-04-01T06:22:19.556153427Z","close_reason":"Extracted why-question-engine for shared target normalization, archaeology, evidence, and report synthesis; rewired CLI default query and LSP hover to consume the shared engine with direct tests.","source_repo":".","compaction_level":0,"original_size":0,"labels":["architecture","claude-code-port","provider-runtime"],"dependencies":[{"issue_id":"why-2ky.1","depends_on_id":"why-2ky","type":"parent-child","created_at":"2026-03-31T16:34:21.928038332Z","created_by":"Codex","metadata":"{}","thread_id":""}]} |
7 | 7 | {"id":"why-2ky.2","title":"Load markdown-defined investigation workflows in why","description":"Load markdown-defined investigation workflows for common why jobs such as root-cause archaeology, design-intent lookup, regression context gathering, and blame-to-commit narrative assembly.","design":"Load markdown-defined investigation workflows for jobs like root-cause archaeology, design-intent lookup, regression context gathering, and blame-to-commit narrative assembly so agents can call named investigation recipes instead of improvising every prompt.","acceptance_criteria":"Why can discover and load investigation workflows from markdown on disk. At least one named workflow is usable by an agent client or local scripted flow. Parsing, loading, and reload behavior are tested.","notes":"Package investigative intent rather than hardcoding prompt strings inside Rust match arms.","status":"closed","priority":2,"issue_type":"task","created_at":"2026-03-31T16:34:22.519107188Z","created_by":"Codex","updated_at":"2026-04-01T06:43:21.014208166Z","closed_at":"2026-04-01T06:43:21.013754766Z","close_reason":"Added markdown workflow files, a dedicated loader crate with reload tests, and MCP list/get workflow tools so agents can consume named why investigation recipes from disk.","source_repo":".","compaction_level":0,"original_size":0,"labels":["agent-integration","claude-code-port","workflow"],"dependencies":[{"issue_id":"why-2ky.2","depends_on_id":"why-2ky","type":"parent-child","created_at":"2026-03-31T16:34:22.519107188Z","created_by":"Codex","metadata":"{}","thread_id":""},{"issue_id":"why-2ky.2","depends_on_id":"why-2ky.1","type":"blocks","created_at":"2026-03-31T16:34:23.070264679Z","created_by":"quangdang","metadata":"{}","thread_id":""}]} |
8 | 8 | {"id":"why-2ky.3","title":"Add bounded evidence budgeting and policy gating in why","description":"Add bounded result budgeting, provider-aware policy checks, and operator-readable gate reasons for expensive why operations so deep git walks, large evidence sets, and costly model calls are explicit and controllable.","design":"Add bounded evidence budgeting, provider-aware policy checks, and operator-readable gate reasons for expensive why operations so deep git walks, large evidence sets, and costly model calls are explicit and controllable.","acceptance_criteria":"Why exposes bounded output and evidence policies for expensive investigations. Gate or truncation reasons appear in structured output or diagnostics. Tests cover representative budgeted and gated scenarios.","notes":"This bead should make why safer for agent automation and long-running usage, not merely stricter for humans.","status":"closed","priority":1,"issue_type":"task","created_at":"2026-03-31T16:34:23.694266474Z","created_by":"Codex","updated_at":"2026-04-01T06:36:06.543249511Z","closed_at":"2026-04-01T06:36:06.542516911Z","close_reason":"Added bounded evidence commit budgets, provider-aware LLM gating, and structured policy/truncation reasons surfaced through why reports and shared question-engine tests.","source_repo":".","compaction_level":0,"original_size":0,"labels":["budgeting","claude-code-port","policy"],"dependencies":[{"issue_id":"why-2ky.3","depends_on_id":"why-2ky","type":"parent-child","created_at":"2026-03-31T16:34:23.694266474Z","created_by":"Codex","metadata":"{}","thread_id":""},{"issue_id":"why-2ky.3","depends_on_id":"why-2ky.1","type":"blocks","created_at":"2026-03-31T16:34:24.310467531Z","created_by":"quangdang","metadata":"{}","thread_id":""}]} |
|
0 commit comments