docs(roadmap): add Jobdori pinpoints #392-398 (init/help/skills/subcommand-help/sandbox/mcp/doctor)

ROADMAP.md

@@ -6301,4 +6301,10 @@ Original filing (2026-04-18): the session emitted `SessionStart hook (completed)
 380. **Top-level `tokens --help --output-format json` hangs with zero stdout/stderr instead of returning bounded command help JSON** — dogfooded 2026-04-30 for the 02:30 nudge on current `origin/main` / rebuilt `./rust/target/debug/claw` with embedded `git_sha` `d95b230c`. After verifying #358 covered `cost --help`, a fresh adjacent probe on the token-budget surface showed the same silent failure class: repeated bounded runs of `timeout 8 ./rust/target/debug/claw tokens --help --output-format json` exited `124` with `stdout=0` and `stderr=0`. In the same rebuilt binary, `version --output-format json` returned promptly with version/build metadata, proving the binary itself and JSON output path are reachable. This is distinct from #358's cost help hang: the affected surface is the sibling `tokens` command help, which agents use before estimating prompt/session token budgets. **Required fix shape:** (a) make `tokens --help --output-format json` return static/bounded stdout JSON with `kind:"help"` or `kind:"tokens"`, `action:"help"`, usage, options, examples, supported output formats, and related slash/direct commands; (b) ensure help rendering does not initialize slow token accounting, session, or provider state; (c) if any dynamic provider is consulted, return a typed JSON timeout/unavailable error instead of hanging; (d) add regression coverage proving tokens help in JSON mode returns within a deterministic budget. **Why this matters:** token budgeting is a preflight clawability surface. If help hangs silently, automation cannot safely discover how to inspect or constrain token usage before running expensive prompts, and budget-aware wrappers stall at the discovery step. Source: gaebal-gajae dogfood follow-up for the 02:30 nudge on rebuilt `./rust/target/debug/claw` `d95b230c`.
 381. **Top-level `cache --help --output-format json` hangs with zero stdout/stderr instead of returning bounded command help JSON** — dogfooded 2026-04-30 for the 03:00 nudge on current `origin/main` / rebuilt `./rust/target/debug/claw` with embedded `git_sha` `d95b230c`. After #358 and #380 landed for the cost/tokens preflight help hangs, a fresh adjacent probe on the cache-control surface showed the same silent failure class: repeated bounded runs of `timeout --kill-after=1s 8s ./rust/target/debug/claw cache --help --output-format json` exited `124` with `stdout=0` and `stderr=0`. In the same rebuilt binary, `version --output-format json` returned promptly with version/build metadata, proving the binary itself and JSON output path are reachable. This is distinct from the separate `/cache` slash-command envelope mismatch class: the affected surface here is top-level `cache` command help, where agents need bounded local discovery before deciding whether to inspect, clear, or summarize cache state. **Required fix shape:** (a) make `cache --help --output-format json` return static/bounded stdout JSON with `kind:"help"` or `kind:"cache"`, `action:"help"`, usage, options, examples, supported output formats, and related slash/direct commands; (b) ensure help rendering does not initialize slow cache/session/provider state; (c) if any dynamic provider is consulted, return a typed JSON timeout/unavailable error instead of hanging; (d) add regression coverage proving cache help in JSON mode returns within a deterministic budget. **Why this matters:** cache inspection and cleanup are recovery/control-plane operations. If cache help hangs silently, claws cannot safely discover cache semantics before attempting cleanup, and automation stalls before it can choose a non-destructive cache action. Source: gaebal-gajae dogfood follow-up for the 03:00 nudge on rebuilt `./rust/target/debug/claw` `d95b230c`.
 
-400. **`status --output-format json` `workspace` has `session: "live-repl"` (non-null string) simultaneously with `session_id: null`, and `session_lifecycle.kind: "saved_only"` with `abandoned: true` — the session name and session ID are reported in contradictory states, and the lifecycle fields provide no `session_path` or `resume_command` to recover the abandoned session** — dogfooded 2026-04-30 by Jobdori on `e939777f`. Running `./claw --output-format json status` outside an active session returns `workspace.session: "live-repl"`, `workspace.session_id: null`, `workspace.session_lifecycle: {"abandoned":true,"kind":"saved_only","pane_command":null,"pane_id":null,"pane_path":null,"workspace_dirty":true}`. The `session` field implies an active named session, but `session_id: null` and `abandoned: true` indicate no active session; automation cannot tell from these fields alone whether a session is resumable, what file to pass to `--resume`, or whether the session name `"live-repl"` is a stable identifier. The `pane_command`/`pane_id`/`pane_path` fields are all null for abandoned sessions, providing no actionable recovery path. **Required fix shape:** (a) make `session` and `session_id` consistent — both null when no active session, both populated when active; (b) add `session_path` (path to the `.jsonl` file) and `resume_command` (full `claw --resume <path>` incantation) to the lifecycle fields when `kind:"saved_only"` so automation can recover without filesystem scraping; (c) add `workspace_dirty` explanation field (e.g., `dirty_reason: "uncommitted_changes"`); (d) add regression coverage proving the session name/ID pair is always consistent. Source: Jobdori live dogfood, `e939777f`, 2026-04-30.
+392. **`init --output-format json` artifact entries only have `name` and `status` fields; `status: "skipped"` artifacts include no `reason` explaining why they were skipped** — dogfooded 2026-04-30 by Jobdori on `74338dc6`. Automation cannot distinguish "already exists" from "permission denied" from "dry_run". **Required fix:** add `reason: "already_exists"|"permission_denied"|"dry_run"|"excluded_by_config"` to each artifact; add `existing_path` for `already_exists`; add regression coverage. Source: Jobdori live dogfood, `74338dc6`, 2026-04-30.
+393. **`help --output-format json` returns `{"kind":"help","message":"..."}` while `/help --output-format json` returns `{"kind":"help","text":"..."}` — the prose content field is named `message` in CLI subcommand form and `text` in slash-command form for the same `kind:"help"` response** — dogfooded 2026-04-30 by Jobdori on `52a909ce`. Automation must check `d.message || d.text`. **Required fix:** standardise on one field name; update SCHEMAS.md; add regression coverage. Source: Jobdori live dogfood, `52a909ce`, 2026-04-30.
+394. **`skills --output-format json` skill entries include no `path` field; `origin.detail_label` is `null` for all 147 skills; two skills have `description: ">"` — a single-character parsing artifact** — dogfooded 2026-04-30 by Jobdori on `52a909ce`. Skill entry keys: `['active','description','name','origin','shadowed_by','source']` — no `path`. **Required fix:** add `path` to each entry; populate `origin.detail_label`; sanitize stub descriptions; add regression coverage. Source: Jobdori live dogfood, `52a909ce`, 2026-04-30.
+395. **`version/doctor/sandbox/status --help` with `--output-format json` return plain-text instead of JSON; `agents/mcp --help` correctly return JSON — inconsistent `--help` JSON contract across subcommands** — dogfooded 2026-04-30 by Jobdori on `d95b230c`. **Required fix:** all subcommands must honour `--output-format json` for `--help`; add regression coverage. Source: Jobdori live dogfood, `d95b230c`, 2026-04-30.
+396. **`sandbox --output-format json` response omits `action` field; `agents/mcp` include `action:"list"` — inconsistent structural envelope; also `requested_namespace:true` + `supported:false` mismatch has no typed `degraded` field** — dogfooded 2026-04-30 by Jobdori on `d95b230c`. **Required fix:** add `action:"status"` to inspect-style commands; add `degraded: bool` + `degraded_reasons[]`; add regression coverage. Source: Jobdori live dogfood, `d95b230c`, 2026-04-30.
+397. **`mcp --output-format json` response has `summary: null` and no `count` field; `agents` has `summary: {active, shadowed, total}` and `count` — inconsistent list-command envelope; also `claw --output-format json mcp` emits unstructured `enabledPlugins is deprecated` warning to stderr** — dogfooded 2026-04-30 by Jobdori on `44cca205`. **Required fix:** add `count` + `summary` to `mcp` JSON; emit deprecation warnings as structured JSON when `--output-format json`; add regression coverage. Source: Jobdori live dogfood, `44cca205`, 2026-04-30.
+398. **`doctor --output-format json` `system` check includes `git_sha` of the compiled binary but does not compare it against repo HEAD, reports `status:"ok"` even when binary SHA ≠ HEAD; `default_model` is `null` when no auth configured but has no typed `reason` or `auth_required` flag** — dogfooded 2026-04-30 by Jobdori on `e939777f`. Binary SHA `5eb1d7d8` ≠ HEAD `e939777f`, yet `system.status:"ok"`. **Required fix:** add `head_sha`, `git_sha_matches_head: bool`, `stale: bool`; set `status:"warn"` on mismatch; add `model_unavailable_reason`/`auth_required` when model is null; add regression coverage. Source: Jobdori live dogfood, `e939777f`, 2026-04-30.