feat: consolidate TraceDecay V2 PR8-PR13 delivery

.cargo/config.toml

@@ -27,12 +27,11 @@ TRACEDECAY_DISABLE_GLOBAL_DB = { value = "1", force = false }
 # in-process. Installed binaries run outside cargo and are unaffected, but the
 # profile does apply to `cargo run` — use the installed binary (or set
 # TRACEDECAY_DATA_DIR yourself) for real `daemon install-service` runs.
-# Enforced by tests/test_profile_isolation_test.rs.
+# Enforced by tests/core_cli_suite/test_profile_isolation_test.rs.
 TRACEDECAY_DATA_DIR = { value = "target/test-profile/.tracedecay", force = false, relative = true }
 
 [alias]
 # Local default for the full Rust test suite. Requires cargo-nextest:
 # https://nexte.st/docs/installation/pre-built-binaries/
-test-all = "nextest run --workspace --no-fail-fast"
-test-ci = "nextest run --workspace --no-fail-fast"
-dogfood = "run --quiet --release --bin tracedecay -- dogfood"
+test-all = "nextest run --workspace --all-features --no-fail-fast"
+test-ci = "nextest run --workspace --all-features --no-fail-fast"

.claude/skills/automation-run-review/.tracedecay-materialization.json

@@ -1,8 +1,8 @@
 {
   "files": {
-    "SKILL.md": "sha256:ce428b37c4067c28a8bfa803e31e5647f023aa6996be5997e065b6e9d75c1ebb"
+    "SKILL.md": "sha256:72250a902f26620d2bb6c5aea1a1ae198aba382f061ae365d58cea71416d3d78"
   },
   "managed_by": "tracedecay-automation",
-  "package_hash": "sha256:070f5045d0af6f415c30166b75ecc0b3f4b2c9aaf61a23eaf8bb42a6900a390e",
+  "package_hash": "sha256:62c256a24e756b8b9270ed092477e24daa7d80aa721328de3d7749b8c232aa9d",
   "skill_id": "automation-run-review"
 }

.claude/skills/automation-run-review/SKILL.md

@@ -1,10 +1,25 @@
 ---
 name: automation-run-review
-description: "Use when Review self-improvement automation runs and activation policy."
+description: "Use when reviewing self-improvement automation run status, validation evidence, automatic skill activation, or memory-curation outcomes."
 managed-by: tracedecay-automation
 skill-id: "automation-run-review"
-content-hash: sha256:070f5045d0af6f415c30166b75ecc0b3f4b2c9aaf61a23eaf8bb42a6900a390e
+content-hash: sha256:62c256a24e756b8b9270ed092477e24daa7d80aa721328de3d7749b8c232aa9d
 skill-version: 1783629450
 ---
 
-Check the run ledger, activation policy, and approval state before applying changes.
+# Automation run review
+
+Review automation without mutating it:
+
+1. Use `tracedecay_automation_run_list` to find the exact run id.
+2. Use `tracedecay_automation_run_view` to inspect terminal status, counts,
+   validation report, effects, and advertised artifact kinds.
+3. Use `tracedecay_automation_run_artifact_view` only for an artifact kind
+   advertised by that run; verify the returned hash-backed payload against the
+   terminal record.
+4. For skill-writer runs, verify automatic validation, activation, and
+   materialization against `tracedecay_skill_list` and
+   `tracedecay_skill_view`. For memory-curator runs, verify committed effects
+   with read-only fact queries.
+5. Report failures after committed effects as reconciliation work. Never rerun
+   blindly or manufacture a manual settlement step.

.claude/skills/evaluating-hook-hints/SKILL.md

@@ -9,7 +9,7 @@ Use this skill for TraceDecay repo development only. These are repo-local dev in
 
 ## Workflow
 
-1. Start with TraceDecay context for `src/hooks/tool_hints.rs`, `src/hooks/tool_hints/classifiers.rs`, `src/hooks/tool_hints/evals.rs`, host adapters in `src/hooks/{codex,claude,cursor}.rs`, and recent transcript evidence.
+1. Start with TraceDecay context for `src/hooks/tool_hints.rs`, `src/hooks/tool_hints/classifiers.rs`, the `src/hooks/tool_hints/evals/` module (`mod.rs` plus `host_cases.rs`), host adapters in `src/hooks/{codex,claude,cursor}.rs`, and recent transcript evidence.
 2. Render model-visible hook input when judging verbosity:
    `scripts/render-codex-hook-inputs.py --glob '/home/zack/.codex/sessions/**/*.jsonl' --all --limit 5 --max-chars 800`.
 3. Run deterministic evals before behavior edits:
@@ -22,7 +22,7 @@ Use this skill for TraceDecay repo development only. These are repo-local dev in
 ## Acceptance Rules
 
 - Hints should be contextual and short; avoid generic TraceDecay availability boilerplate.
-- Real-world transcript cases and synthetic cases should both be represented in `src/hooks/tool_hints/evals.rs`.
+- Real-world transcript cases and synthetic cases should both be represented in `src/hooks/tool_hints/evals/` (`host_cases.rs` holds the per-host scenarios). The module is `#[cfg(test)]`, so it only compiles under a test profile.
 - A normal user prompt should not be wrapped into a noisy `UserPromptSubmit hook (completed)` model-visible user message.
 - No hint is a valid outcome when the request does not need TraceDecay guidance.
 - Repeated native behavior should get at most one initial hint plus one later escalation per category, bounded by the session budget.

.claude/skills/inspecting-automation-cycles/SKILL.md

@@ -1,6 +1,6 @@
 ---
 name: inspecting-automation-cycles
-description: 'TraceDecay Dev: Use when auditing TraceDecay automation loops, skipped runs, memory-curator/session-reflector/skill-writer output, apply policy, or run artifacts.'
+description: 'TraceDecay Dev: Use when auditing TraceDecay automation loops, skipped runs, memory-curator/session-reflector/skill-writer output, terminal receipts, or run artifacts.'
 ---
 
 # TraceDecay Dev: Inspecting Automation Cycles
@@ -12,16 +12,28 @@ analytics prove whether generated output was adopted.
 ## Workflow
 
 1. Start with `tracedecay automation config get` to identify enabled tasks,
-   schedules, locks, profile paths, and apply policy.
-2. List recent runs with `tracedecay automation runs list --limit 100`; group
+   schedules, locks, and profile paths.
+2. When the operator requests an immediate memory-curation cycle, use the sole
+   public semantic launcher, `fact_store_curate`, through its MCP adapter
+   `tracedecay_fact_store_curate`, generic CLI adapter `tracedecay tool
+   fact_store_curate`, or HTTP adapter `POST
+   /api/application/retained/fact_store_curate`. Its request accepts only the
+   optional `fact_review_limit` and `min_confidence_millionths` bounds. Each
+   adapter invokes the same daemon-owned operation; the daemon derives run
+   identity, task selection, operations, validation, policy, and effect
+   settlement.
+3. List recent runs with `tracedecay automation runs list --limit 100`; group
    by task and status before opening individual artifacts.
-3. For failures or suspicious skips, open the relevant artifact with
-   `tracedecay_automation_run_artifact_view` or
-   `tracedecay tool automation_run_artifact_view --args ...`.
-4. Inspect model-managed memory outcomes plus configured managed-skill review
-   queues: `tracedecay automation facts list`, dashboard telemetry, and
-   `tracedecay_skill_list --state pending`.
-5. Check adoption evidence: `tracedecay analytics diagnostics --all --no-sync`,
+4. Inspect one exact run with `tracedecay automation runs view <run_id>`.
+   Read its verified artifacts with
+   `tracedecay automation runs artifact <run_id> <kind> --json`,
+   `GET /api/automation/runs/<run_id>/artifacts/<kind>`, or the read-only MCP
+   tool `tracedecay_automation_run_artifact_view`. MCP automation analytics
+   summarizes run history; exact MCP run list/view is not currently exposed.
+5. Inspect terminal memory outcomes plus active managed-skill adoption:
+   `tracedecay automation facts list`, dashboard telemetry, and
+   `tracedecay_skill_list --state active`.
+6. Check adoption evidence: `tracedecay analytics diagnostics --all --no-sync`,
    `tracedecay sessions search "mcp__tracedecay" --provider all`, and managed
    skill usage counts.
 
@@ -32,15 +44,16 @@ analytics prove whether generated output was adopted.
 | `scheduler_interval_not_elapsed` | Healthy throttling | Count only, do not fix. |
 | `scheduler_lock_active` | Another run owns the loop | Check age before calling stale. |
 | `no_new_session_activity` | Nothing new to process | Verify transcript ingest if surprising. |
-| `validation_gate` artifact | Mutation passed validation | Inspect apply-policy state or dashboard artifact. |
-| Many fact proposal records | Inspect validation/apply telemetry | Use `tracedecay:project-memory`. |
+| `validation_gate` artifact | Mutation passed validation | Inspect terminal automatic application/deployment receipts. |
+| Many automatic fact receipts | Inspect applied/quarantined outcomes and telemetry | Use `tracedecay automation facts list`. |
 | Active managed skills with zero use | Adoption telemetry gap | Use `tracedecay:diagnosing-analytics`. |
 
 ## Guardrails
 
-- Prefer read-only inspection. Do not mutate fact records.
-- Do not approve, reject, delete, or apply managed-skill drafts unless the user
-  explicitly asked for mutation.
+- After any requested run, keep inspection read-only. Do not submit curator
+  operations or approve, reject, or apply its output.
+- Validated memory-curator and skill-writer output settles automatically;
+  inspect receipts rather than waiting for a manual gate.
 - Do not treat skipped runs as failures until grouped by skip reason and age.
 - Avoid parallel `tracedecay_skill_view` calls against one profile while
   automation may write usage ledgers. If a usage read reports a truncated JSON
@@ -50,6 +63,6 @@ analytics prove whether generated output was adopted.
 
 ## Deliverable
 
-Report task/status counts, the exact run or artifact ids inspected, apply-policy
-state, adoption gaps, and the next concrete command for any mutation the user
-should choose.
+Report the launcher adapter used, task/status counts, exact run or artifact ids,
+terminal automatic application/deployment receipts, read-only verification,
+and adoption gaps.

.claude/skills/introspecting-tracedecay-usage/SKILL.md

@@ -21,10 +21,11 @@ failure mode, then code, tests, or bundled skills encode the fix.
    `tracedecay:inspecting-managed-skills`. Start with
    `tracedecay_skill_list`; view skills or run artifacts only when the list
    points to a specific stale, patched, failed, or unused item.
-4. **Durable memory:** Use `tracedecay:project-memory`. Search with
-   `tracedecay_fact_store` before re-deriving project decisions. For curation,
-   run read-only inventory and dry-runs first; never remove facts without
-   explicit approval.
+4. **Durable memory:** Use `tracedecay:project-memory`. Recall prior decisions
+   with `tracedecay_fact_store_search`; record durable decisions and corrections
+   with `tracedecay_fact_store_add`. Delegate broad curation to
+   `tracedecay:project-memory` and inspect its automatic validation and
+   application receipts.
 5. **Code-health and implementation target:** Use `tracedecay:code-health`.
    Let weak dimensions and hotspots decide whether the fix is code, tests,
    docs, evals, or skill guidance.
@@ -38,8 +39,9 @@ failure mode, then code, tests, or bundled skills encode the fix.
   or add a bundled operator skill that prevents the repeated mistake.
 - LCM depth and compression ratios are health signals, not direct quality
   scores. Use raw/session recall to confirm what agents actually missed.
-- Memory curation candidates are proposals, not permission. Prefer merge or
-  update when provenance matters; deletion needs fresh user approval.
+- Memory curation is automation-owned after validation. Inspect validation and
+  applied operation receipts; use `tracedecay:project-memory` for any direct
+  operator override.
 - Analytics fields can be global. `project_id: null` means the run was global,
   not broken.
 

.claude/skills/tracedecay-dev-sweep/SKILL.md

@@ -38,8 +38,8 @@ sessions/run-ids, never conclusions without citations:
    failure modes, misfires, and workarounds from session logs and agent
    transcripts.
 3. **Automation loops** — invoke `inspecting-automation-cycles`. Skipped
-   runs, curator/reflector/skill-writer output quality, apply policy, run
-   artifacts.
+   runs, curator/reflector/skill-writer output quality, automatic validation
+   and activation, terminal records, and advertised run artifacts.
 4. **Hook hints** — invoke `evaluating-hook-hints` (quality, verbosity,
    dedupe, token efficiency, real transcript replays). For profile-managed
    depth, view `agent-hook-hint-quality-review` and
@@ -67,7 +67,8 @@ supported by a single uncited anecdote.
   `tracedecay_skill_view`) — fresh worktree per independent fix set, exact
   scoped edits for subagents, lead reviews diffs.
 - New or updated automation/profile skills: invoke
-  `writing-agent-managed-skills` for the draft→validate→approve loop.
+  `writing-agent-managed-skills` for automatic writer validation and activation,
+  followed by read-only run and adoption review.
 - Repo-local dev-skill updates: edit `.claude/skills/` and `.codex/skills/`
   together — the copies must not drift (host-specific `agents/` overlays are
   the only allowed asymmetry).
@@ -86,5 +87,5 @@ supported by a single uncited anecdote.
 
 Stop and report instead of pushing on when: the Phase 0 gate cannot be
 cleared, a lane's tooling is unavailable even via the `tracedecay` CLI
-fallback, or a proposed fix requires deleting user memory/facts (needs fresh
-explicit approval — never inside the sweep).
+fallback, or a proposed fix requires deleting user memory/facts without an
+exact user instruction naming the destructive intent and target.