v0.7.2: self-help (/why) + CONFIG injection — TDD

- CONFIG section in system prompt: providers, context window, gate count,
  rules learned, docs path
- /why TUI command: shows most recent gate trace from message history
- assemble-config-section reads live state at each think() call
- Core: 75/76  TUI Main: 77/78 (1 pre-existing RCE test flake)

docs/ROADMAP.org

@@ -1273,7 +1273,8 @@ Gate trace data format (already in messages): ~(:gate-trace ((:gate "dispatcher-
 - Send structured approval/denial message to daemon: ~(:type :event :payload (:action :hitl-respond :token "HITL-abcd" :decision :approved))~
 - Render HITL prompts as styled inline panels with colored border (permission theme color), showing the action, explanation, and available choices ("Allow (Enter)" / "Deny (Esc)")
 - After approval/denial, collapse the prompt panel and add a system message: "✓ Approved: shell command" or "✗ Denied: shell command"
-~40 lines.
+- Clarifying-question escalation: when the same action has been blocked twice and retried (2 rejections in the 3-retry loop), the third attempt injects a /clarify prompt with targeted discriminating options instead of a generic rejection. Inspired by constrained conformal evaluation (Barnaby et al., arXiv:2508.15750v1): "This command touches ~/memex/ and /etc/. Is the /etc/ path intended? [1] Intended [2] Accidental [3] Cancel." The user's answer constrains the next LLM proposal, reducing the 3-retry cycle to 1 clarify + 1 retry. ~1.1x token multiplier vs current ~1.39x.
+~60 lines.
 
 *** TODO Message search (/search or Ctrl+F)
 :PROPERTIES:
@@ -2006,6 +2007,19 @@ Telemetry data (v0.9.0) plus the agent's self-knowledge enables coaching: the ag
 - Coaching data sources: command frequency, HITL approval patterns, context usage history, feature adoption rate, telemetry aggregates
 - Coaching is opt-in (privacy-respecting — no data leaves the machine). ~50 lines in telemetry skill + ~30 lines TUI rendering.
 
+*** TODO Failure attribution — tag task failures with probable component
+:PROPERTIES:
+:ID:       id-v090-failure-attribution
+:CREATED:  [2026-05-08 Fri]
+:END:
+
+AHE (arXiv:2604.25850v2) shows that evolution loops work when failures are attributed to specific harness components, not just "the task failed." Passepartout's telemetry records task outcomes but doesn't classify failures by root cause.
+
+- In telemetry skill: when a session ends with a task failure (agent couldn't complete, user interrupted with denial, or dispatcher blocked irrecoverably), the telemeter classifies the failure as one of: ~:tool-failure~ (tool timeout, tool error), ~:gate-overblock~ (dispatcher blocked a necessary command), ~:gate-underblock~ (dispatcher allowed a harmful command), ~:reasoning-error~ (LLM produced a wrong answer), ~:context-overflow~ (context budget exhausted), ~:timeout~ (session timeout)
+- Classification is deterministic: if last action was blocked by dispatcher → gate-overblock. If last action was a tool error → tool-failure. If last action was a successful tool call but wrong output → reasoning-error.
+- Feeds the Skill Creator (v0.11.0) — the agent knows *which* component to fix, not just *that* something went wrong
+~20 lines in telemetry skill.
+
 ** v0.10.0: Tool Ecosystem (MCP-Native) + Voice Gateway
 
 *(Renumbered from old v0.8.0.)*
@@ -2171,6 +2185,23 @@ The voice gateway (v0.10.3) adds parity with OpenClaw's voice features without a
 - Required ~:repl-verified~ flag on all ~defun~ forms — the existing Dispatcher lint check warns on writes without verification. The Skill Creator enforces this at creation time.
 - Skills are the primary extension mechanism for users. The Skill Creator makes skill authoring accessible to non-Lisp-programmers: describe what you want in English, the LLM drafts the Org file, the system verifies it, and the skill is live.
 
+*** TODO Change manifest — skills ship with falsifiable predictions
+:PROPERTIES:
+:ID:       id-v110-change-manifest
+:CREATED:  [2026-05-08 Fri]
+:END:
+
+AHE (arXiv:2604.25850v2) shows that harness edits work better when each edit ships with a self-declared prediction, verified by next-round outcomes. Passepartout's Skill Creator should do the same — every new or modified skill carries predictions that telemetry verifies.
+
+- When the Skill Creator generates a skill, it also generates a ~#+PREDICTION:~ block in the Org frontmatter:
+  - ~#+PREDICTION: reduces token usage by 15% for code-generation tasks~
+  - ~#+PREDICTION: may increase HITL prompts for shell commands outside workspace~
+  - ~#+PREDICTION: should improve success rate on refactoring tasks~
+- Over the next 10 sessions, telemetry compares actual outcomes against predictions. The verification result is appended to the skill file: ~#+VERIFIED: Y token change: -18% (predicted -15%) on 2026-06-01~
+- Disproven predictions flag the skill for review: ~#+DISPROVEN: token usage increased +3% on code tasks (predicted -15%). Skill scheduled for revision.~
+- The change manifest persists in the skill's Org file — every skill carries its own evidence ledger. Users can see which skills worked as predicted and which didn't.
+~40 lines in Skill Creator + telemetry integration.
+
 *** Competitive Advantage Analysis — v0.11.0 Summary
 
 The task tree DAG with terminal states and branch pruning is Passepartout's planning primitive — analogous to Claude Code's TODO list but structural (Org headlines with parent-child relationships) rather than flat.