agentwrangler 0.1.1-next.bca85ea → 0.1.1-next.fbbbe7f

package/README.md

@@ -1,104 +1,184 @@
 <p align="center">
-  <img src="https://raw.githubusercontent.com/Doogit/AgentWrangler/main/docs/assets/logo.png" alt="AgentWrangler logo" width="200">
+  <img src="docs/assets/logo.png" alt="AgentWrangler logo" width="260">
 </p>
 
-# AgentWrangler
+<h1 align="center">AgentWrangler</h1>
 
-See where your Claude Code tokens go, inspect costly sessions, and track whether a change helped.
-AgentWrangler reads local Claude Code transcripts and serves a dashboard on your machine.
-No account or cloud backend is required.
+<p align="center">
+  <b>See where your Claude Code tokens go — and whether the work actually shipped.</b><br>
+  Local-first observability for Claude Code: token spend, session outcomes, waste detection,
+  and installable guardrails. Runs entirely on your machine.
+</p>
 
-## Quick start
+<p align="center">
+  <a href="https://www.npmjs.com/package/agentwrangler"><img src="https://img.shields.io/npm/v/agentwrangler" alt="npm version"></a>
+  <a href="https://github.com/Doogit/AgentWrangler/actions/workflows/ci.yml"><img src="https://github.com/Doogit/AgentWrangler/actions/workflows/ci.yml/badge.svg" alt="CI"></a>
+  <a href="https://img.shields.io/node/v/agentwrangler"><img src="https://img.shields.io/node/v/agentwrangler" alt="node version"></a>
+  <a href="LICENSE"><img src="https://img.shields.io/badge/license-Apache--2.0-blue" alt="license"></a>
+</p>
+
+![AgentWrangler dashboard — spend verdict, model mix, recommendations, and per-repo efficiency](docs/assets/dashboard.gif)
+
+<!--
+  All screenshots and the demo GIF in this README are captured from a SANITIZED instance
+  (Vite test-mode fixtures — anonymized names, no live data) so no real workspace/repository
+  names or paths are committed (SEC-101). Regenerate against `npx vite --mode test`.
+-->
+
+## Why
+
+Claude Code tells you almost nothing about where your token budget goes. Sessions balloon,
+caches miss, background agents idle — and you find out when you hit the rate limit.
+AgentWrangler reads the transcripts Claude Code already writes to your disk and answers three
+questions:
+
+- **Where did the tokens go?** Per-model, per-workspace, per-session spend with cache economics.
+- **Did the work ship?** Sessions are linked to the pull requests they merged or closed.
+- **What should I change?** Ranked waste-source detectors with modeled savings — and one-click
+  guardrail hooks that warn *inside* Claude Code before waste happens.
 
-Requires **Node 22-24 and npm**, plus Claude Code transcripts for populated charts.
+No cloud backend, no telemetry, no account. A daemon on `127.0.0.1`, a dashboard in your
+browser, and a SQLite file in your home directory.
+
+## Quick start
 
 ```sh
 npx agentwrangler@latest
 ```
 
-Open **http://127.0.0.1:47821** if the browser does not open automatically. Keep the terminal
-running; press **Ctrl+C** to stop. The first scan runs in the background. An empty history is
-valid: use Claude Code, then return after ingestion. If a daemon is already running, stop it
-before starting another on the same port.
+That's it — requires Node **22–24**. The daemon starts on `http://127.0.0.1:47821`, opens your
+browser, and scans your `~/.claude/projects` transcripts in the background; the dashboard
+appears immediately and fills in as the scan completes.
+
+More options (install from source, GitHub outcomes sync, environment variables):
+**[Getting started →](docs/getting-started.md)**
+
+## Features
+
+### Overview — verdict first, details on demand
+
+One screen answers "how bad is it this week": a spend verdict with trend, your top waste
+source with a copyable fix prompt, live rate-limit gauges (5-hour and 7-day), a burn forecast
+against your calibrated weekly limit, hot sessions, cache efficiency, and per-model
+context-per-turn tiles.
+
+![Overview tab — at-a-glance verdict, rate limits, burn forecast, hot sessions](docs/assets/overview.png)
+
+### Recommendations — waste-source detectors, ranked by impact
+
+Ten detector families watch your sessions for the patterns that actually burn tokens: cache
+misses (the biggest single lever), session hygiene, retry/redundant-read loops, tool-result
+bloat, model routing, idle background sessions, and more. Each recommendation shows modeled
+weekly savings, a confidence tier, and a concrete action — install a hook, copy a config
+snippet, or copy a guided prompt straight into Claude Code. Adopted changes flow into an
+**impact ledger** that tracks the measured effect, and modeled savings are never counted as
+achieved.
+
+![Recommendations tab — ranked detector families with modeled savings and one-click actions](docs/assets/recommendations.png)
+
+### Installable guardrails — local checks inside Claude Code, before the waste
+
+Five small hooks you can install from the dashboard (directly, or via a copyable prompt that
+Claude Code applies itself):
+
+| Guardrail | What it does |
+|---|---|
+| **Context-budget warning** | Warns when a session's context crosses your soft/hard thresholds |
+| **Loop guard** | Flags repeated identical tool failures before they spiral |
+| **Burn alert** | Catches idle sessions still burning tokens in the background |
+| **Pre-compaction checkpoint** | Copies the raw local transcript before an automatic compaction, subject to a local retention cap |
+| **Dangerous-command guard** | Asks before risky shell commands and denies a small catastrophe list |
+
+The context-budget and burn hooks warn. The loop guard warns before it denies repeated identical
+failures, and the dangerous-command guard can ask or deny. Direct install enables all five hooks;
+the copied install prompt enables the context-budget, loop, and burn hooks only. Thresholds are
+tunable from Settings, and direct uninstall removes every AgentWrangler hook.
+
+### Sessions — who spent it, and on what
+
+The highest-cost sessions ranked with their output-to-context split, model, friction band
+(API errors, tool failures, compactions, interrupts), and a "top X% by spend" self-percentile
+chip. Drill into any session for a turn-by-turn timeline, its cost drivers (which detectors
+fired and how hard), and a guided fix prompt built only from measured numbers.
+
+![Sessions tab — highest-cost sessions with friction bands and spend percentiles](docs/assets/sessions.png)
+
+<details>
+<summary>Session detail view</summary>
+
+![Session detail — per-session KPIs, cost drivers, and a measured-context fix prompt](docs/assets/session-detail.png)
+</details>
+
+### Workspaces — spend efficiency by repository
+
+Every repo you run Claude Code in, with spend share, trend, context-per-turn, cache-write
+share, Opus share, and $/turn. With a GitHub token configured, sessions are linked to the PRs
+and commits they produced — so you can see cost-per-merged-PR, not just cost.
+
+![Workspaces tab — per-repository spend, efficiency, and outcome linkage](docs/assets/workspaces.png)
+
+<details>
+<summary>Workspace detail view</summary>
+
+![Workspace detail — top sessions, context composition, and outcomes](docs/assets/workspace-detail.png)
+</details>
+
+### Weekly brief — one page, three decisions
+
+The week in one screen: spend verdict, what changed vs. last week, the top actions to take —
+with a **Copy as Markdown** button so the whole brief drops into a standup note or a message.
 
-[Install from source, configure scan roots, or troubleshoot](https://github.com/Doogit/AgentWrangler/blob/main/docs/getting-started.md).
+![Briefs tab — weekly verdict, week-over-week deltas, and top actions](docs/assets/briefs.png)
 
-## Your first five minutes
+### Honest numbers, labeled as such
 
-1. **Check the scan.** In Overview, read the onboarding status. A completed scan with no
-   recommendations is a valid result. For an unexpected empty history, inspect scan roots
-   and parser health in Settings; saved scan-root changes require a daemon restart.
-2. **Find one expensive session.** Select a date window, open Workspaces, choose a workspace,
-   then open one of its sessions. Compare context, cache writes, and output before deciding
-   what to change.
-3. **Inspect one recommendation.** Open Recommendations and **Show details** on an instance.
-   Read its evidence and caveats. A modeled amount is a projection; directional advice may
-   have no dollar estimate. If nothing fires, there is nothing to adopt just to finish setup.
-4. **Make one deliberate change.** A copied prompt is an artifact to review and run yourself.
-   It does not edit files. After completing a supported change, use **I completed the change**
-   when offered, then **Track this change** to record a baseline.
-5. **Return to the Impact ledger.** Tracking starts observation, not a savings claim. Eligible
-   signals use a 14-day observation window and may finish inconclusive. You can finish this
-   first visit without a GitHub token, calibration, or installed hooks.
+Every metric carries an honesty-tier chip — `EXACT`, `LIST_EQUIV`, `MODELED`, `PROXY`,
+`DIRECTIONAL`, `EXPERIMENTAL` — so you always know what is measured versus estimated. Dollar
+figures are list-price *equivalents* (subscription plans aren't billed per token; tokens drive
+rate limits), and the built-in glossary ("How to read this dashboard") defines every
+key metric in plain language. The full tour: **[Dashboard tour →](docs/dashboard-tour.md)**
 
-Dollar figures are **list-price equivalents**, not your subscription bill. Modeled savings
-are not achieved savings, and observed improvement does not prove the change caused it.
-GitHub linkage adds outcome metadata; calibration enables the burn forecast. Local spend,
-session inspection, and supported recommendation tracking work without either.
+## Privacy — local-only by design
 
-[Worked example: trim always-loaded context and inspect its effect](https://github.com/Doogit/AgentWrangler/blob/main/docs/getting-started.md#example-trim-always-loaded-context).
+- The daemon binds to **`127.0.0.1`** only. There is no cloud backend, telemetry, or account.
+- Most dashboard data is **aggregates, ids, counts, and structural anchors**. Local command text
+  and filesystem paths can also be retained in SQLite; treat the database as sensitive. The optional
+  direct-install PreCompact hook can separately copy full raw transcripts locally.
+- The optional GitHub token is read locally, never logged, never persisted to the DB.
+- Usage refreshes can call Anthropic with an existing Claude Code sign-in. GitHub outcomes sync
+  calls GitHub only when a token is configured; calibration and G2 judging are separate opt-ins.
 
-## Dashboard preview
+Full details, including exactly what is and isn't stored: **[Privacy model →](docs/privacy.md)**
 
-![Synthetic Overview: spend for the selected window, model mix, and links to sessions and recommendations](https://raw.githubusercontent.com/Doogit/AgentWrangler/main/docs/assets/overview.png)
+## Configuration
 
-This static preview uses synthetic data. [The dashboard tour](https://github.com/Doogit/AgentWrangler/blob/main/docs/dashboard-tour.md)
-contains the other views and an optional animated preview.
+Everything is optional with sensible defaults — port, DB path, scan roots, GitHub token, and
+more are environment variables documented in [Getting started](docs/getting-started.md#configuration)
+and [`.env.example`](.env.example).
 
-## Pick a question
+## Documentation
 
-| I want to... | Start here |
+| Page | What's in it |
 |---|---|
-| Find where my tokens went | [Workspaces and Sessions](https://github.com/Doogit/AgentWrangler/blob/main/docs/dashboard-tour.md#workspaces) |
-| Turn a recommendation into a change | [Worked example](https://github.com/Doogit/AgentWrangler/blob/main/docs/getting-started.md#example-trim-always-loaded-context) |
-| Understand the dollars and verdicts | [Metric vocabulary](https://github.com/Doogit/AgentWrangler/blob/main/docs/dashboard-tour.md#glossary-how-to-read-this-dashboard) |
-| Fix an empty dashboard | [First launch](https://github.com/Doogit/AgentWrangler/blob/main/docs/getting-started.md#first-launch) |
-| Connect GitHub or calibrate limits | [Optional setup](https://github.com/Doogit/AgentWrangler/blob/main/docs/getting-started.md#optional-setup) |
-| Read a weekly summary | [Briefs](https://github.com/Doogit/AgentWrangler/blob/main/docs/dashboard-tour.md#briefs) |
-
-## Installable guardrails — local checks inside Claude Code, before the waste
-
-Hooks are optional and require an explicit install. Settings **Install directly** installs
-five hooks; **Copy install prompt** prepares instructions for three. Copying alone installs nothing.
-
-| Hook | Behavior | Install path |
-|---|---|---|
-| Context-budget | Warns when context crosses configured thresholds | Direct or copied prompt |
-| Loop guard | Warns, then can deny repeated identical failures | Direct or copied prompt |
-| Burn alert | Warns about session budget consumption | Direct or copied prompt |
-| Dangerous-command | Can ask or deny risky commands | Direct only |
-| PreCompact checkpoint | Copies raw transcripts locally, with retention limits | Direct only |
-
-[Installation, removal, and the checkpoint privacy details](https://github.com/Doogit/AgentWrangler/blob/main/docs/getting-started.md#in-session-guardrails).
-
-## Privacy and limits
-
-- The daemon binds to **127.0.0.1**. There is no telemetry or hosted product backend.
-- SQLite contains aggregates and structural data, and can also contain local command text
-  and filesystem paths. Treat it as sensitive. The optional PreCompact hook makes separate
-  raw transcript copies on your machine.
-- Usage refresh can contact Anthropic using your existing Claude Code sign-in. GitHub
-  outcomes sync requires a configured token. [Privacy details](https://github.com/Doogit/AgentWrangler/blob/main/docs/privacy.md).
-- Claude Code format changes can require parser updates. This is a single-user tool.
-- Windows local validation and Linux/macOS CI smoke coverage do not establish full native
-  accessibility or credential-store compatibility on every platform.
-
-## Deeper documentation
-
-[Configuration](https://github.com/Doogit/AgentWrangler/blob/main/docs/getting-started.md#configuration) |
-[Architecture](https://github.com/Doogit/AgentWrangler/blob/main/docs/planning/AgentWrangler_Technical_Architecture_v4_5_0.md) |
-[Data model and metrics](https://github.com/Doogit/AgentWrangler/blob/main/docs/planning/AgentWrangler_Data_Model_and_Metrics_v2.md) |
-[Contributing](https://github.com/Doogit/AgentWrangler/blob/main/.github/CONTRIBUTING.md) |
-[Security policy](https://github.com/Doogit/AgentWrangler/blob/main/.github/SECURITY.md)
-
-[Apache 2.0](https://github.com/Doogit/AgentWrangler/blob/main/LICENSE).
+| [Getting started](docs/getting-started.md) | Install paths, optional setup, configuration, troubleshooting |
+| [Dashboard tour](docs/dashboard-tour.md) | Every tab in depth, plus the metric vocabulary |
+| [Privacy model](docs/privacy.md) | Local storage, raw-checkpoint exception, and network integrations |
+| [Architecture](docs/planning/AgentWrangler_Technical_Architecture_v4_5_0.md) | Daemon, ingestion, detector, and query design |
+| [Data model & metrics](docs/planning/AgentWrangler_Data_Model_and_Metrics_v2.md) | SQLite schema and metric definitions |
+| [Contributing](.github/CONTRIBUTING.md) | Dev setup, checks, PR expectations |
+| [Security policy](.github/SECURITY.md) | Threat model and how to report a vulnerability |
+
+## Limitations
+
+- Reads Claude Code's JSONL transcript format; an upstream format change can require an
+  ingestion update.
+- Tested on Windows; macOS/Linux are believed working — reports welcome.
+- Single local user by design — no multi-user or team-aggregation mode.
+- Outcome linkage needs a read-only GitHub token; without one the feature stays inert (and
+  Settings says so — nothing fails silently).
+
+## License
+
+[Apache 2.0](LICENSE) © 2026 AgentWrangler contributors.
+See [CONTRIBUTING.md](.github/CONTRIBUTING.md), [SECURITY.md](.github/SECURITY.md), and
+[CODE_OF_CONDUCT.md](.github/CODE_OF_CONDUCT.md).

package/dist/apply/jobs.js

@@ -200,7 +200,6 @@ function runClaudePhase(db, job, rec, phase, settingsPath, rt) {
     const changedPaths = [];
     let finalized = false;
     let fatalExitMessage = null;
-    let killTimer;
     const cleanup = () => {
         fs.unlink(settingsPath, () => { });
     };
@@ -252,11 +251,9 @@ function runClaudePhase(db, job, rec, phase, settingsPath, rt) {
         }
     });
     const timer = setTimeout(() => {
-        // Keep the job exclusive until the child has actually closed. Publishing
-        // FAILED here lets a retry (or workspace cleanup) race the dying process.
-        fatalExitMessage ??= "job timed out";
         proc.kill("SIGTERM");
-        killTimer = setTimeout(() => proc.kill("SIGKILL"), 2000);
+        setTimeout(() => proc.kill("SIGKILL"), 2000);
+        markFailed("job timed out");
     }, rt.timeoutMs);
     proc.on("error", (err) => {
         clearTimeout(timer);
@@ -264,7 +261,6 @@ function runClaudePhase(db, job, rec, phase, settingsPath, rt) {
     });
     proc.on("close", (code) => {
         clearTimeout(timer);
-        clearTimeout(killTimer);
         if (finalized)
             return;
         finalized = true;
@@ -302,10 +298,7 @@ function completeApplyPhase(db, job, rec, result, rt) {
     let runId = null;
     const completedAt = rt.now();
     try {
-        adoptRecommendation(job.rec_id, completedAt.getTime(), {
-            machineConfirmed: true,
-            actionRevision: job.job_id,
-        });
+        adoptRecommendation(job.rec_id, completedAt.getTime());
         runId = randomUUID();
         const evidencePackHash = createHash("sha256")
             .update(JSON.stringify(rec.evidence))
@@ -420,9 +413,6 @@ export function rollbackApplyJob(jobId) {
     if (row.status !== "APPLIED" && row.status !== "CONFIRMING") {
         throw new Error("job cannot be rolled back from this state");
     }
-    if (db.prepare("SELECT 1 FROM effect_cycles WHERE rec_id=? LIMIT 1").get(row.rec_id)) {
-        throw new Error("Whole-file backup rollback is not a supported effect inverse. Revert manually and attest the rollback in the effect ledger.");
-    }
     if (row.backup_path === null)
         throw new Error("no backup available");
     fs.copyFileSync(row.backup_path, row.file_ref);

package/dist/daemon/http.js

@@ -138,8 +138,6 @@ function requiresSessionToken(pathname) {
         return true;
     if (/^\/api\/recommendations\/jobs\/[^/]+\/(confirm|rollback)$/.test(pathname))
         return true;
-    if (/^\/api\/esf\/effects\/(track|stop|close|rollback|attest-rollback)$/.test(pathname))
-        return true;
     return false;
 }
 /**

package/dist/daemon/index.js

@@ -22,6 +22,7 @@ import { openDb } from "../db/open.js";
 import { configGet as bptConfigGet, calibrateBytesPerToken } from "../detector/calibration.js";
 import { runContextProbe } from "../detector/context-probe.js";
 import { runDetectors } from "../detector/index.js";
+import { runMeasurementPass } from "../detector/measurement.js";
 import { installHook, uninstallHook } from "../hook/install.js";
 import { collectSessionChurn } from "../ingest/churn-collector.js";
 import { runPostProbeHook, setPostIngestHook, setPostProbeHook } from "../ingest/detector-hook.js";
@@ -36,7 +37,6 @@ import { generateWeeklyReport } from "../query/api/reports.js";
 import { setQueryDb } from "../query/db-context.js";
 import { getSettingsData, setHealthInstance, setRuntimeResetHook, } from "../query/settings-store.js";
 import { loadConfig } from "./config.js";
-import { runEffectMeasurementPass } from "./effect-pass.js";
 import { createServer } from "./http.js";
 import { createOutcomesPassRunner } from "./outcomes-pass.js";
 import { setReady, setScanRoots, setScanState } from "./readiness.js";
@@ -107,10 +107,6 @@ if (isSmoke) {
         "review_findings",
         "recommendations",
         "recommendation_effects",
-        "effect_cycles",
-        "effect_guardrail_results",
-        "effect_rollback_operations",
-        "effect_mutation_keys",
         "apply_jobs",
         "analysis_runs",
         "ingest_quarantine",
@@ -154,16 +150,18 @@ function runProbePass(label) {
         const now = new Date();
         const { rows } = runContextProbe(db, now);
         console.log(`ContextProbe[${label}]: ${rows} row(s) upserted`);
-        // Best-effort measurement after each probe, using the same observation clock.
+        // W4: measurement pass after each probe (best-effort; the seam never throws
+        // through, and runMeasurementPass itself is guarded/log-not-throw).
         runPostProbeHook(db, now);
     }
     catch (e) {
         console.log(`ContextProbe[${label}]: skipped — ${e instanceof Error ? e.message : String(e)}`);
     }
 }
-// Versioned measurement owns new cycles; W4 history stays read-only under the code gate.
+// Wire the W4 Impact Ledger measurement pass onto the post-probe seam. The pass
+// receives the probe's clock (deterministic; NFR-107), is throttled internally.
 setPostProbeHook((probeDb, now) => {
-    runEffectMeasurementPass(probeDb, now);
+    runMeasurementPass(probeDb, now);
 });
 runProbePass("boot");
 // ── Outcomes bootstrap (WP5 — best-effort, never crash daemon) ────────────────

package/dist/daemon/router.js

@@ -14,7 +14,6 @@ import { endSession, getAgentsLiveness } from "../query/api/agents-liveness.js";
 import { getBurnStatus } from "../query/api/burn-status.js";
 import { getCostPerSuccess } from "../query/api/cost-per-success.js";
 import { getDeliveryMetrics } from "../query/api/delivery.js";
-import { EffectRequestError, listEffectEvidence, mutateEffectCycle, trackCompletedChange, } from "../query/api/effect-service.js";
 import { getClosureProxy } from "../query/api/effectiveness.js";
 import { getEfficiencyHeadroom } from "../query/api/efficiency-headroom.js";
 import { getHeadroomTrend } from "../query/api/headroom-trend.js";
@@ -36,19 +35,10 @@ function sendJson(res, status, body) {
     });
     res.end(payload);
 }
-function readBody(req, maxBytes) {
+function readBody(req) {
     return new Promise((resolve, reject) => {
         const chunks = [];
-        let size = 0;
-        req.on("data", (chunk) => {
-            size += chunk.length;
-            if (maxBytes !== undefined && size > maxBytes) {
-                reject(new EffectRequestError(400, "Request body is too large."));
-                req.resume();
-                return;
-            }
-            chunks.push(chunk);
-        });
+        req.on("data", (chunk) => chunks.push(chunk));
         req.on("end", () => resolve(Buffer.concat(chunks).toString("utf-8")));
         req.on("error", reject);
     });
@@ -138,47 +128,6 @@ export function handleApiRequest(_db, req, res, method, url) {
     // Strip query string for routing.
     const pathname = url.split("?")[0] ?? url;
     try {
-        // GET /api/esf/effects — independently keyset-paged versioned and legacy evidence.
-        if (method === "GET" && pathname === "/api/esf/effects") {
-            const params = new URLSearchParams(url.split("?")[1] ?? "");
-            const workspaceId = params.get("workspace_id");
-            sendJson(res, 200, listEffectEvidence(_db, workspaceId, params.get("rec_id") ?? undefined, params.get("limit") ?? undefined, params.get("cycle_cursor") ?? undefined, params.get("legacy_cursor") ?? undefined));
-            return;
-        }
-        const effectAction = pathname.match(/^\/api\/esf\/effects\/(track|stop|close|rollback|attest-rollback)$/)?.[1];
-        if (method === "POST" && effectAction !== undefined) {
-            readBody(req, 4096)
-                .then((raw) => {
-                let body;
-                try {
-                    body = JSON.parse(raw);
-                }
-                catch {
-                    sendJson(res, 400, { error: "Invalid JSON body." });
-                    return;
-                }
-                try {
-                    const result = effectAction === "track"
-                        ? trackCompletedChange(_db, body)
-                        : mutateEffectCycle(_db, effectAction, body);
-                    sendJson(res, 200, result);
-                }
-                catch (error) {
-                    const status = error instanceof EffectRequestError ? error.status : 409;
-                    sendJson(res, status, {
-                        error: error instanceof EffectRequestError
-                            ? error.message
-                            : "Effect request conflicts with the current cycle.",
-                    });
-                }
-            })
-                .catch((error) => sendJson(res, error instanceof EffectRequestError ? error.status : 500, {
-                error: error instanceof EffectRequestError
-                    ? error.message
-                    : "Internal error reading request body",
-            }));
-            return;
-        }
         // GET /api/overview
         if (method === "GET" && pathname === "/api/overview") {
             sendJson(res, 200, getGlobalOverview(parseWindowFilter(url)));
@@ -315,7 +264,7 @@ export function handleApiRequest(_db, req, res, method, url) {
             sendJson(res, 200, getPractices(_db, { from, to }));
             return;
         }
-        // GET /api/efficiency-headroom (individual weekly estimates; separate selected-window spend)
+        // GET /api/efficiency-headroom (BM2 modeled savings vs trailing-window spend)
         if (method === "GET" && pathname === "/api/efficiency-headroom") {
             const { from, to } = resolveWindow(parseWindowFilter(url));
             sendJson(res, 200, getEfficiencyHeadroom(_db, { from, to }));
@@ -557,15 +506,13 @@ export function handleApiRequest(_db, req, res, method, url) {
                     sendJson(res, 400, { error: "Invalid JSON body" });
                     return;
                 }
-                const { rec_id, completed_change } = body;
+                const { rec_id } = body;
                 if (typeof rec_id !== "string" || rec_id.length === 0) {
                     sendJson(res, 400, { error: "rec_id is required" });
                     return;
                 }
                 try {
-                    sendJson(res, 200, adoptRecommendation(rec_id, Date.now(), {
-                        completedChange: completed_change === true,
-                    }));
+                    sendJson(res, 200, adoptRecommendation(rec_id));
                 }
                 catch (e) {
                     sendJson(res, 400, { error: e instanceof Error ? e.message : "Adopt failed" });
@@ -802,11 +749,7 @@ export function handleApiRequest(_db, req, res, method, url) {
         // 404 for everything else.
         sendJson(res, 404, { error: "Not found", path: pathname });
     }
-    catch (error) {
-        if (error instanceof EffectRequestError) {
-            sendJson(res, error.status, { error: error.message });
-            return;
-        }
+    catch {
         // Do not leak internal exception text into a cross-origin-readable 500 body
         // (GET routes are not CSRF-gated). Validation errors on POST routes still
         // return their message via the 400 paths above.

package/dist/detector/context-history-retention.js

@@ -1,6 +1,4 @@
-import { createHash } from "node:crypto";
 import { performance } from "node:perf_hooks";
-import { cycleFromRow } from "../effects/store.js";
 import { GLOBAL_WORKSPACE_ID } from "./context-probe.js";
 import { isD1SourceBackedRecommendation, parseD1SourceIdentity } from "./d1-source-identity.js";
 import { AFTER_WINDOW_DAYS } from "./measurement.js";
@@ -80,15 +78,10 @@ function validateHistoryRows(db) {
     });
 }
 function readOpenEffects(db) {
-    const hasVersioned = db.prepare("SELECT 1 FROM sqlite_master WHERE name='effect_cycles'").get();
-    const versionedExclusion = hasVersioned
-        ? "AND NOT EXISTS (SELECT 1 FROM effect_cycles c WHERE c.rec_id=recommendations.rec_id)"
-        : "";
     const recs = db
         .prepare(`SELECT rec_id, detector_id, scope_workspace_id, evidence_json, target_metric, adopted_at
          FROM recommendations
         WHERE state IN ('ADOPTED', 'MEASURING')
-          ${versionedExclusion}
         ORDER BY rec_id ASC`)
         .all();
     const sourceBacked = recs.filter(isD1SourceBackedRecommendation);
@@ -147,48 +140,6 @@ function readOpenEffects(db) {
     }
     if (malformedN > 0)
         throw new RetentionPlanError("invalid_open_effect", malformedN);
-    if (hasVersioned) {
-        const rows = db
-            .prepare(`SELECT c.*,r.evidence_json,r.scope_workspace_id
-      FROM effect_cycles c JOIN recommendations r ON r.rec_id=c.rec_id
-      WHERE c.detector_id='D1' AND c.state IN ('OPEN_SETTLING','OPEN_MEASURING')`)
-            .all();
-        for (const row of rows) {
-            const cycle = cycleFromRow(row);
-            const identity = parseD1SourceIdentity(String(row.evidence_json));
-            const workspaceId = row.scope_workspace_id === null ? GLOBAL_WORKSPACE_ID : String(row.scope_workspace_id);
-            const beforeToMs = canonicalTimestamp(cycle.baselineTo);
-            const afterFromMs = canonicalTimestamp(cycle.observationFrom);
-            const afterToMs = canonicalTimestamp(cycle.scheduledObservationTo);
-            if (!identity ||
-                !COMPONENTS.has(identity.component) ||
-                !identity.fileRef ||
-                cycle.versionStatus !== "SUPPORTED" ||
-                beforeToMs === null ||
-                afterFromMs === null ||
-                afterToMs === null ||
-                beforeToMs !== afterFromMs ||
-                afterToMs < afterFromMs) {
-                throw new RetentionPlanError("invalid_open_effect", 1);
-            }
-            // Same opaque tuple encoding as the service; a moved/reassigned source is not reinterpreted.
-            const digest = createHash("sha256")
-                .update(JSON.stringify({
-                workspaceId,
-                component: identity.component,
-                fileRef: identity.fileRef,
-            }))
-                .digest("hex");
-            if (digest !== cycle.scope.sourceIdentity)
-                throw new RetentionPlanError("invalid_open_effect", 1);
-            effects.push({
-                sourceKey: sourceKey(workspaceId, identity.component, identity.fileRef),
-                beforeToMs,
-                afterFromMs,
-                afterToMs,
-            });
-        }
-    }
     return effects;
 }
 function emptySummary(mode, startedAt, failureClass, malformedOpenEffectN = 0) {

package/dist/detector/detectors/d10_catalog_footprint.js

@@ -95,7 +95,7 @@ export const d10Detector = {
         const latestProbedAt = rows.reduce((latest, row) => (latest === null || row.probed_at > latest ? row.probed_at : latest), null);
         const refs = rows.map((row) => row.file_ref);
         const evidence = {
-            title: `Review tool catalog: ${Math.round(catalogTokens / 1000)}K estimated tokens`,
+            title: `Review ${state.effective_catalog_state} tool catalog: ${Math.round(catalogTokens / 1000)}K tokens`,
             component: "MCP_SCHEMAS",
             file_ref: refs.length === 1 ? refs[0] : null,
             file_refs: refs,
@@ -120,7 +120,7 @@ export const d10Detector = {
             scopeKey: "D10|global|MCP_SCHEMAS",
             category: "TOOLING",
             scope_workspace_id: null,
-            lever: "The tool catalog exceeds its size target; actual loaded context is not measured",
+            lever: "Too many connected tools, plugins, and skills",
             target_metric: "catalog_context_tokens",
             // R11 is required before catalog size can become a freed-headroom claim.
             modeled_savings_u_per_wk: null,

package/dist/detector/detectors/d1_ctx_always_loaded.js

@@ -29,16 +29,16 @@ function stepsFor(component, fileRef) {
         case "CLAUDE_MD":
             return [
                 `Open ${fileRef}`,
-                "Move changelogs, history, and background explanations to a linked document",
-                "Keep only current rules and links here",
-                "Check the size again after the next local scan",
+                "Move changelog/history/rationale prose to a linked doc",
+                "Keep current-state rules + pointers only",
+                "Re-measure: probe re-sizes on next daemon pass",
             ];
         case "MEMORY":
             return [
                 `Review memory files under ${fileRef}`,
-                "Remove old or duplicate memories",
-                "Combine overlapping facts into concise entries",
-                "Check the size again after the next local scan",
+                "Delete stale or duplicate memories",
+                "Consolidate overlapping facts into concise entries",
+                "Re-measure: probe re-sizes on next daemon pass",
             ];
         case "MCP_SCHEMAS":
             return [
@@ -62,13 +62,13 @@ function titleFor(component, tokens, target) {
 function leverFor(component) {
     switch (component) {
         case "CLAUDE_MD":
-            return "Move changelogs and history out of CLAUDE.md; keep current rules and links.";
+            return "Move changelog/history prose out of CLAUDE.md; keep current-state + pointers.";
         case "MEMORY":
-            return "Remove old or duplicate memories and combine overlapping facts.";
+            return "Prune stale/duplicate memories; consolidate overlapping facts.";
         case "MCP_SCHEMAS":
             return "Identify rarely-used skills/plugins; extract to on-demand or disable.";
         default:
-            return "Shorten this content that is loaded into every conversation.";
+            return "Trim always-loaded context source to the per-source target.";
     }
 }
 export const d1Detector = {