dsh-session-eval 0.1.0 → 0.2.1

package/CHANGELOG.md

@@ -0,0 +1,30 @@
+# Changelog
+
+## 0.2.1 — 2026-09-26
+
+- **Fix: ship the bundle overlay.** v0.2.0 declared `dsh.bundle.patch: ./cordis.patch.yml`
+  in `package.json` but the file was never committed, so the published tarball did not
+  contain it and `dsh web` failed at startup with
+  `failed to read overlay .../dsh-session-eval/cordis.patch.yml: ENOENT`.
+  The overlay (mounting `/eval`, `/eval-diff`, `/eval-history`) is now in the tarball;
+  verified with `npm pack --dry-run`.
+- **Fix: peer ranges match the current harness.** `@deepseek-ai/*` peers and dev
+  dependencies moved from `^0.1.1-rc.2` to `^0.1.5-rc.3` (semver prerelease ranges do not
+  cross `0.1.1-rc.x` → `0.1.5-rc.3`, which let stale `0.1.1-rc.2` copies install into
+  profiles and shadow the running harness). `@deepseek-ai/cordis` pinned to `4.0.2`,
+  matching the official plugins at this harness level.
+- Added this changelog; `files` always listed it but it was never written.
+
+## 0.2.0 — 2026-09-25
+
+- New `/eval-history [N] [--json]` command: lists the current workspace's recent sessions
+  (same `sessionQuery` seam as `/archive`), grades the last N, and diffs first-vs-last for
+  a trend verdict. Caps the manual id-picking that `/eval-diff` required.
+- Version string single-sourced from `src/version.ts` (replaces four hardcoded `v0.1.0`
+  strings).
+- 8 new tests (35 total) and `typecheck` script.
+
+## 0.1.0 — 2026-09-24
+
+- Initial release: `/eval` grade cards from persisted session logs (tool-error rate,
+  follow-up signals, tool load), `/eval-diff` regression comparison, no LLM judge.

package/README.md

@@ -45,7 +45,7 @@ Then in DeepSeek Harness:
 ```
 
 ```text
-Session eval — a1b2c3d4… (dsh-session-eval v0.1.0)
+Session eval — a1b2c3d4… (dsh-session-eval v0.2.0)
 Overall: A
   Reliability   A    2/87 tool results errored (2.3%)
   Re-ask        A    1 re-ask signal(s) over 23 turns (0.4/10 turns)
@@ -67,7 +67,7 @@ Compare two sessions — the regression workflow:
 ```
 
 ```text
-Session diff — a1b2c3d4… → e5f6a7b8… (dsh-session-eval v0.1.0)
+Session diff — a1b2c3d4… → e5f6a7b8… (dsh-session-eval v0.2.0)
 Overall: regressed — 0 improved, 2 regressed, 1 flat.
   Reliability   2.1% → 11.8%   regressed
   Re-ask        0.5 → 3.2      regressed
@@ -76,6 +76,23 @@ Overall: regressed — 0 improved, 2 regressed, 1 flat.
 
 Typical use: grade the ten sessions before and after a plugin or prompt change; a persistent `Reliability` regression is an early warning that the change hurt real work, not just benchmarks.
 
+See the whole trend — no ids to hunt for:
+
+```text
+/eval-history        # last 5 sessions in this workspace
+/eval-history 12     # last 12
+```
+
+```text
+Session history — last 5 in this workspace
+  2026-09-20 14:02  a1b2c3d4…  B   4 turns, 9 tools
+  2026-09-21 09:15  c3d4e5f6…  A   5 turns, 11 tools
+  2026-09-22 17:44  e5f6a7b8…  A   3 turns, 7 tools
+Trend (first → last): improved — 2 improved, 0 regressed, 1 flat.
+```
+
+`/eval-history` finds the sessions for you via the same `sessionQuery` seam `/archive` uses (scoped to the current workspace's `cwd`), grades each, and diffs the first against the last. `/eval-diff` remains the tool when you already know the two ids that matter.
+
 ## Dimensions & thresholds
 
 All grades derive from three deterministic metrics. `n/a` when the session lacks the relevant activity.
@@ -105,6 +122,8 @@ Same session logs in → same grade card out, every time, forever. There is no m
 | `/eval --json` | Machine-readable metrics + card |
 | `/eval-diff <beforeId> <afterId>` | Regression comparison, noise-tolerant |
 | `/eval-diff … --json` | Machine-readable trend report |
+| `/eval-history [N]` | Grade the last N sessions in this workspace and show the trend |
+| `/eval-history … --json` | Machine-readable history report |
 
 ## Development
 

package/README.zh.md

@@ -37,8 +37,12 @@ npm install -g dsh-session-eval
 /eval                 # 当前会话等级卡
 /eval --id <会话ID>    # 指定会话
 /eval-diff <前> <后>   # 回归对比（换插件/prompt 前后各评一次）
+/eval-history         # 本工作区最近 5 个会话的成绩单 + 首末趋势
+/eval-history 12      # 最近 12 个
 ```
 
+`/eval-history` 通过与 `/archive` 相同的 `sessionQuery` 接缝自动找到会话（按当前工作区 `cwd` 过滤），逐个评级，并把首尾两个会话做趋势对比——不用再手动挑 id。
+
 ## 维度与阈值（确定性，无裁判）
 
 | 维度 | 指标 | A | B | C | D | E |

package/cordis.patch.yml

@@ -0,0 +1,6 @@
+# The dsh-session-eval bundle patch: mounts /eval, /eval-diff, and /eval-history.
+# Applied as one insert; requires `commands` and `sessionQuery` services,
+# which the shipped dsh-base / web bundles already provide.
+- insert:
+    - id: session-eval
+      name: 'dsh-session-eval'

package/lib/index.d.ts

@@ -132,10 +132,57 @@ declare function executeEval(ctx: Context, invocation: CommandInvocation, seam?:
 /** Execute /eval-diff against the session-query seam. */
 declare function executeEvalDiff(ctx: Context, invocation: CommandInvocation, seam?: QuerySeam): Promise<CommandResult>;
 //#endregion
+//#region src/historyCommand.d.ts
+declare const EVAL_HISTORY_USAGE = "Usage: /eval-history [N] [--json]  (N = last N sessions, 1-20, default 5)";
+/** Args for /eval-history. */
+interface EvalHistoryArgs {
+  readonly count: number;
+  readonly json: boolean;
+}
+/** Parse /eval-history input; returns args or a usage-error string. */
+declare function parseEvalHistoryArgs(rawInput: string): EvalHistoryArgs | string;
+/** One graded session in a history report. */
+interface HistoryEntry {
+  readonly sessionId: string;
+  readonly createdAt: number | null;
+  readonly metrics: SessionMetrics;
+  readonly card: GradeCard;
+}
+/** The full /eval-history report. */
+interface HistoryReport {
+  readonly entries: readonly HistoryEntry[];
+  readonly trend: TrendReport | null;
+}
+/** The slice of sessionQuery this command consumes (structural, for testability). */
+interface HistorySeam {
+  listSessions(): Promise<ReadonlyArray<{
+    header: {
+      id: unknown;
+      createdAt: unknown;
+      cwd?: unknown;
+    };
+  }>>;
+  readSession(id: ReturnType<typeof SessionId>): Promise<{
+    events: readonly unknown[];
+  }>;
+}
+/** Render a history report as terminal text. */
+declare function renderHistory(report: HistoryReport): string;
+/** Execute /eval-history against the session-query seam. */
+declare function executeEvalHistory(ctx: Context, invocation: CommandInvocation, seam?: HistorySeam): Promise<CommandResult>;
+//#endregion
+//#region src/version.d.ts
+/**
+ * Single source of truth for the plugin version string.
+ *
+ * @module dsh-session-eval/version
+ */
+declare const VERSION = "0.2.1";
+//#endregion
 //#region src/index.d.ts
 declare const name = "session-eval";
 declare const inject: string[];
-/** Plugin entry: mount the /eval and /eval-diff commands. */
+/** Plugin entry: mount the /eval, /eval-diff and /eval-history commands. */
 declare function apply(ctx: Context): void;
 //#endregion
-export { type DimensionDelta, type DimensionGrade, EVAL_DIFF_USAGE, EVAL_USAGE, type EvalArgs, type EvalDiffArgs, type EvalEvent, type EvalEventKind, type Grade, type GradeCard, type SessionMetrics, type TrendReport, adaptEvents, apply, compareSessions, computeMetrics, executeEval, executeEvalDiff, gradeSession, id8, inject, name, parseEvalArgs, parseEvalDiffArgs, renderCard, renderTrend };
+export { type DimensionDelta, type DimensionGrade, EVAL_DIFF_USAGE, EVAL_HISTORY_USAGE, EVAL_USAGE, type EvalArgs, type EvalDiffArgs, type EvalEvent, type EvalEventKind, type EvalHistoryArgs, type Grade, type GradeCard, type HistoryEntry, type HistoryReport, type HistorySeam, type SessionMetrics, type TrendReport, VERSION, adaptEvents, apply, compareSessions, computeMetrics, executeEval, executeEvalDiff, executeEvalHistory, gradeSession, id8, inject, name, parseEvalArgs, parseEvalDiffArgs, parseEvalHistoryArgs, renderCard, renderHistory, renderTrend };

package/lib/index.js

@@ -221,6 +221,14 @@ function compareSessions(before, after) {
 	};
 }
 //#endregion
+//#region src/version.ts
+/**
+* Single source of truth for the plugin version string.
+*
+* @module dsh-session-eval/version
+*/
+const VERSION = "0.2.1";
+//#endregion
 //#region src/evalCommand.ts
 const EVAL_USAGE = "Usage: /eval [--id <sessionId>] [--json]";
 const EVAL_DIFF_USAGE = "Usage: /eval-diff <beforeSessionId> <afterSessionId> [--json]";
@@ -319,14 +327,14 @@ async function executeEval(ctx, invocation, seam = ctx.sessionQuery) {
 	if (parsed.json === true) return {
 		kind: "success",
 		text: JSON.stringify({
-			generator: "dsh-session-eval v0.1.0",
+			generator: "dsh-session-eval v0.2.1",
 			metrics,
 			card
 		}, null, 2)
 	};
 	return {
 		kind: "success",
-		text: renderCard(card, "dsh-session-eval v0.1.0")
+		text: renderCard(card, "dsh-session-eval v0.2.1")
 	};
 }
 /** Execute /eval-diff against the session-query seam. */
@@ -350,20 +358,133 @@ async function executeEvalDiff(ctx, invocation, seam = ctx.sessionQuery) {
 	if (parsed.json === true) return {
 		kind: "success",
 		text: JSON.stringify({
-			generator: "dsh-session-eval v0.1.0",
+			generator: "dsh-session-eval v0.2.1",
+			report
+		}, null, 2)
+	};
+	return {
+		kind: "success",
+		text: renderTrend(report, "dsh-session-eval v0.2.1")
+	};
+}
+//#endregion
+//#region src/historyCommand.ts
+const EVAL_HISTORY_USAGE = "Usage: /eval-history [N] [--json]  (N = last N sessions, 1-20, default 5)";
+/** Parse /eval-history input; returns args or a usage-error string. */
+function parseEvalHistoryArgs(rawInput) {
+	const tokens = rawInput.trim().split(/\s+/).filter((t) => t.length > 0);
+	let count = 5;
+	let json = false;
+	let sawCount = false;
+	for (const token of tokens) {
+		if (token === "--json") {
+			if (json) return `--json may be given only once.\n${EVAL_HISTORY_USAGE}`;
+			json = true;
+			continue;
+		}
+		if (token.startsWith("--")) return `Unknown argument: ${token}\n${EVAL_HISTORY_USAGE}`;
+		if (sawCount) return `Expected at most one count argument.\n${EVAL_HISTORY_USAGE}`;
+		if (!/^\d+$/.test(token)) return `N must be a positive integer.\n${EVAL_HISTORY_USAGE}`;
+		const value = Number(token);
+		if (value < 1 || value > 20) return `N must be between 1 and 20.\n${EVAL_HISTORY_USAGE}`;
+		count = value;
+		sawCount = true;
+	}
+	return {
+		count,
+		json
+	};
+}
+function toMillis(createdAt) {
+	if (typeof createdAt === "number" && Number.isFinite(createdAt)) return createdAt;
+	if (typeof createdAt === "string") {
+		const parsed = Date.parse(createdAt);
+		if (Number.isFinite(parsed)) return parsed;
+	}
+	return null;
+}
+function stamp(ms) {
+	if (ms === null) return "?";
+	return new Date(ms).toISOString().slice(0, 16).replace("T", " ");
+}
+/** Render a history report as terminal text. */
+function renderHistory(report) {
+	const lines = [];
+	if (report.entries.length === 0) return "No sessions found in this workspace; nothing to grade.";
+	lines.push(`Session history — last ${report.entries.length} in this workspace`);
+	for (const entry of report.entries) {
+		const m = entry.metrics;
+		lines.push(`  ${stamp(entry.createdAt)}  ${id8(entry.sessionId)}  ${String(entry.card.overall).padEnd(2)}  ${m.userTurns} turns, ${m.toolCalls} tools`);
+	}
+	const trend = report.trend;
+	if (trend !== null) lines.push(`Trend (first → last): ${trend.overall} — ${trend.summary}`);
+	return lines.join("\n");
+}
+/** Execute /eval-history against the session-query seam. */
+async function executeEvalHistory(ctx, invocation, seam = ctx.sessionQuery) {
+	const parsed = parseEvalHistoryArgs(invocation.rawInput);
+	if (typeof parsed === "string") return {
+		kind: "error",
+		text: parsed
+	};
+	const ownCwd = invocation.agent.session.header?.cwd;
+	let records;
+	try {
+		records = await seam.listSessions();
+	} catch (error) {
+		return {
+			kind: "error",
+			text: `Could not list sessions: ${error instanceof Error ? error.message : String(error)}`
+		};
+	}
+	const recent = records.map((record) => record.header).filter((header) => header != null).filter((header) => ownCwd === void 0 || header.cwd === ownCwd).map((header) => ({
+		id: String(header.id),
+		createdAt: toMillis(header.createdAt)
+	})).sort((a, b) => (a.createdAt ?? 0) - (b.createdAt ?? 0)).slice(-parsed.count);
+	if (recent.length === 0) return {
+		kind: "success",
+		text: "No sessions found in this workspace; nothing to grade."
+	};
+	const entries = [];
+	for (const header of recent) {
+		let events;
+		try {
+			events = (await seam.readSession(SessionId(header.id))).events;
+		} catch (error) {
+			return {
+				kind: "error",
+				text: `Could not read session ${id8(header.id)}: ${error instanceof Error ? error.message : String(error)}`
+			};
+		}
+		const metrics = computeMetrics(header.id, adaptEvents(events));
+		entries.push({
+			sessionId: header.id,
+			createdAt: header.createdAt,
+			metrics,
+			card: gradeSession(metrics)
+		});
+	}
+	const report = {
+		entries,
+		trend: entries.length >= 2 ? compareSessions(entries[0].metrics, entries[entries.length - 1].metrics) : null
+	};
+	if (parsed.json === true) return {
+		kind: "success",
+		text: JSON.stringify({
+			generator: `dsh-session-eval v${VERSION}`,
 			report
 		}, null, 2)
 	};
 	return {
 		kind: "success",
-		text: renderTrend(report, "dsh-session-eval v0.1.0")
+		text: renderHistory(report)
 	};
 }
 //#endregion
 //#region src/index.ts
 const name = "session-eval";
 const inject = ["commands", "sessionQuery"];
-/** Plugin entry: mount the /eval and /eval-diff commands. */
+/** Plugin entry: mount the /eval, /eval-diff and /eval-history commands. */
 function apply(ctx) {
 	ctx.effect(function* () {
 		yield ctx.commands.register({
@@ -376,7 +497,12 @@ function apply(ctx) {
 			description: "Compare two sessions (before, after) and report which dimensions improved or regressed",
 			handler: (invocation) => executeEvalDiff(ctx, invocation)
 		});
+		yield ctx.commands.register({
+			name: "eval-history",
+			description: "Grade the last N sessions in this workspace (default 5) and show whether the trend is improving",
+			handler: (invocation) => executeEvalHistory(ctx, invocation)
+		});
 	}, "session-eval lifecycle");
 }
 //#endregion
-export { EVAL_DIFF_USAGE, EVAL_USAGE, adaptEvents, apply, compareSessions, computeMetrics, executeEval, executeEvalDiff, gradeSession, id8, inject, name, parseEvalArgs, parseEvalDiffArgs, renderCard, renderTrend };
+export { EVAL_DIFF_USAGE, EVAL_HISTORY_USAGE, EVAL_USAGE, VERSION, adaptEvents, apply, compareSessions, computeMetrics, executeEval, executeEvalDiff, executeEvalHistory, gradeSession, id8, inject, name, parseEvalArgs, parseEvalDiffArgs, parseEvalHistoryArgs, renderCard, renderHistory, renderTrend };

package/package.json

@@ -1,7 +1,7 @@
 {
   "name": "dsh-session-eval",
   "description": "Retrospective agent-session evaluation for DeepSeek Harness: deterministic grade cards from persisted session logs, cross-session regression diffs, era comparison — no benchmark runs, no LLM judges.",
-  "version": "0.1.0",
+  "version": "0.2.1",
   "publishConfig": {
     "access": "public"
   },
@@ -38,21 +38,21 @@
     "regression"
   ],
   "peerDependencies": {
-    "@deepseek-ai/cordis": "^4.0.1",
-    "@deepseek-ai/dsh-commands": "^0.1.1-rc.2",
-    "@deepseek-ai/dsh-llm": "^0.1.1-rc.2",
-    "@deepseek-ai/dsh-session": "^0.1.1-rc.2",
-    "@deepseek-ai/dsh-session-query": "^0.1.1-rc.2",
-    "@deepseek-ai/dsh-tools": "^0.1.1-rc.2"
+    "@deepseek-ai/cordis": "4.0.2",
+    "@deepseek-ai/dsh-commands": "^0.1.5-rc.3",
+    "@deepseek-ai/dsh-llm": "^0.1.5-rc.3",
+    "@deepseek-ai/dsh-session": "^0.1.5-rc.3",
+    "@deepseek-ai/dsh-session-query": "^0.1.5-rc.3",
+    "@deepseek-ai/dsh-tools": "^0.1.5-rc.3"
   },
   "devDependencies": {
     "@types/node": "^26.2.0",
     "tsdown": "^0.22.14",
     "typescript": "^7.0.2",
     "vitest": "^4.1.11",
-    "@deepseek-ai/cordis": "^4.0.1",
-    "@deepseek-ai/dsh-commands": "^0.1.1-rc.2",
-    "@deepseek-ai/dsh-session": "^0.1.1-rc.2"
+    "@deepseek-ai/cordis": "4.0.2",
+    "@deepseek-ai/dsh-commands": "^0.1.5-rc.3",
+    "@deepseek-ai/dsh-session": "^0.1.5-rc.3"
   },
   "scripts": {
     "bundle": "tsdown",