@selesai/code 0.13.15 → 0.13.18

package/dist/extensions/capability-gateway/integration.test.ts

@@ -16,6 +16,7 @@ import {
 const EXTENSIONS_DIR = fileURLToPath(new URL("../../", import.meta.url));
 const GATEWAY_DIR = fileURLToPath(new URL(".", import.meta.url));
 const GREP_APP_DIR = fileURLToPath(new URL("../grep-app", import.meta.url));
+const INLINE_SKILLS_FILE = fileURLToPath(new URL("../inline-skills.ts", import.meta.url));
 
 interface Harness {
 	session: AgentSession;
@@ -212,4 +213,26 @@ describe("capability gateway integration", () => {
 		expect(result?.messages?.[0]?.content).toContain("research");
 		expect(h.session.systemPrompt).not.toContain("Research instructions body.");
 	});
+
+	it("does not recommend capability_skill_show for an inline-loaded $skill", async () => {
+		const h = await createGatewaySession({
+			enabled: true,
+			withSkill: true,
+			extensions: [GATEWAY_DIR, GREP_APP_DIR, INLINE_SKILLS_FILE],
+		});
+		harnesses.push(h);
+		const runner = h.session.extensionRunner;
+		const input = await runner.emitInput("Use $research now", undefined, "interactive", undefined);
+		expect(input.action).toBe("transform");
+		if (input.action !== "transform") throw new Error("inline skill was not expanded");
+		expect(input.text).toContain("Research instructions body.");
+
+		const result = await runner.emitBeforeAgentStart(
+			input.text,
+			undefined,
+			h.session.systemPrompt,
+			{ cwd: process.cwd() } as never,
+		);
+		expect(result).toBeUndefined();
+	});
 });

package/dist/extensions/pi-hermes-memory/CHANGELOG.md

@@ -11,14 +11,32 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 
 - **Opt-in memory lifecycle timings**: `PI_TIMING=1` now reports startup synchronization and loading, backfill and live-index callbacks, shutdown flush/index/wait/close, and database open/integrity-check/checkpoint durations. Normal runs produce no timing output.
 
+- **Opt-in SQLite session retention** ([#183](https://github.com/chandra447/pi-hermes-memory/issues/183)): new `sessionRetentionDays` setting (default `0`, disabled). When set to a positive value, sessions whose JSONL source file has not been updated within the window are pruned from SQLite at startup — rows only, the JSONL files themselves are never deleted — and both the deferred backfill and `/memory-index-sessions` skip files outside the window, so pruned sessions stay pruned instead of being re-indexed on every startup. With the default `0`, pruning is fully disabled and startup keeps the legacy count-only backfill preflight.
+
+### Changed
+
+- **Natural-language search now filters common stop words** ([#184](https://github.com/chandra447/pi-hermes-memory/pull/184)): session and memory searches drop function words (`the`, `is`, `what`, …) before FTS5 matching, improving precision for natural-language queries. Intent-bearing words (`can`, `need`, `off`, `like`, `get`, …) are deliberately kept. A query made up entirely of stop words no longer returns an empty result — it degrades to a scoped literal substring search over the original terms.
+
+### Fixed
+
+- **FTS5 index errors during markdown sync are surfaced instead of hidden** ([#184](https://github.com/chandra447/pi-hermes-memory/pull/184)): when the FTS5 search index is broken, memory writes still succeed in Markdown, but the tool result and `/memory-sync-markdown` now report the degraded search state together with the repair command instead of showing a silent zero-count success. Genuine database corruption is unaffected by the fallback and now recovers through the markdown sync path too: reconciliation runs inside `DatabaseManager.withCorruptionRecovery()`, so a corrupt `sessions.db` is quarantined, rebuilt, and the sync retried instead of failing every memory write.
+- **Rapid Markdown memory writes now reuse a recent recovery snapshot** ([#214](https://github.com/chandra447/pi-hermes-memory/issues/214)): successive overwrites within one hour publish atomically without creating another `.recovery-*` sidecar, while slower writes still take a fresh snapshot for crash recovery.
+- **Policy-only memory writes bypass the Markdown character cap** ([#218](https://github.com/chandra447/pi-hermes-memory/issues/218)): SQLite is the query authority in policy-only mode, so adds, replacements, and atomic mutation plans can exceed the Markdown export limit without triggering automatic consolidation. Legacy-inject mode keeps its existing caps, grace windows, auto-consolidation, failure limits, and FIFO eviction.
+
+- **SQLite open integrity scans can be disabled** ([#194](https://github.com/chandra447/pi-hermes-memory/issues/194)): set `quickCheckOnOpen` to `false` to skip the asynchronous startup `PRAGMA quick_check`; operation-time corruption recovery remains enabled.
+
 ### Fixed
 
+- **`memory_search` accepts `target: "project"`** ([#212](https://github.com/chandra447/pi-hermes-memory/issues/212)): the tool schema only declared `memory`/`user`/`failure` as `target` filter values, while `memory_add` writes with `target: "project"` and search results label those very entries `[target=project]` (the value `memory_replace` / `memory_remove` then require) — so filtering by the mutation target shown in the results failed schema validation ("Validation failed for tool") before the handler ever ran, and the only workaround (`project: "<name>"`) required knowing the project name up front. `target: "project"` now passes validation and resolves to `target = 'memory' AND project IS NOT NULL`, exactly the entries whose displayed mutation target is `project`; project-attributed failures remain labeled `[target=failure]` and are not matched. The injected memory-policy guidance now lists the fourth accepted value.
+
 - **Clean process exit on Node 24+** ([#193](https://github.com/chandra447/pi-hermes-memory/issues/193), reported by [@vanneswong](https://github.com/vanneswong)): `better-sqlite3` 12.x inherits Node's raw `node::ObjectWrap`, whose destructor calls `RemoveEnvironmentCleanupHook` after Node has torn down its Environment — so on Node 24 (observed on Linux aarch64) Pi could abort with SIGABRT and a non-zero exit code at every shutdown, after all work completed. The dependency moves to `better-sqlite3@^13.0.3`, the first N-API/node-addon-api release, which removes that crash path. The public API this extension uses is unchanged; the declared engines (`>=22`) cover every Pi-supported runtime.
 
 - **Snapshot retention converges for dormant memory stores** ([#202](https://github.com/chandra447/pi-hermes-memory/issues/202)): retention caps for `.recovery-*` / `.retired-*` sidecar files only ran inside `saveToDisk()`, so a project store that stopped being written kept its snapshots past the count, age, and byte limits forever (one reported store held 171 recovery snapshots against a cap of 32). Each `session_start` now sweeps the global store and every discovered project store with the identical per-file policy under the same mutation lock; enumeration skips symlinks, hidden directories, and nested paths.
 
 - **Reload no longer waits for an unnecessary LLM memory flush**: Pi preserves the current session during `/reload`, but the shutdown handler ignored `event.reason` and awaited direct completion plus possible subprocess fallback after six user turns. Reload now skips both transports; quit and session-replacement reasons keep the existing flush policy.
 
+- **`memory_search` ranks by relevance instead of recency** ([#118](https://github.com/chandra447/pi-hermes-memory/pull/118)): FTS5 matches were ordered by `last_referenced DESC` alone, so a long note that mentions a query term once outranked a short memory that is entirely about it, purely because it had been touched more recently. The match now joins `memory_fts` and orders by `bm25(memory_fts)` ascending with `last_referenced DESC` as the tie-break, so the densest match wins and recency only decides between equally relevant rows. Result *sets* are unchanged; only their order is.
+
 ## [0.9.4] - 2026-08-08
 
 ### Added

package/dist/extensions/pi-hermes-memory/README.md

@@ -61,11 +61,11 @@ No manual action is needed. Launch Pi once after upgrade to let migration/normal
 | 📚 **Procedural Skills** | The agent saves *how* it solved problems as reusable docs |
 | ⚡ **Background Learning** | Every 10 turns (or 15 tool calls) the agent reviews and saves |
 | 🔧 **Correction Detection** | When you correct the agent, it saves immediately |
-| 🔄 **Auto-Consolidation** | When memory hits capacity, auto-merges instead of erroring |
+| 🔄 **Auto-Consolidation** | When legacy-inject memory hits capacity, auto-merges instead of erroring |
 | 🛡️ **Secret Scanning** | API keys, tokens, SSH keys blocked from persistence |
 | 📊 **Memory Aging** | Entries carry timestamps — consolidation knows what's stale |
 | 🏗️ **Two-Tier Memory** | Global + per-project memory, both searchable |
-| 💾 **Extended Store** | Unlimited searchable memories beyond core 5,000-char limit |
+| 💾 **Extended Store** | Policy-only memories remain searchable in SQLite beyond the Markdown export cap |
 | 🎓 **Onboarding** | `/memory-interview` pre-fills your profile on first session |
 
 ## How It Works
@@ -379,14 +379,14 @@ When you correct the agent, it saves immediately — no waiting for the backgrou
 
 ### Auto-Consolidation
 
-When memory, user profile, or failure memory hits its character limit, the extension automatically consolidates instead of returning an error:
+In `legacy-inject` mode, when memory, user profile, or failure memory hits its character limit, the extension automatically consolidates instead of returning an error:
 
 1. Spawns a one-shot `pi.exec()` process with a consolidation prompt
-2. The child agent merges related entries, removes outdated ones, keeps the most important facts
-3. Parent reloads from disk and retries the original save
-4. If consolidation fails, falls back to the original error
+2. The child agent merges related entries, removes outdated ones, and keeps the most important facts
+3. The parent reloads from disk and retries the original save
+4. If consolidation fails, the original error returns
 
-You can also trigger this manually with `/memory-consolidate`.
+In `policy-only` mode, SQLite is the query authority, so adds, replacements, and atomic mutation plans can exceed the Markdown export cap without automatic consolidation. You can still trigger consolidation manually with `/memory-consolidate`.
 
 ### Tool-Call-Aware Review
 
@@ -495,6 +495,8 @@ Create `~/.selesai/agent/hermes-memory-config.json`:
   "memoryDir": "~/.selesai/agent/pi-hermes-memory",
   "projectsMemoryDir": "projects-memory",
   "sessionSearch": { "variant": "legacy" },
+  "sessionRetentionDays": 0,
+  "quickCheckOnOpen": true,
   "llmModelOverride": "openrouter/deepseek/deepseek-v4-flash",
   "llmThinkingOverride": "off",
   "childExtensionPaths": ["~/.selesai/agent/git/github.com/example/custom-provider-extension/index.ts"],
@@ -526,12 +528,14 @@ Create `~/.selesai/agent/hermes-memory-config.json`:
 | `memoryPolicyStyle` | `full` | Policy text used in `policy-only` mode: `full` preserves the default v0.7 policy; `compact` uses shorter built-in guidance; `custom` uses `memoryPolicyCustomText`; `none` injects no policy text |
 | `memoryPolicyCustomText` | unset | Custom policy text used when `memoryPolicyStyle` is `custom`; blank or missing text falls back to `compact` |
 | `standingInstructionsEnabled` | `true` | Inject `STANDING.md` (pinned via `/memory-pin`) into every session, in every memory mode |
-| `memoryCharLimit` | `5000` | Max characters in MEMORY.md |
-| `userCharLimit` | `5000` | Max characters in USER.md |
-| `projectCharLimit` | `5000` | Max characters in project-scoped MEMORY.md |
+| `memoryCharLimit` | `5000` | Max characters in MEMORY.md in `legacy-inject` mode; policy-only writes may exceed the Markdown export cap |
+| `userCharLimit` | `5000` | Max characters in USER.md in `legacy-inject` mode; policy-only writes may exceed the Markdown export cap |
+| `projectCharLimit` | `5000` | Max characters in project-scoped MEMORY.md in `legacy-inject` mode; policy-only writes may exceed the Markdown export cap |
 | `memoryDir` | `~/.selesai/agent/pi-hermes-memory` | Custom directory for extension storage files |
 | `projectsMemoryDir` | `projects-memory` | Subdirectory under `~/.selesai/agent/` for project-scoped memory |
 | `sessionSearch` | `{ "variant": "legacy" }` | Session search implementation: `legacy` keeps the existing SQLite/FTS snippet search; `anchors` uses the opt-in Markdown request surface and returns compact JSONL line-range anchors from `~/.selesai/agent/sessions/` |
+| `sessionRetentionDays` | `0` | Opt-in SQLite session retention, in days. `0` (default) disables pruning entirely and keeps the legacy count-only backfill preflight. When positive, sessions whose JSONL source file was last modified longer ago than the window are pruned from SQLite at startup — **rows only; the JSONL files in `~/.selesai/agent/sessions/` are never deleted** — and both the deferred backfill and `/memory-index-sessions` skip files outside the window, so pruned sessions stay pruned instead of being re-indexed |
+| `quickCheckOnOpen` | `true` | Run a full SQLite integrity check asynchronously after opening the database; set to `false` to skip the startup scan (operation-time recovery remains enabled) |
 | `llmModelOverride` | unset | Optional model override for background review (direct and subprocess), correction save, session flush, and consolidation |
 | `llmThinkingOverride` | unset | Optional thinking override for those LLM calls; valid values are `off`, `minimal`, `low`, `medium`, `high`, and `xhigh`. If `llmModelOverride` is set and this is omitted, review/child calls default to `off` |
 | `childExtensionPaths` | unset | Trusted provider/auth extension sources explicitly allowed in isolated child Pi processes. Values are passed to Pi's standard `-e` resolver, so absolute paths, `~/...`, paths relative to the child working directory, and `git:`/`npm:` package sources are supported. Sibling packages matching the `*-oauth-adapter`/`*-auth-adapter` naming convention (including scoped packages, via their `package.json` `pi.extensions` manifest) are detected automatically. This setting is only needed for custom providers or adapters that are not detected. In-process direct transport (the default for review/flush/correction/consolidation) doesn't need it, since it reads whatever provider auth is already registered. |
@@ -540,7 +544,7 @@ Create `~/.selesai/agent/hermes-memory-config.json`:
 | `reviewRecentMessages` | `0` | Recent messages included in background review (`0` = all) |
 | `reviewEnabled` | `true` | Enable/disable background learning loop |
 | `reviewTransport` | `direct` | LLM transport for background review, session flush, correction save, and manual consolidation: `direct` uses in-process `completeSimple()` with subprocess fallback; `subprocess` forces legacy `pi -p` only |
-| `memoryOverflowStrategy` | `auto-consolidate` | Behavior when MEMORY.md, USER.md, failures.md, or project-scoped memory reaches its character limit: `auto-consolidate` runs the existing consolidation flow; `reject` returns an error; `fifo-evict` rotates older entries in file order until the new entry fits |
+| `memoryOverflowStrategy` | `auto-consolidate` | Legacy-inject behavior when a Markdown memory file reaches its character limit: `auto-consolidate` runs the existing consolidation flow; `reject` returns an error; `fifo-evict` rotates older entries in file order until the new entry fits |
 | `autoConsolidate` | `true` | Legacy alias for `memoryOverflowStrategy` when `memoryOverflowStrategy` is not set (`true` = `auto-consolidate`, `false` = `reject`) |
 | `consolidationTimeoutMs` | `180000` | Maximum time in milliseconds for a consolidation run (auto and `/memory-consolidate` alike). Configured values are used verbatim; a consolidation pays child-process boot plus a full LLM turn, so values below the default are frequently killed mid-run and log a warning at startup |
 | `overflowGraceMs` | `180000` | Wall-clock grace period after a memory overflow before automatic consolidation is retried; this gives the active agent time to consolidate manually. Set to `0` to disable the grace period |
@@ -615,7 +619,7 @@ The `sessions.db` SQLite database stores session history and extended memory ent
 - **Background review cost**: Each review cycle costs one full LLM API call via a child `pi -p` process. Correction detection and explicit skill saves can add additional calls when the agent decides they are worth it.
 - **Session search requires indexing**: Past sessions must be indexed before they're searchable. Run `/memory-index-sessions` to bulk-import, or let the extension auto-index on session shutdown.
 - **Older Markdown memories may need backfill**: If you saved memories before the SQLite mirror existed or search looks stale, run `/memory-sync-markdown`.
-- **Core memory limits still apply**: SQLite search mirroring does not bypass the 5,000-char core Markdown limit. If consolidation cannot free space, the write fails instead of becoming SQLite-only memory invisibly.
+- **Core memory limits apply in `legacy-inject` mode**: policy-only writes can exceed the Markdown export cap because SQLite is the query authority, while manual `/memory-consolidate` remains available.
 - **System prompts are invisible**: Pi's TUI does not display the system prompt. Use `/memory-preview-context` to inspect whether policy-only or legacy memory injection is active.
 - **Project skill visibility depends on Pi discovery cycles**: project skills are exposed through `resources_discover` using the active project's `skills/` path. If a moved or newly created project skill doesn't show up immediately in a running session, trigger a reload/new session so Pi refreshes discovered resources.
 - **Project move requires active project context**: in `/memory-skills`, the `p` hotkey is disabled when Pi is not currently in a detected project directory.

package/dist/extensions/pi-hermes-memory/docs/ROADMAP.md

@@ -294,7 +294,7 @@ Agent has access to tools:
 - [ ] Auto-index session on shutdown
 - [ ] Char limits: MEMORY.md 2,200 → 5,000, USER.md 1,375 → 5,000, project 2,200 → 5,000
 - [ ] Config: `sessionSearchEnabled: boolean` (default: true)
-- [ ] Config: `sessionRetentionDays: number` (default: 90)
+- [x] Config: `sessionRetentionDays: number` (default: `0` = disabled) — shipped via [#184](https://github.com/chandra447/pi-hermes-memory/pull/184)
 
 ### What Does NOT Change