Solution for long term memory for agent coding CLIs and to facilitate handoff between different agent vendors
Rust
Merge branch 'fix/1186-powershell-mcp'
AkitaOnRailsbddaf8398b6b
diff --cc CHANGELOG.mdindex e1bb3a9b,cb5e29ff..d3cdc4ed--- a/CHANGELOG.md+++ b/CHANGELOG.md@@@ -8,80 -8,12 +8,86 @@@ and this project adheres to [Semantic V## [Unreleased]### Fixed+- Fixed a purged session coming back. `purge-session` leaves a tombstone so a+ late event cannot recreate the session, but live hook ingest creates its+ session row on a path that never checked it, so the next event for a purged+ session brought back the session and a new observation. Hook ingest now+ refuses it, and the delivery is acknowledged as `dropped_invalid` instead of+ failing and being retried from the client's spool. (#1194)+- Fixed `purge-session` leaving the user's own sentences behind in the+ cross-project profile's evidence: the profile harvests preference-shaped+ sentences from prompts into candidate rows keyed to the session, and the+ purge removed the session but not those rows, so a later pass could still+ converge a purged sentence into a profile page. The purge now deletes the+ session's prompt candidates in the same transaction. (#1195)+- Fixed `move-project` leaving rows on the old workspace. Pending+ cross-project messages (addressed to the project and sent by it), entities,+ page feedback, session purge tombstones and the profile evidence were not+ re-stamped with the project's other tables, so the moved project lost its+ pending mail, its entity retrieval and open feedback findings, and a purged+ session could be recreated. They now move in the same transaction. (#1196)+- Fixed a Codex, Pi, OMP or Grok session going missing once its store held more+ than 2,000 transcripts. Looking a session up by id read the first 2,000 files+ in directory-walk order, so the rest came back as not found: `ai-memory run`+ dropped the linked session and started a fresh one, and a transcript import+ failed. The lookup now reads the transcript that names the session id first,+ then the newest. (#1189)+- Fixed Crush sub-agent sessions being listed as sessions of their own:+ `backfill`, `doctor` and the automatic session pick of `ai-memory run` read+ the Crush `sessions` table without skipping rows that have a parent, so a+ sub-agent session could be imported as a separate session or chosen for the+ resume. The listing now skips them, as session discovery already did.+ (#1190)+- Fixed rules titled in a script without ASCII letters (Cyrillic, CJK, Arabic+ and others) overwriting each other: multi-page consolidation named every such+ rule page `_rules/rule.md`, so only the last survived in the live rules list.+ Each rule now gets a `_rules/rule-<hash>.md` name derived from its title. Rule+ titles in Latin scripts are named as before. A restated non-Latin title+ (case, spacing or punctuation aside) updates its own page. An existing+ `_rules/rule.md` is left in place; delete it once its rule is restated.+ (#1191)+- Fixed auto-improve accepting a proposal whose confidence is outside 0 to 1:+ a model that answered in percent (`85`) cleared the confidence floor and was+ staged, shown to the reviewer as 8500% and ranked first when sorting by+ confidence. Such a value is now rejected as `confidence_out_of_range` and+ recorded with the other rejected candidates. (#1192)+- Fixed the curl hook installer (`ai-memory-install-hooks`) installing event+ scripts that could not run. Every script sources the shared `_lib.sh` helper+ from its own directory or the one above it, but the installer fetched only+ the per-agent scripts, so the helper was never written and each script+ stopped at the line that sources it. The installer now also extracts+ `_lib.sh` from the verified archive into the install root, beside the agent+ directories, and refuses to continue when the archive does not contain it.+ (#1184)+- Fixed the curl hook installer (`ai-memory-install-hooks`) disagreeing with+ the hook bundles about which scripts an agent has. `--agent antigravity-cli`+ always failed: it asked for the seven default event scripts, the Antigravity+ bundle ships four, and the install stopped at the first missing one.+ `--agent claude-code` and `--agent grok` never installed `subagent-start.sh`+ and `subagent-stop.sh`, which their hook config points at, so `install-hooks`+ warned that both were missing. The installer now installs the scripts each+ bundle ships, and a test checks every script-based agent against the+ repository bundles. (#1185)+- Fixed Kiro CLI tool calls being stored with no title or content: Kiro's+ `PreToolUse` and `PostToolUse` hooks carry `tool_name` and `tool_input`+ (plus `tool_response` after the call), and the capture policy already read+ them, but Kiro was missing from the tool-capture mapping, so every Kiro tool+ observation reached the store with a generic title and an empty body. They+ now get the same tool-family title and output summary as Claude Code's.+ (#1187)+- Fixed the generated OpenCode, OpenCode 2, OMP, Pi and OpenClaw integrations+ losing hook events when the server is saturated. They treated every 4xx as a+ permanent rejection, so a `429` (or a `408` or `425`) was dropped instead of+ spooled, and their spool drain deleted each queued entry it met on such a+ response. Both now keep `408`, `425`, `429` and every `5xx` for a later+ drain, as the shell, PowerShell and native hooks already do. Re-run+ `install-hooks --apply` for the agent to regenerate its plugin. (#1188)+ - Fixed Claude Code's Windows `PowerShell` tool being classified as an+ unknown tool, so its output never reached the session record and+ `[capture] ignore_paths` never checked its command. It is now a shell tool+ like `Bash`, in the native hook, the server, and the generated TypeScript+ integrations, and the shell argument reader also follows PowerShell's+ `-Param:value` binding (`Get-Content -Path:docs\adr\x.md`). (#1186)- Fixed generated TypeScript integrations (OpenCode, OpenCode 2, OMP,Pi, OpenClaw) flashing a console window on Windows.`discoverRemoteIdentity` spawned `git config --get remote.<name>.url`diff --cc crates/ai-memory-hooks/src/payload.rsindex cbf518df,7aa6362b..43c4162f--- a/crates/ai-memory-hooks/src/payload.rs+++ b/crates/ai-memory-hooks/src/payload.rs@@@ -2856,71 -2855,48 +2856,113 @@@ mod testsassert!(pre.body_excerpt.is_some_and(|body| !body.is_empty()));}+ /// Kiro CLI's tool hooks carry `tool_name` and `tool_input`, and its+ /// `PostToolUse` adds `tool_response`: a plain string on the v3 engine+ /// (live capture, Kiro CLI 2.16.2) and an object with a `success` flag on+ /// v2. The capture policy already read this shape, but Kiro was absent from+ /// `closed_tool_agent`, so its tool observations were stored with no title+ /// or body, the failure mode Grok had in #931.+ #[test]+ fn kiro_cli_tool_events_keep_their_family_title_and_output() {+ let v3 = HookEnvelope::from_query_and_body(+ HookQuery {+ event: "post-tool-use".into(),+ agent: Some("kiro-cli".into()),+ ..Default::default()+ },+ serde_json::json!({+ "hook_event_name": "PostToolUse",+ "session_id": "kiro-v3-session",+ "cwd": "/workspace/project",+ "tool_name": "read_file",+ "tool_input": {"path": "/workspace/project/sample.txt"},+ "tool_response": "MARKER_KIRO_V3_OUTPUT",+ }),+ );+ assert_eq!(v3.agent, AgentKind::KiroCli);+ assert_eq!(v3.title_hint.as_deref(), Some("tool file"));+ let body = v3.body_excerpt.expect("kiro v3 post-tool body");+ assert!(body.contains("MARKER_KIRO_V3_OUTPUT"), "{body:?}");++ let v2 = HookEnvelope::from_query_and_body(+ HookQuery {+ event: "post-tool-use".into(),+ agent: Some("kiro-cli".into()),+ ..Default::default()+ },+ serde_json::json!({+ "session_id": "kiro-v2-session",+ "cwd": "/workspace/project",+ "tool_name": "fs_read",+ "tool_input": {"operations": [{"mode": "Line", "path": "src/lib.rs"}]},+ "tool_response": {"success": true, "result": ["MARKER_KIRO_V2_OUTPUT"]},+ }),+ );+ assert_eq!(v2.title_hint.as_deref(), Some("tool file"));+ let body = v2.body_excerpt.expect("kiro v2 post-tool body");+ assert!(body.contains("outcome: success"), "{body:?}");+ assert!(body.contains("MARKER_KIRO_V2_OUTPUT"), "{body:?}");++ let pre = HookEnvelope::from_query_and_body(+ HookQuery {+ event: "pre-tool-use".into(),+ agent: Some("kiro-cli".into()),+ ..Default::default()+ },+ serde_json::json!({+ "hook_event_name": "PreToolUse",+ "session_id": "kiro-v3-session",+ "cwd": "/workspace/project",+ "tool_name": "read_file",+ "tool_input": {"path": "/workspace/project/sample.txt"},+ }),+ );+ assert_eq!(pre.title_hint.as_deref(), Some("tool file"));+ assert!(pre.body_excerpt.is_some_and(|body| !body.is_empty()));+ }++ /// Claude Code's Windows `PowerShell` tool shares Bash's payload shape but+ /// fell through to the unknown family, so its output was never stored+ /// (#1186). The PreToolUse body still never carries the command.+ #[test]+ fn claude_code_powershell_tool_keeps_its_family_title_and_output() {+ let post = HookEnvelope::from_query_and_body(+ HookQuery {+ event: "post-tool-use".into(),+ agent: Some("claude-code".into()),+ ..Default::default()+ },+ serde_json::json!({+ "session_id": "s",+ "tool_name": "PowerShell",+ "tool_input": {"command": "Get-ChildItem SENTINEL_COMMAND", "description": "list"},+ "tool_response": {"stdout": "MARKER_POWERSHELL_1186", "stderr": ""},+ "tool_use_id": "toolu_1186",+ }),+ );+ assert_eq!(post.title_hint.as_deref(), Some("tool non-file"));+ let body = post.body_excerpt.expect("powershell post-tool body");+ assert!(body.contains("tool_family: non-file"), "{body:?}");+ assert!(body.contains("MARKER_POWERSHELL_1186"), "{body:?}");++ let pre = HookEnvelope::from_query_and_body(+ HookQuery {+ event: "pre-tool-use".into(),+ agent: Some("claude-code".into()),+ ..Default::default()+ },+ serde_json::json!({+ "session_id": "s",+ "tool_name": "PowerShell",+ "tool_input": {"command": "Get-ChildItem SENTINEL_COMMAND"},+ "tool_use_id": "toolu_1186",+ }),+ );+ assert_eq!(pre.title_hint.as_deref(), Some("tool non-file"));+ let body = pre.body_excerpt.expect("powershell pre-tool body");+ assert!(!body.contains("SENTINEL_COMMAND"), "{body:?}");+ }+/// Grok Build CLI posts a `PostToolUse` with Claude Code's snake_case/// aliases (`tool_name` / `tool_input` / `tool_use_id`). It was absent from/// both `closed_tool_agent` and the `tool_observation_metadata` match, so