Solution for long term memory for agent coding CLIs and to facilitate handoff between different agent vendors
Rust
Merge main into release/3.3
AkitaOnRails7e52f77290e1
diff --cc CHANGELOG.mdindex fed4851f,3c43cec9..d5d2de36--- a/CHANGELOG.md+++ b/CHANGELOG.md@@@ -11,417 -11,13 +11,422 @@@ version in [`docs/changelog/`](docs/cha## [Unreleased]+### Added++- Added `[ingest] record_tool_names` (`AI_MEMORY_INGEST__RECORD_TOOL_NAMES`),+ off by default. When it is on, each tool call keeps its own name, so a+ Claude Code shell call is stored as `tool non-file: Bash` instead of+ `tool non-file`. A `Skill` call also keeps the skill it ran, and an `Agent`+ call keeps its subagent type. Session pages count calls by name and+ handoffs list them by name. Only short identifiers are kept, never a tool's+ arguments, and a call that a capture policy reduced to metadata stays+ unnamed (#1851).++- `global_scope_hits` now include their workspace, project, and global scope,+ and `memory_read_page` accepts `scope: "global"`. Supplemental global search+ results can therefore be read directly without risking a same-path lookup in+ the caller's active project (#1802).++- Added `--project-id` to managed launches and checkout-local discovery to+ recover populated legacy name collisions without moving or merging history.+ An interactive launch offers authorized project choices and remembers the+ selection for that server and checkout. Resumes reuse the binding, and+ ID-selected runs keep startup context and hook capture in the selected scope+ after checking current access, run ownership and native session identity.+ Existing name selectors and legacy runs retain their behavior (#1833).++- Added `ai-memory run --no-exit-prompt`, `[run] exit_prompt = false`, and+ `AI_MEMORY_RUN_EXIT_PROMPT=false` to skip the switch/rerun menu after a+ successful interactive session. The menu remains enabled by default (#1776).++- `ai-memory merge-project --workspace <w> --from <source> --into <target>`+ losslessly joins two project identities inside one workspace. Its default is+ an exact dry run; `--confirm` re-stamps page history, sessions, observations,+ handoffs, embeddings and managed workstreams in one writer transaction, then+ removes the source project. Same-path pages get a new target version that+ appends the source body behind an `ai-memory:merged-from` marker while both+ prior histories remain restorable. The target frontmatter wins, a one-sided+ expiry is removed, and the combined page is flagged stale for consolidation.+ `restore-page --page-id <uuid>` restores either retained history even after+ the source identity is removed. Open sessions and live managed runs refuse+ the merge (#1645).++- `audit-contamination` now reports projects in one workspace whose names+ collide after Unicode compatibility decomposition, case folding, and+ removal of non-spacing marks. Findings distinguish case from accent+ differences and include page/session counts plus last activity (#1645).++- Cross-project messages can carry an optional epistemic `nature` (`unknown`,+ `measured`, `reported`, or `inferred`) and bounded supporting `evidence`.+ The server refuses a `measured` send without non-empty evidence; existing+ messages and callers remain `unknown` by default (#1428).++- Added `memory_patch_page` for atomic, heading-anchored edits to an existing+ Markdown page without re-emitting its body or metadata. It requires the+ page's current `page_id`; section replacement additionally requires the+ bounded SHA-256 token returned by `memory_read_page`. Missing, duplicate or+ fenced-code headings, stale tokens, conflicting edits, failed admission and+ concurrent writes leave the page unchanged. The typed TypeScript client+ exposes the same contract as `pages.patch` (#1697).++- Added an offline `ai-memory-eval abstention` benchmark with versioned+ clean-room answerable, hard-negative, conflicting, partial and+ missing-channel fixtures; raw lexical/score/density/belief signals;+ FSR/FAR/coverage threshold sweeps with undefined denominators preserved;+ optional reuse of pinned LongMemEval `*_abs` cases; and optional structured+ LLM answerability through the existing QA provider path. Conflicting and+ partial cases remain separate from binary ground truth, no threshold is+ presented as calibrated, and production runtime behavior is unchanged.+ The retrieval evaluator now also parses production's structured+ `{text,citations}` answer shape instead of a stale string (#1717).++- Added `[briefing] inject_on_subagent_start` to `.ai-memory.toml`. A project+ that sets it hands each `claude-code` subagent the project brief when the+ subagent starts: the same pinned, `_rules/` and `_slots/` brief that+ `inject_on_session_start` adds at session start, kept within `max_chars` and+ within the 10,000-character limit of that agent's hook context. The hook+ reads it from a new read-only `GET /brief`, which resolves and authorizes the+ project as `/handoff` does but never reads or claims a handoff, so a subagent+ cannot take its parent session's baton. A server without the route answers+ 404 and the subagent starts as before. The native hook and the+ `hooks/claude-code` shell and PowerShell scripts deliver it, and every marker+ parser treats the key as a settings boundary. It is off by default (#1715).++- Added an optional `[query_answer] max_context_tokens` admission budget for+ answer synthesis. It preserves retrieval hits, reports omitted or clipped+ evidence, prioritizes known newer corrections, prefers whole snippets and+ clips only complete trailing sentences or statements into leftover space. It+ skips the model when no meaningful evidence fits. The default+ remains disabled (#1684).++- `GET /admin/status` and `ai-memory status --json` now carry a+ `consolidation` block: the queue counts plus up to 20 `failed_sessions`+ (`session_id`, `attempts`, `failed_at_us`, scrubbed `last_error`), newest+ first. A consolidation run that gives up after its retries now has a+ machine-readable record with the session ids needed to re-run it, instead of+ only a journal line and the `/health` panel's count — which also resets with+ the process. The web health panel's own view stays counts-only, and an older+ server's status shape is unchanged (#1692).++- Added the bundled `coding-v1` retrieval-evaluation corpus for offline checks+ of decision rationale, resolved-error causes, correction evidence, and late+ session details. It reuses the existing scorer and A/B reports; it measures+ evidence retrieval, not semantic answer correctness or handoff behavior (#1686).++- `[auto_improve.eval] builtin = "structure"` runs the eval gate's structural+ checks in process, so the gate needs no interpreter, no scorer script inside+ the container and no timeout to hit. It checks an H1, an upper-case+ `TODO`/`TBD` placeholder (a hard failure), a `##` section and a list of steps+ for `procedures/`, and text beyond the heading within 2,400 characters for+ `_rules/` — never a section name or a wording, so the wiki's language does+ not matter. `eval_results` records `checker_name = "builtin:structure"`.+ `builtin` and `command` are mutually exclusive; `command` is unchanged for+ project-specific scorers (#1638).++- `ai-memory llm-test --server` probes the server's own configured provider+ instead of building one from the caller's environment, through a new+ root-only `POST /admin/llm-test`. The retry hint that `status` and the health+ panel print now names it: with the server in a container or on another host+ its keys exist only there, so the old client-side hint failed with "no API+ key" or a provider `400` while the server was healthy. The probe runs one+ fixed short prompt, reports provider, model, latency and the error class, and+ scrubs the provider's message before printing it (#1639).++- Added `[handoff] deliver_on_session_start = false` to `.ai-memory.toml`. A+ project that sets it no longer gets its handoff, or the continuity notice, at+ session start; the handoff is still created when the session ends and stays+ open for `memory_handoff_accept`. The native hook, the shell and PowerShell+ scripts and the generated TypeScript integrations send `handoff=0` only when+ the value is explicitly falsy (#1621).++- Added first-party Qoder CLI/IDE lifecycle and MCP support. Both installers+ merge into `~/.qoder/settings.json`: `install-mcp --client qoder` writes a+ sessionless stdio bridge, while `install-hooks --agent qoder` registers the+ eight documented memory-bearing events as native commands. Session start+ delivers a pending handoff through `hookSpecificOutput.additionalContext`,+ prompt/tool capture uses Qoder's Claude-shaped payloads, and a missing hook+ `cwd` falls back only to `QODER_PROJECT_DIR`. Setup detects `~/.qoder`,+ uninstall removes both entries, and agent backups include its settings and+ shared AGENTS-compatible skills/instructions (#1611).++- Profile writes now return `digest_warning` when the selected summary,+ abstract, or prose statement exceeds the 240-byte session-start digest+ limit. The write still succeeds, but its author can shorten the summary+ instead of discovering the truncation only in a later session (#1609).++- Added project routing for the named profiles of a multiplexing Hermes+ gateway. The gateway exports only the default profile's `terminal.cwd`, so+ every other profile's events used to fall back to the gateway's own working+ directory and all its bots landed in one project. A gateway event of a named+ profile now routes by an `.ai-memory.toml` placed in that profile's Hermes+ home (`~/.hermes/profiles/<name>`, or under the gateway's `HERMES_HOME`), and+ that marker's capture exclusions and server profile apply. A profile without+ such a marker keeps the old behavior. The profile name is checked against+ Hermes' profile-id pattern before it is used as a path (#1597).++- Added Hermes Agent hook consent to `ai-memory doctor`. Hermes runs a shell+ hook only when that exact command is approved in the home's+ `shell-hooks-allowlist.json`, and each profile under+ `~/.hermes/profiles/<name>` keeps its own allowlist. A profile with the+ ai-memory hooks in `config.yaml` but no approvals captured nothing, and its+ gateway only logged `not allowlisted — skipped` for each event. `doctor` now+ reads the root home and every profile, reports which ai-memory hook events+ each one wires, and warns about every profile whose events are not+ allowlisted (unless `hooks_auto_accept` is on), with the `hermes -p <name>+ --accept-hooks` command that approves them. The JSON output gains a `hermes`+ array. It never writes either file and never prints the hook commands,+ which can embed a bearer token (#1598).++- Added `AI_MEMORY_RERANK_TIMEOUT_SECS` (`rerank_timeout_secs` in+ `config.toml`) to set the `memory_query` reranker budget, which was fixed at+ 20 seconds. The default stays 20 and zero is rejected at startup. A hosted+ provider behind an LLM fallback chain can spend the whole fixed budget on one+ slow 503 before the next candidate answers, and every such query then keeps+ its pre-rerank order. ([#1614](https://github.com/akitaonrails/ai-memory/issues/1614))++- `ai-memory status` now shows the client's version next to the server's: a+ `ai-memory X (client)` line under `ai-memory X (server)`, and `version` in+ the JSON `client` object. In a split install (native client and hooks, the+ server in a container or on another host) the two drift apart when only one+ side is upgraded, and nothing showed it. When they differ in major version,+ the text report adds a warning to upgrade the older side (#1644).++- Added editing for queued messages in the web inbox. Edit takes a message that+ is still waiting out of the queue, so no agent can collect it, and opens an+ inline editor. Saving puts the new text back at the message's original place+ in the queue, after the usual sanitizer, size caps and `message_send`+ admission. Discarding returns it unchanged. A held message shows as Editing,+ with a count above the list and a way back into the editor. Editing needs+ write access to the mailbox project and to the project the message came from,+ and a message an agent already collected cannot be edited. Held messages use a+ new `editing` state (migration V95) that no claim path selects (#1832).++- Added server-side response investigation to the project dashboard. Responses+ can be filtered by UTC period, exact model, harness, session, turn and tool,+ with complete pagination, filtered token totals and bounded native turn and+ tool provenance. The context lives in extra `token_calls` columns and a+ `token_call_tools` table (migration V94). A response from an older hook keeps+ its provenance unknown instead of guessed. Filters apply after project+ authorization and the session-owner check and before counting, ranking and+ pagination (#1830).++- Added version-specific knowledge evidence to the page and project views:+ readable source links, declared contradictions, expiration context and an+ on-page recall recomputation that reuses the original search filters (#1830).++- Added caller-aware installation states and next steps to feature guides and+ the authenticated `/api/v1/docs/features/status` reference. They+ separate effective settings from client facts the server cannot know, and+ administrative settings are masked for callers without admin rights (#1830).++- Replaced the static Inbox label with live, access-filtered pending counts and+ project links throughout the web navigation. Counts are grouped by workspace+ and project, hide restricted projects, never consume mail, and link to the+ pending-only mailbox of the project that has mail. Received inboxes open on+ pending messages, with older queued requests behind collected history, and the+ composer shows the current project explicitly (#1830).++- Added bundled product documentation to the web UI and the API. The guides and+ release notes are compiled into the binary and served at `/web/docs`,+ `/web/docs/changelog` and `/web/docs/{id}` (a `.md` suffix returns the+ Markdown). They include searchable feature activation guides, per-release+ changelogs, and authenticated `/api/v1/docs` JSON and Markdown references for+ agents. No network access or LLM is needed, and the pages describe shipped+ capabilities without exposing the running server's configuration or+ credentials. The source-built Docker image now copies `CHANGELOG.md` for this+ (#1829).++- Organized project pages into accessible tabs showing one section at a time: Overview,+ Agents, Token usage, Sessions and Knowledge. The selected tab is kept in the+ URL (`?tab=agents`), which keeps reload, shared links and browser history in+ sync, and the tabs support Left, Right, Home and End. Existing+ `#agents`-style section bookmarks still open the matching tab (#1829).++- Updated the browser inbox composer to default To project to the source+ project and list only harnesses with captured sessions in the destination+ workspace and project. It resets a stale recipient when a project changes,+ and it disables sending, with an explanation, for a project that has no+ registered agent (#1829).++- Redesigned the responsive web dashboard. It has persistent workspace+ navigation, searchable project cards, per-agent consumption and coverage, and+ session drilldowns that show the token totals recorded for each agent (#1828).++- Added a browser inbox at `/web/inbox`. It lists received and sent mail+ without consuming it. A caller with write access to both the source and the+ destination project can also queue a message for a registered harness of that+ project. The text goes through the configured sanitizer and admission before+ the single writer, and the browser never claims mail or starts an agent.+ Messages can now be addressed to one harness (`to_agent`, migration V93).+ `memory_message_pop` and `ai-memory message pop` take an optional `agent`,+ and only that harness can claim the message, even by id. Existing shared mail+ (`to_agent = NULL`) behaves as before. A claim from a session-aware client+ whose routing metadata arrives before its session start was persisted is no+ longer refused. A browser session opened with the legacy read-only login can+ send with an explicit write token supplied for that one request and cleared+ right after, with no browser persistence (#1828).++- Added live, deduplicated response token accounting for Claude Code and Codex.+ Updated native hooks to send measured response usage on `post-tool-use`,+ `stop`, `pre-compact` and `session-end`, keeping open-session totals current+ rather than waiting for session end. Each response is stored once by its+ native identity in a new `token_calls` ledger (V92). A partial or replayed+ delivery raises the stored counters column by column and never adds the same+ response twice. Live extraction reads a bounded 4 MiB transcript tail and+ reports at most 256 responses per event. Fresh input excludes cache reads, so+ Codex, whose reports included cached input, is normalized once during the+ upgrade. The project page has a Token usage panel listing the fifty largest+ captured responses. It flags contexts of at least 100,000 tokens, outputs of+ at least 20,000 tokens and responses above three times the project average.+ Only counters, response identities and model names are kept, and project+ authorization and session-owner filters apply before ranking or aggregation+ (#1811).++- Added Light, Dark and System theme controls to the web UI. The choice is+ stored in the browser and System follows the operating system. Tailwind's+ dark variant now uses the `dark` class instead of the media query, so a+ manual choice overrides the system setting (#1811).++- Added a memory dashboard to the read-only web home, using sanitized data:+ projects, sessions, sanitized capture events, compiled pages, open-session+ continuity signals and last activity. Project cards separate captured work+ from compiled pages, so an active hook no longer looks empty just because+ its sessions have not ended (#1803).++- Added dashboard hook-health counters for accepted, policy-dropped,+ capacity-shed and rate-limited events. They count events since the process+ started, and prompt, command, path and payload data is neither persisted nor+ rendered (#1803).++- Added agent CLI attribution to the project overview to show which harnesses+ produced a project's memory. The stats card has an "Agents" badge row with session counts per+ harness, and each Recent Activity entry shows the harness whose session last+ contributed evidence to that page version. Both are best effort: a page or+ project with no session evidence shows no badge (#1803).++- Added per-session token accounting. At `session-end` the native hook (Claude Code+ and Codex) reads the harness's own transcript and reports cumulative input,+ output, cache-write and cache-read totals. It scans Claude Code's JSONL in+ full and reads only the tail of Codex's rollout file, since both can reach+ hundreds of MB. The server stores the totals with a `MAX(existing, reported)`+ upsert, so a replayed or out-of-order delivery never lowers a total. The+ project overview page shows a "Tokens" total in the stats card and a Sessions+ table (agent, start, duration, events, tokens) with the 20 most recent+ sessions. A session whose harness never reported usage, an unsupported+ harness or an older client shows no number, never a zero (#1803).++- Added recovery of usage and closure for sessions missing a graceful+ `session-end`, which previously stayed open without tokens. This usually+ happens when a paid quota runs out mid-task and the operator switches agents. When a new session+ starts in the same scope and finds one quiet for at least 15 minutes, the+ client looks for the old session's own transcript (Claude Code and Codex),+ reports its usage and closes it with a normal synthetic `session-end`. That+ is safe if the old session turns out to be live, because a later real+ `session-end` with more work runs the full end path again. A second, more+ conservative scheduled sweep closes sessions nobody continues anywhere,+ after 48 hours without activity in any scope, so `open_session_count` stops+ growing. It attaches no usage and starts no consolidation, because the+ server cannot read a client's transcript outside a live hook request (#1803).++- Added optional `max_chars` to `memory_read_page` (default 12000,+ minimum 500, maximum 64000). It caps the returned body with the same visible+ truncation marker as `memory_read_session_observations`. The response always+ includes `truncated` and `total_chars`, which report whether the body was cut+ and its full size (#1827).++### Changed++- `memory_lint` now reports embedding-band pairs as+ `similarity_candidate` instead of `contradiction`, and no longer infers that+ a newer page supersedes an older one from timestamps alone. Explicit+ `contradicts` edges remain `contradiction` findings (#1685).++- `move-project` now refuses the **copy+purge merge** — the path taken when the+ destination workspace already holds a project of the same name — unless+ `--allow-lossy-merge` is passed as well as `--confirm`. That path keeps only+ the source's latest pages and deletes the project with its sessions,+ observations, handoffs and older page versions, which `--confirm` written for+ "move this project" did not say; the refusal answers `409` with the counts it+ would discard. A true-move (fresh destination, everything preserved) is+ unchanged, and `merge-workspace`, whose command already says merge, keeps+ working without the extra flag (#1713).++- `memory_install_self_routing(compact: true)` and `ai-memory+ install-instructions --compact` now return a block that is actually compact:+ 2.1 KB instead of 5.9 KB, close to the 7.9 KB full block it was supposed to+ replace. It keeps the rules a session needs without reading anything else+ (scope selection for session-aware and static clients, managed-run resume,+ capture, the untrusted-memory trust rule, and where rules belong) and points+ at the installed `ai-memory-*` Agent Skills for the rest, which it already+ required to be installed (#1672).++- When the native session linked to a workstream is missing from its store,+ an interactive `ai-memory run <harness>` now also names the newest session+ this checkout still holds for that harness and the native selector that+ resumes it, such as `resume <id>` for Codex. The launch still starts fresh+ as before; running the same command again with that selector right after+ the harness name links that session instead (#1654).++- Managed-workstream startup packets now render completed tool calls and+ results as compact provenance stubs instead of spending the 30,000-character+ resume budget on raw command output or generated file content. Conversation,+ checkpoints, compactions, and annotations remain inline; the complete+ sanitized tool evidence stays searchable in the ledger (#1607).++- The LLM fallback chain now logs its own events. A transient candidate+ failure logs a warning with that candidate's provider, model, chain+ position, error class, HTTP status and cooldown, and an info line records+ each change of the answering candidate. Before, the chain logged nothing,+ and callers such as the reranker named only the first candidate, so a log+ could blame the primary for a timeout another candidate caused. Response+ bodies are never logged (#1628).++- Reduced the default output of `memory_read_session_observations`: `limit`+ from 50 to 20 and `body_max_chars` from 4000 to 1000. Callers can still raise+ them to the unchanged ceilings of 200 and 16384. The smaller response reduces+ token costs for routine "what did this session do" lookups. Updated the+ retrieval skill with an `order="desc"` recipe using a narrow `kinds` filter+ and small `limit` and `body_max_chars` values to avoid reading the whole+ session (#1827).+### Fixed+- Fixed live response capture after transcript gaps. Bounded batches now resume+ from durable enqueue checkpoints, including across hook processes and+ transcript read windows (#1830).++- Fixed response search, signal filtering and recent ordering so they query all+ authorized calls before pagination. Response pages are independent, and+ session detail pages refresh usage live (#1830).++- Updated scoped session reads to treat substantive work after an old end as a+ resumed session, matching the activity feed while preserving persisted+ lifecycle watermarks. Completed-only listings exclude those resumed sessions (#1830).++- Moved token model label sanitization before truncation to prevent the size+ limit from exposing a prefix of private text (#1830).++- Updated release selection on the changelog page to load notes immediately+ and keep the URL, outline and Markdown reference in sync. The form still submits+ without JavaScript (#1830).++- Added a read-only recovery snapshot at agent startup when the previous+ substantive session in the project ended without a `SessionEnd` (quota+ exhaustion, a killed process, a machine restart). The snapshot is built on+ demand from at most 64 sanitized observations and capped at 6,000+ characters, so no rolling copy of the transcript exists. It is scoped to the+ project and owner, leaves out the receiving session, keeps the+ untrusted-memory boundary, and never closes or claims the source, which may+ be a legitimate parallel agent. It skips work a handoff already covers and+ never mixes another live session's transcript into a delivered handoff.+ Normal single-use handoffs and managed workstream packets are unchanged+ (#1803).++ - Excluded Claude Code's synthetic cross-session messages and plugin-submitted+ prompts from cross-project profile harvesting, and removed a leading+ side-agent quote while retaining the user's words after it. Generated text+ can no longer become a standing preference attributed to the user (#1855).+- Serialized mutating wikisync runs per destination across their fullread/plan/write lifecycle, so overlapping exports no longer race on theshared state temporary file or apply plans from the same baseline (#1847).