Skip to main content
Glama
deenesjakoruzh
EremesNG

Thoth-Mem

by EremesNG
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Local

Thoth-Mem

Memoria persistente para agentes de codificación de IA

npm version Node.js License: MIT

Proporciona a los agentes de codificación memoria de proyecto duradera entre sesiones, compactaciones y reinicios de contexto.

Thoth-Mem es un servidor MCP local-first respaldado por SQLite y FTS5. Preserva decisiones útiles, correcciones de errores, convenciones y continuidad de sesión, y luego recupera solo la evidencia que un agente necesita. La misma instalación también proporciona una CLI, una API HTTP opcional e integraciones nativas de ciclo de vida para los entornos de codificación compatibles.

El ámbito global gestiona la configuración del entorno del usuario actual; el ámbito de proyecto es explícito y se limita al proyecto seleccionado y a su árbol de recibos. Engram, thoth-agents u otra integración de memoria pueden solaparse; trátese solo como una advertencia: thoth-mem no edita, deshabilita, elimina ni escribe en repositorios externos.

Inicio rápido

Requiere Node.js 18 o superior. La configuración nativa es opcional: una conexión MCP manual solo necesita el comando mcp.

Ejecutar el paquete publicado

Inicia el último servidor MCP publicado sin instalar un comando global:

npx -y thoth-mem@latest mcp

Esto inicia el servidor MCP y su puente HTTP local. Añade --no-http cuando solo se quiera el transporte MCP. Las nuevas configuraciones de cliente deben usar el subcomando mcp explícito.

Las integraciones nativas invocan el comando persistente thoth-mem después de la configuración, así que instala o actualiza ese comando globalmente antes de configurar un entorno. Usa npx para ejecutar la implementación de configuración desde el último paquete publicado, inspecciona su plan de cero escrituras y luego aplícalo:

npx -y thoth-mem@latest setup codex --scope global --plan --json
npx -y thoth-mem@latest setup codex --scope global --json

Reemplaza codex por opencode o claude para otro entorno compatible y reinicia ese entorno. Ejecutar setup solo no instala ni actualiza el paquete npm.

Instalar este repositorio

Usa el flujo del repositorio para probar confirmaciones que aún no se han publicado:

pnpm install
pnpm run build
pnpm add -g .
thoth-mem version
thoth-mem setup codex --scope global --plan --json
thoth-mem setup codex --scope global --json

thoth-mem@latest solo contiene la última versión publicada. Reconstruye y vuelve a ejecutar pnpm add -g . después de obtener confirmaciones más recientes no publicadas.

Actualizar una instalación existente

Actualiza primero el paquete. Si hay una integración nativa instalada, vuelve a ejecutar su configuración para que los recursos copiados, habilidades, hooks y declaraciones gestionadas converjan a la nueva versión del paquete:

pnpm add -g thoth-mem@latest
npx -y thoth-mem@latest setup codex --scope global --plan --json
npx -y thoth-mem@latest setup codex --scope global --json

Luego reinicia el entorno o el proceso MCP. Los usuarios de MCP manual no necesitan setup; basta con reiniciar npx -y thoth-mem@latest mcp.

La configuración preserva la base de datos de memoria y la configuración propiedad del usuario. Al iniciar, los campos de configuración faltantes pueden rellenarse automáticamente, pero los valores explícitos, como un modelo de LM Studio, permanecen seleccionados. El formato de configuración sigue siendo "version": 1. Para una instalación publicada, actualiza manualmente una URL $schema anterior a la versión de esa publicación para la validación y el autocompletado actuales del editor. Una copia de trabajo no publicada debe usar config.schema.json de este repositorio para una validación coincidente, porque unpkg no puede exponer el cambio antes de la publicación. La URL del esquema no controla la migración en tiempo de ejecución.

Cambiar un modelo de embedding es una operación de configuración, no de setup. Edita embedding.provider, model, baseUrl y dimensions nativas según sea necesario; profile: "auto" resuelve las familias de modelos compatibles. Reinicia thoth-mem y deja que el linaje de embeddings modificado ponga en cola la reconstrucción idempotente del índice semántico.

Related MCP server: LumenCore

El bucle de memoria

Un flujo de trabajo de agente útil es pequeño y repetible:

  1. Guarda la lección duradera. Usa mem_save para una decisión, causa raíz, convención u otro hecho no obvio que deba sobrevivir al contexto actual.

  2. Recupera de forma acotada. Comienza con mem_recall(mode="compact"), expande los candidatos sólidos con mode="context" y obtén un registro seleccionado completo con mem_get.

  3. Reanuda con identidad. Mantén el mismo session_id y project estables; usa mem_context para la continuidad reciente y mem_session para los eventos de ciclo de vida propiedad de la raíz.

Ejemplo de observación:

{
  "kind": "observation",
  "title": "Retry SQLite writes in a new transaction",
  "type": "bugfix",
  "project": "my-project",
  "topic_key": "sqlite/busy-retry",
  "content": "**What**: Roll back after SQLITE_BUSY and retry in a new transaction.\n**Why**: Retrying inside the failed transaction repeats the failure.\n**Where**: write transaction helper.\n**Learned**: Use bounded backoff before opening the new transaction."
}

Elimina el contenido dentro de <private>...</private> antes de la persistencia. No almacenes credenciales, transcripciones completas, prompts de agente generados como intención del usuario ni registros sin procesar sin una lección reutilizable.

Seis herramientas MCP

Herramienta

Úsala para

mem_save

Persistir una observación, un prompt de usuario real, un resumen propiedad de la raíz o aprendizaje pasivo.

mem_recall

Ejecutar recuperación fusionada acotada; usa resultados compactos antes de expandir el contexto.

mem_context

Leer sesiones, prompts, observaciones recientes y continuidad recuperada opcional.

mem_get

Obtener una observación o prompt por ID, con paginación acotada o contexto de línea temporal.

mem_project

Navegar por proyectos, temas, vistas de grafo y salud operativa.

mem_session

Iniciar, guardar un checkpoint o resumir una sesión de memoria propiedad de la raíz.

Los comandos de configuración, sincronización, migración, reconstrucción y mantenimiento son administración CLI/HTTP, no herramientas MCP adicionales.

Inspeccionar comunidades de grafo

Las comunidades son resúmenes acotados derivados del grafo de conocimiento de un proyecto. Un operador construye o actualiza los resúmenes confirmados mediante la CLI:

thoth-mem rebuild-communities --project my-project

Un agente los obtiene a través de mem_project:

{
  "action": "graph",
  "project": "my-project",
  "navigation": "community",
  "limit": 5,
  "max_chars": 2000
}

La respuesta informa del estado y la frescura de la comunidad, y luego entradas como community=<id>, cobertura del grafo, confianza, estado de degradación, un resumen acotado y sources=obs:<id>. La inspección de comunidades requiere un proyecto, pero no un nodo focal ni un ID de observación. Si no hay resúmenes confirmados, lo indica en lugar de sintetizar una respuesta global.

Para inspeccionar la evidencia detrás de una comunidad, toma un obs:<id> de su campo sources y llama a mem_get(kind="observation", id=<id>). Los IDs de observación también aparecen en los resultados de recuperación. Para un vecindario de grafo acotado, reutiliza uno como focus_node_id="obs:<id>" con navigation="neighborhood".

Integraciones nativas de entornos

La configuración nativa instala la declaración MCP empaquetada, la habilidad de memoria y los hooks de ciclo de vida donde el entorno los soporta. Inspecciona primero el plan de cero escrituras y luego vuelve a ejecutarlo sin --plan para aplicarlo:

Entorno

Plan

Aplicar

OpenCode

thoth-mem setup opencode --scope global --plan --json

thoth-mem setup opencode --scope global --json

Codex

thoth-mem setup codex --scope global --plan --json

thoth-mem setup codex --scope global --json

Claude Code

thoth-mem setup claude --scope global --plan --json

thoth-mem setup claude --scope global --json

El comando de configuración predeterminado de OpenCode es thoth-mem setup opencode; añade thoth-mem setup opencode --scope project --project /path/to/project --force cuando se apunte explícitamente a un proyecto, o usa thoth-mem setup codex --rollback /path/to/receipt.json para una reversión limitada al recibo.

El estado de la configuración y los códigos de salida del proceso son estables:

Estado

Código de salida

complete

0

failed

1

partial

2

requires_user_action

3

La configuración local de proyecto es explícita:

thoth-mem setup opencode --scope project --project /path/to/project --plan --json

Revisa los conflictos detectados antes de aplicar. Usa --force solo para ubicaciones conflictivas cuya propiedad de thoth-mem ya esté demostrada. Codex 0.144.x, 0.146.x y 0.147.x pertenecen al conjunto de compatibilidad probado y no requieren --force. Para otras versiones de Codex, --force solo puede anular la barrera de versión probada cuando el ámbito seleccionado aún expone capacidades completas e independientemente verificables del gestor de plugins; la configuración emite una advertencia cuando usa esa anulación. No elude la verificación de estado, la propiedad, el confinamiento, la reconciliación ni las salvaguardas de limpieza, y no otorga autoridad sobre configuraciones no relacionadas.

Claude Code también admite su flujo de marketplace nativo:

claude plugin marketplace add EremesNG/thoth-mem
claude plugin install thoth-mem

La integración nativa es opcional. Las memorias existentes y el servidor MCP de seis herramientas siguen funcionando con una conexión manual.

Respaldo de MCP manual

Los hooks nativos son opcionales. Mantén una conexión MCP simple de seis herramientas cuando no quieras configuración gestionada ni un plugin nativo; las memorias existentes siguen disponibles.

Transición a la integración nativa de entornos

La configuración nativa es opcional: inspecciona el plan de cero escrituras, revisa los conflictos y luego aplica el comando de entorno correspondiente. Para Codex, abre /plugins, instala thoth-mem desde EremesNG/thoth-mem y verifica el estado del marketplace y del plugin. El registro externo de Codex no es atómicamente reversible, así que confirma el estado externo antes de reintentar o revertir la configuración local.

Contrato de configuración gestionada: el modo Plan realiza cero escrituras y solo muta en ubicaciones gestionadas por thoth-mem. Las copias de seguridad se crean antes de la primera mutación; OpenCode acepta opencode.json u opencode.jsonc. Cada intento de mutación escribe un recibo protegido con HMAC con estado in_progress antes de los cambios:

  • recibos globales: <thoth-data-dir>/setup/receipts/<receipt-id>/receipt.json

  • recibos de proyecto: <project>/.thoth/setup/receipts/<receipt-id>/receipt.json

Los recibos faltantes o manipulados fallan de forma segura. Una reversión verificada preserva la configuración no relacionada, mientras que la deriva o las capacidades no disponibles devuelven requires_user_action. La configuración repetida y la reversión completada repetida son no operativas cuando el estado verificado ya coincide.

Gemini CLI: MCP manual

Gemini CLI es una ruta de cliente MCP manual, no una integración nativa gestionada de thoth-mem. Añade esta entrada a ~/.gemini/settings.json:

{
  "mcpServers": {
    "thoth": {
      "command": "npx",
      "args": ["-y", "thoth-mem@latest", "mcp"]
    }
  }
}

Evaluar la calidad de la recuperación y del grafo

El repositorio incluye comandos de evaluación deterministas:

pnpm run eval:retrieval
pnpm run eval:kg
pnpm run eval:embedding-models -- --help

eval:retrieval siembra observaciones de señal más distractores y mide si la memoria esperada se clasifica cerca de la parte superior. Lee su informe como una colección de señales:

  • Recuerdo y clasificación muestran si se encontró la evidencia correcta y con qué antelación.

  • Ruido y mezcla de casos muestran robustez en ejemplos directos, reformulados y derivados del repositorio.

  • Compresión muestra cuánta evidencia se eliminó antes de la entrega del contexto; es una señal de eficiencia, no una prueba de que el texto restante sea correcto.

  • Evidencia de vía y de respaldo muestra la participación léxica, semántica cruda/HyDE y de KG, incluido el comportamiento semántico pendiente o degradado.

  • Linaje y procedencia muestran si la evidencia devuelta sigue siendo atribuible a su fuente.

eval:kg mide el recuerdo esperado de sujeto-relación-objeto, la fuga de tripletas prohibidas, el comportamiento de extracción determinista y el enriquecimiento opcional validado con LLM. Los hechos esperados faltantes indican brechas de cobertura; los aciertos prohibidos indican invención insegura del grafo.

Estas evaluaciones son compuertas de desarrollo deterministas sobre fixtures curados y sintéticos. No predicen todos los corpus de producción, no reemplazan la revisión humana, no prueban una integración nativa de entorno ni justifican por sí solas habilitar rutas de lectura de comunidad opcionales. Compara los casos individuales y los mensajes de error en lugar de tratar un número agregado como calidad universal.

Perfiles de embedding y comparación de modelos

Los datos de entrada de embeddings semánticos se formatean mediante un perfil de modelo versionado. auto reconoce los alias de familias de modelos Nomic, EmbeddingGemma y Qwen3-Embedding; los modelos desconocidos usan raw y no reciben formato asimétrico inferido. La configuración pública no tiene intencionadamente un campo task global: la intención de recuperación y el rol consulta/documento se asignan internamente para cada entrada, incluidas las respuestas HyDE con rol de documento.

{
  "embedding": {
    "provider": "lmstudio",
    "model": "text-embedding-embeddinggemma-300m",
    "baseUrl": "http://127.0.0.1:1234",
    "dimensions": 768,
    "profile": "auto",
    "normalize": true
  }
}

Los valores de perfil admitidos son auto, nomic, embeddinggemma, qwen3 y raw. THOTH_EMBEDDING_PROFILE y THOTH_EMBEDDING_NORMALIZE anulan los valores persistidos. La versión de perfil resuelta y el indicador de normalización forman parte del linaje del índice semántico, por lo que cambiarlos marca como obsoletos los vectores anteriores y utiliza la cola de reconstrucción idempotente existente.

La inferencia local de Transformers.js puede optar por un dispositivo de ejecución ONNX específico:

{
  "embedding": {
    "provider": "transformers_local",
    "model": "onnx-community/embeddinggemma-300m-ONNX",
    "device": "dml",
    "dimensions": 768,
    "profile": "auto",
    "normalize": true
  }
}

Los valores de dispositivo admitidos son auto, cpu, dml, cuda y coreml; cpu es el valor predeterminado. THOTH_EMBEDDING_DEVICE anula el valor persistido de embedding.device. Con el runtime Node ONNX precompilado que usa Transformers.js, dml apunta a DirectML en Windows, cuda apunta a instalaciones CUDA x64 de Linux compatibles y coreml apunta a macOS. Un dispositivo no disponible explícito hace fallar la inicialización del modelo en lugar de cambiar silenciosamente a CPU. auto delega la selección de proveedor específica de la plataforma y la recuperación ante fallos a Transformers.js, por lo que su backend efectivo puede variar entre hosts o versiones de dependencias.

La selección de dispositivo solo afecta a transformers_local; las solicitudes remotas a Ollama y LM Studio no se ven afectadas. Los backends GPU pueden tener un arranque en frío considerablemente más lento, por lo que son más útiles para procesos MCP persistentes o lotes de embeddings más grandes. El dispositivo se excluye deliberadamente del linaje del índice semántico: cambiar solo embedding.device no marca los vectores existentes como obsoletos ni pone en cola una reconstrucción.

Ejemplos de modelos por proveedor:

Perfil

ID de modelo LM Studio

ID de modelo Transformers.js

Dimensiones nativas

Nomic

use el ID exacto de /v1/models, por ejemplo text-embedding-nomic-embed-text-v1.5@q8_0

nomic-ai/nomic-embed-text-v1.5

768

EmbeddingGemma

text-embedding-embeddinggemma-300m para la instalación GGUF verificada

onnx-community/embeddinggemma-300m-ONNX

768

Qwen3-Embedding-0.6B

text-embedding-qwen3-embedding-0.6b para la instalación GGUF verificada

onnx-community/Qwen3-Embedding-0.6B-ONNX

1024

La ejecución local de EmbeddingGemma consume sentence_embedding. La ejecución local de Qwen aplica la instrucción de recuperación solo a las consultas y utiliza el token oculto de última atención para la agrupación. Todos los proveedores rechazan lotes incompletos, no finitos, cero o con dimensiones inconsistentes. Los índices de respuesta de LM Studio se validan y las filas válidas fuera de orden se restauran al orden de entrada; los índices faltantes, duplicados o no válidos se rechazan. Durante la recuperación, estos errores degradan explícitamente la recuperación semántica mientras la recuperación léxica y KG continúan.

Ejecute la compuerta de calidad de tres modelos con IDs de modelo explícitos y una ruta de salida duradera:

pnpm run eval:embedding-models -- --provider lmstudio --base-url http://127.0.0.1:1234 --nomic-model <nomic-id> --embeddinggemma-model <gemma-id> --qwen3-model <qwen-id> --output <result.json>

La compuerta requiere que las tres ejecuciones se completen y que al menos un candidato cumpla los umbrales Recall@1/Recall@5/MRR sin regresiones en ninguna métrica de Nomic. Nomic es el comparador relativo, no un candidato sujeto a los umbrales absolutos. Si ambos candidatos califican, una puntuación de calidad explícita y un orden de desempate estable seleccionan al ganador. Un modelo faltante, un vector no válido, ningún candidato elegible o un fallo de escritura del informe hace que se salga con código distinto de cero y se conserve el valor predeterminado actual.

La ejecución registrada de LM Studio del 2026-08-08 seleccionó EmbeddingGemma como el valor predeterminado local distribuido. EmbeddingGemma y Qwen3 se completaron ambas con Recall@1 1.00, Recall@5 1.00 y MRR 1.00, frente a Nomic con 0.50, 1.00 y 0.7167; ambos candidatos eran elegibles y EmbeddingGemma ganó el desempate exacto de calidad según la regla estable de ID de perfil léxico. La latencia mediana en la ejecución de decisión persistida fue de 190.5 ms para Nomic, 195 ms para EmbeddingGemma y 320.5 ms para Qwen3.

Los tamaños de archivo de Qwen3 dependen del artefacto de runtime:

Artefacto de Qwen3

Cuantización

Bytes

MiB

model.safetensors original de Transformers

BF16

1,191,586,416

1,136.39

onnx/model_quantized.onnx de Transformers.js

Q8

613,527,631

585.11

Qwen3-Embedding-0.6B-Q8_0.gguf de LM Studio

Q8_0

639,150,592

609.54

El modelo Qwen3 Q8 es 304,069,133 bytes más grande que EmbeddingGemma Q8 en Transformers.js y 305,559,648 bytes más grande en LM Studio. También utiliza vectores nativos de 1024 dimensiones en lugar de las 768 dimensiones de EmbeddingGemma. El ejecutor no instala ni descubre modelos de proveedores en nombre del operador.

Escale el ruido de recuperación cuando quiera una ejecución local más exigente:

$env:THOTH_RETRIEVAL_EVAL_NOISE='250'
pnpm run eval:retrieval

Operaciones avanzadas

  • Ejecute thoth-mem help para ver la lista completa de comandos y opciones de la CLI.

  • Abra el panel local en http://localhost:7438/ y la documentación de OpenAPI en http://localhost:7438/docs.

  • Use thoth-mem sync --dir=.thoth-sync y thoth-mem sync-import --dir=.thoth-sync para una portabilidad compatible con Git.

  • repair-sync-journal (--project <name> | --all) --apply previsualiza y vincula su lote de reparación internamente. El --expected-fingerprint opcional permanece disponible cuando un flujo de trabajo externo ya tiene un enlace de previsualización.

  • prune-operation-traces (--project <name> | --all) --apply vincula igualmente un lote de retención internamente. Añada --until-complete para procesar el backlog inicialmente limitado con un instante efectivo fijo y huellas posteriores más recientes. Un enlace suministrado externamente debe incluir tanto --expected-fingerprint como --effective-now.

  • compact-database [--data-dir <path>] realiza una previsualización de solo lectura. Añada --apply solo después de revisar sus estimaciones de espacio recuperable y capacidad. La aplicación puede requerir el doble del mayor de los tamaños de base de datos físicos y lógicos, puede ser bloqueada por otros clientes SQLite y solo informa éxito después de las comprobaciones de integridad, claves foráneas, esquema, recuento duradero y WAL. Utiliza checkpoint gestionado por SQLite y VACUUM; no promete reversión después de una compactación confirmada.

  • La compactación nunca es automática. Ejecutarla sobre datos en vivo requiere autorización separada del operador; las pruebas del repositorio utilizan solo bases de datos desechables.

  • Revise config.schema.json para la configuración persistida y los ajustes respaldados por entorno.

  • Los datos viven en ~/.thoth/thoth.db de forma predeterminada; anule el directorio de datos con THOTH_DATA_DIR o --data-dir.

La indexación semántica no es bloqueante. Si los embeddings o sqlite-vec no están disponibles, la recuperación sigue siendo utilizable mediante evidencia léxica y de grafos compatible e informa del carril degradado en lugar de afirmar silenciosamente éxito semántico.

Desarrollo

pnpm install
pnpm run integration:verify
pnpm run build
pnpm test

Licencia

MIT

Available Tools

6 tools
mem_contextC

Build bounded handoff-first continuity. project_key required; root_session_key and harness together for session context, neither for project context.

NameRequiredDescriptionDefault
harnessNoVerified native harness.
project_keyYesVerified project_key, copied verbatim; never derived.
budget_charsNo
correlation_idNo
finalize_answerNo
root_session_keyNoVerified root session key.

TDQS

C2.8/5.0
Behavior2/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description bears the full burden. It implies a build/continuity operation but does not state whether it writes data, what side effects or permissions exist, whether it is idempotent, or what the result contains.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is two compact sentences with no filler, and the required-parameter guidance is front-loaded. The only weakness is that the opening sentence is so terse and jargon-heavy that it obscures meaning.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness2/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a six-parameter tool with no annotations and no output schema, the description is too thin. It explains the session/project context split but omits behavioral details, output expectations, and several parameter meanings.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The description adds important conditional semantics for project_key, root_session_key, and harness, including the session-vs-project mode distinction. However, with only 50% schema description coverage, it leaves budget_chars, correlation_id, and finalize_answer unexplained.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose3/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description says it builds 'bounded handoff-first continuity,' which gestures at context creation but is vague jargon rather than a clear verb+resource statement. It also does not distinguish this tool from siblings such as mem_recall, mem_session, or mem_project.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

It specifies project_key is required and explains that root_session_key plus harness together select session context while neither selects project context. That is useful conditional guidance, but it gives no explicit when-to-use-this-tool-vs-alternatives guidance or exclusions relative to sibling tools.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

mem_getB

Expand one selected record from a prior tool result.

NameRequiredDescriptionDefault
idYesMemory, summary, observation, or evidence id.
historyNoInclude predecessors; evidence has none.
correlation_idNo

TDQS

B3.1/5.0
Behavior2/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries the full burden of behavioral disclosure. It does not state that this is a read-only retrieval, does not explain what expansion returns, does not mention the optional history behavior, and gives no permission or side-effect context. The word 'expand' hints at non-destructive retrieval but that is the only signal.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

A single focused sentence with no wasted words, front-loading the core action. It is perhaps too terse for the gaps it leaves, but structurally it is efficient and readable.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness2/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With no annotations and no output schema, the description is the only source of behavioral context, and it says nothing about return shape, history semantics, or the undocumented correlation_id. For a retrieval tool that may return variable content, this leaves the agent without enough to call it confidently.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 67%: the schema documents 'id' and 'history' with useful detail, while 'correlation_id' is undocumented. The description's only contribution is that 'id' refers to a record from a prior tool result, which adds marginal context beyond the schema. Baseline 3 fits given the partial coverage.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The verb 'expand' plus the object 'one selected record from a prior tool result' makes the purpose reasonably clear: fetch the full detail of a single record referenced by a previous result. It does not differentiate itself from the sibling mem_recall, so an agent cannot tell from the text alone which retrieval tool to pick.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The phrase 'from a prior tool result' implies the context of use — after another tool has returned a record stub — which gives some usage guidance. However, it never states when to use this vs. mem_recall or mem_context, and offers no exclusions or prerequisites.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

mem_projectC

Read-only project views. list: no fields required; returns at most 256 exact aliases/project with aliasCount/aliasesTruncated. timeline: project_key required; accepts only since, until, cursor, limit, budget_chars. briefing/summaries/observations: project_key required; optional session filter selects summaries/observations, not briefing's project-wide memories. history: id required from a prior result.

NameRequiredDescriptionDefault
idNo
limitNoTimeline/observations: 1-100 items.
sinceNoInclusive lower ISO-8601 instant; <= until.
stateNo
untilNoInclusive upper ISO-8601 instant.
actionYes
cursorNoUnchanged nextCursor; preserve project_key, since, until.
harnessNo
temporalNoSummaries/observations: current=latest summaries/correction leaves; history=predecessors.
project_keyNoVerified project_key, copied verbatim; never derived.
budget_charsNoAggregate chars; timeline: positive integer clamped to 1024-20000.
root_session_keyNoSession filter; pair with harness.

TDQS

C2.8/5.0
Behavior3/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are present, so the description carries the full burden. It does disclose read-only behavior and several useful constraints: list returns at most 256 aliases with aliasCount/aliasesTruncated, timeline accepts only a specific set of filters, and a session filter affects summaries/observations but not briefing. However, permissions, return shapes for most actions, and error behavior are not described.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is short and front-loads the read-only nature. It is dense and semicolon-delimited, making it harder to scan than a bulleted structure, but every clause conveys actionable information with little waste.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness2/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The tool has six actions and twelve parameters with no output schema, yet the description explains return values only for list. It does not explain when to use briefing versus summaries or observations, what those actions return, or how temporal/state/harness parameters affect behavior. Significant gaps remain for an agent to invoke the tool correctly across all actions.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 67%, so the schema already documents many parameters. The description adds action-specific constraints not obvious from the schema: timeline accepts only since/until/cursor/limit/budget_chars, list requires no fields and returns a capped alias set, history id must come from a prior result, and the session filter behavior varies by action. It leaves state, harness, temporal, and root_session_key semantics largely unaddressed beyond the schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose3/5

Does the description clearly state what the tool does and how it differs from similar tools?

Starts with 'Read-only project views,' which is a vague resource description, then lists action names and parameter requirements. The action list gives some clarity about what the tool can do, but the overall purpose ('project views') is not concretely defined and the tool is not distinguished from siblings like mem_context or mem_recall.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Provides per-action parameter requirements (e.g., timeline requires project_key and accepts only certain filters), but gives no guidance on when to use this tool versus alternatives or which action to choose for a given intent. There are no exclusions or alternative-tool references.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

mem_recallB

Call at the start of non-trivial repository work before exploring, with task key terms, unprompted. Search promoted project memory before expanding selected records.

NameRequiredDescriptionDefault
modeNocompact (default): snippets; context: selected content.
limitNo
queryYesNon-empty task search terms.
temporalNocurrent (default) or historical guidance.
project_keyYesVerified project_key, copied verbatim; never derived.
budget_charsNo
correlation_idNo
finalize_answerNo

TDQS

B3.3/5.0
Behavior3/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries the full burden; it does disclose a two-stage retrieval workflow (search snippets, then expand selected records) and that results are pre-promoted memory. However, it says nothing about what finalize_answer, correlation_id, or budget_chars do, what the response looks like, or whether the operation has any side effects. Useful workflow context, but not enough for an 8-parameter tool without annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Two short sentences with the imperative and timing front-loaded; nothing is filler. The phrase 'with task key terms, unprompted' is slightly awkward but still parses as useful guidance.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness2/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a tool with 8 parameters, no annotations, and no output schema, the description covers purpose and timing but omits the semantics of most parameters and the shape of results. An agent would need to open the schema and still lack clarity on finalize_answer and correlation_id.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters2/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

At 50% schema coverage, the description must compensate, and it only hints at 'query' ('with task key terms') and implicitly at mode via 'expanding selected records'. The remaining parameters (project_key, limit, temporal, budget_chars, correlation_id, finalize_answer) get no explanation in the description beyond the schema's own text.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description names a specific action (search promoted project memory) and adds scope ('promoted', 'project memory') that is more than a restatement of the tool name. It doesn't explicitly contrast with siblings like mem_context or mem_get, leaving the agent to infer the boundary.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

It gives a clear trigger ('at the start of non-trivial repository work, before exploring') and says to call it unprompted, plus a follow-up step ('before expanding selected records'). It stops short of naming which sibling to use instead when the task isn't repository work.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

mem_saveA

Save unprompted as soon as decisions, root causes, failed approaches, or non-obvious conventions are verified. Save durable discoveries and continuation handoffs. Direct promoted memory (not handoff): memory.content uses labeled Result, Rationale, Scope, Caveat / safe action lines; omit inapplicable Scope/Caveat and never invent details. Handoffs: Objective, Completed, First pending action, Blockers, Key files/checks; require a stable workstream topic_key; close a finished handoff by saving its outcome under the same topic_key. Send exactly one branch: evidence, observation, observation_review, or observation_promotion. Supply root_session_key and harness together or omit both.

NameRequiredDescriptionDefault
memoryNoDirect promoted memory; requires evidence without metadata.
harnessNoVerified native harness.
evidenceNoCompact factual evidence; metadata requires event_key + session pair and forbids memory.
event_keyNoStable idempotency key.
observationNoSupported candidate, not promoted; requires event_key. Session scope needs session pair + coverage; project scope forbids coverage.
project_keyYesCopy opaque project_key verbatim from verified native identity; never derive from names, paths, remotes, branches, worktrees, host IDs, listings, or recalled content.
project_nameYesDisplay/creation name, not identity; prefer persisted lifecycle/project name.
root_session_keyNoVerified root session key; blank is absent.
observation_reviewNoReview supported observation; requires event_key + session pair.
observation_promotionNoPromote accepted observation without new prose; requires event_key + session pair.

TDQS

A3.9/5.0
Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries the burden well: it discloses branch mutual exclusivity, the root_session_key/harness all-or-nothing pairing constraint, and the requirement of a stable topic_key to close a handoff. It does not say what happens on supersede/dedup or what the call returns, leaving those gaps.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Front-loaded with the trigger condition, and every clause carries a rule rather than filler. Density is high and semicolon-chained, with terse terms like 'safe action lines' that take re-reading, but nothing is expendable.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a 10-parameter, deeply nested write tool with no annotations and no output schema, the description covers branch selection and the session-pair constraint but omits return behavior, supersede semantics, and how the four branches relate to each other downstream. Adequate to make a correct call, not complete.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so the baseline is 3, but the description adds meaning the schema cannot express: the labeled Result/Rationale/Scope/Caveat shape of memory.content and the Objective/Completed/First pending action/Blockers structure of a handoff. It leaves supersedes_id, outcome, and the memory-vs-evidence relationship to the schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The imperative verb 'Save' plus enumerated resource types (decisions, root causes, failed approaches, conventions, handoffs) makes clear this tool persists memory. It does not explicitly contrast itself with the read-oriented siblings (mem_get, mem_recall, mem_context), but the write framing is unmistakable.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Strong trigger guidance: 'Save unprompted as soon as... verified', plus durable discoveries and continuation handoffs. It also gives branch-selection rules ('Send exactly one branch'). It never names a sibling tool as an alternative or states a when-not-to-save condition, which keeps it off a 5.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

mem_sessionB

Record verified root lifecycle events, never ordinary saves. guide_post_compact content carries host compaction text.

NameRequiredDescriptionDefault
contentNo
harnessYesVerified native harness.
summaryNoSession summary.
event_keyYesStable lifecycle key; retries must resend identical content/summary.
operationYesRoot lifecycle operation.
project_keyYesVerified project_key, copied verbatim; never derived.
project_nameYesDisplay/creation name, not identity; prefer persisted lifecycle/project name.
root_session_keyYesStable verified root session key.

TDQS

B3.1/5.0
Behavior2/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries the full burden, but it only says these are lifecycle events and that guide_post_compact content carries host compaction text. It does not disclose mutation semantics, idempotency expectations, permission/auth requirements, or what happens for each lifecycle operation beyond what the schema implies.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is two short sentences, front-loads the core action, and contains no filler. It is efficient, though its brevity contributes to gaps elsewhere rather than being a structural flaw itself.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness2/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

This is a complex tool with eight parameters, nested summary objects, six lifecycle operations, and no annotations or output schema. The description does not explain the lifecycle operations, what is recorded or changed, retry behavior, or the relationship between required fields, leaving too much for the agent to infer.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is high at 88%, so the schema already documents most parameters. The description adds one valuable clarification: content for guide_post_compact carries host compaction text, but it does not add meaning for the other parameters or nested summary fields.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description states a specific verb and resource: 'Record verified root lifecycle events,' and explicitly distinguishes this from 'ordinary saves,' which helps separate it from mem_save. It is less clear about what a root lifecycle event is, but the operation enum and sibling contrast keep the purpose identifiable.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

It gives one useful exclusion, 'never ordinary saves,' which points agents away from mem_save for normal persistence. However, it does not explain when to use enroll, recover, capture_root, checkpoint_pre_compact, guide_post_compact, or finalize, so operation selection remains implied by the schema rather than guided.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

  1. 6 tool updatesv0.6.2
    • Changedmem_context2 fields changed
      • removedInput schema / properties / project_key / minLength
        Removed value: -1
      • removedInput schema / properties / root_session_key / minLength
        Removed value: -1
    • Changedmem_get1 field changed
      • changedInput schema / properties / history / description
        Previous value: -"true: include predecessor lineage; evidence has no lineage."New value: +"Include predecessors; evidence has none."
    • Changedmem_project20 fields changed
      • removedInput schema / properties / action / description
        Removed value: -"Project view."
      • changedInput schema / properties / budget_chars / description
        Previous value: -"Aggregate character budget for timeline/briefing/summaries/observations; timeline clamps positive integers to 1024-20000."New value: +"Aggregate chars; timeline: positive integer clamped to 1024-20000."
      • changedInput schema / properties / cursor / description
        Previous value: -"Timeline nextCursor, unchanged; keep project_key, since, until unchanged."New value: +"Unchanged nextCursor; preserve project_key, since, until."
      • removedInput schema / properties / cursor / maxLength
        Removed value: -4096
      • removedInput schema / properties / cursor / minLength
        Removed value: -1
      • removedInput schema / properties / harness / description
        Removed value: -"Native harness for session filter."
      • removedInput schema / properties / id / description
        Removed value: -"Prior-result record id."
      • removedInput schema / properties / id / minLength
        Removed value: -1
      • changedInput schema / properties / limit / description
        Previous value: -"Maximum items for timeline/observations."New value: +"Timeline/observations: 1-100 items."
      • removedInput schema / properties / limit / exclusiveMinimum
        Removed value: -0
      • removedInput schema / properties / limit / maximum
        Removed value: -100
      • removedInput schema / properties / project_key / minLength
        Removed value: -1
      • changedInput schema / properties / root_session_key / description
        Previous value: -"Verified session filter; pair with harness or omit both."New value: +"Session filter; pair with harness."
      • removedInput schema / properties / root_session_key / minLength
        Removed value: -1
      • changedInput schema / properties / since / description
        Previous value: -"Timeline inclusive lower ISO-8601 instant; <= until."New value: +"Inclusive lower ISO-8601 instant; <= until."
      • removedInput schema / properties / since / minLength
        Removed value: -1
      • removedInput schema / properties / state / description
        Removed value: -"Observations state filter."
      • changedInput schema / properties / temporal / description
        Previous value: -"Summaries/observations only: current=latest summaries/correction leaves; history=older summaries/observation predecessors."New value: +"Summaries/observations: current=latest summaries/correction leaves; history=predecessors."
      • changedInput schema / properties / until / description
        Previous value: -"Timeline inclusive upper ISO-8601 instant."New value: +"Inclusive upper ISO-8601 instant."
      • removedInput schema / properties / until / minLength
        Removed value: -1
    • Changedmem_recall4 fields changed
      • changedInput schema / properties / mode / description
        Previous value: -"compact (default): bounded snippets; context: selected content."New value: +"compact (default): snippets; context: selected content."
      • removedInput schema / properties / project_key / minLength
        Removed value: -1
      • removedInput schema / properties / query / minLength
        Removed value: -1
      • changedInput schema / properties / temporal / description
        Previous value: -"current (default): current guidance; history: historical records."New value: +"current (default) or historical guidance."
    • Changedmem_save58 fields changed
      • removedInput schema / properties / evidence / anyOf
        Removed value: -[
-  {
-    "additionalProperties": false,
-    "properties": {
-      "content": {
-        "minLength": 1,
-        "type": "string"
-      },
-      "kind": {
-        "enum": [
-          "root_prompt",
-          "explicit_save",
-          "checkpoint",
-          "handoff",
-          "legacy_prompt",
-          "legacy_observation",
-          "session_summary"
-        ],
-        "type": "string"
-      },
-      "source_ref": {
-        "type": "string"
-      }
-    },
-    "required": [
-      "kind",
-      "content"
-    ],
-    "type": "object"
-  },
-  {
-    "additionalProperties": false,
-    "properties": {
-      "content": {
-        "minLength": 1,
-        "type": "string"
-      },
-      "kind": {
-        "const": "explicit_save",
-        "type": "string"
-      },
-      "metadata": {
-        "additionalProperties": false,
-        "properties": {
-          "observation_validation": {
-            "additionalProperties": false,
-            "properties": {
-              "method": {
-                "maxLength": 500,
-                "minLength": 1,
-                "type": "string"
-              },
-              "observation_id": {
-                "maxLength": 200,
-                "minLength": 1,
-                "type": "string"
-              },
-              "result": {
-                "enum": [
-                  "passed",
-                  "failed"
-                ],
-                "type": "string"
-              }
-            },
-            "required": [
-              "observation_id",
-              "result",
-              "method"
-            ],
-            "type": "object"
-          }
-        },
-        "required": [
-          "observation_validation"
-        ],
-        "type": "object"
-      },
-      "source_ref": {
-        "type": "string"
-      }
-    },
-    "required": [
-      "kind",
-      "content",
-      "metadata"
-    ],
-    "type": "object"
-  },
-  {
-    "additionalProperties": false,
-    "properties": {
-      "content": {
-        "minLength": 1,
-        "type": "string"
-      },
-      "kind": {
-        "const": "handoff",
-        "type": "string"
-      },
-      "metadata": {
-        "additionalProperties": false,
-        "properties": {
-          "observation_review_attestation": {
-            "additionalProperties": false,
-            "properties": {
-              "method": {
-                "maxLength": 500,
-                "minLength": 1,
-                "type": "string"
-              },
-              "observation_id": {
-                "maxLength": 200,
-                "minLength": 1,
-                "type": "string"
-              },
-              "reviewer": {
-                "maxLength": 200,
-                "minLength": 1,
-                "type": "string"
-              },
-              "verdict": {
-                "enum": [
-                  "accepted",
-                  "rejected"
-                ],
-                "type": "string"
-              }
-            },
-            "required": [
-              "observation_id",
-              "verdict",
-              "reviewer",
-              "method"
-            ],
-            "type": "object"
-          }
-        },
-        "required": [
-          "observation_review_attestation"
-        ],
-        "type": "object"
-      },
-      "source_ref": {
-        "type": "string"
-      }
-    },
-    "required": [
-      "kind",
-      "content",
-      "metadata"
-    ],
-    "type": "object"
-  }
-]
      • addedInput schema / properties / evidence / properties
        Added value: +{
+  "content": {
+    "type": "string"
+  },
+  "kind": {
+    "enum": [
+      "root_prompt",
+      "explicit_save",
+      "checkpoint",
+      "handoff",
+      "legacy_prompt",
+      "legacy_observation",
+      "session_summary"
+    ],
+    "type": "string"
+  },
+  "metadata": {
+    "properties": {
+      "observation_review_attestation": {
+        "properties": {
+          "method": {
+            "type": "string"
+          },
+          "observation_id": {
+            "type": "string"
+          },
+          "reviewer": {
+            "type": "string"
+          },
+          "verdict": {
+            "enum": [
+              "accepted",
+              "rejected"
+            ],
+            "type": "string"
+          }
+        },
+        "required": [
+          "observation_id",
+          "verdict",
+          "reviewer",
+          "method"
+        ],
+        "type": "object"
+      },
+      "observation_validation": {
+        "properties": {
+          "method": {
+            "type": "string"
+          },
+          "observation_id": {
+            "type": "string"
+          },
+          "result": {
+            "enum": [
+              "passed",
+              "failed"
+            ],
+            "type": "string"
+          }
+        },
+        "required": [
+          "observation_id",
+          "result",
+          "method"
+        ],
+        "type": "object"
+      }
+    },
+    "type": "object"
+  },
+  "source_ref": {
+    "type": "string"
+  }
+}
      • addedInput schema / properties / evidence / required
        Added value: +[
+  "kind",
+  "content"
+]
      • addedInput schema / properties / evidence / type
        Added value: +"object"
      • removedInput schema / properties / memory / additionalProperties
        Removed value: -false
      • removedInput schema / properties / memory / properties / content / minLength
        Removed value: -1
      • removedInput schema / properties / memory / properties / title / minLength
        Removed value: -1
      • removedInput schema / properties / observation / additionalProperties
        Removed value: -false
      • removedInput schema / properties / observation / properties / claim / maxLength
        Removed value: -4000
      • removedInput schema / properties / observation / properties / claim / minLength
        Removed value: -1
      • removedInput schema / properties / observation / properties / concepts / items / maxLength
        Removed value: -200
      • removedInput schema / properties / observation / properties / concepts / items / minLength
        Removed value: -1
      • removedInput schema / properties / observation / properties / concepts / maxItems
        Removed value: -16
      • removedInput schema / properties / observation / properties / coverage / additionalProperties
        Removed value: -false
      • removedInput schema / properties / observation / properties / coverage / properties / from_sequence / exclusiveMinimum
        Removed value: -0
      • removedInput schema / properties / observation / properties / coverage / properties / from_sequence / maximum
        Removed value: -9007199254740991
      • removedInput schema / properties / observation / properties / coverage / properties / to_sequence / exclusiveMinimum
        Removed value: -0
      • removedInput schema / properties / observation / properties / coverage / properties / to_sequence / maximum
        Removed value: -9007199254740991
      • removedInput schema / properties / observation / properties / files / items / maxLength
        Removed value: -500
      • removedInput schema / properties / observation / properties / files / items / minLength
        Removed value: -1
      • removedInput schema / properties / observation / properties / files / maxItems
        Removed value: -16
      • removedInput schema / properties / observation / properties / generator / additionalProperties
        Removed value: -false
      • removedInput schema / properties / observation / properties / generator / properties / config_hash / pattern
        Removed value: -"^[0-9a-f]{64}$"
      • removedInput schema / properties / observation / properties / generator / properties / name / maxLength
        Removed value: -200
      • removedInput schema / properties / observation / properties / generator / properties / name / minLength
        Removed value: -1
      • removedInput schema / properties / observation / properties / generator / properties / version / maxLength
        Removed value: -200
      • removedInput schema / properties / observation / properties / generator / properties / version / minLength
        Removed value: -1
      • removedInput schema / properties / observation / properties / predecessor_id / maxLength
        Removed value: -200
      • removedInput schema / properties / observation / properties / predecessor_id / minLength
        Removed value: -1
      • removedInput schema / properties / observation / properties / proposed_memory / additionalProperties
        Removed value: -false
      • removedInput schema / properties / observation / properties / proposed_memory / properties / content / minLength
        Removed value: -1
      • removedInput schema / properties / observation / properties / proposed_memory / properties / title / minLength
        Removed value: -1
      • removedInput schema / properties / observation / properties / support_ids / items / maxLength
        Removed value: -200
      • removedInput schema / properties / observation / properties / support_ids / items / minLength
        Removed value: -1
      • removedInput schema / properties / observation / properties / support_ids / maxItems
        Removed value: -16
      • removedInput schema / properties / observation / properties / support_ids / minItems
        Removed value: -1
      • removedInput schema / properties / observation / properties / title / maxLength
        Removed value: -500
      • removedInput schema / properties / observation / properties / title / minLength
        Removed value: -1
      • removedInput schema / properties / observation_promotion / additionalProperties
        Removed value: -false
      • removedInput schema / properties / observation_promotion / properties / observation_id / maxLength
        Removed value: -200
      • removedInput schema / properties / observation_promotion / properties / observation_id / minLength
        Removed value: -1
      • removedInput schema / properties / observation_review / additionalProperties
        Removed value: -false
      • removedInput schema / properties / observation_review / properties / observation_id / maxLength
        Removed value: -200
      • removedInput schema / properties / observation_review / properties / observation_id / minLength
        Removed value: -1
      • removedInput schema / properties / observation_review / properties / policy / additionalProperties
        Removed value: -false
      • removedInput schema / properties / observation_review / properties / policy / properties / id / maxLength
        Removed value: -200
      • removedInput schema / properties / observation_review / properties / policy / properties / id / minLength
        Removed value: -1
      • removedInput schema / properties / observation_review / properties / policy / properties / version / maxLength
        Removed value: -200
      • removedInput schema / properties / observation_review / properties / policy / properties / version / minLength
        Removed value: -1
      • removedInput schema / properties / observation_review / properties / reason / maxLength
        Removed value: -1000
      • removedInput schema / properties / observation_review / properties / reason / minLength
        Removed value: -1
      • removedInput schema / properties / observation_review / properties / support_ids / items / maxLength
        Removed value: -200
      • removedInput schema / properties / observation_review / properties / support_ids / items / minLength
        Removed value: -1
      • removedInput schema / properties / observation_review / properties / support_ids / maxItems
        Removed value: -16
      • removedInput schema / properties / observation_review / properties / support_ids / minItems
        Removed value: -1
      • removedInput schema / properties / project_key / minLength
        Removed value: -1
      • changedInput schema / properties / project_name / description
        Previous value: -"Display/creation metadata only, not identity; prefer the persisted name from lifecycle/project output."New value: +"Display/creation name, not identity; prefer persisted lifecycle/project name."
      • removedInput schema / properties / project_name / minLength
        Removed value: -1
    • Changedmem_session27 fields changed
      • removedInput schema / properties / event_key / minLength
        Removed value: -1
      • removedInput schema / properties / project_key / minLength
        Removed value: -1
      • changedInput schema / properties / project_name / description
        Previous value: -"Display/creation metadata only, not identity; prefer the persisted name from lifecycle/project output."New value: +"Display/creation name, not identity; prefer persisted lifecycle/project name."
      • removedInput schema / properties / project_name / minLength
        Removed value: -1
      • removedInput schema / properties / root_session_key / minLength
        Removed value: -1
      • removedInput schema / properties / summary / additionalProperties
        Removed value: -false
      • removedInput schema / properties / summary / properties / claims / items / additionalProperties
        Removed value: -false
      • removedInput schema / properties / summary / properties / claims / items / properties / content / minLength
        Removed value: -1
      • changedInput schema / properties / summary / properties / claims / items / properties / support_ids / description
        Previous value: -"Distinct evidence ids inside coverage from this project_key + root_session_key/harness session; never memory, summary, or observation ids."New value: +"Distinct same-session evidence ids within coverage; no memory/summary/observation ids."
      • removedInput schema / properties / summary / properties / claims / items / properties / support_ids / items / maxLength
        Removed value: -200
      • removedInput schema / properties / summary / properties / claims / items / properties / support_ids / items / minLength
        Removed value: -1
      • removedInput schema / properties / summary / properties / claims / items / properties / support_ids / maxItems
        Removed value: -16
      • removedInput schema / properties / summary / properties / claims / items / properties / support_ids / minItems
        Removed value: -1
      • removedInput schema / properties / summary / properties / claims / maxItems
        Removed value: -32
      • removedInput schema / properties / summary / properties / claims / minItems
        Removed value: -1
      • removedInput schema / properties / summary / properties / coverage / additionalProperties
        Removed value: -false
      • removedInput schema / properties / summary / properties / coverage / properties / from_sequence / exclusiveMinimum
        Removed value: -0
      • removedInput schema / properties / summary / properties / coverage / properties / from_sequence / maximum
        Removed value: -9007199254740991
      • changedInput schema / properties / summary / properties / coverage / properties / to_sequence / description
        Previous value: -"Last sequence: >= from_sequence and >= the current summary's ending sequence for this session."New value: +">= from_sequence and the previous summary end."
      • removedInput schema / properties / summary / properties / coverage / properties / to_sequence / exclusiveMinimum
        Removed value: -0
      • removedInput schema / properties / summary / properties / coverage / properties / to_sequence / maximum
        Removed value: -9007199254740991
      • removedInput schema / properties / summary / properties / generator / additionalProperties
        Removed value: -false
      • removedInput schema / properties / summary / properties / generator / properties / config_hash / pattern
        Removed value: -"^[0-9a-f]{64}$"
      • removedInput schema / properties / summary / properties / generator / properties / name / maxLength
        Removed value: -200
      • removedInput schema / properties / summary / properties / generator / properties / name / minLength
        Removed value: -1
      • removedInput schema / properties / summary / properties / generator / properties / version / maxLength
        Removed value: -200
      • removedInput schema / properties / summary / properties / generator / properties / version / minLength
        Removed value: -1
  2. 6 tool updatesv0.6.1
    • Changedmem_context3 fields changed
      • changedInput schema / properties / harness / description
        Previous value: -"Native harness for root_session_key; supply both for session context, or omit both for project context."New value: +"Verified native harness."
      • changedInput schema / properties / project_key / description
        Previous value: -"Exact opaque project_key copied verbatim from verified native identity; never derive it from a display name, path hint, remote, branch, worktree name, host ID, listing, or recalled content."New value: +"Verified project_key, copied verbatim; never derived."
      • changedInput schema / properties / root_session_key / description
        Previous value: -"Optional verified root session key; supply with harness for session context, or omit both for project context."New value: +"Verified root session key."
    • Changedmem_get2 fields changed
      • changedInput schema / properties / history / description
        Previous value: -"Set true to expand predecessor lineage for memory, summary, or observation records; evidence ids have no lineage."New value: +"true: include predecessor lineage; evidence has no lineage."
      • changedInput schema / properties / id / description
        Previous value: -"Memory, summary, observation, or evidence id returned by a prior tool result."New value: +"Memory, summary, observation, or evidence id."
    • Changedmem_project12 fields changed
      • changedInput schema / properties / action / description
        Previous value: -"Inspect project views without mutation. action=\"list\": no fields required. action=\"timeline\": project_key required; optionally since, until, cursor, limit, and budget_chars. action=\"briefing\", \"summaries\", or \"observations\": project_key required; optionally supply both root_session_key and harness to select that session's summaries/observations (briefing still includes project-wide memories). action=\"history\": id required from a prior result. temporal filters summaries/observations, not timeline. list returns at most 256 exact aliases per project plus aliasCount and aliasesTruncated metadata."New value: +"Project view."
      • changedInput schema / properties / budget_chars / description
        Previous value: -"Optional aggregate character budget for timeline, briefing, summaries, or observations; timeline clamps a positive integer to 1024-20000 characters."New value: +"Aggregate character budget for timeline/briefing/summaries/observations; timeline clamps positive integers to 1024-20000."
      • changedInput schema / properties / cursor / description
        Previous value: -"Unchanged nextCursor from a prior mem_project action=\"timeline\" result; keep project_key, since, and until unchanged."New value: +"Timeline nextCursor, unchanged; keep project_key, since, until unchanged."
      • changedInput schema / properties / harness / description
        Previous value: -"Native harness for the optional root_session_key filter; supply both or omit both. Not accepted for action=\"timeline\"."New value: +"Native harness for session filter."
      • changedInput schema / properties / id / description
        Previous value: -"Required for action=\"history\"; send a record id returned by a prior tool result."New value: +"Prior-result record id."
      • changedInput schema / properties / limit / description
        Previous value: -"Maximum items (1-100) for action=\"timeline\" or \"observations\"."New value: +"Maximum items for timeline/observations."
      • changedInput schema / properties / project_key / description
        Previous value: -"Exact opaque project_key copied verbatim from verified native identity; never derive it from a display name, path hint, remote, branch, worktree name, host ID, listing, or recalled content. Required for action=\"timeline\", \"briefing\", \"summaries\", or \"observations\"; not required for \"list\" or \"history\"."New value: +"Verified project_key, copied verbatim; never derived."
      • changedInput schema / properties / root_session_key / description
        Previous value: -"Optional session filter for action=\"briefing\", \"summaries\", or \"observations\"; supply with harness or omit both."New value: +"Verified session filter; pair with harness or omit both."
      • changedInput schema / properties / since / description
        Previous value: -"Optional inclusive lower ISO-8601 instant for action=\"timeline\" only; must be <= until."New value: +"Timeline inclusive lower ISO-8601 instant; <= until."
      • changedInput schema / properties / state / description
        Previous value: -"Optional state filter for action=\"observations\"."New value: +"Observations state filter."
      • changedInput schema / properties / temporal / description
        Previous value: -"Filter summaries/observations: current selects current summary versions or observation correction-chain leaves; history includes older summary versions or selects observation predecessors. Not accepted for action=\"timeline\"."New value: +"Summaries/observations only: current=latest summaries/correction leaves; history=older summaries/observation predecessors."
      • changedInput schema / properties / until / description
        Previous value: -"Optional inclusive upper ISO-8601 instant for action=\"timeline\" only; must be >= since."New value: +"Timeline inclusive upper ISO-8601 instant."
    • Changedmem_recall4 fields changed
      • changedInput schema / properties / mode / description
        Previous value: -"compact (default) returns bounded snippets; context adds selected memory content."New value: +"compact (default): bounded snippets; context: selected content."
      • changedInput schema / properties / project_key / description
        Previous value: -"Exact opaque project_key copied verbatim from verified native identity; never derive it from a display name, path hint, remote, branch, worktree name, host ID, listing, or recalled content."New value: +"Verified project_key, copied verbatim; never derived."
      • changedInput schema / properties / query / description
        Previous value: -"Non-empty search string for promoted project memory."New value: +"Non-empty task search terms."
      • changedInput schema / properties / temporal / description
        Previous value: -"current (default) searches current guidance; history includes historical records."New value: +"current (default): current guidance; history: historical records."
    • Changedmem_save10 fields changed
      • changedInput schema / properties / event_key / description
        Previous value: -"Stable event key for idempotency; required for observation, observation_review, observation_promotion, and evidence with metadata."New value: +"Stable idempotency key."
      • changedInput schema / properties / evidence / description
        Previous value: -"Direct evidence { kind, content }; optionally add memory for a promoted save. Structured metadata forbids memory and requires event_key, root_session_key, and harness."New value: +"Compact factual evidence; metadata requires event_key + session pair and forbids memory."
      • changedInput schema / properties / harness / description
        Previous value: -"Native harness for root_session_key; supply both or omit both. Required wherever root_session_key is required."New value: +"Verified native harness."
      • changedInput schema / properties / memory / description
        Previous value: -"Promoted memory for direct evidence only; requires evidence without metadata. Do not combine with observation, observation_review, or observation_promotion."New value: +"Direct promoted memory; requires evidence without metadata."
      • changedInput schema / properties / observation / description
        Previous value: -"Submit a supported candidate without promotion; requires event_key. Session scope also requires root_session_key, harness, and coverage."New value: +"Supported candidate, not promoted; requires event_key. Session scope needs session pair + coverage; project scope forbids coverage."
      • changedInput schema / properties / observation_promotion / description
        Previous value: -"Promote one accepted observation without new prose; requires event_key, root_session_key, and harness. Send no other operation branch or memory."New value: +"Promote accepted observation without new prose; requires event_key + session pair."
      • changedInput schema / properties / observation_review / description
        Previous value: -"Review one supported observation; requires event_key, root_session_key, and harness. Send no other operation branch or memory."New value: +"Review supported observation; requires event_key + session pair."
      • changedInput schema / properties / project_key / description
        Previous value: -"Exact opaque project_key copied verbatim from verified native identity; never derive it from a display name, path hint, remote, branch, worktree name, host ID, listing, or recalled content."New value: +"Copy opaque project_key verbatim from verified native identity; never derive from names, paths, remotes, branches, worktrees, host IDs, listings, or recalled content."
      • changedInput schema / properties / project_name / description
        Previous value: -"Creation/display metadata only; never participates in project identity equality. Prefer the database-persisted name returned by lifecycle or project output."New value: +"Display/creation metadata only, not identity; prefer the persisted name from lifecycle/project output."
      • changedInput schema / properties / root_session_key / description
        Previous value: -"Verified root session key; supply with harness or omit both. Required for session-scoped observations, observation_review, observation_promotion, and evidence with metadata; blank counts as absent."New value: +"Verified root session key; blank is absent."
    • Changedmem_session15 fields changed
      • changedInput schema / properties / event_key / description
        Previous value: -"Stable lifecycle event key; retries for the same operation must resend identical content/summary."New value: +"Stable lifecycle key; retries must resend identical content/summary."
      • changedInput schema / properties / harness / description
        Previous value: -"Verified native harness for root_session_key in project_key."New value: +"Verified native harness."
      • changedInput schema / properties / operation / description
        Previous value: -"Lifecycle operation; summary is allowed only for checkpoint_pre_compact (checkpoint) or finalize (final)."New value: +"Root lifecycle operation."
      • changedInput schema / properties / project_key / description
        Previous value: -"Exact opaque project_key copied verbatim from verified native identity; never derive it from a display name, path hint, remote, branch, worktree name, host ID, listing, or recalled content."New value: +"Verified project_key, copied verbatim; never derived."
      • changedInput schema / properties / project_name / description
        Previous value: -"Creation/display metadata only; never participates in project identity equality. Prefer the database-persisted name returned by lifecycle or project output."New value: +"Display/creation metadata only, not identity; prefer the persisted name from lifecycle/project output."
      • changedInput schema / properties / root_session_key / description
        Previous value: -"Stable verified root session key; required with harness for every operation."New value: +"Stable verified root session key."
      • changedInput schema / properties / summary / description
        Previous value: -"Optional only for operation=\"checkpoint_pre_compact\" (kind=\"checkpoint\") or operation=\"finalize\" (kind=\"final\"). coverage starts at 1 and to_sequence must advance the current summary for this session and kind. support_ids must be evidence ids from this project_key + root_session_key/harness session inside coverage. Canonical submission limit: 20000 UTF-16 units."New value: +"Session summary."
      • changedInput schema / properties / summary / properties / claims / description
        Previous value: -"1-32 atomic supported claims; keep the canonical summary within 20000 UTF-16 units."New value: +"Supported claims; canonical summary <=20000 UTF-16 units."
      • changedInput schema / properties / summary / properties / claims / items / properties / content / description
        Previous value: -"Atomic claim content; at most 2000 code points after privacy filtering."New value: +"Atomic claim; <=2000 code points after privacy filtering."
      • changedInput schema / properties / summary / properties / claims / items / properties / support_ids / description
        Previous value: -"1-16 distinct evidence ids from this project_key + root_session_key/harness session inside summary.coverage; never memory, summary, or observation ids."New value: +"Distinct evidence ids inside coverage from this project_key + root_session_key/harness session; never memory, summary, or observation ids."
      • changedInput schema / properties / summary / properties / coverage / description
        Previous value: -"Inclusive session evidence coverage; start at 1 and advance to_sequence for this session and summary kind."New value: +"Inclusive session evidence range."
      • changedInput schema / properties / summary / properties / coverage / properties / from_sequence / description
        Previous value: -"Inclusive first session event sequence; must start at 1."New value: +"First event sequence: 1."
      • changedInput schema / properties / summary / properties / coverage / properties / to_sequence / description
        Previous value: -"Inclusive last session event sequence; must be >= from_sequence and exceed the current summary ending sequence for this session and kind."New value: +"Last sequence: >= from_sequence and >= the current summary's ending sequence for this session."
      • removedInput schema / properties / summary / properties / kind
        Removed value: -{
-  "description": "Send checkpoint for operation=\"checkpoint_pre_compact\" or final for operation=\"finalize\".",
-  "enum": [
-    "checkpoint",
-    "final"
-  ],
-  "type": "string"
-}
      • changedInput schema / properties / summary / required
        Previous value: -[
-  "kind",
-  "coverage",
-  "generator",
-  "claims"
-]New value: +[
+  "coverage",
+  "generator",
+  "claims"
+]
  3. 6 tool updatesv0.5.6
    • Changedmem_context13 fields changed
      • addedInput schema / properties / budget_chars
        Added value: +{
+  "type": "number"
+}
      • addedInput schema / properties / correlation_id
        Added value: +{
+  "type": "string"
+}
      • addedInput schema / properties / finalize_answer
        Added value: +{
+  "type": "boolean"
+}
      • addedInput schema / properties / harness
        Added value: +{
+  "description": "Native harness for root_session_key; supply both for session context, or omit both for project context.",
+  "enum": [
+    "opencode",
+    "codex",
+    "claude",
+    "pi",
+    "mcp",
+    "cli",
+    "import"
+  ],
+  "type": "string"
+}
      • removedInput schema / properties / limit
        Removed value: -{
-  "description": "Number of observations to retrieve (default: 20)",
-  "type": "number"
-}
      • removedInput schema / properties / max_chars
        Removed value: -{
-  "description": "Output character budget; 0 disables the context cap",
-  "minimum": 0,
-  "type": "number"
-}
      • removedInput schema / properties / project
        Removed value: -{
-  "description": "Filter by project name",
-  "type": "string"
-}
      • addedInput schema / properties / project_key
        Added value: +{
+  "description": "Exact opaque project_key copied verbatim from verified native identity; never derive it from a display name, path hint, remote, branch, worktree name, host ID, listing, or recalled content.",
+  "minLength": 1,
+  "type": "string"
+}
      • removedInput schema / properties / recall_query
        Removed value: -{
-  "description": "Optional query to append fused recall evidence without changing base context sections",
-  "type": "string"
-}
      • addedInput schema / properties / root_session_key
        Added value: +{
+  "description": "Optional verified root session key; supply with harness for session context, or omit both for project context.",
+  "minLength": 1,
+  "type": "string"
+}
      • removedInput schema / properties / scope
        Removed value: -{
-  "description": "Filter by scope",
-  "enum": [
-    "project",
-    "personal"
-  ],
-  "type": "string"
-}
      • removedInput schema / properties / session_id
        Removed value: -{
-  "description": "Filter to a specific session",
-  "type": "string"
-}
      • addedInput schema / required
        Added value: +[
+  "project_key"
+]
    • Changedmem_get10 fields changed
      • removedInput schema / properties / after
        Removed value: -{
-  "description": "Timeline observations after the focus item (default: 5)",
-  "maximum": 20,
-  "minimum": 0,
-  "type": "number"
-}
      • removedInput schema / properties / before
        Removed value: -{
-  "description": "Timeline observations before the focus item (default: 5)",
-  "maximum": 20,
-  "minimum": 0,
-  "type": "number"
-}
      • addedInput schema / properties / correlation_id
        Added value: +{
+  "type": "string"
+}
      • addedInput schema / properties / history
        Added value: +{
+  "description": "Set true to expand predecessor lineage for memory, summary, or observation records; evidence ids have no lineage.",
+  "type": "boolean"
+}
      • changedInput schema / properties / id / description
        Previous value: -"Record ID to retrieve, interpreted according to kind"New value: +"Memory, summary, observation, or evidence id returned by a prior tool result."
      • changedInput schema / properties / id / type
        Previous value: -"number"New value: +"string"
      • removedInput schema / properties / include_timeline
        Removed value: -{
-  "description": "Include surrounding observations in the same session",
-  "type": "boolean"
-}
      • removedInput schema / properties / kind
        Removed value: -{
-  "description": "Memory kind to retrieve (defaults to observation)",
-  "enum": [
-    "observation",
-    "prompt"
-  ],
-  "type": "string"
-}
      • removedInput schema / properties / max_length
        Removed value: -{
-  "description": "Max characters to return (default: 50000)",
-  "minimum": 100,
-  "type": "number"
-}
      • removedInput schema / properties / offset
        Removed value: -{
-  "description": "Character offset for large content (default: 0)",
-  "minimum": 0,
-  "type": "number"
-}
    • Changedmem_project26 fields changed
      • changedInput schema / properties / action / description
        Previous value: -"Project view to return"New value: +"Inspect project views without mutation. action=\"list\": no fields required. action=\"timeline\": project_key required; optionally since, until, cursor, limit, and budget_chars. action=\"briefing\", \"summaries\", or \"observations\": project_key required; optionally supply both root_session_key and harness to select that session's summaries/observations (briefing still includes project-wide memories). action=\"history\": id required from a prior result. temporal filters summaries/observations, not timeline. list returns at most 256 exact aliases per project plus aliasCount and aliasesTruncated metadata."
      • changedInput schema / properties / action / enum
        Previous value: -[
-  "list",
-  "summary",
-  "graph",
-  "topics",
-  "topic",
-  "health"
-]New value: +[
+  "list",
+  "timeline",
+  "briefing",
+  "history",
+  "summaries",
+  "observations"
+]
      • addedInput schema / properties / budget_chars
        Added value: +{
+  "description": "Optional aggregate character budget for timeline, briefing, summaries, or observations; timeline clamps a positive integer to 1024-20000 characters.",
+  "type": "number"
+}
      • removedInput schema / properties / continuation
        Removed value: -{
-  "description": "Opaque continuation token returned by graph navigation views",
-  "type": "string"
-}
      • addedInput schema / properties / cursor
        Added value: +{
+  "description": "Unchanged nextCursor from a prior mem_project action=\"timeline\" result; keep project_key, since, and until unchanged.",
+  "maxLength": 4096,
+  "minLength": 1,
+  "type": "string"
+}
      • removedInput schema / properties / focus_node_id
        Removed value: -{
-  "description": "Graph focus node id for navigation=neighborhood, currently obs:<id>",
-  "type": "string"
-}
      • addedInput schema / properties / harness
        Added value: +{
+  "description": "Native harness for the optional root_session_key filter; supply both or omit both. Not accepted for action=\"timeline\".",
+  "enum": [
+    "opencode",
+    "codex",
+    "claude",
+    "pi",
+    "mcp",
+    "cli",
+    "import"
+  ],
+  "type": "string"
+}
      • addedInput schema / properties / id
        Added value: +{
+  "description": "Required for action=\"history\"; send a record id returned by a prior tool result.",
+  "minLength": 1,
+  "type": "string"
+}
      • removedInput schema / properties / include_superseded
        Removed value: -{
-  "description": "Explicit history opt-in; honored by navigation=superseded only",
-  "type": "boolean"
-}
      • changedInput schema / properties / limit / description
        Previous value: -"Maximum items to return"New value: +"Maximum items (1-100) for action=\"timeline\" or \"observations\"."
      • addedInput schema / properties / limit / exclusiveMinimum
        Added value: +0
      • changedInput schema / properties / limit / maximum
        Previous value: -500New value: +100
      • removedInput schema / properties / limit / minimum
        Removed value: -1
      • changedInput schema / properties / limit / type
        Previous value: -"number"New value: +"integer"
      • removedInput schema / properties / max_chars
        Removed value: -{
-  "description": "Response character budget; 0 is supported for action=summary only",
-  "maximum": 20000,
-  "minimum": 0,
-  "type": "integer"
-}
      • removedInput schema / properties / navigation
        Removed value: -{
-  "description": "Graph navigation mode for action=graph; defaults to ledger",
-  "enum": [
-    "ledger",
-    "neighborhood",
-    "lineage",
-    "community",
-    "superseded"
-  ],
-  "type": "string"
-}
      • removedInput schema / properties / observation_id
        Removed value: -{
-  "description": "Observation id for lineage or superseded graph navigation",
-  "exclusiveMinimum": 0,
-  "maximum": 9007199254740991,
-  "type": "integer"
-}
      • removedInput schema / properties / project
        Removed value: -{
-  "description": "Project name. Required except action=list and optional for action=topics or health",
-  "type": "string"
-}
      • addedInput schema / properties / project_key
        Added value: +{
+  "description": "Exact opaque project_key copied verbatim from verified native identity; never derive it from a display name, path hint, remote, branch, worktree name, host ID, listing, or recalled content. Required for action=\"timeline\", \"briefing\", \"summaries\", or \"observations\"; not required for \"list\" or \"history\".",
+  "minLength": 1,
+  "type": "string"
+}
      • removedInput schema / properties / relation
        Removed value: -{
-  "description": "Graph relation filter for action=graph",
-  "enum": [
-    "HAS_TYPE",
-    "IN_PROJECT",
-    "HAS_TOPIC_KEY",
-    "HAS_WHAT",
-    "HAS_WHY",
-    "HAS_WHERE",
-    "HAS_LEARNED"
-  ],
-  "type": "string"
-}
      • addedInput schema / properties / root_session_key
        Added value: +{
+  "description": "Optional session filter for action=\"briefing\", \"summaries\", or \"observations\"; supply with harness or omit both.",
+  "minLength": 1,
+  "type": "string"
+}
      • addedInput schema / properties / since
        Added value: +{
+  "description": "Optional inclusive lower ISO-8601 instant for action=\"timeline\" only; must be <= until.",
+  "minLength": 1,
+  "type": "string"
+}
      • addedInput schema / properties / state
        Added value: +{
+  "description": "Optional state filter for action=\"observations\".",
+  "enum": [
+    "pending",
+    "accepted",
+    "rejected",
+    "promoted"
+  ],
+  "type": "string"
+}
      • addedInput schema / properties / temporal
        Added value: +{
+  "description": "Filter summaries/observations: current selects current summary versions or observation correction-chain leaves; history includes older summary versions or selects observation predecessors. Not accepted for action=\"timeline\".",
+  "enum": [
+    "current",
+    "history"
+  ],
+  "type": "string"
+}
      • removedInput schema / properties / topic_key
        Removed value: -{
-  "description": "Topic key for action=topic or graph filtering",
-  "type": "string"
-}
      • addedInput schema / properties / until
        Added value: +{
+  "description": "Optional inclusive upper ISO-8601 instant for action=\"timeline\" only; must be >= since.",
+  "minLength": 1,
+  "type": "string"
+}
    • Changedmem_recall20 fields changed
      • addedInput schema / properties / budget_chars
        Added value: +{
+  "type": "number"
+}
      • addedInput schema / properties / correlation_id
        Added value: +{
+  "type": "string"
+}
      • removedInput schema / properties / debug
        Removed value: -{
-  "description": "Include retrieval defaults and semantic input sources",
-  "type": "boolean"
-}
      • addedInput schema / properties / finalize_answer
        Added value: +{
+  "type": "boolean"
+}
      • removedInput schema / properties / hyde
        Removed value: -{
-  "description": "Request HyDE query expansion when configured",
-  "type": "boolean"
-}
      • removedInput schema / properties / limit / description
        Removed value: -"Maximum evidence items (default: 5)"
      • removedInput schema / properties / limit / maximum
        Removed value: -20
      • removedInput schema / properties / limit / minimum
        Removed value: -1
      • changedInput schema / properties / mode / description
        Previous value: -"compact returns evidence lines; context includes retrieved text"New value: +"compact (default) returns bounded snippets; context adds selected memory content."
      • removedInput schema / properties / project
        Removed value: -{
-  "description": "Optional project filter",
-  "type": "string"
-}
      • addedInput schema / properties / project_key
        Added value: +{
+  "description": "Exact opaque project_key copied verbatim from verified native identity; never derive it from a display name, path hint, remote, branch, worktree name, host ID, listing, or recalled content.",
+  "minLength": 1,
+  "type": "string"
+}
      • changedInput schema / properties / query / description
        Previous value: -"Recall/search query"New value: +"Non-empty search string for promoted project memory."
      • removedInput schema / properties / scope
        Removed value: -{
-  "description": "Optional scope filter",
-  "enum": [
-    "project",
-    "personal"
-  ],
-  "type": "string"
-}
      • removedInput schema / properties / session_id
        Removed value: -{
-  "description": "Optional session filter",
-  "type": "string"
-}
      • addedInput schema / properties / temporal
        Added value: +{
+  "description": "current (default) searches current guidance; history includes historical records.",
+  "enum": [
+    "current",
+    "history"
+  ],
+  "type": "string"
+}
      • removedInput schema / properties / time_from
        Removed value: -{
-  "description": "Optional inclusive created_at lower bound",
-  "type": "string"
-}
      • removedInput schema / properties / time_to
        Removed value: -{
-  "description": "Optional inclusive created_at upper bound",
-  "type": "string"
-}
      • removedInput schema / properties / topic_key
        Removed value: -{
-  "description": "Optional exact topic_key filter",
-  "type": "string"
-}
      • removedInput schema / properties / type
        Removed value: -{
-  "description": "Optional observation type filter",
-  "enum": [
-    "decision",
-    "architecture",
-    "bugfix",
-    "pattern",
-    "config",
-    "discovery",
-    "learning",
-    "session_summary",
-    "manual"
-  ],
-  "type": "string"
-}
      • changedInput schema / required
        Previous value: -[
-  "query"
-]New value: +[
+  "project_key",
+  "query"
+]
    • Changedmem_save19 fields changed
      • removedInput schema / properties / content
        Removed value: -{
-  "description": "Memory content, prompt text, session summary, or text containing a Key Learnings section",
-  "type": "string"
-}
      • addedInput schema / properties / event_key
        Added value: +{
+  "description": "Stable event key for idempotency; required for observation, observation_review, observation_promotion, and evidence with metadata.",
+  "type": "string"
+}
      • addedInput schema / properties / evidence
        Added value: +{
+  "anyOf": [
+    {
+      "additionalProperties": false,
+      "properties": {
+        "content": {
+          "minLength": 1,
+          "type": "string"
+        },
+        "kind": {
+          "enum": [
+            "root_prompt",
+            "explicit_save",
+            "checkpoint",
+            "handoff",
+            "legacy_prompt",
+            "legacy_observation",
+            "session_summary"
+          ],
+          "type": "string"
+        },
+        "source_ref": {
+          "type": "string"
+        }
+      },
+      "required": [
+        "kind",
+        "content"
+      ],
+      "type": "object"
+    },
+    {
+      "additionalProperties": false,
+      "properties": {
+        "content": {
+          "minLength": 1,
+          "type": "string"
+        },
+        "kind": {
+          "const": "explicit_save",
+          "type": "string"
+        },
+        "metadata": {
+          "additionalProperties": false,
+          "properties": {
+            "observation_validation": {
+              "additionalProperties": false,
+              "properties": {
+                "method": {
+                  "maxLength": 500,
+                  "minLength": 1,
+                  "type": "string"
+                },
+                "observation_id": {
+                  "maxLength": 200,
+                  "minLength": 1,
+                  "type": "string"
+                },
+                "result": {
+                  "enum": [
+                    "passed",
+                    "failed"
+                  ],
+                  "type": "string"
+                }
+              },
+              "required": [
+                "observation_id",
+                "result",
+                "method"
+              ],
+              "type": "object"
+            }
+          },
+          "required": [
+            "observation_validation"
+          ],
+          "type": "object"
+        },
+        "source_ref": {
+          "type": "string"
+        }
+      },
+      "required": [
+        "kind",
+        "content",
+        "metadata"
+      ],
+      "type": "object"
+    },
+    {
+      "additionalProperties": false,
+      "properties": {
+        "content": {
+          "minLength": 1,
+          "type": "string"
+        },
+        "kind": {
+          "const": "handoff",
+          "type": "string"
+        },
+        "metadata": {
+          "additionalProperties": false,
+          "properties": {
+            "observation_review_attestation": {
+              "additionalProperties": false,
+              "properties": {
+                "method": {
+                  "maxLength": 500,
+                  "minLength": 1,
+                  "type": "string"
+                },
+                "observation_id": {
+                  "maxLength": 200,
+                  "minLength": 1,
+                  "type": "string"
+                },
+                "reviewer": {
+                  "maxLength": 200,
+                  "minLength": 1,
+                  "type": "string"
+                },
+                "verdict": {
+                  "enum": [
+                    "accepted",
+                    "rejected"
+                  ],
+                  "type": "string"
+                }
+              },
+              "required": [
+                "observation_id",
+                "verdict",
+                "reviewer",
+                "method"
+              ],
+              "type": "object"
+            }
+          },
+          "required": [
+            "observation_review_attestation"
+          ],
+          "type": "object"
+        },
+        "source_ref": {
+          "type": "string"
+        }
+      },
+      "required": [
+        "kind",
+        "content",
+        "metadata"
+      ],
+      "type": "object"
+    }
+  ],
+  "description": "Direct evidence { kind, content }; optionally add memory for a promoted save. Structured metadata forbids memory and requires event_key, root_session_key, and harness."
+}
      • addedInput schema / properties / harness
        Added value: +{
+  "description": "Native harness for root_session_key; supply both or omit both. Required wherever root_session_key is required.",
+  "enum": [
+    "opencode",
+    "codex",
+    "claude",
+    "pi",
+    "mcp",
+    "cli",
+    "import"
+  ],
+  "type": "string"
+}
      • removedInput schema / properties / kind
        Removed value: -{
-  "description": "Write mode. Defaults to observation",
-  "enum": [
-    "observation",
-    "prompt",
-    "session_summary",
-    "passive_learnings"
-  ],
-  "type": "string"
-}
      • addedInput schema / properties / memory
        Added value: +{
+  "additionalProperties": false,
+  "description": "Promoted memory for direct evidence only; requires evidence without metadata. Do not combine with observation, observation_review, or observation_promotion.",
+  "properties": {
+    "content": {
+      "minLength": 1,
+      "type": "string"
+    },
+    "kind": {
+      "enum": [
+        "decision",
+        "convention",
+        "architecture",
+        "discovery",
+        "failure",
+        "project_structure",
+        "handoff",
+        "preference"
+      ],
+      "type": "string"
+    },
+    "outcome": {
+      "enum": [
+        "unknown",
+        "succeeded",
+        "failed",
+        "mixed"
+      ],
+      "type": "string"
+    },
+    "supersedes_id": {
+      "type": "string"
+    },
+    "title": {
+      "minLength": 1,
+      "type": "string"
+    },
+    "topic_key": {
+      "type": "string"
+    }
+  },
+  "required": [
+    "kind",
+    "title",
+    "content"
+  ],
+  "type": "object"
+}
      • addedInput schema / properties / observation
        Added value: +{
+  "additionalProperties": false,
+  "description": "Submit a supported candidate without promotion; requires event_key. Session scope also requires root_session_key, harness, and coverage.",
+  "properties": {
+    "claim": {
+      "maxLength": 4000,
+      "minLength": 1,
+      "type": "string"
+    },
+    "concepts": {
+      "items": {
+        "maxLength": 200,
+        "minLength": 1,
+        "type": "string"
+      },
+      "maxItems": 16,
+      "type": "array"
+    },
+    "coverage": {
+      "additionalProperties": false,
+      "properties": {
+        "from_sequence": {
+          "exclusiveMinimum": 0,
+          "maximum": 9007199254740991,
+          "type": "integer"
+        },
+        "to_sequence": {
+          "exclusiveMinimum": 0,
+          "maximum": 9007199254740991,
+          "type": "integer"
+        }
+      },
+      "required": [
+        "from_sequence",
+        "to_sequence"
+      ],
+      "type": "object"
+    },
+    "files": {
+      "items": {
+        "maxLength": 500,
+        "minLength": 1,
+        "type": "string"
+      },
+      "maxItems": 16,
+      "type": "array"
+    },
+    "generator": {
+      "additionalProperties": false,
+      "properties": {
+        "config_hash": {
+          "pattern": "^[0-9a-f]{64}$",
+          "type": "string"
+        },
+        "kind": {
+          "enum": [
+            "root_agent",
+            "harness",
+            "model"
+          ],
+          "type": "string"
+        },
+        "name": {
+          "maxLength": 200,
+          "minLength": 1,
+          "type": "string"
+        },
+        "version": {
+          "maxLength": 200,
+          "minLength": 1,
+          "type": "string"
+        }
+      },
+      "required": [
+        "kind",
+        "name"
+      ],
+      "type": "object"
+    },
+    "kind": {
+      "enum": [
+        "decision",
+        "constraint",
+        "fact",
+        "procedure",
+        "result",
+        "failure",
+        "preference"
+      ],
+      "type": "string"
+    },
+    "predecessor_id": {
+      "maxLength": 200,
+      "minLength": 1,
+      "type": "string"
+    },
+    "proposed_memory": {
+      "additionalProperties": false,
+      "properties": {
+        "content": {
+          "minLength": 1,
+          "type": "string"
+        },
+        "kind": {
+          "enum": [
+            "decision",
+            "convention",
+            "architecture",
+            "discovery",
+            "failure",
+            "project_structure",
+            "handoff",
+            "preference"
+          ],
+          "type": "string"
+        },
+        "outcome": {
+          "enum": [
+            "unknown",
+            "succeeded",
+            "failed",
+            "mixed"
+          ],
+          "type": "string"
+        },
+        "title": {
+          "minLength": 1,
+          "type": "string"
+        },
+        "topic_key": {
+          "type": "string"
+        }
+      },
+      "required": [
+        "kind",
+        "title",
+        "content"
+      ],
+      "type": "object"
+    },
+    "scope": {
+      "enum": [
+        "session",
+        "project"
+      ],
+      "type": "string"
+    },
+    "support_ids": {
+      "items": {
+        "maxLength": 200,
+        "minLength": 1,
+        "type": "string"
+      },
+      "maxItems": 16,
+      "minItems": 1,
+      "type": "array"
+    },
+    "title": {
+      "maxLength": 500,
+      "minLength": 1,
+      "type": "string"
+    }
+  },
+  "required": [
+    "kind",
+    "scope",
+    "title",
+    "claim",
+    "proposed_memory",
+    "support_ids",
+    "generator"
+  ],
+  "type": "object"
+}
      • addedInput schema / properties / observation_promotion
        Added value: +{
+  "additionalProperties": false,
+  "description": "Promote one accepted observation without new prose; requires event_key, root_session_key, and harness. Send no other operation branch or memory.",
+  "properties": {
+    "observation_id": {
+      "maxLength": 200,
+      "minLength": 1,
+      "type": "string"
+    }
+  },
+  "required": [
+    "observation_id"
+  ],
+  "type": "object"
+}
      • addedInput schema / properties / observation_review
        Added value: +{
+  "additionalProperties": false,
+  "description": "Review one supported observation; requires event_key, root_session_key, and harness. Send no other operation branch or memory.",
+  "properties": {
+    "basis": {
+      "enum": [
+        "root_user_confirmed",
+        "observable_validation",
+        "independent_review"
+      ],
+      "type": "string"
+    },
+    "observation_id": {
+      "maxLength": 200,
+      "minLength": 1,
+      "type": "string"
+    },
+    "policy": {
+      "additionalProperties": false,
+      "properties": {
+        "id": {
+          "maxLength": 200,
+          "minLength": 1,
+          "type": "string"
+        },
+        "version": {
+          "maxLength": 200,
+          "minLength": 1,
+          "type": "string"
+        }
+      },
+      "required": [
+        "id",
+        "version"
+      ],
+      "type": "object"
+    },
+    "reason": {
+      "maxLength": 1000,
+      "minLength": 1,
+      "type": "string"
+    },
+    "support_ids": {
+      "items": {
+        "maxLength": 200,
+        "minLength": 1,
+        "type": "string"
+      },
+      "maxItems": 16,
+      "minItems": 1,
+      "type": "array"
+    },
+    "verdict": {
+      "enum": [
+        "accepted",
+        "rejected"
+      ],
+      "type": "string"
+    }
+  },
+  "required": [
+    "observation_id",
+    "verdict",
+    "basis",
+    "policy",
+    "reason",
+    "support_ids"
+  ],
+  "type": "object"
+}
      • removedInput schema / properties / project
        Removed value: -{
-  "description": "Project name",
-  "type": "string"
-}
      • addedInput schema / properties / project_key
        Added value: +{
+  "description": "Exact opaque project_key copied verbatim from verified native identity; never derive it from a display name, path hint, remote, branch, worktree name, host ID, listing, or recalled content.",
+  "minLength": 1,
+  "type": "string"
+}
      • addedInput schema / properties / project_name
        Added value: +{
+  "description": "Creation/display metadata only; never participates in project identity equality. Prefer the database-persisted name returned by lifecycle or project output.",
+  "minLength": 1,
+  "type": "string"
+}
      • addedInput schema / properties / root_session_key
        Added value: +{
+  "description": "Verified root session key; supply with harness or omit both. Required for session-scoped observations, observation_review, observation_promotion, and evidence with metadata; blank counts as absent.",
+  "type": "string"
+}
      • removedInput schema / properties / scope
        Removed value: -{
-  "description": "Observation scope",
-  "enum": [
-    "project",
-    "personal"
-  ],
-  "type": "string"
-}
      • removedInput schema / properties / session_id
        Removed value: -{
-  "description": "Session ID (default: manual-save-{project})",
-  "type": "string"
-}
      • removedInput schema / properties / title
        Removed value: -{
-  "description": "Short searchable title. Required for kind=observation",
-  "type": "string"
-}
      • removedInput schema / properties / topic_key
        Removed value: -{
-  "description": "Stable key for observation upserts",
-  "type": "string"
-}
      • removedInput schema / properties / type
        Removed value: -{
-  "description": "Observation category for kind=observation",
-  "enum": [
-    "decision",
-    "architecture",
-    "bugfix",
-    "pattern",
-    "config",
-    "discovery",
-    "learning",
-    "session_summary",
-    "manual"
-  ],
-  "type": "string"
-}
      • changedInput schema / required
        Previous value: -[
-  "content"
-]New value: +[
+  "project_key",
+  "project_name"
+]
    • Changedmem_session17 fields changed
      • removedInput schema / properties / action
        Removed value: -{
-  "description": "Session action",
-  "enum": [
-    "start",
-    "summary",
-    "checkpoint"
-  ],
-  "type": "string"
-}
      • removedInput schema / properties / content / description
        Removed value: -"Full session summary for action=summary"
      • removedInput schema / properties / directory
        Removed value: -{
-  "description": "Working directory for action=start",
-  "type": "string"
-}
      • addedInput schema / properties / event_key
        Added value: +{
+  "description": "Stable lifecycle event key; retries for the same operation must resend identical content/summary.",
+  "minLength": 1,
+  "type": "string"
+}
      • addedInput schema / properties / harness
        Added value: +{
+  "description": "Verified native harness for root_session_key in project_key.",
+  "enum": [
+    "opencode",
+    "codex",
+    "claude",
+    "pi",
+    "mcp",
+    "cli",
+    "import"
+  ],
+  "type": "string"
+}
      • removedInput schema / properties / id
        Removed value: -{
-  "description": "Session ID. Required for action=start; defaults to manual-save-{project} for summary/checkpoint",
-  "type": "string"
-}
      • addedInput schema / properties / operation
        Added value: +{
+  "description": "Lifecycle operation; summary is allowed only for checkpoint_pre_compact (checkpoint) or finalize (final).",
+  "enum": [
+    "enroll",
+    "recover",
+    "capture_root",
+    "checkpoint_pre_compact",
+    "guide_post_compact",
+    "finalize"
+  ],
+  "type": "string"
+}
      • removedInput schema / properties / project
        Removed value: -{
-  "description": "Project name",
-  "type": "string"
-}
      • addedInput schema / properties / project_key
        Added value: +{
+  "description": "Exact opaque project_key copied verbatim from verified native identity; never derive it from a display name, path hint, remote, branch, worktree name, host ID, listing, or recalled content.",
+  "minLength": 1,
+  "type": "string"
+}
      • addedInput schema / properties / project_name
        Added value: +{
+  "description": "Creation/display metadata only; never participates in project identity equality. Prefer the database-persisted name returned by lifecycle or project output.",
+  "minLength": 1,
+  "type": "string"
+}
      • addedInput schema / properties / root_session_key
        Added value: +{
+  "description": "Stable verified root session key; required with harness for every operation.",
+  "minLength": 1,
+  "type": "string"
+}
      • addedInput schema / properties / summary / additionalProperties
        Added value: +false
      • changedInput schema / properties / summary / description
        Previous value: -"Short checkpoint summary for action=checkpoint"New value: +"Optional only for operation=\"checkpoint_pre_compact\" (kind=\"checkpoint\") or operation=\"finalize\" (kind=\"final\"). coverage starts at 1 and to_sequence must advance the current summary for this session and kind. support_ids must be evidence ids from this project_key + root_session_key/harness session inside coverage. Canonical submission limit: 20000 UTF-16 units."
      • addedInput schema / properties / summary / properties
        Added value: +{
+  "claims": {
+    "description": "1-32 atomic supported claims; keep the canonical summary within 20000 UTF-16 units.",
+    "items": {
+      "additionalProperties": false,
+      "properties": {
+        "content": {
+          "description": "Atomic claim content; at most 2000 code points after privacy filtering.",
+          "minLength": 1,
+          "type": "string"
+        },
+        "kind": {
+          "enum": [
+            "objective",
+            "completed",
+            "decision",
+            "changed_surface",
+            "verification",
+            "pending",
+            "blocker",
+            "next_action"
+          ],
+          "type": "string"
+        },
+        "outcome": {
+          "enum": [
+            "unknown",
+            "succeeded",
+            "failed",
+            "mixed"
+          ],
+          "type": "string"
+        },
+        "support_ids": {
+          "description": "1-16 distinct evidence ids from this project_key + root_session_key/harness session inside summary.coverage; never memory, summary, or observation ids.",
+          "items": {
+            "maxLength": 200,
+            "minLength": 1,
+            "type": "string"
+          },
+          "maxItems": 16,
+          "minItems": 1,
+          "type": "array"
+        }
+      },
+      "required": [
+        "kind",
+        "content",
+        "support_ids"
+      ],
+      "type": "object"
+    },
+    "maxItems": 32,
+    "minItems": 1,
+    "type": "array"
+  },
+  "coverage": {
+    "additionalProperties": false,
+    "description": "Inclusive session evidence coverage; start at 1 and advance to_sequence for this session and summary kind.",
+    "properties": {
+      "from_sequence": {
+        "description": "Inclusive first session event sequence; must start at 1.",
+        "exclusiveMinimum": 0,
+        "maximum": 9007199254740991,
+        "type": "integer"
+      },
+      "to_sequence": {
+        "description": "Inclusive last session event sequence; must be >= from_sequence and exceed the current summary ending sequence for this session and kind.",
+        "exclusiveMinimum": 0,
+        "maximum": 9007199254740991,
+        "type": "integer"
+      }
+    },
+    "required": [
+      "from_sequence",
+      "to_sequence"
+    ],
+    "type": "object"
+  },
+  "generator": {
+    "additionalProperties": false,
+    "properties": {
+      "config_hash": {
+        "pattern": "^[0-9a-f]{64}$",
+        "type": "string"
+      },
+      "kind": {
+        "enum": [
+          "root_agent",
+          "harness",
+          "model"
+        ],
+        "type": "string"
+      },
+      "name": {
+        "maxLength": 200,
+        "minLength": 1,
+        "type": "string"
+      },
+      "version": {
+        "maxLength": 200,
+        "minLength": 1,
+        "type": "string"
+      }
+    },
+    "required": [
+      "kind",
+      "name"
+    ],
+    "type": "object"
+  },
+  "kind": {
+    "description": "Send checkpoint for operation=\"checkpoint_pre_compact\" or final for operation=\"finalize\".",
+    "enum": [
+      "checkpoint",
+      "final"
+    ],
+    "type": "string"
+  }
+}
      • addedInput schema / properties / summary / required
        Added value: +[
+  "kind",
+  "coverage",
+  "generator",
+  "claims"
+]
      • changedInput schema / properties / summary / type
        Previous value: -"string"New value: +"object"
      • changedInput schema / required
        Previous value: -[
-  "action",
-  "project"
-]New value: +[
+  "operation",
+  "harness",
+  "project_key",
+  "project_name",
+  "root_session_key",
+  "event_key"
+]
  4. 5 tool updatesv0.4.13
    • Addedmem_context
    • Addedmem_get
    • Addedmem_project
    • Addedmem_save
    • Addedmem_session
  5. 5 tool updatesv0.4.1
    • Removedmem_context
    • Removedmem_get
    • Removedmem_project
    • Removedmem_save
    • Removedmem_session
  6. 6 tool updatesv0.3.7
    • First observedmem_context
    • First observedmem_get
    • First observedmem_project
    • First observedmem_recall
    • First observedmem_save
    • First observedmem_session
Deploy Server
Context All Your Agents Can ShareAgents share what they learn, hand off work, and hold it when you switch models. Start with 5 GB free.fulcradynamics.comAd

TDQS

B3.3/5.0

Scored across 6 tools

Disambiguation4/5

mem_save and mem_session both persist information, but mem_session is explicitly limited to lifecycle events. The read-side tools (mem_recall, mem_context, mem_project) have overlapping search/context/view roles, which could cause misselection, though descriptions provide clear trigger guidance.

Naming Consistency4/5

All tools use a consistent mem_ prefix in snake_case, making names predictable and readable. Minor inconsistency exists because some names are verbs (save, get, recall) and others are nouns (context, project, session), but the pattern is still coherent.

Tool Count5/5

Six tools is well within the ideal range for a focused memory server. Each tool maps to a distinct stage of the memory lifecycle—save, recall, expand, context building, project inspection, and session events—without obvious redundancy.

Completeness3/5

The surface covers saving, searching, retrieval, context building, project views, and session lifecycle. However, there is no explicit update or delete/forget operation for memories, and listing memories beyond search results or project views is limited, which may hinder correcting or pruning stored knowledge.

Maintenance

ActivityActive
ResponsivenessNo issues

Resources

Related MCP Connectors

Related MCP Servers

  • MCP Vector Memory

    vertexhub-ai
    A
    license
    Not graded
    quality
    Not graded
    maintenance
    Provides AI coding agents with persistent, long-term memory through local semantic search and SQLite storage. It enables agents to save and retrieve architectural decisions or project context across different conversation sessions without requiring cloud services.
    MIT

  • LumenCore

    arclightdynamics
    A
    license
    Not graded
    quality
    D
    maintenance
    Provides AI coding assistants with persistent project memory to retain architectural decisions, code patterns, and domain knowledge across sessions. It stores data locally in a SQLite database, allowing agents to remember, recall, and manage project-specific context using full-text search.
    4 npm
    Apache 2.0

  • code-recall

    AbianS
    A
    license
    Not graded
    quality
    C
    maintenance
    Gives AI coding agents persistent memory by storing observations, decisions, and learnings in a local SQLite database with vector search, full-text search, and a rules engine.
    4
    MIT