@agentmemory/agentmemory 0.9.29 → 0.9.31

package/integrations/openclaw/skills/recap/TROUBLESHOOTING.md

@@ -0,0 +1,70 @@
+<!-- AUTOGEN:troubleshooting START - generated by scripts/skills/generate.ts, do not edit by hand -->
+# Troubleshooting agentmemory skills
+
+Recovery steps for separately installed skills. This document is generated into
+each skill directory so native skill readers can open it without parent traversal.
+
+## "MCP tool not available"
+
+Missing tools can mean a stopped MCP process, a disconnected daemon, or an
+explicitly reduced tool surface. Walk these in order:
+
+1. Identify the host. In Claude Code, inspect `/plugin list` and `/mcp`.
+   In Hermes, inspect the configured memory provider and `mcp_servers` separately.
+   In OpenClaw, validate the host configuration and inspect its MCP servers and
+   native plugins separately. In Pi or OMP, inspect `/agentmemory-status` and the
+   MCP inventory separately; native save/search does not prove the broader tools
+   are connected. Do not run another host's setup commands.
+2. Restart or reload the affected host connection after configuration changes.
+3. Inspect the connected tool inventory. Hermes may namespace MCP tools; invoke
+   the actual advertised names and schemas. A native memory provider is not
+   proof that every MCP tool or shared skill is available.
+4. Check `agentmemory status` and the daemon's `AGENTMEMORY_TOOLS` setting.
+   Codex's bundled bridge lists the daemon's enabled tools. The standalone shim
+   used by other hosts can fall back to seven basic tools with a separate store.
+   Do not claim full daemon functionality based on those seven tools.
+5. If `agentmemory connect codex` and the Codex plugin are both enabled, choose
+   one MCP connection. Check `/hooks` before adding global hook fallbacks.
+
+Hermes, OpenClaw, Pi and OMP connector installations bundle skills; other hosts
+may install them separately. Check the host's skill inventory and open this file
+from the installed skill directory. Test automatic capture with a real turn and
+a recorded observation; tool connectivity alone does not establish lifecycle
+capture.
+
+An outage or timeout is not an empty search result. Report the failure. A write
+may have committed before the response was lost; inspect state before retrying.
+
+## REST fallback
+
+When the MCP tools stay unavailable but the daemon is running, call the REST
+API directly:
+
+1. Set `AGENTMEMORY_URL` to the daemon base URL (default `http://localhost:3111`).
+2. The REST API requires a bearer credential by default. Use the host's explicit
+   `AGENTMEMORY_SECRET`; for loopback URLs only, fall back to the secret in
+   `~/.agentmemory/.env` and then `~/.agentmemory/secret`. Load the value locally
+   without displaying it. Never send a local-file secret to a remote URL.
+   If `AGENTMEMORY_CREDENTIAL_MODE=explicit`, require the explicit host credential
+   and do not read local credential files.
+   Authenticated REST fallback requests require HTTPS for non-loopback
+   URLs; HTTP is allowed for loopback URLs (`localhost`, `127.0.0.0/8`, or `[::1]`).
+   Reject redirects on authenticated requests. Do not print or save the secret.
+
+Endpoint map by skill:
+
+| Skill           | REST call                                                        |
+| --------------- | --------------------------------------------------------------- |
+| remember        | `POST /agentmemory/remember`                                     |
+| recall          | `POST /agentmemory/smart-search`                                 |
+| recap           | `GET /agentmemory/sessions` + `POST /agentmemory/smart-search`   |
+| handoff         | `GET /agentmemory/sessions` + `POST /agentmemory/smart-search`   |
+| session-history | `GET /agentmemory/sessions`                                      |
+| commit-context  | `GET /agentmemory/session/by-commit?sha=<sha>`                   |
+| commit-history  | `GET /agentmemory/commits` (URL-encode every query param)       |
+
+The MCP host reads the plugin MCP configuration. Restart the daemon after
+changing its configuration, then restart or reconnect the host MCP process after
+changing its URL or explicit secret. The local bridge reads the credential files
+for each request; it does not inherit other daemon `.env` settings.
+<!-- AUTOGEN:troubleshooting END -->

package/integrations/openclaw/skills/remember/EXAMPLES.md

@@ -0,0 +1,67 @@
+# remember worked examples
+
+## 1. Saving a decision
+
+User: "Remember that we decided to drop Redis and use the iii-engine state store for session caching."
+
+Invocation:
+
+```json
+memory_save {
+  "content": "We decided to drop Redis and use the iii-engine state store for session caching to remove a moving part.",
+  "concepts": "session-caching, state-worker-store, dropped-redis",
+  "files": ""
+}
+```
+
+Response:
+
+```json
+{ "id": "7f3a9c21", "concepts": ["session-caching", "state-worker-store", "dropped-redis"], "saved": true }
+```
+
+Present:
+
+> Saved. Tagged it `session-caching`, `state-worker-store`, `dropped-redis`, so a
+> later recall on caching or Redis will surface this decision.
+
+## 2. Saving a code-specific gotcha
+
+User: "Save this: the rate limiter in middleware/limit.ts counts per-IP, not per-user, so logged-in users on shared IPs collide."
+
+Invocation:
+
+```json
+memory_save {
+  "content": "The rate limiter in middleware/limit.ts counts per-IP, not per-user, so logged-in users on shared IPs collide.",
+  "concepts": "rate-limiter, per-ip-bug, shared-ip-collision",
+  "files": "src/middleware/limit.ts"
+}
+```
+
+Response:
+
+```json
+{ "id": "b21d004e", "concepts": ["rate-limiter", "per-ip-bug", "shared-ip-collision"], "saved": true }
+```
+
+Present:
+
+> Saved memory `b21d004e` referencing `src/middleware/limit.ts`. Concepts:
+> `rate-limiter`, `per-ip-bug`, `shared-ip-collision`.
+
+## 3. Vague request, no files
+
+User: "Remember this for later."
+
+Ask once for the substance, then save:
+
+```json
+memory_save {
+  "content": "Staging deploys must run the migration job before the app rollout, never after.",
+  "concepts": "staging-deploy, migration-ordering, rollout-sequence",
+  "files": ""
+}
+```
+
+Present the confirmation with the concepts echoed back.

package/integrations/openclaw/skills/remember/SKILL.md

@@ -0,0 +1,66 @@
+---
+name: remember
+description: Save an insight, decision, or learning to agentmemory's long-term storage with searchable concept tags. Use when the user says "remember this", "save this", "note that", "don't forget", or wants to preserve knowledge for future sessions.
+argument-hint: "[what to remember]"
+user-invocable: true
+---
+
+The user wants to save this to long-term memory: $ARGUMENTS
+
+## Quick start
+
+```json
+memory_save {
+  "content": "We rotate JWT refresh tokens on every use; the old token is revoked server-side in auth/refresh.ts.",
+  "concepts": "jwt-refresh-rotation, token-revocation, auth-flow",
+  "files": "src/auth/refresh.ts"
+}
+```
+
+Expected output:
+
+```text
+Saved memory abc12345 with 3 concepts: jwt-refresh-rotation, token-revocation, auth-flow.
+```
+
+## Why
+
+A memory is only as useful as the terms that retrieve it. Tag with specific
+concepts so a future `recall` finds it, and preserve the user's own phrasing.
+
+## Workflow
+
+1. Pull the core insight, decision, or fact out of `$ARGUMENTS`.
+2. Extract 2-5 lowercased concept phrases. Prefer specific over generic
+   (`jwt-refresh-rotation` beats `auth`).
+3. Extract referenced file paths (absolute or repo-relative). Empty if none.
+4. Call `memory_save` with `content`, `concepts` (comma-separated string), and
+   `files` (comma-separated string). In a multi-agent setup pass `agentId` so
+   the memory lands in the right agent's scope.
+5. Confirm the save and echo the concepts so the user knows the retrieval terms.
+6. To update a fact, save the corrected version outright: near-duplicate content
+   supersedes the old record, which leaves recall but stays in the version chain.
+
+## Anti-patterns
+
+WRONG: `concepts: "stuff, code, notes"` (generic tags nothing can find later).
+
+RIGHT: `concepts: "jwt-refresh-rotation, token-revocation"` (specific, retrievable).
+
+## Checklist
+
+- Content preserves the user's phrasing, not a paraphrase.
+- Concepts are specific, lowercased, 2-5 items.
+- File paths are real references, not guesses.
+- Confirmation echoes the exact concepts tagged.
+
+## See also
+
+- `recall`: retrieve what you save here (the pair to this skill).
+- `forget`: remove a memory you saved by mistake.
+- `lesson`: behavioral rules from corrections; memories are for facts.
+- `memory-discipline`: when to save unprompted.
+
+## Troubleshooting
+
+See [TROUBLESHOOTING.md](TROUBLESHOOTING.md) if `memory_save` is not available.

package/integrations/openclaw/skills/remember/TROUBLESHOOTING.md

@@ -0,0 +1,70 @@
+<!-- AUTOGEN:troubleshooting START - generated by scripts/skills/generate.ts, do not edit by hand -->
+# Troubleshooting agentmemory skills
+
+Recovery steps for separately installed skills. This document is generated into
+each skill directory so native skill readers can open it without parent traversal.
+
+## "MCP tool not available"
+
+Missing tools can mean a stopped MCP process, a disconnected daemon, or an
+explicitly reduced tool surface. Walk these in order:
+
+1. Identify the host. In Claude Code, inspect `/plugin list` and `/mcp`.
+   In Hermes, inspect the configured memory provider and `mcp_servers` separately.
+   In OpenClaw, validate the host configuration and inspect its MCP servers and
+   native plugins separately. In Pi or OMP, inspect `/agentmemory-status` and the
+   MCP inventory separately; native save/search does not prove the broader tools
+   are connected. Do not run another host's setup commands.
+2. Restart or reload the affected host connection after configuration changes.
+3. Inspect the connected tool inventory. Hermes may namespace MCP tools; invoke
+   the actual advertised names and schemas. A native memory provider is not
+   proof that every MCP tool or shared skill is available.
+4. Check `agentmemory status` and the daemon's `AGENTMEMORY_TOOLS` setting.
+   Codex's bundled bridge lists the daemon's enabled tools. The standalone shim
+   used by other hosts can fall back to seven basic tools with a separate store.
+   Do not claim full daemon functionality based on those seven tools.
+5. If `agentmemory connect codex` and the Codex plugin are both enabled, choose
+   one MCP connection. Check `/hooks` before adding global hook fallbacks.
+
+Hermes, OpenClaw, Pi and OMP connector installations bundle skills; other hosts
+may install them separately. Check the host's skill inventory and open this file
+from the installed skill directory. Test automatic capture with a real turn and
+a recorded observation; tool connectivity alone does not establish lifecycle
+capture.
+
+An outage or timeout is not an empty search result. Report the failure. A write
+may have committed before the response was lost; inspect state before retrying.
+
+## REST fallback
+
+When the MCP tools stay unavailable but the daemon is running, call the REST
+API directly:
+
+1. Set `AGENTMEMORY_URL` to the daemon base URL (default `http://localhost:3111`).
+2. The REST API requires a bearer credential by default. Use the host's explicit
+   `AGENTMEMORY_SECRET`; for loopback URLs only, fall back to the secret in
+   `~/.agentmemory/.env` and then `~/.agentmemory/secret`. Load the value locally
+   without displaying it. Never send a local-file secret to a remote URL.
+   If `AGENTMEMORY_CREDENTIAL_MODE=explicit`, require the explicit host credential
+   and do not read local credential files.
+   Authenticated REST fallback requests require HTTPS for non-loopback
+   URLs; HTTP is allowed for loopback URLs (`localhost`, `127.0.0.0/8`, or `[::1]`).
+   Reject redirects on authenticated requests. Do not print or save the secret.
+
+Endpoint map by skill:
+
+| Skill           | REST call                                                        |
+| --------------- | --------------------------------------------------------------- |
+| remember        | `POST /agentmemory/remember`                                     |
+| recall          | `POST /agentmemory/smart-search`                                 |
+| recap           | `GET /agentmemory/sessions` + `POST /agentmemory/smart-search`   |
+| handoff         | `GET /agentmemory/sessions` + `POST /agentmemory/smart-search`   |
+| session-history | `GET /agentmemory/sessions`                                      |
+| commit-context  | `GET /agentmemory/session/by-commit?sha=<sha>`                   |
+| commit-history  | `GET /agentmemory/commits` (URL-encode every query param)       |
+
+The MCP host reads the plugin MCP configuration. Restart the daemon after
+changing its configuration, then restart or reconnect the host MCP process after
+changing its URL or explicit secret. The local bridge reads the credential files
+for each request; it does not inherit other daemon `.env` settings.
+<!-- AUTOGEN:troubleshooting END -->

package/integrations/openclaw/skills/session-history/EXAMPLES.md

@@ -0,0 +1,59 @@
+# session-history worked examples
+
+## 1. Standard timeline
+
+User: "Show me the session history."
+
+Invocation:
+
+```json
+memory_sessions { "project": "app", "limit": 20 }
+```
+
+Response:
+
+```json
+{
+  "sessions": [
+    { "id": "7f3a9c21", "project": "app", "startedAt": "2026-06-07T09:00:00Z",
+      "status": "completed", "observationCount": 14,
+      "summary": "Reworked refresh rotation",
+      "highlights": [ { "type": "decision", "title": "Rotate refresh tokens on every use" } ] },
+    { "id": "b21d004e", "project": "app", "startedAt": "2026-06-05T14:00:00Z",
+      "status": "completed", "observationCount": 9,
+      "highlights": [ { "type": "code", "title": "limit.ts counts per-IP" } ] }
+  ]
+}
+```
+
+Present:
+
+> - `7f3a9c2` app, 2026-06-07 09:00, completed, 14 obs
+>   - decision: Rotate refresh tokens on every use (summary: Reworked refresh rotation)
+> - `b21d004` app, 2026-06-05 14:00, completed, 9 obs
+>   - code: limit.ts counts per-IP
+
+## 2. Session with no observations
+
+If a returned session has `observationCount: 0`, list it but say so:
+
+> - `c98f110` app, 2026-06-04 11:00, abandoned, 0 obs (no recorded work)
+
+## 3. Empty history
+
+User: "What did we do last time?"
+
+```json
+memory_sessions { "project": "app", "limit": 20 }
+```
+
+Response:
+
+```json
+{ "sessions": [] }
+```
+
+Present:
+
+> No recorded sessions yet for this project. Once you work with memory capture
+> on, they will show here. Use `remember` to save a note now.

package/integrations/openclaw/skills/session-history/SKILL.md

@@ -0,0 +1,67 @@
+---
+name: session-history
+description: Show what happened in recent past sessions on this project as a clean timeline. Use when the user asks "what did we do last time", "session history", "past sessions", or wants an overview of previous work.
+user-invocable: true
+---
+
+The user wants an overview of recent sessions on this project.
+
+## Quick start
+
+```json
+memory_sessions { "project": "<current-project-id>", "limit": 20 }
+```
+
+Expected output:
+
+```text
+7f3a9c2 · app · 2026-06-07 09:00 · completed · 14 obs
+  - decision: Rotate refresh tokens on every use
+b21d004 · app · 2026-06-05 14:00 · completed · 9 obs
+  - code: limit.ts counts per-IP
+```
+
+## Why
+
+Only show sessions and observations the tool returned. An empty history is a
+real answer, never a cue to invent past work.
+
+## Workflow
+
+1. Use the exact project identifier recorded by the host and pass it to
+   `memory_sessions`, with `agentId` when requested. If it is unknown, page
+   through sessions using `nextCursor` and match normalized `cwd` by directory
+   boundary before choosing the most recent 20. Never substitute another project.
+2. Preserve scope filters on every page; stop at the requested count or a null
+   `nextCursor`. State when the displayed history is a partial page. Present in
+   reverse chronological order: session id (first 8), project, start
+   time, status.
+3. For sessions with observations, show the key highlights (type plus title).
+4. Note the total observation count per session.
+5. When a session summary exists, surface its title and the key decisions.
+
+## Anti-patterns
+
+WRONG: the tool returns two sessions, you describe "several sessions of steady
+progress" and add ones you remember from the conversation.
+
+RIGHT: show exactly the two sessions returned, each with its real id, status, and
+observation count.
+
+## Checklist
+
+- Every session shown came from the tool response.
+- Project/directory scope was checked before selecting the displayed window.
+- Order is reverse-chronological.
+- Per-session observation counts match the response.
+- No session or highlight was invented or merged.
+
+## See also
+
+- `recap`: same data grouped by date with highlights.
+- `handoff`: jump straight into the most recent session.
+- `recall`: search across all sessions by topic.
+
+## Troubleshooting
+
+See [TROUBLESHOOTING.md](TROUBLESHOOTING.md) if `memory_sessions` is not available.

package/integrations/openclaw/skills/session-history/TROUBLESHOOTING.md

@@ -0,0 +1,70 @@
+<!-- AUTOGEN:troubleshooting START - generated by scripts/skills/generate.ts, do not edit by hand -->
+# Troubleshooting agentmemory skills
+
+Recovery steps for separately installed skills. This document is generated into
+each skill directory so native skill readers can open it without parent traversal.
+
+## "MCP tool not available"
+
+Missing tools can mean a stopped MCP process, a disconnected daemon, or an
+explicitly reduced tool surface. Walk these in order:
+
+1. Identify the host. In Claude Code, inspect `/plugin list` and `/mcp`.
+   In Hermes, inspect the configured memory provider and `mcp_servers` separately.
+   In OpenClaw, validate the host configuration and inspect its MCP servers and
+   native plugins separately. In Pi or OMP, inspect `/agentmemory-status` and the
+   MCP inventory separately; native save/search does not prove the broader tools
+   are connected. Do not run another host's setup commands.
+2. Restart or reload the affected host connection after configuration changes.
+3. Inspect the connected tool inventory. Hermes may namespace MCP tools; invoke
+   the actual advertised names and schemas. A native memory provider is not
+   proof that every MCP tool or shared skill is available.
+4. Check `agentmemory status` and the daemon's `AGENTMEMORY_TOOLS` setting.
+   Codex's bundled bridge lists the daemon's enabled tools. The standalone shim
+   used by other hosts can fall back to seven basic tools with a separate store.
+   Do not claim full daemon functionality based on those seven tools.
+5. If `agentmemory connect codex` and the Codex plugin are both enabled, choose
+   one MCP connection. Check `/hooks` before adding global hook fallbacks.
+
+Hermes, OpenClaw, Pi and OMP connector installations bundle skills; other hosts
+may install them separately. Check the host's skill inventory and open this file
+from the installed skill directory. Test automatic capture with a real turn and
+a recorded observation; tool connectivity alone does not establish lifecycle
+capture.
+
+An outage or timeout is not an empty search result. Report the failure. A write
+may have committed before the response was lost; inspect state before retrying.
+
+## REST fallback
+
+When the MCP tools stay unavailable but the daemon is running, call the REST
+API directly:
+
+1. Set `AGENTMEMORY_URL` to the daemon base URL (default `http://localhost:3111`).
+2. The REST API requires a bearer credential by default. Use the host's explicit
+   `AGENTMEMORY_SECRET`; for loopback URLs only, fall back to the secret in
+   `~/.agentmemory/.env` and then `~/.agentmemory/secret`. Load the value locally
+   without displaying it. Never send a local-file secret to a remote URL.
+   If `AGENTMEMORY_CREDENTIAL_MODE=explicit`, require the explicit host credential
+   and do not read local credential files.
+   Authenticated REST fallback requests require HTTPS for non-loopback
+   URLs; HTTP is allowed for loopback URLs (`localhost`, `127.0.0.0/8`, or `[::1]`).
+   Reject redirects on authenticated requests. Do not print or save the secret.
+
+Endpoint map by skill:
+
+| Skill           | REST call                                                        |
+| --------------- | --------------------------------------------------------------- |
+| remember        | `POST /agentmemory/remember`                                     |
+| recall          | `POST /agentmemory/smart-search`                                 |
+| recap           | `GET /agentmemory/sessions` + `POST /agentmemory/smart-search`   |
+| handoff         | `GET /agentmemory/sessions` + `POST /agentmemory/smart-search`   |
+| session-history | `GET /agentmemory/sessions`                                      |
+| commit-context  | `GET /agentmemory/session/by-commit?sha=<sha>`                   |
+| commit-history  | `GET /agentmemory/commits` (URL-encode every query param)       |
+
+The MCP host reads the plugin MCP configuration. Restart the daemon after
+changing its configuration, then restart or reconnect the host MCP process after
+changing its URL or explicit secret. The local bridge reads the credential files
+for each request; it does not inherit other daemon `.env` settings.
+<!-- AUTOGEN:troubleshooting END -->

package/integrations/openclaw/skills/write-agentmemory-skill/SKILL.md

@@ -0,0 +1,41 @@
+---
+name: write-agentmemory-skill
+description: The house format and rules for writing or updating an agentmemory skill. Use when adding a new skill, restructuring an existing one, or reviewing a skill contribution for consistency.
+user-invocable: false
+---
+
+agentmemory skills follow one tiered format so they stay skimmable, accurate, and current. Match it exactly.
+
+## Directory layout
+
+```text
+plugin/skills/<name>/
+  SKILL.md      (required, under 100 lines)
+  REFERENCE.md  (optional, dense facts; auto-generate data tables)
+  EXAMPLES.md   (optional, worked transcripts)
+  TROUBLESHOOTING.md (generated support file)
+```
+
+## SKILL.md rules
+
+- Frontmatter: `name`, `description`, optional `argument-hint`, and `user-invocable`. Set `user-invocable: true` only for skills the user runs as a slash command; reference and knowledge skills are `false`.
+- Description is two sentences and the only thing the agent sees when deciding to load the skill. Sentence one states the capability. Sentence two starts "Use when" and lists concrete triggers. Keep it distinct from sibling skills, under 1024 chars, third person.
+- Body order: Quick start (one concrete example), Why (the governing principle), Workflow (numbered steps with decision gates), Anti-patterns (a WRONG vs RIGHT callout for the top mistake), Checklist, See also (cross-link siblings), Reference or Troubleshooting pointer.
+- Stay under 100 lines. Move dense facts to REFERENCE.md and examples to EXAMPLES.md.
+- Keep supporting files inside the skill directory so each skill works when installed separately. Link [TROUBLESHOOTING.md](TROUBLESHOOTING.md); the generator copies shared recovery instructions into each skill root.
+
+## Keep it current
+
+Facts that exist in source (tool names and parameters, REST endpoints, env vars, connect adapters, hook events) are generated, never hand-typed. Edit the source, then run `npm run skills:gen`. CI runs `npm run skills:check` and fails on drift, so generated tables cannot fall behind the code.
+
+## Style
+
+No external or competitor product names. No emojis. No em-dashes. No filler. State the thing and stop.
+
+## Checklist
+
+- Description has a "Use when" sentence with real triggers.
+- SKILL.md is under 100 lines.
+- No time-sensitive claims and no duplicated troubleshooting block.
+- Concrete example present; generated facts come from the generator.
+- Cross-links resolve and go one level deep.

package/integrations/openclaw/skills/write-agentmemory-skill/TROUBLESHOOTING.md

@@ -0,0 +1,70 @@
+<!-- AUTOGEN:troubleshooting START - generated by scripts/skills/generate.ts, do not edit by hand -->
+# Troubleshooting agentmemory skills
+
+Recovery steps for separately installed skills. This document is generated into
+each skill directory so native skill readers can open it without parent traversal.
+
+## "MCP tool not available"
+
+Missing tools can mean a stopped MCP process, a disconnected daemon, or an
+explicitly reduced tool surface. Walk these in order:
+
+1. Identify the host. In Claude Code, inspect `/plugin list` and `/mcp`.
+   In Hermes, inspect the configured memory provider and `mcp_servers` separately.
+   In OpenClaw, validate the host configuration and inspect its MCP servers and
+   native plugins separately. In Pi or OMP, inspect `/agentmemory-status` and the
+   MCP inventory separately; native save/search does not prove the broader tools
+   are connected. Do not run another host's setup commands.
+2. Restart or reload the affected host connection after configuration changes.
+3. Inspect the connected tool inventory. Hermes may namespace MCP tools; invoke
+   the actual advertised names and schemas. A native memory provider is not
+   proof that every MCP tool or shared skill is available.
+4. Check `agentmemory status` and the daemon's `AGENTMEMORY_TOOLS` setting.
+   Codex's bundled bridge lists the daemon's enabled tools. The standalone shim
+   used by other hosts can fall back to seven basic tools with a separate store.
+   Do not claim full daemon functionality based on those seven tools.
+5. If `agentmemory connect codex` and the Codex plugin are both enabled, choose
+   one MCP connection. Check `/hooks` before adding global hook fallbacks.
+
+Hermes, OpenClaw, Pi and OMP connector installations bundle skills; other hosts
+may install them separately. Check the host's skill inventory and open this file
+from the installed skill directory. Test automatic capture with a real turn and
+a recorded observation; tool connectivity alone does not establish lifecycle
+capture.
+
+An outage or timeout is not an empty search result. Report the failure. A write
+may have committed before the response was lost; inspect state before retrying.
+
+## REST fallback
+
+When the MCP tools stay unavailable but the daemon is running, call the REST
+API directly:
+
+1. Set `AGENTMEMORY_URL` to the daemon base URL (default `http://localhost:3111`).
+2. The REST API requires a bearer credential by default. Use the host's explicit
+   `AGENTMEMORY_SECRET`; for loopback URLs only, fall back to the secret in
+   `~/.agentmemory/.env` and then `~/.agentmemory/secret`. Load the value locally
+   without displaying it. Never send a local-file secret to a remote URL.
+   If `AGENTMEMORY_CREDENTIAL_MODE=explicit`, require the explicit host credential
+   and do not read local credential files.
+   Authenticated REST fallback requests require HTTPS for non-loopback
+   URLs; HTTP is allowed for loopback URLs (`localhost`, `127.0.0.0/8`, or `[::1]`).
+   Reject redirects on authenticated requests. Do not print or save the secret.
+
+Endpoint map by skill:
+
+| Skill           | REST call                                                        |
+| --------------- | --------------------------------------------------------------- |
+| remember        | `POST /agentmemory/remember`                                     |
+| recall          | `POST /agentmemory/smart-search`                                 |
+| recap           | `GET /agentmemory/sessions` + `POST /agentmemory/smart-search`   |
+| handoff         | `GET /agentmemory/sessions` + `POST /agentmemory/smart-search`   |
+| session-history | `GET /agentmemory/sessions`                                      |
+| commit-context  | `GET /agentmemory/session/by-commit?sha=<sha>`                   |
+| commit-history  | `GET /agentmemory/commits` (URL-encode every query param)       |
+
+The MCP host reads the plugin MCP configuration. Restart the daemon after
+changing its configuration, then restart or reconnect the host MCP process after
+changing its URL or explicit secret. The local bridge reads the credential files
+for each request; it does not inherit other daemon `.env` settings.
+<!-- AUTOGEN:troubleshooting END -->