@quantumclaw/quantumclaw 2026.3.22

package/docs/reference/prompt-caching.md

@@ -0,0 +1,185 @@
+---
+title: "Prompt Caching"
+summary: "Prompt caching knobs, merge order, provider behavior, and tuning patterns"
+read_when:
+  - You want to reduce prompt token costs with cache retention
+  - You need per-agent cache behavior in multi-agent setups
+  - You are tuning heartbeat and cache-ttl pruning together
+---
+
+# Prompt caching
+
+Prompt caching means the model provider can reuse unchanged prompt prefixes (usually system/developer instructions and other stable context) across turns instead of re-processing them every time. The first matching request writes cache tokens (`cacheWrite`), and later matching requests can read them back (`cacheRead`).
+
+Why this matters: lower token cost, faster responses, and more predictable performance for long-running sessions. Without caching, repeated prompts pay the full prompt cost on every turn even when most input did not change.
+
+This page covers all cache-related knobs that affect prompt reuse and token cost.
+
+For Anthropic pricing details, see:
+[https://docs.anthropic.com/docs/build-with-claude/prompt-caching](https://docs.anthropic.com/docs/build-with-claude/prompt-caching)
+
+## Primary knobs
+
+### `cacheRetention` (model and per-agent)
+
+Set cache retention on model params:
+
+```yaml
+agents:
+  defaults:
+    models:
+      "anthropic/claude-opus-4-6":
+        params:
+          cacheRetention: "short" # none | short | long
+```
+
+Per-agent override:
+
+```yaml
+agents:
+  list:
+    - id: "alerts"
+      params:
+        cacheRetention: "none"
+```
+
+Config merge order:
+
+1. `agents.defaults.models["provider/model"].params`
+2. `agents.list[].params` (matching agent id; overrides by key)
+
+### Legacy `cacheControlTtl`
+
+Legacy values are still accepted and mapped:
+
+- `5m` -> `short`
+- `1h` -> `long`
+
+Prefer `cacheRetention` for new config.
+
+### `contextPruning.mode: "cache-ttl"`
+
+Prunes old tool-result context after cache TTL windows so post-idle requests do not re-cache oversized history.
+
+```yaml
+agents:
+  defaults:
+    contextPruning:
+      mode: "cache-ttl"
+      ttl: "1h"
+```
+
+See [Session Pruning](/concepts/session-pruning) for full behavior.
+
+### Heartbeat keep-warm
+
+Heartbeat can keep cache windows warm and reduce repeated cache writes after idle gaps.
+
+```yaml
+agents:
+  defaults:
+    heartbeat:
+      every: "55m"
+```
+
+Per-agent heartbeat is supported at `agents.list[].heartbeat`.
+
+## Provider behavior
+
+### Anthropic (direct API)
+
+- `cacheRetention` is supported.
+- With Anthropic API-key auth profiles, QuantumClaw seeds `cacheRetention: "short"` for Anthropic model refs when unset.
+
+### Amazon Bedrock
+
+- Anthropic Claude model refs (`amazon-bedrock/*anthropic.claude*`) support explicit `cacheRetention` pass-through.
+- Non-Anthropic Bedrock models are forced to `cacheRetention: "none"` at runtime.
+
+### OpenRouter Anthropic models
+
+For `openrouter/anthropic/*` model refs, QuantumClaw injects Anthropic `cache_control` on system/developer prompt blocks to improve prompt-cache reuse.
+
+### Other providers
+
+If the provider does not support this cache mode, `cacheRetention` has no effect.
+
+## Tuning patterns
+
+### Mixed traffic (recommended default)
+
+Keep a long-lived baseline on your main agent, disable caching on bursty notifier agents:
+
+```yaml
+agents:
+  defaults:
+    model:
+      primary: "anthropic/claude-opus-4-6"
+    models:
+      "anthropic/claude-opus-4-6":
+        params:
+          cacheRetention: "long"
+  list:
+    - id: "research"
+      default: true
+      heartbeat:
+        every: "55m"
+    - id: "alerts"
+      params:
+        cacheRetention: "none"
+```
+
+### Cost-first baseline
+
+- Set baseline `cacheRetention: "short"`.
+- Enable `contextPruning.mode: "cache-ttl"`.
+- Keep heartbeat below your TTL only for agents that benefit from warm caches.
+
+## Cache diagnostics
+
+QuantumClaw exposes dedicated cache-trace diagnostics for embedded agent runs.
+
+### `diagnostics.cacheTrace` config
+
+```yaml
+diagnostics:
+  cacheTrace:
+    enabled: true
+    filePath: "~/.quantumclaw/logs/cache-trace.jsonl" # optional
+    includeMessages: false # default true
+    includePrompt: false # default true
+    includeSystem: false # default true
+```
+
+Defaults:
+
+- `filePath`: `$QUANTUMCLAW_STATE_DIR/logs/cache-trace.jsonl`
+- `includeMessages`: `true`
+- `includePrompt`: `true`
+- `includeSystem`: `true`
+
+### Env toggles (one-off debugging)
+
+- `QUANTUMCLAW_CACHE_TRACE=1` enables cache tracing.
+- `QUANTUMCLAW_CACHE_TRACE_FILE=/path/to/cache-trace.jsonl` overrides output path.
+- `QUANTUMCLAW_CACHE_TRACE_MESSAGES=0|1` toggles full message payload capture.
+- `QUANTUMCLAW_CACHE_TRACE_PROMPT=0|1` toggles prompt text capture.
+- `QUANTUMCLAW_CACHE_TRACE_SYSTEM=0|1` toggles system prompt capture.
+
+### What to inspect
+
+- Cache trace events are JSONL and include staged snapshots like `session:loaded`, `prompt:before`, `stream:context`, and `session:after`.
+- Per-turn cache token impact is visible in normal usage surfaces via `cacheRead` and `cacheWrite` (for example `/usage full` and session usage summaries).
+
+## Quick troubleshooting
+
+- High `cacheWrite` on most turns: check for volatile system-prompt inputs and verify model/provider supports your cache settings.
+- No effect from `cacheRetention`: confirm model key matches `agents.defaults.models["provider/model"]`.
+- Bedrock Nova/Mistral requests with cache settings: expected runtime force to `none`.
+
+Related docs:
+
+- [Anthropic](/providers/anthropic)
+- [Token Use and Costs](/reference/token-use)
+- [Session Pruning](/concepts/session-pruning)
+- [Gateway Configuration Reference](/gateway/configuration-reference)

package/docs/reference/rpc.md

@@ -0,0 +1,43 @@
+---
+summary: "RPC adapters for external CLIs (signal-cli, legacy imsg) and gateway patterns"
+read_when:
+  - Adding or changing external CLI integrations
+  - Debugging RPC adapters (signal-cli, imsg)
+title: "RPC Adapters"
+---
+
+# RPC adapters
+
+QuantumClaw integrates external CLIs via JSON-RPC. Two patterns are used today.
+
+## Pattern A: HTTP daemon (signal-cli)
+
+- `signal-cli` runs as a daemon with JSON-RPC over HTTP.
+- Event stream is SSE (`/api/v1/events`).
+- Health probe: `/api/v1/check`.
+- QuantumClaw owns lifecycle when `channels.signal.autoStart=true`.
+
+See [Signal](/channels/signal) for setup and endpoints.
+
+## Pattern B: stdio child process (legacy: imsg)
+
+> **Note:** For new iMessage setups, use [BlueBubbles](/channels/bluebubbles) instead.
+
+- QuantumClaw spawns `imsg rpc` as a child process (legacy iMessage integration).
+- JSON-RPC is line-delimited over stdin/stdout (one JSON object per line).
+- No TCP port, no daemon required.
+
+Core methods used:
+
+- `watch.subscribe` → notifications (`method: "message"`)
+- `watch.unsubscribe`
+- `send`
+- `chats.list` (probe/diagnostics)
+
+See [iMessage](/channels/imessage) for legacy setup and addressing (`chat_id` preferred).
+
+## Adapter guidelines
+
+- Gateway owns the process (start/stop tied to provider lifecycle).
+- Keep RPC clients resilient: timeouts, restart on exit.
+- Prefer stable IDs (e.g., `chat_id`) over display strings.

package/docs/reference/secretref-credential-surface.md

@@ -0,0 +1,140 @@
+---
+summary: "Canonical supported vs unsupported SecretRef credential surface"
+read_when:
+  - Verifying SecretRef credential coverage
+  - Auditing whether a credential is eligible for `secrets configure` or `secrets apply`
+  - Verifying why a credential is outside the supported surface
+title: "SecretRef Credential Surface"
+---
+
+# SecretRef credential surface
+
+This page defines the canonical SecretRef credential surface.
+
+Scope intent:
+
+- In scope: strictly user-supplied credentials that QuantumClaw does not mint or rotate.
+- Out of scope: runtime-minted or rotating credentials, OAuth refresh material, and session-like artifacts.
+
+## Supported credentials
+
+### `quantumclaw.json` targets (`secrets configure` + `secrets apply` + `secrets audit`)
+
+[//]: # "secretref-supported-list-start"
+
+- `models.providers.*.apiKey`
+- `models.providers.*.headers.*`
+- `skills.entries.*.apiKey`
+- `agents.defaults.memorySearch.remote.apiKey`
+- `agents.list[].memorySearch.remote.apiKey`
+- `talk.apiKey`
+- `talk.providers.*.apiKey`
+- `messages.tts.elevenlabs.apiKey`
+- `messages.tts.openai.apiKey`
+- `tools.web.fetch.firecrawl.apiKey`
+- `plugins.entries.brave.config.webSearch.apiKey`
+- `plugins.entries.google.config.webSearch.apiKey`
+- `plugins.entries.xai.config.webSearch.apiKey`
+- `plugins.entries.moonshot.config.webSearch.apiKey`
+- `plugins.entries.perplexity.config.webSearch.apiKey`
+- `plugins.entries.firecrawl.config.webSearch.apiKey`
+- `plugins.entries.tavily.config.webSearch.apiKey`
+- `tools.web.search.apiKey`
+- `tools.web.search.gemini.apiKey`
+- `tools.web.search.grok.apiKey`
+- `tools.web.search.kimi.apiKey`
+- `tools.web.search.perplexity.apiKey`
+- `gateway.auth.password`
+- `gateway.auth.token`
+- `gateway.remote.token`
+- `gateway.remote.password`
+- `cron.webhookToken`
+- `channels.telegram.botToken`
+- `channels.telegram.webhookSecret`
+- `channels.telegram.accounts.*.botToken`
+- `channels.telegram.accounts.*.webhookSecret`
+- `channels.slack.botToken`
+- `channels.slack.appToken`
+- `channels.slack.userToken`
+- `channels.slack.signingSecret`
+- `channels.slack.accounts.*.botToken`
+- `channels.slack.accounts.*.appToken`
+- `channels.slack.accounts.*.userToken`
+- `channels.slack.accounts.*.signingSecret`
+- `channels.discord.token`
+- `channels.discord.pluralkit.token`
+- `channels.discord.voice.tts.elevenlabs.apiKey`
+- `channels.discord.voice.tts.openai.apiKey`
+- `channels.discord.accounts.*.token`
+- `channels.discord.accounts.*.pluralkit.token`
+- `channels.discord.accounts.*.voice.tts.elevenlabs.apiKey`
+- `channels.discord.accounts.*.voice.tts.openai.apiKey`
+- `channels.irc.password`
+- `channels.irc.nickserv.password`
+- `channels.irc.accounts.*.password`
+- `channels.irc.accounts.*.nickserv.password`
+- `channels.bluebubbles.password`
+- `channels.bluebubbles.accounts.*.password`
+- `channels.feishu.appSecret`
+- `channels.feishu.encryptKey`
+- `channels.feishu.verificationToken`
+- `channels.feishu.accounts.*.appSecret`
+- `channels.feishu.accounts.*.encryptKey`
+- `channels.feishu.accounts.*.verificationToken`
+- `channels.msteams.appPassword`
+- `channels.mattermost.botToken`
+- `channels.mattermost.accounts.*.botToken`
+- `channels.matrix.password`
+- `channels.matrix.accounts.*.password`
+- `channels.nextcloud-talk.botSecret`
+- `channels.nextcloud-talk.apiPassword`
+- `channels.nextcloud-talk.accounts.*.botSecret`
+- `channels.nextcloud-talk.accounts.*.apiPassword`
+- `channels.zalo.botToken`
+- `channels.zalo.webhookSecret`
+- `channels.zalo.accounts.*.botToken`
+- `channels.zalo.accounts.*.webhookSecret`
+- `channels.googlechat.serviceAccount` via sibling `serviceAccountRef` (compatibility exception)
+- `channels.googlechat.accounts.*.serviceAccount` via sibling `serviceAccountRef` (compatibility exception)
+
+### `auth-profiles.json` targets (`secrets configure` + `secrets apply` + `secrets audit`)
+
+- `profiles.*.keyRef` (`type: "api_key"`)
+- `profiles.*.tokenRef` (`type: "token"`)
+
+[//]: # "secretref-supported-list-end"
+
+Notes:
+
+- Auth-profile plan targets require `agentId`.
+- Plan entries target `profiles.*.key` / `profiles.*.token` and write sibling refs (`keyRef` / `tokenRef`).
+- Auth-profile refs are included in runtime resolution and audit coverage.
+- For SecretRef-managed model providers, generated `agents/*/agent/models.json` entries persist non-secret markers (not resolved secret values) for `apiKey`/header surfaces.
+- Marker persistence is source-authoritative: QuantumClaw writes markers from the active source config snapshot (pre-resolution), not from resolved runtime secret values.
+- For web search:
+  - In explicit provider mode (`tools.web.search.provider` set), only the selected provider key is active.
+  - In auto mode (`tools.web.search.provider` unset), only the first provider key that resolves by precedence is active.
+  - In auto mode, non-selected provider refs are treated as inactive until selected.
+  - Legacy `tools.web.search.*` provider paths still resolve during the compatibility window, but the canonical SecretRef surface is `plugins.entries.<plugin>.config.webSearch.*`.
+
+## Unsupported credentials
+
+Out-of-scope credentials include:
+
+[//]: # "secretref-unsupported-list-start"
+
+- `commands.ownerDisplaySecret`
+- `channels.matrix.accessToken`
+- `channels.matrix.accounts.*.accessToken`
+- `hooks.token`
+- `hooks.gmail.pushToken`
+- `hooks.mappings[].sessionKey`
+- `auth-profiles.oauth.*`
+- `discord.threadBindings.*.webhookToken`
+- `whatsapp.creds.json`
+
+[//]: # "secretref-unsupported-list-end"
+
+Rationale:
+
+- These credentials are minted, rotated, session-bearing, or OAuth-durable classes that do not fit read-only external SecretRef resolution.