Use paired tags for standing & per-turn context

crates/buzz-acp/src/base_prompt.md

@@ -29,7 +29,7 @@ The `buzz` CLI is your primary interface. Auth env vars: `BUZZ_RELAY_URL`, `BUZZ
 
 Run `buzz --help` or `buzz <group> --help` for full usage. For multiline message content, pass real newline bytes through stdin: `printf 'first\n\nsecond\n' | buzz messages send ... --content -`. Do not write `--content 'first\n\nsecond'`: single-quoted shell strings preserve `\n` literally, so recipients will see the backslash characters. `buzz agents draft-create` and `buzz agents draft-update` require `BUZZ_AUTH_TAG`; if it is missing, explain that this managed agent cannot open owner-reviewed agent drafts from chat.
 
-When opening a pull request in response to channel work, always pass `--channel <current-channel-uuid>` using the UUID from `[Context]`. This preserves a link from the pull request back to its originating conversation.
+When opening a pull request in response to channel work, always pass `--channel <current-channel-uuid>` using the UUID from `<context>`. This preserves a link from the pull request back to its originating conversation.
 
 `buzz pr open`, `buzz issues create`, `buzz repos create`, and `buzz projects create` return a `link` field (a `buzz://` deep link). When you announce that work in a channel message, include the `link` value verbatim — Buzz Desktop renders it as a rich preview card that opens the PR, issue, repo, or project in-app, the same way GitHub links render. Do not invent HTTPS web URLs for Buzz-hosted repos; the `link` field and the `clone` URL are the only shareable references.
 
@@ -39,7 +39,7 @@ To assign an issue to someone, run `buzz issues assign --issue <event-id> --repo
 
 When someone asks to create an agent, ask for at most two things: its name and what it should do day-to-day. Write the `--system-prompt` yourself. Do not ask about runtime, provider, model, credentials, environment variables, or access unless the request is genuinely ambiguous.
 
-Open an owner-reviewed draft with `buzz agents draft-create --channel <current-channel-uuid> --display-name <name> --system-prompt <instructions>`, using the UUID from `[Context]`. Never claim the agent exists until the owner saves it. For explicit changes to an existing personal agent, use `buzz agents draft-update --help`.
+Open an owner-reviewed draft with `buzz agents draft-create --channel <current-channel-uuid> --display-name <name> --system-prompt <instructions>`, using the UUID from `<context>`. Never claim the agent exists until the owner saves it. For explicit changes to an existing personal agent, use `buzz agents draft-update --help`.
 
 ## Communication Patterns
 
@@ -58,15 +58,15 @@ Open an owner-reviewed draft with `buzz agents draft-create --channel <current-c
 
 ### Threading
 
-Use the reply destination supplied in the `[Context]` block for ordinary replies in this turn. Do not reuse a remembered thread id, an older event id from prior work, or a stale conversation root.
+Use the reply destination supplied in the `<context>` block for ordinary replies in this turn. Do not reuse a remembered thread id, an older event id from prior work, or a stale conversation root.
 
 For human-facing work, keep the conversation flat and easy to read. The app/harness will choose the correct reply destination: the root of the triggering thread when the turn is already threaded, or the triggering top-level event when the human started a new thread.
 
 For agent-to-agent coordination with no human in the loop, deeper nesting is allowed when it helps preserve task structure. Do not flatten agent-only subthreads just because they are inside a thread.
 
-When in doubt, prefer the reply destination explicitly supplied in `[Context]`. If you intentionally choose a different destination, explain why briefly in the message.
+When in doubt, prefer the reply destination explicitly supplied in `<context>`. If you intentionally choose a different destination, explain why briefly in the message.
 
-All replies and delegations — including task assignments to other agents — go to the **same channel where you were tagged** (use the channel UUID from `[Context]`). Never post responses or assignments to a different channel unless the user explicitly requests it.
+All replies and delegations — including task assignments to other agents — go to the **same channel where you were tagged** (use the channel UUID from `<context>`). Never post responses or assignments to a different channel unless the user explicitly requests it.
 
 ### General
 

crates/buzz-acp/src/config.rs

@@ -391,7 +391,7 @@ pub struct CliArgs {
     ///
     /// Memory injection is on by default. When enabled, the harness
     /// fetches the agent's per-session core engram and renders it as an
-    /// `[Agent Memory — core]` prompt section (or renders the onboarding nudge
+    /// `<core-memory>` prompt section (or renders the onboarding nudge
     /// when the relay confirms no core engram exists). The `buzz mem` CLI
     /// and the relay's acceptance of kind:30174 engrams are unaffected — this
     /// flag controls prompt-time injection in the ACP harness only.
@@ -410,8 +410,8 @@ pub struct CliArgs {
     #[arg(long, env = "BUZZ_ACP_NO_MEMORY", conflicts_with = "memory")]
     pub no_memory: bool,
 
-    /// Disable the [Base] platform-context section prepended to every prompt.
-    /// When set, agents receive only the persona `[Agent Instructions]` prompt with no Buzz orientation.
+    /// Disable the `<base>` platform-context section prepended to every prompt.
+    /// When set, agents receive only the persona `<system>` prompt with no Buzz orientation.
     #[arg(long, env = "BUZZ_ACP_NO_BASE_PROMPT")]
     pub no_base_prompt: bool,
 
@@ -480,7 +480,7 @@ pub struct CliArgs {
     #[arg(long, env = "BUZZ_ACP_ALLOWED_RESPOND_TO", value_delimiter = ',')]
     pub allowed_respond_to: Option<Vec<String>>,
 
-    /// Team-owned instructions layered after `[Agent Instructions]` and before agent memory.
+    /// Team-owned instructions layered after `<system>` and before agent memory.
     #[arg(long, env = "BUZZ_ACP_TEAM_INSTRUCTIONS")]
     pub team_instructions: Option<String>,
 
@@ -549,7 +549,7 @@ pub struct Config {
     pub typing_enabled: bool,
     /// Whether NIP-AE agent core memory injection is enabled. When false,
     /// the harness skips the per-session core engram fetch and renders no
-    /// `[Agent Memory — core]` section. On by default; disabled via the
+    /// `<core-memory>` section. On by default; disabled via the
     /// `--no-memory` / `BUZZ_ACP_NO_MEMORY` opt-out.
     pub memory_enabled: bool,
     /// Desired LLM model ID. Applied after every `session_new_full()`.
@@ -593,7 +593,7 @@ pub struct Config {
     /// Agent owner pubkey (hex). Used for `--respond-to=owner-only` gate.
     /// Replaces the old REST-based owner lookup.
     pub agent_owner: Option<String>,
-    /// Disable the [Base] platform-context section prepended to every prompt.
+    /// Disable the `<base>` platform-context section prepended to every prompt.
     pub no_base_prompt: bool,
     /// Resolved content from `--base-prompt-file`, read and validated in
     /// `from_cli()`. `None` when using the compiled-in default or when

crates/buzz-acp/src/engram_fetch.rs

@@ -3,7 +3,7 @@
 //!
 //! Scope per Tyler's spec:
 //! - Fire one synchronous query for the core head when a *new* session is born.
-//! - If a body is found, emit `[Agent Memory — core]\n<profile>`.
+//! - If a body is found, emit `<core-memory>…</core-memory>`.
 //! - If no body is found, emit an onboarding nudge so the agent learns how
 //!   to set its own core.
 //! - On any *error* (transport, parse), log and emit nothing. We must not
@@ -17,9 +17,6 @@ use nostr::{Event, Keys, PublicKey};
 
 use crate::relay::RestClient;
 
-/// Section header rendered into the prompt.
-const SECTION_LABEL: &str = "Agent Memory — core";
-
 /// Onboarding nudge for new agents with no core yet.
 ///
 /// Wording is from Tyler's brief: "No core memory found. Use `buzz mem`
@@ -42,8 +39,14 @@ pub async fn build_core_section(
     owner: &PublicKey,
 ) -> Option<String> {
     match fetch_core_body(rest, agent_keys, owner).await {
-        Ok(Some(profile)) => Some(format!("[{SECTION_LABEL}]\n{profile}")),
-        Ok(None) => Some(format!("[{SECTION_LABEL}]\n{ONBOARDING_NUDGE}")),
+        Ok(Some(profile)) => Some(crate::prompt_framing::semantic_section(
+            "core-memory",
+            &profile,
+        )),
+        Ok(None) => Some(crate::prompt_framing::semantic_section(
+            "core-memory",
+            ONBOARDING_NUDGE,
+        )),
         Err(reason) => {
             tracing::warn!(
                 target: "engram::core",

crates/buzz-acp/src/lib.rs

@@ -7,6 +7,7 @@ mod filter;
 mod observer;
 mod pool;
 mod pool_lifecycle;
+mod prompt_framing;
 mod queue;
 mod relay;
 mod setup_mode;
@@ -3653,15 +3654,21 @@ fn try_native_steer(
     // channel context and the actor's profile in the original prompt,
     // duplicating it here would defeat the point of non-cancelling
     // steering (which is to inject only what's new).
-    let (header, closing) = queue::native_steer_framing();
+    let (tag, closing) = queue::native_steer_framing();
     let event_id_hex = event.id.to_hex();
     let be = queue::BatchEvent {
         event,
         prompt_tag: prompt_tag.clone(),
         received_at: std::time::Instant::now(),
     };
     let event_block = queue::format_event_block(channel_id, None, &be, None);
-    let body = format!("{header}\n\n[Buzz event: {prompt_tag}]\n{event_block}\n\n{closing}");
+    let new_message = prompt_framing::semantic_section(tag, "");
+    let event_section = prompt_framing::semantic_section_with_attributes(
+        "buzz-event",
+        &[("type", prompt_tag.as_str())],
+        &event_block,
+    );
+    let body = format!("{new_message}\n\n{event_section}\n\n{closing}");
 
     let (ack_tx, ack_rx) = tokio::sync::oneshot::channel::<pool::SteerAck>();
     let request = pool::SteerRequest {
@@ -4454,6 +4461,14 @@ mod agent_draft_prompt_tests {
         assert!(prompt.contains("Do not ask about runtime, provider, model, credentials"));
     }
 
+    #[test]
+    fn shared_base_prompt_names_current_context_framing() {
+        let prompt = include_str!("base_prompt.md");
+        assert!(prompt.contains("UUID from `<context>`"));
+        assert!(prompt.contains("reply destination supplied in the `<context>` block"));
+        assert!(!prompt.contains("`[Context]`"));
+    }
+
     #[test]
     fn shared_base_prompt_teaches_real_newlines_for_multiline_messages() {
         let prompt = include_str!("base_prompt.md");
@@ -5092,8 +5107,8 @@ mod heartbeat_base_prompt_tests {
     use super::*;
 
     // Pins the heartbeat dispatch path (dispatch_heartbeat, ~line 2359): a
-    // legacy agent WITH a base_prompt must get [Base] prepended to the
-    // heartbeat user message, composed as `[Base]\n{bp}\n\n{prompt}`. This is
+    // legacy agent WITH a base_prompt must get <base> prepended to the
+    // heartbeat user message. This is
     // the second half of the round-2 regression (the first being initial_message).
 
     fn heartbeat_standing() -> queue::StandingContext<'static> {
@@ -5106,12 +5121,12 @@ mod heartbeat_base_prompt_tests {
     #[test]
     fn test_heartbeat_legacy_agent_gets_base_prepended() {
         // protocol_version 1 + Some(base_prompt): heartbeat prompt is prefixed
-        // with the [Base] section exactly as the legacy session/new path would.
+        // with the <base> section exactly as the legacy session/new path would.
         let prompt = "[System: Heartbeat]\nrun feed get";
         let composed = pool::prepend_standing_for_legacy(1, &heartbeat_standing(), prompt);
         assert_eq!(
             composed,
-            "[Base]\nyou are a helpful agent\n\n[System: Heartbeat]\nrun feed get"
+            "<base>\nyou are a helpful agent\n</base>\n\n[System: Heartbeat]\nrun feed get"
         );
     }