memoryd: where a finished turn goes in Honcho, decided from brokerd and the log

Co-Authored-By: ornith-1.5-35b-a3b <agent@wntrmute.dev>
2026-09-28 11:41:38 -07:00
parent 8aaeb74f36
commit a339eb58b6
4 changed files with 660 additions and 0 deletions
@@ -0,0 +1,467 @@
+//! Where a finished turn goes in Honcho (M5c spec, sections 4 and 5): the trusted or untrusted
+//! workspace, or nowhere and why, from `brokerd`'s answer and the session's log; the order of the
+//! checks; and the helpers that find a turn in the log. Do not edit.
+
+use bxcore::sanitize::TAGS;
+use bxcore::{
+    CallId, DataClass, Epoch, Hash32, LogRecord, SessionId, SessionStateReply, Timestamp, ToolCall,
+};
+use memoryd::honcho::decide::{
+    AGENT_SPEAKER, BAD_SPEAKER, NO_REPLY, NO_SPEAKER, NoSuchTurn, SECRET_CLASS, SECRET_TEXT,
+    decide, has_secret, peer_name, turn_records, turns,
+};
+use memoryd::honcho::ledger::{Action, Workspace};
+
+const AGENT: &str = "boxmaker0";
+
+fn time() -> Timestamp {
+    Timestamp::parse("2026-09-28T10:00:00.000Z").unwrap()
+}
+
+fn start() -> LogRecord {
+    LogRecord::SessionStart {
+        time: time(),
+        session: SessionId::new("chat-1").unwrap(),
+        epoch: Epoch(0),
+        slot: 0,
+        baseline: Hash32::ZERO,
+    }
+}
+
+fn user(content: &str, speaker: Option<&str>) -> LogRecord {
+    LogRecord::User {
+        time: time(),
+        content: content.to_string(),
+        speaker: speaker.map(str::to_string),
+    }
+}
+
+fn reply(content: Option<&str>) -> LogRecord {
+    LogRecord::Assistant {
+        time: time(),
+        content: content.map(str::to_string),
+        reasoning_content: Some("thinking".to_string()),
+        tool_calls: Vec::new(),
+    }
+}
+
+fn calls_tool() -> LogRecord {
+    calls_tool_saying(None)
+}
+
+/// A tool round; a model may say something beside its tool calls.
+fn calls_tool_saying(content: Option<&str>) -> LogRecord {
+    LogRecord::Assistant {
+        time: time(),
+        content: content.map(str::to_string),
+        reasoning_content: None,
+        tool_calls: vec![ToolCall {
+            id: "c1".to_string(),
+            name: "fetch".to_string(),
+            arguments: "{}".to_string(),
+        }],
+    }
+}
+
+fn result(untrusted: bool) -> LogRecord {
+    LogRecord::ToolResult {
+        time: time(),
+        call: CallId(1),
+        tool_call_id: "c1".to_string(),
+        content: "the page".to_string(),
+        class: DataClass::Public,
+        untrusted,
+        truncated: false,
+    }
+}
+
+fn usage() -> LogRecord {
+    LogRecord::Usage {
+        time: time(),
+        cache_n: 0,
+        prompt_n: 10,
+        predicted_n: 5,
+        reasoning_tokens: 2,
+        thinking_capped: false,
+    }
+}
+
+/// One finished turn: its `User` record, then the reply and its usage.
+fn turn(text: &str, speaker: Option<&str>, answer: &str) -> Vec<LogRecord> {
+    vec![user(text, speaker), reply(Some(answer)), usage()]
+}
+
+/// A finished turn with a tool round: the tool's result is labelled `untrusted`.
+fn turn_with_tool(speaker: Option<&str>, untrusted: bool) -> Vec<LogRecord> {
+    vec![
+        user("look this up", speaker),
+        calls_tool(),
+        usage(),
+        result(untrusted),
+        reply(Some("here it is")),
+        usage(),
+    ]
+}
+
+fn log(turns: &[Vec<LogRecord>]) -> Vec<LogRecord> {
+    let mut records = vec![start()];
+    for t in turns {
+        records.extend(t.iter().cloned());
+    }
+    records
+}
+
+fn state(class: DataClass, untrusted: bool) -> SessionStateReply {
+    SessionStateReply { class, untrusted }
+}
+
+fn clean() -> SessionStateReply {
+    state(DataClass::Private, false)
+}
+
+fn to(workspace: Workspace, speaker: &str) -> Action {
+    Action::Turn {
+        workspace,
+        speaker: speaker.to_string(),
+    }
+}
+
+fn skip(why: &str) -> Action {
+    Action::Skip {
+        why: why.to_string(),
+    }
+}
+
+/// `decide` for the last turn of `records`.
+fn last(state: &SessionStateReply, records: &[LogRecord]) -> Action {
+    decide(state, records, turns(records), AGENT).unwrap()
+}
+
+/// `n` characters of `A1b2`…, which the secret rules take for a key's run.
+fn mixed(n: usize) -> String {
+    "A1b2".chars().cycle().take(n).collect()
+}
+
+/// A GitHub token, built from pieces so that no file holds one whole.
+fn github_token() -> String {
+    format!("{}{}", ["gh", "p_"].concat(), mixed(36))
+}
+
+#[test]
+fn the_skip_reasons_are_these_texts() {
+    assert_eq!(SECRET_CLASS, "the session is secret");
+    assert_eq!(NO_SPEAKER, "the turn has no single speaker");
+    assert_eq!(BAD_SPEAKER, "the speaker is not a Honcho peer name");
+    assert_eq!(AGENT_SPEAKER, "the speaker has the agent's peer name");
+    assert_eq!(NO_REPLY, "the turn has no reply");
+    assert_eq!(SECRET_TEXT, "the turn's text holds a secret");
+}
+
+#[test]
+fn turns_counts_the_user_records() {
+    assert_eq!(turns(&[]), 0);
+    assert_eq!(turns(&[start()]), 0);
+    let records = log(&[
+        turn("one", Some("kyle"), "a"),
+        turn_with_tool(Some("kyle"), false),
+        vec![user("failed before any answer", Some("kyle"))],
+        turn("four", None, "d"),
+    ]);
+    assert_eq!(turns(&records), 4);
+}
+
+#[test]
+fn a_turn_runs_from_its_user_record_to_the_next() {
+    let one = turn("one", Some("kyle"), "a");
+    let two = turn_with_tool(Some("ana"), true);
+    let three = vec![user("three", None), calls_tool()];
+    let records = log(&[one.clone(), two.clone(), three.clone()]);
+    assert_eq!(turn_records(&records, 1), Some(&one[..]));
+    assert_eq!(turn_records(&records, 2), Some(&two[..]));
+    assert_eq!(turn_records(&records, 3), Some(&three[..]));
+    for n in [0, 4, u64::MAX] {
+        assert_eq!(turn_records(&records, n), None, "{n}");
+    }
+    assert_eq!(turn_records(&[start()], 1), None);
+}
+
+#[test]
+fn a_turn_not_in_the_log_is_an_error() {
+    let records = log(&[
+        turn("one", Some("kyle"), "a"),
+        turn("two", Some("kyle"), "b"),
+    ]);
+    for n in [0, 3, u64::MAX] {
+        let err = decide(&clean(), &records, n, AGENT).unwrap_err();
+        assert_eq!(err, NoSuchTurn { turn: n, turns: 2 });
+    }
+    assert_eq!(
+        NoSuchTurn { turn: 3, turns: 2 }.to_string(),
+        "turn 3 is not in the session's log, which has 2 turns"
+    );
+    let err = decide(&clean(), &[], 1, AGENT).unwrap_err();
+    assert_eq!(err, NoSuchTurn { turn: 1, turns: 0 });
+}
+
+#[test]
+fn a_clean_turn_goes_to_the_trusted_workspace() {
+    let records = log(&[turn("hello", Some("kyle"), "hi")]);
+    for class in [DataClass::Private, DataClass::Public] {
+        assert_eq!(
+            last(&state(class, false), &records),
+            to(Workspace::Trusted, "kyle")
+        );
+    }
+    let records = log(&[turn_with_tool(Some("kyle"), false)]);
+    assert_eq!(last(&clean(), &records), to(Workspace::Trusted, "kyle"));
+}
+
+#[test]
+fn the_speaker_becomes_a_peer_name() {
+    assert_eq!(peer_name("first.last"), "first_last");
+    assert_eq!(peer_name("a.b.c-d_e"), "a_b_c-d_e");
+    assert_eq!(peer_name("kyle"), "kyle");
+    let records = log(&[turn("hello", Some("ana.b"), "hi")]);
+    assert_eq!(last(&clean(), &records), to(Workspace::Trusted, "ana_b"));
+}
+
+#[test]
+fn untrusted_by_brokerd_or_by_a_label_goes_to_the_untrusted_workspace() {
+    let plain = turn("hello", Some("kyle"), "hi");
+    let records = log(std::slice::from_ref(&plain));
+    assert_eq!(
+        last(&state(DataClass::Private, true), &records),
+        to(Workspace::Untrusted, "kyle")
+    );
+    assert_eq!(
+        last(&state(DataClass::Public, true), &records),
+        to(Workspace::Untrusted, "kyle")
+    );
+    // A label in this turn, or in an earlier one, with `brokerd` saying clean.
+    let records = log(&[turn_with_tool(Some("kyle"), true)]);
+    assert_eq!(last(&clean(), &records), to(Workspace::Untrusted, "kyle"));
+    let records = log(&[turn_with_tool(None, true), plain.clone()]);
+    assert_eq!(last(&clean(), &records), to(Workspace::Untrusted, "kyle"));
+}
+
+#[test]
+fn a_label_after_the_turn_does_not_count() {
+    let records = log(&[
+        turn("hello", Some("kyle"), "hi"),
+        turn_with_tool(Some("kyle"), true),
+    ]);
+    assert_eq!(
+        decide(&clean(), &records, 1, AGENT).unwrap(),
+        to(Workspace::Trusted, "kyle")
+    );
+    assert_eq!(
+        decide(&clean(), &records, 2, AGENT).unwrap(),
+        to(Workspace::Untrusted, "kyle")
+    );
+}
+
+#[test]
+fn a_secret_session_goes_nowhere() {
+    for untrusted in [false, true] {
+        let records = log(&[turn("hello", Some("kyle"), "hi")]);
+        assert_eq!(
+            last(&state(DataClass::Secret, untrusted), &records),
+            skip(SECRET_CLASS)
+        );
+    }
+}
+
+#[test]
+fn no_speaker_goes_nowhere() {
+    let records = log(&[turn("hello", None, "hi")]);
+    assert_eq!(last(&clean(), &records), skip(NO_SPEAKER));
+}
+
+#[test]
+fn a_speaker_that_is_not_a_peer_name_goes_nowhere() {
+    let long = "a".repeat(513);
+    for name in [
+        "",
+        "a b",
+        "caf\u{e9}",
+        "a/b",
+        "a@b",
+        "\u{661}",
+        long.as_str(),
+    ] {
+        let records = log(&[turn("hello", Some(name), "hi")]);
+        assert_eq!(last(&clean(), &records), skip(BAD_SPEAKER), "{name:?}");
+    }
+    let longest = "a".repeat(512);
+    let records = log(&[turn("hello", Some(&longest), "hi")]);
+    assert_eq!(last(&clean(), &records), to(Workspace::Trusted, &longest));
+    let records = log(&[turn("hello", Some("."), "hi")]);
+    assert_eq!(last(&clean(), &records), to(Workspace::Trusted, "_"));
+}
+
+#[test]
+fn a_speaker_with_the_agents_name_goes_nowhere() {
+    let records = log(&[turn("hello", Some(AGENT), "hi")]);
+    assert_eq!(last(&clean(), &records), skip(AGENT_SPEAKER));
+    let records = log(&[turn("hello", Some("box.maker"), "hi")]);
+    assert_eq!(
+        decide(&clean(), &records, 1, "box_maker").unwrap(),
+        skip(AGENT_SPEAKER)
+    );
+    let records = log(&[turn("hello", Some("Boxmaker0"), "hi")]);
+    assert_eq!(
+        last(&clean(), &records),
+        to(Workspace::Trusted, "Boxmaker0")
+    );
+}
+
+#[test]
+fn a_turn_without_a_reply_goes_nowhere() {
+    let cases = [
+        vec![user("hello", Some("kyle"))],
+        vec![user("hello", Some("kyle")), usage()],
+        vec![user("hello", Some("kyle")), calls_tool(), usage()],
+        vec![
+            user("hello", Some("kyle")),
+            calls_tool_saying(Some("let me look")),
+            usage(),
+        ],
+        vec![
+            user("hello", Some("kyle")),
+            calls_tool(),
+            usage(),
+            result(false),
+        ],
+        vec![user("hello", Some("kyle")), reply(None), usage()],
+        vec![user("hello", Some("kyle")), reply(Some("")), usage()],
+        vec![user("hello", Some("kyle")), reply(Some(" \n\t")), usage()],
+        vec![user("hello", Some("kyle")), reply(Some("hi")), calls_tool()],
+    ];
+    for case in cases {
+        let records = log(std::slice::from_ref(&case));
+        assert_eq!(last(&clean(), &records), skip(NO_REPLY), "{case:?}");
+    }
+    // A later turn is decided on its own records.
+    let records = log(&[
+        vec![user("hello", Some("kyle"))],
+        turn("again", Some("kyle"), "hi"),
+    ]);
+    assert_eq!(last(&clean(), &records), to(Workspace::Trusted, "kyle"));
+}
+
+#[test]
+fn a_secret_in_the_text_or_the_reply_goes_nowhere() {
+    let key = github_token();
+    let texts = [
+        format!("my token is {key}, keep it"),
+        key.clone(),
+        format!("line one\r\n{key}\r\n"),
+        format!("\u{7}{key}"),
+        format!("\u{200b}{key}"),
+        format!("{}{}", ["AK", "IA"].concat(), "IOSFODNN7EXAMPLE"),
+        format!("{}{}", ["sk", "-proj-"].concat(), mixed(40)),
+    ];
+    for text in &texts {
+        let records = log(&[turn(text, Some("kyle"), "noted")]);
+        assert_eq!(last(&clean(), &records), skip(SECRET_TEXT), "{text:?}");
+        let records = log(&[turn("what is my token?", Some("kyle"), text)]);
+        assert_eq!(last(&clean(), &records), skip(SECRET_TEXT), "{text:?}");
+    }
+}
+
+#[test]
+fn a_secret_where_nothing_is_sent_does_not_count() {
+    let key = github_token();
+    let mut records = log(&[turn_with_tool(Some("kyle"), false)]);
+    for record in &mut records {
+        match record {
+            LogRecord::ToolResult { content, .. } => *content = key.clone(),
+            LogRecord::Assistant {
+                reasoning_content, ..
+            } => *reasoning_content = Some(key.clone()),
+            _ => {}
+        }
+    }
+    assert_eq!(last(&clean(), &records), to(Workspace::Trusted, "kyle"));
+    let records = log(&[
+        turn(&key, Some("kyle"), "noted"),
+        turn("hello", Some("kyle"), "hi"),
+    ]);
+    assert_eq!(last(&clean(), &records), to(Workspace::Trusted, "kyle"));
+}
+
+#[test]
+fn only_the_secret_rules_count() {
+    let tag = TAGS[0].text;
+    for text in [
+        "a bell \u{7} and a carriage return \r".to_string(),
+        "a zero width\u{200b}space".to_string(),
+        format!("the model's {tag} marker"),
+        "ghp_ is how GitHub tokens start; sk-learn is a library".to_string(),
+        format!("{}{}", ["gh", "p_"].concat(), mixed(35)),
+    ] {
+        assert!(!has_secret(&text), "{text:?}");
+        let records = log(&[turn(&text, Some("kyle"), &text)]);
+        assert_eq!(last(&clean(), &records), to(Workspace::Trusted, "kyle"));
+    }
+}
+
+#[test]
+fn has_secret_sees_past_the_character_rules() {
+    let key = github_token();
+    assert!(has_secret(&key));
+    for mark in ["\r", "\u{7}", "\u{200b}", "\u{e000}", "\u{fdd0}", "\u{7f}"] {
+        assert!(has_secret(&format!("{mark}{key}")), "{mark:?} before");
+        assert!(has_secret(&format!("{key}{mark}")), "{mark:?} after");
+        assert!(has_secret(&format!("x{mark}{mark}{key}")), "{mark:?} twice");
+    }
+    // A letter joined to the prefix still hides it, as it does for `refuse`.
+    assert!(!has_secret(&format!("x{key}")));
+    let tag = TAGS[1].text;
+    assert!(has_secret(&format!("{tag}{key}")));
+}
+
+#[test]
+fn the_checks_run_in_their_order() {
+    let key = github_token();
+    let secret = state(DataClass::Secret, true);
+    let untrusted = state(DataClass::Private, true);
+    // Each case breaks the rule named and every rule after it; the first one decides.
+    let cases: Vec<(SessionStateReply, Vec<LogRecord>, &str)> = vec![
+        (
+            secret.clone(),
+            vec![user(&key, None), calls_tool()],
+            SECRET_CLASS,
+        ),
+        (secret.clone(), vec![user("hi", Some("a b"))], SECRET_CLASS),
+        (
+            untrusted.clone(),
+            vec![user(&key, None), calls_tool()],
+            NO_SPEAKER,
+        ),
+        (
+            untrusted.clone(),
+            vec![user(&key, Some("a b"))],
+            BAD_SPEAKER,
+        ),
+        (
+            untrusted.clone(),
+            vec![user(&key, Some(AGENT))],
+            AGENT_SPEAKER,
+        ),
+        (
+            untrusted.clone(),
+            vec![user(&key, Some("kyle")), calls_tool()],
+            NO_REPLY,
+        ),
+        (
+            untrusted.clone(),
+            vec![user("hi", Some("kyle")), reply(Some(&key))],
+            SECRET_TEXT,
+        ),
+    ];
+    for (state, turn, why) in cases {
+        let records = log(std::slice::from_ref(&turn));
+        assert_eq!(last(&state, &records), skip(why), "{turn:?}");
+    }
+}