el/lang/swarm/ccr.el

// ccr.el — Compiled Context Routing for work distribution.
//
// The same spine as the API's vantage-read, applied per worker. Instead of
// handing every worker the coordinator's full memory, CCR compiles a MINIMAL,
// BOUNDED context package scoped to exactly one worker's input (CCR §5, "Compiled
// Context Injection"; Swarm §9.3, "The Compiled Context Boundary as Security
// Boundary").
//
// The pipeline is CCR §5.1: Retrieval -> Scoping -> Compilation -> (Injection,
// which here is placing the package into the worker's task envelope).
//
//   1. Retrieval  — resolve the blueprint's knowledge refs + the input's salient
//                   terms against the mind (primitive_attend).
//   2. Scoping    — keep only what THIS input needs; drop everything else. A
//                   worker never receives sibling inputs or unrelated memory.
//   3. Compilation— compact to a CTX string within a token budget (lossless of
//                   meaning, smaller in tokens): collapse blank runs, dedupe
//                   lines, then bound to the budget.
//
// The package a worker receives is therefore (a) sufficient for its task and
// (b) incapable of leaking what it was never given — the containment boundary
// and the security boundary are the same object.

// ── token budget helpers ─────────────────────────────────────────────────────

// ccr_est_tokens — cheap token estimate (~4 chars/token).
fn ccr_est_tokens(s: String) -> Int {
    return str_len(s) / 4
}

// ccr_default_budget — default per-worker context budget in tokens.
//   Override with CCR_TOKEN_BUDGET.
fn ccr_default_budget() -> Int {
    let b: String = env("CCR_TOKEN_BUDGET")
    if str_eq(b, "") {
        return 1200
    }
    return str_to_int(b)
}

// ── stage 3: compaction ──────────────────────────────────────────────────────

// ccr_compact — collapse blank-line runs and drop exact duplicate lines, then
// bound the result to `budget` tokens (truncate on a line boundary). Meaning is
// preserved; token count falls (CCR §5.2).
fn ccr_compact(text: String, budget: Int) -> String {
    let lines: [String] = str_split_lines(text)
    let n: Int = el_list_len(lines)
    let seen: String = "\n"
    let out: String = ""
    let out_tokens = 0
    let i = 0
    while i < n {
        let ln: String = str_trim(el_list_get(lines, i))
        if str_eq(ln, "") {
            let i = i + 1
        } else {
            let marker: String = "\n" + ln + "\n"
            if str_contains(seen, marker) {
                // duplicate line — skip
                let i = i + 1
            } else {
                let seen = seen + ln + "\n"
                let line_tokens: Int = ccr_est_tokens(ln) + 1
                if out_tokens + line_tokens > budget {
                    // budget exhausted — stop (bounded)
                    let i = n
                } else {
                    let out = out + ln + "\n"
                    let out_tokens = out_tokens + line_tokens
                    let i = i + 1
                }
            }
        }
    }
    return out
}

// ── stages 1+2: retrieve + scope ─────────────────────────────────────────────

// ccr_retrieve_scoped — pull context relevant to this input and its blueprint
// knowledge refs, scoped to a fraction of the budget so no single source floods
// the package. Returns compacted retrieved text (may be empty if the mind is
// unreachable — the input alone is still a valid minimal context).
fn ccr_retrieve_scoped(blueprint: String, knowledge_refs: String, input_item: String, budget: Int) -> String {
    let acc: String = ""
    // knowledge_refs is a JSON array of query strings.
    let m: Int = json_array_len(knowledge_refs)
    let i = 0
    while i < m {
        let ref: String = json_array_get(knowledge_refs, i)
        let hit: String = primitive_attend(ref, 3)
        let acc = acc + "# ref:" + ref + "\n" + hit + "\n"
        let i = i + 1
    }
    // the input's own salient text also seeds retrieval
    let hit2: String = primitive_attend(input_item, 3)
    let acc = acc + "# input-context\n" + hit2 + "\n"
    // scope retrieval to ~60% of budget; the input itself gets the rest
    let retr_budget: Int = (budget * 6) / 10
    return ccr_compact(acc, retr_budget)
}

// ── ccr_compile — assemble the bounded per-worker context package ─────────────
//
//   blueprint      : task blueprint name
//   knowledge_refs : JSON array of retrieval queries from the blueprint
//   input_item     : THIS worker's single input (and nothing else)
//   corr_id        : swarm correlation ID
//   worker_id      : this worker's ID
//   scope_token    : the worker's containment token (closed boundary)
//
// Returns a JSON package: { blueprint, corr_id, worker_id, scope_token,
// input, knowledge, budget_tokens, compiled_tokens }. `knowledge` is compiled
// and bounded; the package as a whole is bounded by budget.
fn ccr_compile(blueprint: String, knowledge_refs: String, input_item: String,
               corr_id: String, worker_id: String, scope_token: String) -> String {
    let budget: Int = ccr_default_budget()
    let knowledge: String = ccr_retrieve_scoped(blueprint, knowledge_refs, input_item, budget)

    let kv: [String] = el_list_empty()
    let kv = el_list_append(kv, "blueprint")
    let kv = el_list_append(kv, blueprint)
    let kv = el_list_append(kv, "corr_id")
    let kv = el_list_append(kv, corr_id)
    let kv = el_list_append(kv, "worker_id")
    let kv = el_list_append(kv, worker_id)
    let kv = el_list_append(kv, "input")
    let kv = el_list_append(kv, input_item)
    let kv = el_list_append(kv, "knowledge")
    let kv = el_list_append(kv, knowledge)
    let kv = el_list_append(kv, "budget_tokens")
    let kv = el_list_append(kv, int_to_str(budget))
    let pkg: String = json_build_object(kv)
    // stamp the scope token as a nested object, and the measured size
    let pkg2: String = json_set(pkg, "scope_token", scope_token)
    let compiled_tokens: Int = ccr_est_tokens(pkg2)
    let pkg3: String = json_set(pkg2, "compiled_tokens", int_to_str(compiled_tokens))
    return pkg3
}

// ccr_within_budget — did the compiled package stay within its budget?
// (Retrieval is bounded to 60% and the input is small; this asserts the whole
// package is bounded — the property distribution relies on.)
fn ccr_within_budget(pkg: String) -> Bool {
    let budget: Int = str_to_int(json_get_string(pkg, "budget_tokens"))
    let compiled: Int = str_to_int(json_get_string(pkg, "compiled_tokens"))
    // allow a small envelope for JSON framing overhead
    if compiled <= budget + 200 {
        return true
    }
    return false
}