aver/codegen/

mod.rs

/// Aver → target language transpilation.
///
/// The codegen module transforms a type-checked Aver AST into source code
/// for a target language. Current backends: Rust deployment and Lean proof export.
pub(crate) mod builtin_helpers;
pub(crate) mod builtin_records;
pub(crate) mod builtins;
pub mod common;
#[cfg(feature = "runtime")]
pub mod dafny;
#[cfg(feature = "runtime")]
pub mod lean;
#[cfg(feature = "runtime")]
pub mod lemma_discovery;
pub mod program_view;
pub mod proof_lower;
#[cfg(feature = "runtime")]
pub(crate) mod proof_recognize;
#[cfg(feature = "runtime")]
pub mod recursion;
#[cfg(feature = "runtime")]
pub mod rust;
pub mod scc;
#[cfg(feature = "wasip2")]
pub mod wasip2;
#[cfg(feature = "wasm-compile")]
pub mod wasm_gc;

use std::collections::{HashMap, HashSet};

use crate::ast::{FnDef, TopLevel, TypeDef};
use crate::source::LoadedModule;
use crate::types::checker::TypeCheckResult;

/// Information about a dependent module loaded for codegen.
pub struct ModuleInfo {
    /// Qualified module path, e.g. "Models.User".
    pub prefix: String,
    /// Direct `depends [...]` entries from the source module.
    pub depends: Vec<String>,
    /// Type definitions from the module.
    pub type_defs: Vec<TypeDef>,
    /// Function definitions from the module (excluding `main`).
    pub fn_defs: Vec<FnDef>,
    /// IR-level analysis facts produced by the dep module's pipeline run
    /// (`analyze` stage). `None` for modules loaded via paths that skip
    /// the analyze stage (none in production today; left optional for
    /// future ad-hoc loaders). Aver's module DAG invariant makes per-module
    /// analysis sufficient — see `project_aver_module_dag` memory and
    /// `src/ir/analyze.rs` for why cross-module SCCs are impossible.
    pub analysis: Option<crate::ir::AnalysisResult>,
}

impl ModuleInfo {
    /// Build a [`ModuleInfo`] from a freshly-parsed [`LoadedModule`].
    /// Skips the analyze stage — callers that need per-dep analysis
    /// facts should run the pipeline themselves (see
    /// `crate::main::commands::load_compile_deps` /
    /// `playground::loaded_to_module_info`). Used by ad-hoc loaders
    /// (`vm_profile`, the eval-spec test helpers) that just need the
    /// dep's symbol layout to feed `SymbolTable::build` /
    /// `pipeline::run`'s `dep_modules` slot.
    pub fn from_loaded(loaded: &LoadedModule) -> Self {
        let depends = loaded
            .items
            .iter()
            .find_map(|i| match i {
                TopLevel::Module(m) => Some(m.depends.clone()),
                _ => None,
            })
            .unwrap_or_default();
        let type_defs = loaded
            .items
            .iter()
            .filter_map(|i| match i {
                TopLevel::TypeDef(td) => Some(td.clone()),
                _ => None,
            })
            .collect();
        let fn_defs = loaded
            .items
            .iter()
            .filter_map(|i| match i {
                TopLevel::FnDef(fd) if fd.name != "main" => Some(fd.clone()),
                _ => None,
            })
            .collect();
        Self {
            prefix: loaded.dep_name.clone(),
            depends,
            type_defs,
            fn_defs,
            analysis: None,
        }
    }
}

/// Collected context from the Aver program, shared across all backends.
///
/// # Invariant (epic #170 Phase 2)
///
/// **`resolved_program` is the primary backend input.** Every
/// identity-sensitive decision (call/ctor/type lookup, fn-by-id
/// dispatch, mutual-SCC analysis) belongs to that view; the
/// pipeline produced it once and `build_context` projects it through.
///
/// The legacy AST-shape fields below — `items`, `fn_defs`,
/// `type_defs`, `resolved_fn_defs`, `resolved_module_fn_defs` — are
/// **source metadata / migration caches**, not independent sources
/// of truth:
///
/// - `items`, `fn_defs`, `type_defs` retain source-shape spans and
///   diagnostics; backends mid-migration still walk them. They are
///   NOT the place to add new identity-sensitive logic.
/// - `resolved_fn_defs` / `resolved_module_fn_defs` are projections
///   of `resolved_program` kept for callsites that don't yet route
///   through the `FnId` index. New code should reach
///   `resolved_program.fn_by_id(fn_id)` instead.
///
/// Subsequent epic phases migrate backends (Rust, Lean, Dafny,
/// wasm-gc) to iterate the view directly. New code in backends
/// should default to the view. AST consumption requires a clear
/// category in a code comment: `diagnostic-only`,
/// `syntax-discovery-only`, `backend-link-stage`, `display-only`,
/// or `temporary-migration-bridge`.
pub struct CodegenContext {
    /// All top-level items (post-TCO transform, post-typecheck).
    ///
    /// **Source metadata** — kept for span / diagnostic / syntax
    /// discovery access. Backends iterating fn bodies should reach
    /// `resolved_program.entry_fns()` instead.
    pub items: Vec<TopLevel>,
    /// User-defined type definitions (for struct/enum generation).
    ///
    /// **Source metadata.** Type-id-keyed lookups go through
    /// `symbol_table` (see [`Self::symbol_table`]); fn bodies that
    /// need a resolved type reach it via `Type::Named(TypeId, _)`
    /// after the typechecker stamps. This list stays for ergonomic
    /// iteration over user-declared types in syntax-discovery sites
    /// (e.g. cataloguing all `enum` declarations for the proof
    /// pipeline's refinement detection).
    pub type_defs: Vec<TypeDef>,
    /// User-defined function definitions.
    ///
    /// **Source metadata.** Backends mid-migration walk this for
    /// fn-signature shape; new identity-sensitive code reaches
    /// `resolved_program.entry_fns()` / `fn_by_id(fn_id)` instead.
    /// Synthesized FnDefs (TCO hoists) appended after
    /// the pipeline ran live here too; the on-demand resolver
    /// (`Self::resolve_fn_def`) lifts them through the symbol table.
    pub fn_defs: Vec<FnDef>,
    /// Project/binary name.
    pub project_name: String,
    /// Dependent modules loaded for inlining.
    pub modules: Vec<ModuleInfo>,
    /// Set of module prefixes for qualified name resolution (e.g. "Models.User").
    pub module_prefixes: HashSet<String>,
    /// Embedded runtime policy from `aver.toml` for generated code.
    #[cfg(feature = "runtime")]
    pub policy: Option<crate::config::ProjectConfig>,
    /// Emit generated scoped runtime support (replay and/or runtime-loaded policy).
    pub emit_replay_runtime: bool,
    /// Load runtime policy from the active module root instead of embedding it.
    pub runtime_policy_from_env: bool,
    /// Explicit guest entry boundary for scoped replay/policy.
    pub guest_entry: Option<String>,
    /// Emit extra generated helpers needed only by the cached self-host helper.
    pub emit_self_host_support: bool,
    /// Extra fn_defs visible during current module emission (not in `fn_defs` or `modules`).
    /// Set temporarily by the Rust backend when emitting a dependent module so that
    /// `find_fn_def_by_name` can resolve same-module calls.
    pub extra_fn_defs: Vec<FnDef>,
    /// Functions that are part of a mutual-TCO SCC group (emitted as
    /// trampoline + wrappers). Functions NOT in this set but with
    /// TailCalls are emitted as plain self-TCO loops. Keyed by opaque
    /// [`crate::ir::FnId`] from the symbol table — entry-module fns
    /// and dep-module fns with the same bare name can't accidentally
    /// merge under bare-name keying.
    pub mutual_tco_members: HashSet<crate::ir::FnId>,
    /// Functions that call themselves directly or transitively. Set-
    /// form union of `entry_analysis.recursive_fns` plus each
    /// module's `analysis.recursive_fns`. Keyed by opaque
    /// [`crate::ir::FnId`] — same disambiguation guarantee as
    /// `mutual_tco_members`. Used by codegen sites that previously
    /// called `call_graph::find_recursive_fns` ad-hoc.
    pub recursive_fns: HashSet<crate::ir::FnId>,
    /// Buffer-build sink fns (`List.prepend`/`reverse` builders consumed
    /// by `String.join`). The Rust backend emits a `<fn>__buffered`
    /// variant alongside each entry; the WASM backend rewrites bodies
    /// to call `rt_buffer_*` helpers. Detection lives in `ir::buffer_build`.
    pub buffer_build_sinks: HashMap<String, crate::ir::BufferBuildShape>,
    /// Fusion sites detected for `String.join(<sink>(...), sep)` calls.
    /// Each entry pairs an enclosing fn + line + sink fn name; the
    /// emitter rewrites these call expressions to use buffered variants
    /// in place of the producer + consumer chain.
    pub buffer_fusion_sites: Vec<crate::ir::FusionSite>,
    /// Synthesized `<fn>__buffered` variants for every buffer-build
    /// sink, produced by `ir::synthesize_buffered_variants`. These are
    /// real `FnDef`s with proper body AST; backends iterate over them
    /// alongside `fn_defs` so they reach codegen through the same
    /// pipeline (TCO / no-alloc / mutual-recursion all apply
    /// identically). Empty when no sinks are detected.
    pub synthesized_buffered_fns: Vec<FnDef>,
    /// Proof-export decision IR populated by `proof_lower::lower`
    /// during `build_context`. Backends (Lean, Dafny) read from
    /// here to decide refinement-record lift, recursion contracts,
    /// law-theorem shape, etc. Single source of truth — both
    /// backends see the same decisions so cross-backend drift
    /// becomes impossible at the shape level. Step 2: only
    /// `refined_types` is populated; backends still consume legacy
    /// `refinement_info_for` for now. Step 3+ migrates backends.
    #[cfg(feature = "runtime")]
    pub proof_ir: crate::ir::ProofIR,
    /// Resolved-identity table (#138 phase E). Always populated:
    /// `pipeline::run` builds it unconditionally and threads it
    /// through `build_context`. Consumers (proof IR lookups,
    /// backend FnId/TypeId resolution) read it directly — no
    /// `Option` wrapper to unwrap at each callsite.
    pub symbol_table: crate::ir::SymbolTable,
    /// Resolved-HIR forms of every entry-scope fn in `fn_defs`,
    /// in the same source order.
    ///
    /// **Compatibility projection of `resolved_program.entry_fns()`**
    /// (epic #170 Phase 1). Position-aligned with the entry slice of
    /// `resolved_program.entry_items`. New code should prefer
    /// `resolved_program.entry_fns()` / `fn_by_id(fn_id)` so the
    /// `FnId` index is the lookup mechanism. This vec stays for
    /// callsites that haven't yet been migrated to the view; it will
    /// be retired once Phase 3-6 migrate all backends.
    pub resolved_fn_defs: Vec<crate::ir::hir::ResolvedFnDef>,
    /// Module scope currently active for name resolution. Set by a
    /// backend dispatcher before emitting a dep-module's fns so that
    /// legacy resolve-on-demand adapters (e.g. Lean's
    /// `emit_expr_legacy`) thread the right scope into
    /// `resolve_expr` / `resolve_stmt` instead of defaulting to entry.
    /// Empty by default. Set with [`Self::with_module_scope`] in a
    /// scoped manner.
    pub current_module_scope: std::cell::RefCell<Option<String>>,
    /// Per-dep resolved fn defs, parallel to `modules`.
    ///
    /// **Compatibility projection of `resolved_program.modules[i].fn_defs`**
    /// (epic #170 Phase 1). Position-aligned with `modules` for
    /// callsites that index by `modules[i]`. New code should prefer
    /// `resolved_program.module_fns(prefix)` or the global
    /// `fn_by_id(fn_id)` index — that's where cross-module bare-name
    /// disambiguation happens for free. Retired alongside
    /// `resolved_fn_defs` once Phase 3-6 migrate the remaining
    /// backends.
    pub resolved_module_fn_defs: Vec<Vec<crate::ir::hir::ResolvedFnDef>>,
    /// Canonical resolved-program view of the whole codegen input —
    /// entry items (post-pipeline `NameResolve`) + per-dep-module
    /// resolved fn defs + `FnId`-keyed lookup.
    ///
    /// **Epic #170 Phase 1 invariant.** `resolved_program` is the
    /// primary source of truth for backend codegen — `fn_defs`,
    /// `type_defs`, `items`, `resolved_fn_defs`, and
    /// `resolved_module_fn_defs` remain available as projection /
    /// source metadata / migration cache, but consumers should reach
    /// the view first when an `FnId` / `TypeId` is in hand. Subsequent
    /// phases (#170 Phase 3+) migrate backends to iterate the view as
    /// their primary input; this field is the foundation those PRs
    /// build on.
    pub resolved_program: crate::codegen::program_view::ResolvedProgramView,
    /// Whole-program shape facts — typed Archetype labels + call-graph
    /// SCC per `FnId`. Computed once per compilation by
    /// [`analyze_program`](crate::analysis::shape::analyze_program) at
    /// `build_context` time. Stage 5+ of #232 (0.23 "Shape") migrates
    /// ad-hoc fn-shape detectors in proof codegen to read this instead
    /// of rewalking the AST. `None` only for tests that assemble the
    /// ctx by hand without calling `build_context`; downstream callers
    /// should treat that as opt-out (preserve legacy detection path).
    pub program_shape: Option<crate::analysis::shape::ProgramShape>,
    /// Optimized Core MIR for the whole codegen input (entry + dep
    /// module fns), `FnId`-keyed. Built once at `build_context` from
    /// the resolved program — the same lowering + optimizer pass the
    /// VM / wasm-gc / wasip2 backends run. The Rust backend reads
    /// `fn_by_id(fn_id)` here to drive its sole codegen path
    /// (`from_mir::emit_mir_fn_body_routed`): the MIR walker owns all
    /// runtime codegen after the HIR walker's deletion (W6/Stage-3).
    /// `None` for hand-assembled test contexts that skip `build_context`.
    pub mir_program: Option<crate::ir::mir::MirProgram>,
    /// Kernel-proved lemmas parsed back from a committed
    /// `DiscoveredLemmas.lean` (the `--discover` artifact), set by the CLI
    /// on a normal `aver proof` run when the discovery-surface hash still
    /// matches. The Lean backend embeds each pinned lemma's text before the
    /// first law theorem that uses it (re-proving it in the same build) and
    /// `simp`s over its name (`ProofStrategy::SimpOverLemmas`). Empty unless
    /// the CLI wired it — discovery feedback is strictly opt-in.
    pub discovered_lemmas: Vec<crate::codegen::lemma_discovery::CommittedLemma>,
    /// VM-computed ground-truth values for verify cases, keyed by
    /// `(common::verify_block_counter_key(vb), global_case_index)` →
    /// `aver_repr_literal` rendering of the case's expected (right-side)
    /// value. Set by the CLI on `aver proof --backend lean` from a Declared-
    /// mode `aver verify` run over the entry items; empty everywhere else.
    /// The Lean emitter literalizes the expected side of bounded sample
    /// checks from this table (model-vs-ground-truth) so that fuel
    /// exhaustion — where `panic!` returns `default` and a model-vs-model
    /// equation becomes vacuously true under `native_decide` — cannot
    /// kernel-certify a false equation. Entries exist only for cases that
    /// PASSED `aver verify`; failing/skipped cases keep the source RHS.
    pub sample_expected: std::collections::HashMap<(String, usize), String>,
}

/// Output files from a codegen backend.
pub struct ProjectOutput {
    /// Files to write: (relative_path, content).
    pub files: Vec<(String, String)>,
}

/// Build a CodegenContext from parsed + type-checked items.
///
/// `entry_analysis` is the `analyze` stage output for `items` (entry
/// module). When provided, codegen reads `mutual_tco_members`,
/// `recursive_fns`, and per-fn `FnAnalysis` from it instead of recomputing.
/// Each `ModuleInfo` in `modules` carries its own per-module analysis;
/// codegen unions the per-module sets to build a global view (sound
/// under Aver's module DAG invariant — no cross-module SCCs possible,
/// see `src/ir/analyze.rs` doc).
///
/// `symbol_table` is the resolved-identity layer built by the
/// pipeline (`pipeline_result.symbol_table`). Always required:
/// `pipeline::run` builds it unconditionally so every caller has
/// one available. The ad-hoc test helpers that drive a stripped
/// pipeline build their own via `SymbolTable::build(&items,
/// &modules)` and pass it here.
#[allow(clippy::too_many_arguments)]
pub fn build_context(
    items: Vec<TopLevel>,
    _tc_result: &TypeCheckResult,
    entry_analysis: Option<&crate::ir::AnalysisResult>,
    project_name: String,
    modules: Vec<ModuleInfo>,
    symbol_table: crate::ir::SymbolTable,
    resolved_items: Vec<crate::ir::hir::ResolvedTopLevel>,
) -> CodegenContext {
    let type_defs: Vec<TypeDef> = items
        .iter()
        .filter_map(|item| {
            if let TopLevel::TypeDef(td) = item {
                Some(td.clone())
            } else {
                None
            }
        })
        .collect();

    let fn_defs: Vec<FnDef> = items
        .iter()
        .filter_map(|item| {
            if let TopLevel::FnDef(fd) = item {
                Some(fd.clone())
            } else {
                None
            }
        })
        .collect();

    let module_prefixes: HashSet<String> = modules.iter().map(|m| m.prefix.clone()).collect();

    // Mutual-TCO membership unions per-scope sets from the analyze
    // stage (entry's `entry_analysis` + each dep module's
    // `module.analysis`); falls back to recomputing per-scope via
    // `call_graph::tailcall_scc_components` when no analysis ran.
    // Aver's module DAG invariant guarantees SCCs never span
    // modules — per-scope union is the correct global view (see
    // `project_aver_module_dag` memory + `src/ir/analyze.rs`). The
    // FnId resolution happens inside the `scc` wrappers below.
    let mut mutual_tco_members: HashSet<crate::ir::FnId> = HashSet::new();
    match entry_analysis {
        Some(a) => mutual_tco_members.extend(scc::analysis_set_to_fn_ids(
            &a.mutual_tco_members,
            &symbol_table,
            None,
        )),
        None => {
            // No entry analysis: compute the per-scope SCC set inline
            // via `call_graph` and project to FnIds. Same effect as
            // running the analyze stage's mutual-TCO discovery.
            // **syntax-discovery-only** (epic #170 Phase 8 guardrail):
            // `entry_fns` is filtered from `fn_defs` — the entry-scope
            // FnDef vec — so `FnKey::entry(&fd.name)` below is the
            // correct keying by construction (every `fd` here is
            // entry-scope).
            let entry_fns: Vec<&FnDef> = fn_defs.iter().filter(|fd| fd.name != "main").collect();
            for group in crate::call_graph::tailcall_scc_components(&entry_fns) {
                if group.len() < 2 {
                    continue;
                }
                for fd in group {
                    if let Some(id) = symbol_table.fn_id_of(&crate::ir::FnKey::entry(&fd.name)) {
                        mutual_tco_members.insert(id);
                    }
                }
            }
        }
    }
    for module in &modules {
        match module.analysis.as_ref() {
            Some(a) => mutual_tco_members.extend(scc::analysis_set_to_fn_ids(
                &a.mutual_tco_members,
                &symbol_table,
                Some(&module.prefix),
            )),
            None => {
                let mod_fns: Vec<&FnDef> = module.fn_defs.iter().collect();
                for group in crate::call_graph::tailcall_scc_components(&mod_fns) {
                    if group.len() < 2 {
                        continue;
                    }
                    for fd in group {
                        if let Some(id) = symbol_table.fn_id_of(&crate::ir::FnKey::in_module(
                            module.prefix.clone(),
                            &fd.name,
                        )) {
                            mutual_tco_members.insert(id);
                        }
                    }
                }
            }
        }
    }

    // `recursive_fns` follows the same shape — per-scope union with
    // analyze-stage fallback. Keyed by opaque `FnId` so entry +
    // dep-module same-bare-name fns stay distinct.
    let mut recursive_fns: HashSet<crate::ir::FnId> = HashSet::new();
    match entry_analysis {
        Some(a) => recursive_fns.extend(scc::analysis_set_to_fn_ids(
            &a.recursive_fns,
            &symbol_table,
            None,
        )),
        None => recursive_fns.extend(scc::bare_names_to_fn_ids(
            crate::call_graph::find_recursive_fns(&items)
                .iter()
                .map(String::as_str),
            &symbol_table,
            None,
        )),
    }
    for module in &modules {
        match module.analysis.as_ref() {
            Some(a) => recursive_fns.extend(scc::analysis_set_to_fn_ids(
                &a.recursive_fns,
                &symbol_table,
                Some(&module.prefix),
            )),
            None => {
                let mod_items: Vec<TopLevel> = module
                    .fn_defs
                    .iter()
                    .map(|fd| TopLevel::FnDef(fd.clone()))
                    .collect();
                recursive_fns.extend(scc::bare_names_to_fn_ids(
                    crate::call_graph::find_recursive_fns(&mod_items)
                        .iter()
                        .map(String::as_str),
                    &symbol_table,
                    Some(&module.prefix),
                ));
            }
        }
    }

    // Detection layer for buffer-build sinks + fusion sites. The
    // ACTUAL rewrite + synthesis must happen BEFORE the resolver
    // pass (callers run it via `ir::run_buffer_build_pass` between
    // TCO and resolver) — the detector matches on `Expr::Ident`
    // shapes that resolver later rewrites to `Expr::Resolved`. We
    // rerun detection here against the final items so the resulting
    // ctx fields reflect what's actually in the AST. With pre-
    // resolver pass having already run, sinks/sites should be the
    // same set (sinks are fns, not call sites; fusion sites were
    // rewritten away so the post-rewrite count is zero in normal flow).
    let detect_fns: Vec<&FnDef> = fn_defs
        .iter()
        .chain(modules.iter().flat_map(|m| m.fn_defs.iter()))
        .collect();
    let buffer_build_sinks = crate::ir::compute_buffer_build_sinks(&detect_fns);
    let buffer_fusion_sites = crate::ir::find_fusion_sites(&detect_fns, &buffer_build_sinks);
    // The synthesizer already ran in the pre-resolver compile pass
    // (`ir::run_buffer_build_pass`); the resulting `<fn>__buffered`
    // variants live in `items` (or in dep `module.fn_defs`) directly,
    // so we just collect references for the ctx field instead of
    // re-synthesizing — re-running here would duplicate every fn
    // and confuse the WASM emitter's fn_indices table.
    let synthesized_buffered_fns: Vec<FnDef> = fn_defs
        .iter()
        .chain(modules.iter().flat_map(|m| m.fn_defs.iter()))
        .filter(|fd| fd.name.ends_with("__buffered"))
        .cloned()
        .collect();

    // Epic #170 Phase 1: build the canonical `ResolvedProgramView`
    // once, from the pipeline's already-resolved entry items + the
    // dep modules' AST fn defs. The view does the module-side
    // resolution (pinning `ResolveCtx.current_module = Some(prefix)`)
    // — that's the only producer in the codebase. `resolved_fn_defs`
    // / `resolved_module_fn_defs` then project FROM the view rather
    // than running an independent second resolve, eliminating the
    // "two truths" hazard build_context carried since PR 9.
    let resolved_program = crate::codegen::program_view::ResolvedProgramView::build(
        resolved_items,
        &modules,
        &symbol_table,
    );
    let resolved_fn_defs: Vec<crate::ir::hir::ResolvedFnDef> =
        resolved_program.entry_fns().cloned().collect();
    let resolved_module_fn_defs: Vec<Vec<crate::ir::hir::ResolvedFnDef>> = resolved_program
        .modules
        .iter()
        .map(|m| m.fn_defs.clone())
        .collect();

    // Compute program shape before moving items / modules into ctx.
    // Once-per-compilation analysis substrate (#232 stage 4+); ad-hoc
    // detectors in codegen (e.g. dafny's `is_directly_recursive`,
    // future stage 6 adapters for `refinement_info_for`) read from
    // this instead of rewalking the AST.
    let program_shape = {
        let mut all_fns: Vec<&crate::ir::hir::ResolvedFnDef> =
            resolved_program.entry_fns().collect();
        for m in &resolved_program.modules {
            for fd in &m.fn_defs {
                all_fns.push(fd);
            }
        }
        Some(crate::analysis::shape::analyze_program_with_modules(
            &all_fns, &items, &modules,
        ))
    };

    // Lower the whole resolved program (entry + dep-module fns) to
    // optimized Core MIR, once, and key it by `FnId`. The Rust
    // backend reads `fn_by_id` here to render every fn body (its sole
    // codegen path); building it here (rather than per-fn) keeps the
    // lowering cost O(program) instead of O(program²). Same
    // `lower_program` → `optimize` pass the other MIR backends run.
    let mir_program = {
        let mut mir_items: Vec<crate::ir::hir::ResolvedTopLevel> = resolved_program
            .entry_fns()
            .cloned()
            .map(crate::ir::hir::ResolvedTopLevel::FnDef)
            .collect();
        for m in &resolved_program.modules {
            for fd in &m.fn_defs {
                mir_items.push(crate::ir::hir::ResolvedTopLevel::FnDef(fd.clone()));
            }
        }
        Some(crate::ir::mir::optimize(crate::ir::mir::lower_program(
            &mir_items,
        )))
    };

    let ctx = CodegenContext {
        items,
        type_defs,
        fn_defs,
        project_name,
        modules,
        module_prefixes,
        #[cfg(feature = "runtime")]
        policy: None,
        emit_replay_runtime: false,
        runtime_policy_from_env: false,
        guest_entry: None,
        emit_self_host_support: false,
        extra_fn_defs: Vec::new(),
        mutual_tco_members,
        recursive_fns,
        buffer_build_sinks,
        buffer_fusion_sites,
        synthesized_buffered_fns,
        #[cfg(feature = "runtime")]
        proof_ir: crate::ir::ProofIR::default(),
        // Symbol table threaded through from the pipeline (or
        // built locally in fallback). The FnId-keyed `recursive_
        // fns` / `mutual_tco_members` above used it; backends
        // (proof_lower / Lean / Rust / Dafny) read it directly off
        // ctx for opaque-ID lookups.
        symbol_table,
        resolved_fn_defs,
        resolved_module_fn_defs,
        current_module_scope: std::cell::RefCell::new(None),
        program_shape,
        resolved_program,
        mir_program,
        discovered_lemmas: Vec::new(),
        sample_expected: std::collections::HashMap::new(),
    };
    // ProofIR no longer populated here. Pipeline owns the lowerings
    // (`PipelineStage::RefinementLower`, `PipelineStage::ContractLower`);
    // proof backends opt in via `PipelineConfig.run_refinement_lower` /
    // `run_contract_lower` and read `pipeline_result.proof_ir` back.
    // Runtime backends (VM / WASM / Rust) leave both off and skip the
    // work. Tests that bypass the pipeline assemble the ctx by hand
    // and call `refresh_facts()` to populate the field — the field
    // stays `default()` here for those callers until they explicitly
    // refresh.
    ctx
}

impl CodegenContext {
    /// Set `current_module_scope` for the duration of `f`. Backends
    /// wrap their per-module emit calls with this so legacy
    /// resolve-on-demand adapters see the correct prefix.
    pub fn with_module_scope<R>(&self, scope: Option<&str>, f: impl FnOnce() -> R) -> R {
        let prev = self
            .current_module_scope
            .replace(scope.map(|s| s.to_string()));
        let out = f();
        *self.current_module_scope.borrow_mut() = prev;
        out
    }

    /// Snapshot of the active module scope. Cloned so callers may
    /// pass `as_deref()` into resolver/emitter APIs without holding
    /// the `RefCell` borrow.
    pub fn active_module_scope(&self) -> Option<String> {
        self.current_module_scope.borrow().clone()
    }

    /// Identity-keyed lookup from a bare fn name + scope to the
    /// matching `&FnDef` in `fn_defs` / `modules[i].fn_defs`. Resolves
    /// the name through the symbol table to an `FnId` first, then
    /// recovers the AST `FnDef` via `fn_id_for_decl` pointer-eq scope
    /// matching — so two same-bare-name fns across modules can't
    /// cross-resolve.
    ///
    /// **Epic #170 Phase 5 helper.** Replaces the
    /// `ctx.fn_defs.iter().find(|fd| fd.name == name)` pattern that
    /// proof-mode law / verify rewriters used pre-migration. Backends
    /// that still need a `&FnDef` (rather than the resolved twin —
    /// e.g. `rewrite_effectful_calls_in_law` consumes AST shape)
    /// reach this method instead of walking by bare name.
    ///
    /// Returns `None` when the symbol table doesn't know the name
    /// under the given scope, or when the resolved `FnId` doesn't
    /// match any `&FnDef` in that scope (synthetic FnDefs added
    /// post-pipeline fall through here — callers can fallback to a
    /// bare-name walk over `extra_fn_defs` etc. when that matters).
    pub fn fn_def_by_name(&self, name: &str, scope: Option<&str>) -> Option<&FnDef> {
        use crate::ir::FnKey;
        let key = match scope {
            Some(prefix) => FnKey::in_module(prefix.to_string(), name),
            None => FnKey::entry(name),
        };
        let fn_id = self.symbol_table.fn_id_of(&key)?;
        let matches = |fd: &&FnDef| crate::codegen::common::fn_id_for_decl(self, fd) == Some(fn_id);
        match scope {
            None => self.fn_defs.iter().find(matches),
            Some(prefix) => self
                .modules
                .iter()
                .find(|m| m.prefix == prefix)?
                .fn_defs
                .iter()
                .find(matches),
        }
    }
}

impl CodegenContext {
    /// Test-only bridge: recompute every derived fact
    /// (`mutual_tco_members`, `recursive_fns`, `proof_ir`,
    /// `resolved_program`) from the current `items` and `modules`.
    /// Used exclusively by unit tests that construct a
    /// `CodegenContext` piecewise — pushing synthetic `FnDef`s
    /// straight into the items list rather than going through the
    /// parser and pipeline. Production code never needs this: every
    /// derived fact is populated by the pipeline stages (analyze,
    /// proof_lower) and propagated through `build_context`. Calling
    /// `refresh_facts` on a production-built ctx is redundant work
    /// that produces the same answer — leave it off the hot path.
    ///
    /// **Single-source-of-truth invariant** (epic #170 Phase 1+2):
    /// rebuilds `resolved_program` once from the freshly-resolved
    /// items, then derives `resolved_fn_defs` /
    /// `resolved_module_fn_defs` as projections of that view. There
    /// is no parallel resolve path here.
    pub fn refresh_facts(&mut self) {
        // Synthetic-ctx path must own its symbol table too — FnId-
        // keyed sets below resolve through it, same shape as the
        // production `build_context` flow.
        let symbol_table = crate::ir::SymbolTable::build(&self.items, &self.modules);
        let entry_fn_id = |name: &str| -> Option<crate::ir::FnId> {
            symbol_table.fn_id_of(&crate::ir::FnKey::entry(name))
        };
        let module_fn_id = |prefix: &str, name: &str| -> Option<crate::ir::FnId> {
            symbol_table.fn_id_of(&crate::ir::FnKey::in_module(prefix.to_string(), name))
        };

        let entry_fn_refs: Vec<&FnDef> =
            self.fn_defs.iter().filter(|fd| fd.name != "main").collect();

        let mut mutual_tco_members: HashSet<crate::ir::FnId> = HashSet::new();
        for group in crate::call_graph::tailcall_scc_components(&entry_fn_refs) {
            if group.len() < 2 {
                continue;
            }
            for fd in group {
                if let Some(id) = entry_fn_id(&fd.name) {
                    mutual_tco_members.insert(id);
                }
            }
        }
        for module in &self.modules {
            let mod_fns: Vec<&FnDef> = module.fn_defs.iter().collect();
            for group in crate::call_graph::tailcall_scc_components(&mod_fns) {
                if group.len() < 2 {
                    continue;
                }
                for fd in group {
                    if let Some(id) = module_fn_id(&module.prefix, &fd.name) {
                        mutual_tco_members.insert(id);
                    }
                }
            }
        }
        self.mutual_tco_members = mutual_tco_members;

        let mut recursive_fns: HashSet<crate::ir::FnId> = scc::bare_names_to_fn_ids(
            crate::call_graph::find_recursive_fns(&self.items)
                .iter()
                .map(String::as_str),
            &symbol_table,
            None,
        );
        for module in &self.modules {
            let mod_items: Vec<TopLevel> = module
                .fn_defs
                .iter()
                .map(|fd| TopLevel::FnDef(fd.clone()))
                .collect();
            recursive_fns.extend(scc::bare_names_to_fn_ids(
                crate::call_graph::find_recursive_fns(&mod_items)
                    .iter()
                    .map(String::as_str),
                &symbol_table,
                Some(&module.prefix),
            ));
        }
        self.recursive_fns = recursive_fns;

        // Reuse the symbol table built at the top of this function
        // for proof_lower below — it already resolved every FnId we
        // need for `recursive_fns` / `mutual_tco_members`.
        self.symbol_table = symbol_table;

        // Rebuild the canonical resolved view from the current items
        // + modules (post-PR-A: this is the single source for resolved
        // bodies). Entry-side resolved items are produced by
        // `resolve_program`, then the view runs the per-dep-module
        // resolve internally and indexes everything by `FnId`. The
        // `resolved_fn_defs` / `resolved_module_fn_defs` mirrors below
        // are projections of this view, kept for callsites that still
        // walk them directly during the #170 backend-migration arc.
        let entry_resolved_items = crate::ir::hir::resolve_program(&self.symbol_table, &self.items);
        self.resolved_program = crate::codegen::program_view::ResolvedProgramView::build(
            entry_resolved_items,
            &self.modules,
            &self.symbol_table,
        );
        self.resolved_fn_defs = self.resolved_program.entry_fns().cloned().collect();
        self.resolved_module_fn_defs = self
            .resolved_program
            .modules
            .iter()
            .map(|m| m.fn_defs.clone())
            .collect();

        // ProofIR's `fn_contracts` / `refined_types` are derived from
        // the just-recomputed item set + the recursion classifier, so
        // they must stay in step with the rest of the facts. Test
        // helpers that build the context piecewise and call
        // `refresh_facts` rely on this to see the same proof decisions
        // the production pipeline would emit.
        let inputs = crate::codegen::proof_lower::ProofLowerInputs::from_ctx(self);
        self.proof_ir = crate::codegen::proof_lower::lower(&inputs);
    }

    /// Look up the resolved-HIR mirror of a source-shape [`FnDef`]
    /// previously stashed in [`resolved_fn_defs`] /
    /// [`resolved_module_fn_defs`]. Falls back to a fresh per-call
    /// resolver lift against the entry's [`crate::ir::SymbolTable`]
    /// when neither path covers `fd` — this happens for synthetic
    /// FnDefs inserted between `build_context` and emit (TCO hoist
    /// rewrites, test fixtures) which the resolver hasn't lifted
    /// upfront.
    ///
    /// `scope` is the owning module prefix when `fd` came from a
    /// dependency module's `module.fn_defs`, `None` when `fd` is part
    /// of the entry's `ctx.fn_defs`. Lookup keys by
    /// [`crate::ir::FnKey`] through the [`crate::ir::SymbolTable`] so
    /// two modules that share a bare fn name (e.g. `Util.format` and
    /// `Other.format`) resolve to their own [`crate::ir::FnId`]
    /// without bare-name collisions. Pre-PR-9.3a this matched by
    /// `rfd.name == fd.name` against a flat search of every resolved
    /// table — fragile the moment flatten changes (or doesn't run)
    /// and two scopes share a name.
    ///
    /// Phase E shared lookup boundary — Rust codegen (PR 8) already
    /// consumes this through `rust::toplevel::resolved_fn_def_for`;
    /// wasm-gc / Lean / Dafny / self-host backends pick it up in
    /// their follow-up PRs.
    ///
    /// [`resolved_fn_defs`]: Self::resolved_fn_defs
    /// [`resolved_module_fn_defs`]: Self::resolved_module_fn_defs
    pub fn resolve_fn_def<'a>(
        &'a self,
        fd: &'a FnDef,
        scope: Option<&str>,
    ) -> std::borrow::Cow<'a, crate::ir::hir::ResolvedFnDef> {
        use crate::ir::FnKey;
        use crate::ir::hir::{
            ResolveCtx, ResolvedFnBody, ResolvedFnDef, ResolvedStmt, resolve_fn_def_external,
        };
        use std::borrow::Cow;

        // Resolve identity via the symbol table — entry scope vs
        // dependency module scope is the caller's stated context.
        let key = match scope {
            Some(prefix) => FnKey::in_module(prefix.to_string(), fd.name.clone()),
            None => FnKey::entry(fd.name.clone()),
        };
        if let Some(fn_id) = self.symbol_table.fn_id_of(&key) {
            // Canonical lookup goes through the resolved-program view —
            // its `fn_by_id` index is the single FnId-keyed source for
            // the resolved body, replacing the dual-walk over
            // `resolved_fn_defs` + `resolved_module_fn_defs` that
            // predated #170 Phase 1.
            if let Some(rfd) = self.resolved_program.fn_by_id(fn_id) {
                return Cow::Borrowed(rfd);
            }
            // Symbol table knew the key but the view didn't index it.
            // Falls through to the synthetic-fallback path below; in
            // production this shouldn't happen.
        }

        // Synthetic FnDef path — TCO hoist rewrites, test fixtures
        // the resolver never saw. Lift on demand against the entry's
        // resolver context.
        let module_name = self.items.iter().find_map(|i| match i {
            TopLevel::Module(m) => Some(m.name.clone()),
            _ => None,
        });
        let mut rctx = ResolveCtx::new(&self.symbol_table);
        rctx.current_module = scope.map(String::from).or(module_name);
        let lifted = resolve_fn_def_external(&rctx, fd).unwrap_or_else(|| {
            let stmts: Vec<ResolvedStmt> = match fd.body.as_ref() {
                crate::ast::FnBody::Block(stmts) => {
                    stmts.iter().map(|s| self.resolve_stmt(s, scope)).collect()
                }
            };
            ResolvedFnDef {
                fn_id: crate::ir::FnId(u32::MAX),
                name: fd.name.clone(),
                line: fd.line,
                params: fd
                    .params
                    .iter()
                    .map(|(n, ann)| (n.clone(), crate::types::parse_type_str(ann)))
                    .collect(),
                return_type: crate::types::parse_type_str(&fd.return_type),
                effects: fd.effects.clone(),
                desc: fd.desc.clone(),
                body: std::sync::Arc::new(ResolvedFnBody::Block(stmts)),
                resolution: fd.resolution.clone(),
            }
        });
        Cow::Owned(lifted)
    }

    /// Entry module's name from `items` (the `module X` declaration's
    /// X). `None` for ad-hoc test programs without a module decl.
    fn entry_module_name(&self) -> Option<String> {
        self.items.iter().find_map(|i| match i {
            TopLevel::Module(m) => Some(m.name.clone()),
            _ => None,
        })
    }

    /// Resolve a source-shape `Spanned<Expr>` on demand using the
    /// entry's resolver context. Used by emit helpers that still walk
    /// `Expr` (TCO hoisting, mutual TCO, verify blocks, follow-up
    /// backends pre-migration) and need to feed the resolved shape
    /// into the migrated emitter. The returned `Spanned<ResolvedExpr>`
    /// carries the same line + type stamp as the input.
    ///
    /// `scope` is the owning module prefix when the caller knows
    /// which dep module the expression lives in, `None` for entry-
    /// scope code. Required for cross-module name resolution — e.g.,
    /// a call site in module `A` referring to `Val.ValOk` declared
    /// in module `B` only resolves to `ResolvedCtor::User` when the
    /// resolver's `current_module` matches the call site's owning
    /// scope. Pre-PR-9.4 the helper used the *entry* module name
    /// uniformly, which broke cross-module ctor / fn classification
    /// for the legacy emit paths (mutual TCO trampolines, TCO hoist
    /// — they walked dep-module fn bodies but the resolver context
    /// said "you're in the entry module"; the self-host regen
    /// surfaced the gap when same-name shadowing across modules was
    /// no longer an option).
    pub fn resolve_expr(
        &self,
        expr: &crate::ast::Spanned<crate::ast::Expr>,
        scope: Option<&str>,
    ) -> crate::ast::Spanned<crate::ir::hir::ResolvedExpr> {
        use crate::ir::hir::{ResolveCtx, ResolvedStmt};
        let mut rctx = ResolveCtx::new(&self.symbol_table);
        rctx.current_module = scope.map(String::from).or_else(|| self.entry_module_name());
        let stmt = crate::ast::Stmt::Expr(expr.clone());
        match crate::ir::hir::resolve::resolve_stmt_external(&rctx, &stmt) {
            ResolvedStmt::Expr(s) => s,
            ResolvedStmt::Binding { value, .. } => value,
        }
    }

    /// Same as [`Self::resolve_expr`] but for whole statements
    /// (`Binding(name, ty_ann, expr)` or `Expr(expr)`).
    pub fn resolve_stmt(
        &self,
        stmt: &crate::ast::Stmt,
        scope: Option<&str>,
    ) -> crate::ir::hir::ResolvedStmt {
        use crate::ir::hir::ResolveCtx;
        let mut rctx = ResolveCtx::new(&self.symbol_table);
        rctx.current_module = scope.map(String::from).or_else(|| self.entry_module_name());
        crate::ir::hir::resolve::resolve_stmt_external(&rctx, stmt)
    }

    /// Resolve a source-shape [`crate::ast::Pattern`] to its resolved
    /// HIR form. Wraps the pattern in a synthetic match arm + drops
    /// it through `resolve_stmt_external`, since the resolver doesn't
    /// expose a standalone pattern lifter — same workaround
    /// `rust/toplevel.rs` used pre-PR-9.
    pub fn resolve_pattern(
        &self,
        pat: &crate::ast::Pattern,
        scope: Option<&str>,
    ) -> crate::ir::hir::ResolvedPattern {
        use crate::ast::{Expr, Literal, MatchArm, Spanned, Stmt};
        use crate::ir::hir::{ResolveCtx, ResolvedExpr, ResolvedStmt};
        let mut rctx = ResolveCtx::new(&self.symbol_table);
        rctx.current_module = scope.map(String::from).or_else(|| self.entry_module_name());
        let synthetic_arm = MatchArm {
            pattern: pat.clone(),
            body: Box::new(Spanned::bare(Expr::Literal(Literal::Unit))),
            binding_slots: std::sync::OnceLock::new(),
        };
        let stmt = Stmt::Expr(Spanned::bare(Expr::Match {
            subject: Box::new(Spanned::bare(Expr::Literal(Literal::Unit))),
            arms: vec![synthetic_arm],
        }));
        let resolved_stmt = crate::ir::hir::resolve::resolve_stmt_external(&rctx, &stmt);
        let ResolvedStmt::Expr(spanned) = resolved_stmt else {
            unreachable!()
        };
        let ResolvedExpr::Match { arms, .. } = spanned.node else {
            unreachable!()
        };
        arms.into_iter().next().unwrap().pattern
    }
}

/// Per-key projection of the legacy `fn_sigs` map: routes a source-
/// level name through `resolved_program` first (entry + every dep
/// module's resolved fns), then walks `TypeDef`s for constructor sigs,
/// then handles the synthesised `__buf_*` intrinsics. Lets a
/// `CodegenContext` answer `FnSigOracle::fn_sig` without materialising
/// the whole `FnSigMap` up front — the verify-law helpers query
/// individual names, so per-key resolution is cheaper than per-call
/// rebuild.
fn codegen_ctx_fn_sig(ctx: &CodegenContext, name: &str) -> Option<crate::verify_law::FnSigInfo> {
    use crate::verify_law::FnSigInfo;

    if let Some(fn_id) = crate::codegen::common::fn_id_for_dotted_name(ctx, name)
        && let Some(rfd) = ctx.resolved_program.fn_by_id(fn_id)
    {
        return Some(FnSigInfo {
            return_type: rfd.return_type.clone(),
            is_pure: rfd.effects.is_empty(),
        });
    }

    // Constructor lookup: `Type.Variant` (entry sum), `Module.Type.
    // Variant` (module sum), `Box` (entry product), `Module.Box`
    // (module product). Walks the same `TypeDef` surfaces the
    // legacy fn_sigs population did via SymbolRegistry.
    let walk = |td: &crate::ast::TypeDef, scope: Option<&str>| -> Option<FnSigInfo> {
        match td {
            crate::ast::TypeDef::Sum {
                name: parent,
                variants,
                ..
            } => {
                let parent_full = match scope {
                    Some(prefix) => format!("{prefix}.{parent}"),
                    None => parent.clone(),
                };
                for v in variants {
                    let bare = format!("{parent}.{}", v.name);
                    let full = format!("{parent_full}.{}", v.name);
                    if name == bare || name == full {
                        return Some(FnSigInfo {
                            return_type: crate::types::Type::named(parent_full.clone()),
                            is_pure: true,
                        });
                    }
                }
                None
            }
            crate::ast::TypeDef::Product { name: parent, .. } => {
                let parent_full = match scope {
                    Some(prefix) => format!("{prefix}.{parent}"),
                    None => parent.clone(),
                };
                if name == parent || name == parent_full {
                    return Some(FnSigInfo {
                        return_type: crate::types::Type::named(parent_full),
                        is_pure: true,
                    });
                }
                None
            }
        }
    };
    for item in &ctx.items {
        if let TopLevel::TypeDef(td) = item
            && let Some(info) = walk(td, None)
        {
            return Some(info);
        }
    }
    for m in &ctx.modules {
        for td in &m.type_defs {
            if let Some(info) = walk(td, Some(&m.prefix)) {
                return Some(info);
            }
        }
    }

    // Synthesised `__buf_*` intrinsics — the deforestation pipeline
    // emits these as opaque callables; verify-law walkers may surface
    // a reference if a user's law body sketches the buffer pipeline.
    match name {
        "__buf_new" => Some(FnSigInfo {
            return_type: crate::types::Type::named("Buffer"),
            is_pure: true,
        }),
        "__buf_append" | "__buf_append_sep_unless_first" => Some(FnSigInfo {
            return_type: crate::types::Type::named("Buffer"),
            is_pure: true,
        }),
        "__buf_finalize" => Some(FnSigInfo {
            return_type: crate::types::Type::Str,
            is_pure: true,
        }),
        _ => None,
    }
}

impl crate::verify_law::FnSigOracle for CodegenContext {
    fn fn_sig(&self, name: &str) -> Option<crate::verify_law::FnSigInfo> {
        codegen_ctx_fn_sig(self, name)
    }
}