feat(lsp): resolution-first semantic tokens rework#3867
Open
codeshaunted wants to merge 18 commits into
Open
Conversation
Rework the BAML semantic-tokens classifier to be resolution-driven (rust-analyzer style): walk the lossless CST for token positions and syntactic tokens (keywords/operators/punctuation), and resolve identifier meaning through the HIR/inference rather than guessing from the CST. - tokens/index.rs: span-keyed resolution index built over every inference-bearing scope (function / lambda / let) via the new uniform tir::scope_body lookup, so names in spawn/block/closure bodies classify with their own scope's inference. - Interface members now resolve like class members: resolve_interface_member records MemberResolution::InterfaceMethod / InterfaceField. MIR-safe (new variants lower to None item-refs and fall through to interface dispatch). - Highlighting fixes: as / with / is keywords, generators, generic type args and params (typeParameter), associated types (decl + binding), self member accesses, methods after .as<Interface>, string escapes (escapeSequence), byte strings, qualified type paths, true/false/null literals, object/map keys vs values. - bitflags-backed ModifierSet; classifier shared with `baml describe`. - tools_semantic_tokens: standalone web viewer for the classifier. 78 fixtures. See crates/baml_lsp2_actions/src/tokens/GAPS.md for the scaling next-steps (on-demand resolution, range/viewport, delta) and the remaining known gaps.
|
The latest updates on your projects. Learn more about Vercel for GitHub.
|
Contributor
📝 WalkthroughWalkthroughThis PR adds modifier-aware semantic tokens, contextual keyword and literal handling, interface-member and catch-binding resolution, and a semantic-tokens viewer with fixture snapshots, range queries, and delta support. ChangesSemantic tokens, resolution, and viewer
Sequence Diagram(s)sequenceDiagram
participant Browser
participant AxumServer
participant Analysis
participant Staleness
Browser->>AxumServer: /api/fixtures, /api/fixture, /api/tokens, /api/accept
AxumServer->>Analysis: compute_tokens / load_fixture / accept_fixture
AxumServer->>Staleness: build_id / status
Staleness-->>Browser: rebuild state changes
Estimated code review effort🎯 5 (Critical) | ⏱️ ~120 minutes Possibly related PRs
Poem
🚥 Pre-merge checks | ✅ 5✅ Passed checks (5 passed)
✨ Finishing Touches📝 Generate docstrings
🧪 Generate unit tests (beta)
Thanks for using CodeRabbit! It's free for OSS, and your support helps us grow. If you like it, consider giving us a shout-out. Comment |
![coderabbitai[bot]](https://avatars.githubusercontent.com/in/347564?s=60&v=4){kind=small}
Contributor
There was a problem hiding this comment.
Actionable comments posted: 20
Caution
Some comments are outside the diff and can’t be posted inline due to platform limitations.
⚠️ Outside diff range comments (1)
baml_language/crates/baml_compiler2_mir/src/lower.rs (1)
6111-6145: 🎯 Functional Correctness | 🟠 Major | ⚡ Quick winHandle captured roots in interface-method value lowering.
This path only runs when the first segment is a local. A captured receiver in
let f = x.eqskips the candidate-switch branch and falls through tolower_multi_segment_path_as_field_chain, so the method value gets lowered like a field/map lookup instead of a bound-method dispatch.🤖 Prompt for AI Agents
Verify each finding against current code. Fix only still-valid issues, skip the rest with a brief reason, keep changes minimal, and validate. In `@baml_language/crates/baml_compiler2_mir/src/lower.rs` around lines 6111 - 6145, The interface-method value lowering in the path that starts by checking self.locals for the first segment only handles plain locals, so captured receivers like let f = x.eq bypass bound-method dispatch and get treated as field/map chains. Update the logic in lower.rs around the method-candidate resolution branch to recognize captured roots as valid receivers, then route them through lower_path_receiver_to_local and emit_bound_method_candidate_switch just like local roots, instead of falling through to lower_multi_segment_path_as_field_chain.
🧹 Nitpick comments (1)
baml_language/crates/tools_semantic_tokens/src/analysis.rs (1)
46-244: 📐 Maintainability & Code Quality | 🔵 Trivial | ⚡ Quick winAdd unit tests around the offset/parser helpers.
This file is mostly pure string/offset logic, so a small
#[cfg(test)]module for UTF-16 offsets, escaped snapshot lines, and text-only diff cases would give faster and more targeted coverage than end-to-end fixtures alone. As per coding guidelines, "Prefer writing Rust unit tests over integration tests where possible."🤖 Prompt for AI Agents
Verify each finding against current code. Fix only still-valid issues, skip the rest with a brief reason, keep changes minimal, and validate. In `@baml_language/crates/tools_semantic_tokens/src/analysis.rs` around lines 46 - 244, Add a focused #[cfg(test)] module in analysis.rs to unit test the pure helpers instead of relying only on fixture flows. Cover offset_to_line_col, utf16_offset, parse_expected, and diff_count with cases for non-ASCII/UTF-16 positioning, escaped or quoted snapshot text lines, and text-only token diffs. Use the existing helper symbols and Token shape to keep the tests local and resilient to line changes.Source: Coding guidelines
🤖 Prompt for all review comments with AI agents
Verify each finding against current code. Fix only still-valid issues, skip the
rest with a brief reason, keep changes minimal, and validate.
Inline comments:
In `@baml_language/crates/baml_compiler2_tir/src/builder.rs`:
- Around line 12397-12405: The default-method branch in builder.rs is writing a
redundant MemberResolution::InterfaceMethod into self.resolutions that is always
overwritten later by InterfaceDefaultMethod. Remove the insert in the
default-method loop around the bound check, and keep InterfaceMethod only in the
required-method loop where no later overwrite occurs; use the existing
iface_loc/method_name and func_loc resolution paths to keep the intended
behavior clear.
In
`@baml_language/crates/baml_lsp2_actions_tests/test_files/semantic_tokens/catch_throw.baml`:
- Line 10: The semantic tokens fixture for catch handling is missing coverage
for the catch binding identifier, so update the `catch_throw.baml` expectations
to include the bound name in the `MayFail(x) catch (e) {` case and the other
referenced catch blocks. Make sure the `semantic_tokens` test asserts token
classification for the catch variable itself, not just the `catch` keyword, so
the resolution-driven identifier behavior is verified through the existing
fixture.
In
`@baml_language/crates/baml_lsp2_actions_tests/test_files/semantic_tokens/constructor_spread.baml`:
- Line 8: The semantic-tokens fixture for constructor spreads is missing the
spread operand token, so extend the expected token list in the semantic token
test around the MyClass constructor spread case to include the x in ...x. Update
the fixture used by the semantic_tokens test for constructor_spread.baml (and
the related cases in the same test block) so the spread operand is asserted and
regressions in operand classification are caught.
In
`@baml_language/crates/baml_lsp2_actions_tests/test_files/semantic_tokens/dynamic_type_builder.baml`:
- Around line 21-27: The semantic-tokens fixture records `functions
[ExtractResume]` but never asserts that `ExtractResume` is classified as a
function reference, so add the missing token assertion in the
`dynamic_type_builder.baml` test around `test ReturnDynamicClassTest` using the
existing semantic token expectations for `functions[...]`. Make sure the
assertion explicitly covers the `ExtractResume` identifier so regressions in
function-reference classification inside `functions [...]` are caught, and apply
the same update to the matching fixture noted in the comment.
In
`@baml_language/crates/baml_lsp2_actions_tests/test_files/semantic_tokens/field_alias.baml`:
- Around line 35-37: Update the semantic tokens fixture for field alias handling
so it asserts both alias endpoints, not just the `as` keyword. In
`field_alias.baml`, expand the expectations around the `name as display_name`
alias to include tokens for the source field (`name`) and the target alias
(`display_name`) alongside the existing `as` token, using the same semantic
token test pattern used elsewhere in these fixtures.
In
`@baml_language/crates/baml_lsp2_actions_tests/test_files/semantic_tokens/index_access.baml`:
- Around line 45-46: The semantic tokens fixture is incorrectly marked as
diagnostic-free even though the preceding examples document validation errors.
Update the fixture around the diagnostics marker so it no longer uses
<no-diagnostics-expected> in the index_access.baml test content; either add the
expected diagnostics for the cases shown above or split the negative examples
into a separate fixture and keep this one truly diagnostic-free. Use the
existing semantic_tokens fixture structure and diagnostics comment block to
locate the change.
In
`@baml_language/crates/baml_lsp2_actions_tests/test_files/semantic_tokens/ns_images_pipeline.baml`:
- Around line 40-41: The semantic token test only asserts the client property
key in ns_images_pipeline.baml and misses the actual client symbol reference, so
regressions in client-reference classification could go unnoticed. Update the
expected tokens in the semantic tokens test data to also assert the
AiGatewayImagenImageClient reference inside the function config, using the
existing semantic token fixture around the client/prompt entries to keep the
check tied to the relevant symbols.
In
`@baml_language/crates/baml_lsp2_actions_tests/test_files/semantic_tokens/requires_clause.baml`:
- Around line 1-30: The semantic-tokens fixture for requires-chain coverage does
not currently exercise the transitive Aged member through Person requires Named,
Aged. Update the test content in requires_clause.baml to add a Person-typed or
self.age access that resolves age via the requires chain, so the fixture
actually validates the grandparent-interface flow instead of only the concrete
Employee field. Use the existing Person, Aged, and get_age symbols to place the
new access alongside the current example.
In `@baml_language/crates/baml_lsp2_actions/src/definition.rs`:
- Around line 426-436: The interface member resolution in definition.rs is
currently collapsing both MemberResolution::InterfaceMethod and
MemberResolution::InterfaceField to Definition::Interface, which makes
go-to-definition jump to the interface header instead of the accessed member.
Update the definition lookup in the branch handling
MemberResolution::InterfaceMethod and MemberResolution::InterfaceField to use
the member-specific identifier from the resolution and resolve the corresponding
interface method/field span, following the same pattern used by the Field and
method branches above. Ensure utils::definition_span is called with the member
declaration target rather than the interface declaration.
In `@baml_language/crates/baml_lsp2_actions/src/tokens/index.rs`:
- Around line 56-63: The token indexing logic in the scope filter is skipping
template-body scopes entirely, which leaves template interpolations like string
tokens unprocessed. Update the scope handling in the token indexer to not
unconditionally continue on scope.is_template_body, and instead let those bodies
be indexed with the same inference context as the enclosing ExprBody. Keep the
existing function/lambda/let scope checks in the token indexing flow, but ensure
template-body synthetic scopes are still traversed so resolution-driven
highlighting works.
- Around line 157-176: In tokens/index.rs, the fallback in the
path-classification logic currently marks unresolved leaf segments as Namespace,
which incorrectly masks typos as valid identifiers. Update the resolve/classify
flow around the `resolve_path_at` and `classify::classify_resolved` branch so
only non-leaf prefixes can fall back to `SemanticTokenType::Namespace`, while
the final unresolved segment stays neutral when `inference.resolution(expr_id)`
is missing and `local_root` does not apply.
In `@baml_language/crates/tools_semantic_tokens/src/analysis.rs`:
- Around line 202-207: `load_fixture` and `list_fixture_names` are swallowing
load failures by fabricating empty results, so update them to return errors
instead of defaulting to empty source or empty names. In `load_fixture`, use the
parsed file presence in `parsed.files` as a required condition and surface an
`InvalidData` error when no virtual file is available; in `list_fixture_names`,
stop flattening away `read_dir` failures and propagate the underlying I/O error.
Keep the fix localized to the `load_fixture` and `list_fixture_names` paths so
callers can distinguish “no data” from “failed to load.”
- Around line 225-243: The diff_count function is only comparing token type and
modifiers for matching position/length, so text-only snapshot drift can be
missed even when the committed semantic_tokens fixture would still change.
Update diff_count in analysis.rs to also compare the normalized committed lexeme
or raw snapshot text for each token key, and treat any text-only mismatch as a
diff alongside the existing type/modifier checks.
In `@baml_language/crates/tools_semantic_tokens/src/index.html`:
- Around line 440-445: The load-failure handler in the fixture fetch flow should
clear stale state instead of only rendering the error pane. In the catch path
around getJson in index.html, reset detail, disable the Accept control, and
clear the inspector/status state so the UI does not keep reflecting the previous
fixture after a failed /api/fixture request.
- Around line 456-469: The accept button flow in the click handler for acceptEl
leaves the control disabled after a failed /api/accept request, so the user
cannot retry without reselecting a fixture. Update the async click handler to
restore the enabled state in a finally block after the getJson("/api/accept"),
refreshFixtures(), and select(selected) sequence, and base that restore on the
current selection state (for example the same condition used before disabling).
- Around line 296-312: Stop interpolating fixture names directly into HTML
attributes in renderList(). The current esc() usage in the fixture button markup
still leaves data-name and title vulnerable because quotes are not escaped.
Update the row-building logic in renderList() to set these attributes through
DOM APIs or use an attribute-safe escape for f.name before inserting it, while
keeping the Scratchpad row consistent.
- Around line 414-427: The renderScratch flow applies any finished /api/tokens
response even if it was started for an older scratchText value, so update it to
ignore stale results. Add a request version/sequence check inside renderScratch
around the getJson("/api/tokens") call and only assign scratchTokens and render
when the response still matches the latest request for the current scratchText,
using the existing renderScratch, scratchTokens, and selected/SCRATCH logic to
locate the fix.
In `@baml_language/crates/tools_semantic_tokens/src/main.rs`:
- Around line 87-95: The port selection logic in bind can overflow when adding
the scan offset to a high preferred port. Update the loop in bind to clamp the
upper bound at u16::MAX before probing ports, so the SocketAddr construction
never wraps or panics; keep the rest of the TcpListener::bind retry behavior
unchanged and preserve the existing error path when no port is available.
In `@baml_language/crates/tools_semantic_tokens/src/server.rs`:
- Around line 183-196: resolve_fixture currently trusts Path::is_file, which
follows symlinks and can let fixture names escape fixtures_dir; update the
validation in resolve_fixture to reject symlinked entries before returning the
path. Use the existing resolve_fixture helper and its dir.join(name) result to
check the resolved candidate itself is a regular file owned inside the fixture
tree, and return an error for any symlink or non-regular path before
/api/fixture or /api/accept can use it.
In `@baml_language/crates/tools_semantic_tokens/src/staleness.rs`:
- Around line 31-37: The staleness watcher in newest_source_mtime only tracks
this crate and baml_lsp2_actions, but semantic token behavior also depends on
baml_compiler2_tir, baml_compiler2_mir, and baml_compiler_syntax. Update the
roots list (and any related watcher logic in staleness.rs) so those compiler
crates are included in the mtime scan, ensuring edits there trigger the viewer
restart and keep semantic tokens fresh.
---
Outside diff comments:
In `@baml_language/crates/baml_compiler2_mir/src/lower.rs`:
- Around line 6111-6145: The interface-method value lowering in the path that
starts by checking self.locals for the first segment only handles plain locals,
so captured receivers like let f = x.eq bypass bound-method dispatch and get
treated as field/map chains. Update the logic in lower.rs around the
method-candidate resolution branch to recognize captured roots as valid
receivers, then route them through lower_path_receiver_to_local and
emit_bound_method_candidate_switch just like local roots, instead of falling
through to lower_multi_segment_path_as_field_chain.
---
Nitpick comments:
In `@baml_language/crates/tools_semantic_tokens/src/analysis.rs`:
- Around line 46-244: Add a focused #[cfg(test)] module in analysis.rs to unit
test the pure helpers instead of relying only on fixture flows. Cover
offset_to_line_col, utf16_offset, parse_expected, and diff_count with cases for
non-ASCII/UTF-16 positioning, escaped or quoted snapshot text lines, and
text-only token diffs. Use the existing helper symbols and Token shape to keep
the tests local and resilient to line changes.
🪄 Autofix (Beta)
Fix all unresolved CodeRabbit comments on this PR:
- Push a commit to this branch (recommended)
- Create a new PR with the fixes
ℹ️ Review info
⚙️ Run configuration
Configuration used: Repository UI
Review profile: CHILL
Plan: Pro
Run ID: 3f4c5b6e-52a8-4a11-bea9-e5d65b8d4846
⛔ Files ignored due to path filters (1)
baml_language/Cargo.lockis excluded by!**/*.lock
📒 Files selected for processing (100)
baml_language/Cargo.tomlbaml_language/crates/baml_cli/src/paint.rsbaml_language/crates/baml_compiler2_mir/src/lower.rsbaml_language/crates/baml_compiler2_tir/src/builder.rsbaml_language/crates/baml_compiler2_tir/src/inference.rsbaml_language/crates/baml_compiler_syntax/src/syntax_kind.rsbaml_language/crates/baml_lsp2_actions/Cargo.tomlbaml_language/crates/baml_lsp2_actions/src/definition.rsbaml_language/crates/baml_lsp2_actions/src/lib.rsbaml_language/crates/baml_lsp2_actions/src/tokens.rsbaml_language/crates/baml_lsp2_actions/src/tokens/GAPS.mdbaml_language/crates/baml_lsp2_actions/src/tokens/classify.rsbaml_language/crates/baml_lsp2_actions/src/tokens/index.rsbaml_language/crates/baml_lsp2_actions_tests/src/runner.rsbaml_language/crates/baml_lsp2_actions_tests/test_files/semantic_tokens/array_pattern.bamlbaml_language/crates/baml_lsp2_actions_tests/test_files/semantic_tokens/attributes.bamlbaml_language/crates/baml_lsp2_actions_tests/test_files/semantic_tokens/backtick_string.bamlbaml_language/crates/baml_lsp2_actions_tests/test_files/semantic_tokens/block_attributes.bamlbaml_language/crates/baml_lsp2_actions_tests/test_files/semantic_tokens/break_continue.bamlbaml_language/crates/baml_lsp2_actions_tests/test_files/semantic_tokens/byte_strings.bamlbaml_language/crates/baml_lsp2_actions_tests/test_files/semantic_tokens/cancel_token.bamlbaml_language/crates/baml_lsp2_actions_tests/test_files/semantic_tokens/catch_all_keyword.bamlbaml_language/crates/baml_lsp2_actions_tests/test_files/semantic_tokens/catch_throw.bamlbaml_language/crates/baml_lsp2_actions_tests/test_files/semantic_tokens/class.bamlbaml_language/crates/baml_lsp2_actions_tests/test_files/semantic_tokens/client.bamlbaml_language/crates/baml_lsp2_actions_tests/test_files/semantic_tokens/config_dictionary.bamlbaml_language/crates/baml_lsp2_actions_tests/test_files/semantic_tokens/const_binding.bamlbaml_language/crates/baml_lsp2_actions_tests/test_files/semantic_tokens/const_let_else_defer.bamlbaml_language/crates/baml_lsp2_actions_tests/test_files/semantic_tokens/constructor_spread.bamlbaml_language/crates/baml_lsp2_actions_tests/test_files/semantic_tokens/deep_method_call.bamlbaml_language/crates/baml_lsp2_actions_tests/test_files/semantic_tokens/dynamic_type_builder.bamlbaml_language/crates/baml_lsp2_actions_tests/test_files/semantic_tokens/enum_decls.bamlbaml_language/crates/baml_lsp2_actions_tests/test_files/semantic_tokens/enum_member_access.bamlbaml_language/crates/baml_lsp2_actions_tests/test_files/semantic_tokens/exhaustive.bamlbaml_language/crates/baml_lsp2_actions_tests/test_files/semantic_tokens/extends_chain.bamlbaml_language/crates/baml_lsp2_actions_tests/test_files/semantic_tokens/field_alias.bamlbaml_language/crates/baml_lsp2_actions_tests/test_files/semantic_tokens/for_loops.bamlbaml_language/crates/baml_lsp2_actions_tests/test_files/semantic_tokens/function.bamlbaml_language/crates/baml_lsp2_actions_tests/test_files/semantic_tokens/generators.bamlbaml_language/crates/baml_lsp2_actions_tests/test_files/semantic_tokens/generic_field_chain.bamlbaml_language/crates/baml_lsp2_actions_tests/test_files/semantic_tokens/generic_function_call.bamlbaml_language/crates/baml_lsp2_actions_tests/test_files/semantic_tokens/header_comments.bamlbaml_language/crates/baml_lsp2_actions_tests/test_files/semantic_tokens/http_config.bamlbaml_language/crates/baml_lsp2_actions_tests/test_files/semantic_tokens/if_else.bamlbaml_language/crates/baml_lsp2_actions_tests/test_files/semantic_tokens/if_expression.bamlbaml_language/crates/baml_lsp2_actions_tests/test_files/semantic_tokens/if_let_chain.bamlbaml_language/crates/baml_lsp2_actions_tests/test_files/semantic_tokens/implements_for.bamlbaml_language/crates/baml_lsp2_actions_tests/test_files/semantic_tokens/index_access.bamlbaml_language/crates/baml_lsp2_actions_tests/test_files/semantic_tokens/interface_impl.bamlbaml_language/crates/baml_lsp2_actions_tests/test_files/semantic_tokens/interfaces_inferred_generic_type_args.bamlbaml_language/crates/baml_lsp2_actions_tests/test_files/semantic_tokens/interfaces_iter_core.bamlbaml_language/crates/baml_lsp2_actions_tests/test_files/semantic_tokens/interfaces_sort_comparable.bamlbaml_language/crates/baml_lsp2_actions_tests/test_files/semantic_tokens/is_operator.bamlbaml_language/crates/baml_lsp2_actions_tests/test_files/semantic_tokens/iterator.bamlbaml_language/crates/baml_lsp2_actions_tests/test_files/semantic_tokens/jinja_control_prompt.bamlbaml_language/crates/baml_lsp2_actions_tests/test_files/semantic_tokens/json_map_literal.bamlbaml_language/crates/baml_lsp2_actions_tests/test_files/semantic_tokens/json_parse_stringify_intrinsics.bamlbaml_language/crates/baml_lsp2_actions_tests/test_files/semantic_tokens/lambda_advanced.bamlbaml_language/crates/baml_lsp2_actions_tests/test_files/semantic_tokens/literal_types.bamlbaml_language/crates/baml_lsp2_actions_tests/test_files/semantic_tokens/llm_function.bamlbaml_language/crates/baml_lsp2_actions_tests/test_files/semantic_tokens/map_literal_keys.bamlbaml_language/crates/baml_lsp2_actions_tests/test_files/semantic_tokens/map_type_and_methods.bamlbaml_language/crates/baml_lsp2_actions_tests/test_files/semantic_tokens/match_expr.bamlbaml_language/crates/baml_lsp2_actions_tests/test_files/semantic_tokens/match_literal_types.bamlbaml_language/crates/baml_lsp2_actions_tests/test_files/semantic_tokens/method_explicit_type_args.bamlbaml_language/crates/baml_lsp2_actions_tests/test_files/semantic_tokens/multi_segment_path.bamlbaml_language/crates/baml_lsp2_actions_tests/test_files/semantic_tokens/ns_agent_clients.bamlbaml_language/crates/baml_lsp2_actions_tests/test_files/semantic_tokens/ns_ansi.bamlbaml_language/crates/baml_lsp2_actions_tests/test_files/semantic_tokens/ns_game_clients.bamlbaml_language/crates/baml_lsp2_actions_tests/test_files/semantic_tokens/ns_images_pipeline.bamlbaml_language/crates/baml_lsp2_actions_tests/test_files/semantic_tokens/ns_sentiment.bamlbaml_language/crates/baml_lsp2_actions_tests/test_files/semantic_tokens/patterns_new.bamlbaml_language/crates/baml_lsp2_actions_tests/test_files/semantic_tokens/remap_role.bamlbaml_language/crates/baml_lsp2_actions_tests/test_files/semantic_tokens/requires_clause.bamlbaml_language/crates/baml_lsp2_actions_tests/test_files/semantic_tokens/retry_policy_valid_retry.bamlbaml_language/crates/baml_lsp2_actions_tests/test_files/semantic_tokens/self_qualified_call.bamlbaml_language/crates/baml_lsp2_actions_tests/test_files/semantic_tokens/signature_variety.bamlbaml_language/crates/baml_lsp2_actions_tests/test_files/semantic_tokens/stream_llm_inferred_typeargs.bamlbaml_language/crates/baml_lsp2_actions_tests/test_files/semantic_tokens/task_group.bamlbaml_language/crates/baml_lsp2_actions_tests/test_files/semantic_tokens/template_string.bamlbaml_language/crates/baml_lsp2_actions_tests/test_files/semantic_tokens/template_string_calls.bamlbaml_language/crates/baml_lsp2_actions_tests/test_files/semantic_tokens/test_block.bamlbaml_language/crates/baml_lsp2_actions_tests/test_files/semantic_tokens/test_expr_throwing_body.bamlbaml_language/crates/baml_lsp2_actions_tests/test_files/semantic_tokens/testset.bamlbaml_language/crates/baml_lsp2_actions_tests/test_files/semantic_tokens/testset_vibes_nested.bamlbaml_language/crates/baml_lsp2_actions_tests/test_files/semantic_tokens/throws_clause.bamlbaml_language/crates/baml_lsp2_actions_tests/test_files/semantic_tokens/top_level_binding.bamlbaml_language/crates/baml_lsp2_actions_tests/test_files/semantic_tokens/type_alias.bamlbaml_language/crates/baml_lsp2_actions_tests/test_files/semantic_tokens/type_aliases_jinja.bamlbaml_language/crates/baml_lsp2_actions_tests/test_files/semantic_tokens/watch_let.bamlbaml_language/crates/baml_lsp2_actions_tests/test_files/semantic_tokens/while_loop.bamlbaml_language/crates/baml_lsp2_actions_tests/test_files/semantic_tokens/with_keyword.bamlbaml_language/crates/bex_project/src/bex_lsp/multi_project/request.rsbaml_language/crates/tools_semantic_tokens/Cargo.tomlbaml_language/crates/tools_semantic_tokens/README.mdbaml_language/crates/tools_semantic_tokens/src/analysis.rsbaml_language/crates/tools_semantic_tokens/src/index.htmlbaml_language/crates/tools_semantic_tokens/src/main.rsbaml_language/crates/tools_semantic_tokens/src/server.rsbaml_language/crates/tools_semantic_tokens/src/staleness.rs
…oolean literals Move the semantic-tokens classifier toward the rust-analyzer architecture: - scope_resolution_index: a per-ScopeId salsa-cached resolution index (RA's body-granularity memoization) — editing one scope only invalidates that scope's index, not the whole file. build() merges them for a full document; resolve_token_class resolves a single name on demand (RA's Semantics::resolve model), walking the scope chain. - semantic_tokens_in_range: viewport highlighting (RA's highlight_range) — a range-gated walk that skips out-of-range subtrees and resolves on demand, so only the scopes the viewport touches are ever indexed. Proven equal to the full result filtered to the range across every sub-range (new range_tokens_test). - boolean semantic-token type: true/false -> `boolean` (was keyword). The inert KW_TRUE/FALSE/NULL/AS/TYPE token kinds + is_ident_token/is_keyword updates are laid for the principled parser-token remap (deferred: it ripples into hover/formatter/CST snapshots — see tokens/DESIGN.md). - tokens/DESIGN.md + GAPS.md: target RA architecture, prerequisite parser/AST changes, and remaining phases (LSP range/delta wiring, flat traversal, parser-token remap, typed-AST accessors).
…ing) Advertise and implement the range request: convert the LSP range to byte offsets, call semantic_tokens_in_range (on-demand, only resolves the scopes the viewport touches), and delta-encode via a shared encoder factored out of the full handler. Range query proven equal to full-filtered-to-range.
…okens) Advertise Delta + cache the last-sent tokens per file under a monotonic result_id. The delta handler diffs the new token array against the cached one (common prefix/suffix trim at token granularity; offsets scaled by 5 since the LSP stream is 5 u32 per token) and returns just the edits, falling back to the full set on a result_id miss. The full handler now emits a result_id. Diff covered by unit tests (identical/middle/append/truncate).
Replace the recursive Walk::node dispatch with rust-analyzer's flat traverse shape: one preorder_with_tokens() loop (Walk::run) that range-gates each subtree, hands subtree-spanning nodes (strings, comments, type exprs, object literals, generators) to a wholesale handler then skip_subtree, and classifies every other token from its parent kind via the free fn classify_token (rust-analyzer's IdentClass::classify_token model). The stateful cases (type-alias type-kw/name, object-field key, generic-param name) read off typed ast accessors (ObjectField::key, GenericParam::name) instead of positional sibling scanning. Behavior-preserving: all 440 tests pass and the 78 semantic_tokens fixtures are byte-identical.
Make the `as` cast/projection/field-link keyword and the `type` alias / associated-type keyword real tokens (KW_AS / KW_TYPE) instead of bare WORDs, so the semantic-tokens classifier reads them by kind rather than by text. Updates every token-kind consumer (the principled cleanup the remap enables): - ast.rs: TypeAliasDef::name no longer skips a leading `type` WORD (it's KW_TYPE now); the five `(WORD && text=="as")` checks read KW_AS. - baml_fmt: add TypeKw / As keyword tokens; TypeAliasDecl + AssociatedTypeDecl `keyword` and InterfaceFieldLink + AssociatedProjectionType `as_token` fields read them (drops the "type is just a WORD" workaround). - lsp classifier: `as` classifies via is_keyword (the text-match arm is gone); classify_type_decl_word detects KW_TYPE for the decl-vs-binding distinction. - 28 parser CST snapshots regenerated — purely mechanical WORD -> KW_AS/KW_TYPE (the meta-type value `type` correctly stays WORD). Validated: compiler2_ast 73/73, lsp 440/440, baml_tests 2661/2665 (the 4 generic_arg_soundness failures are pre-existing WIP red tests for a known TIR generics gap, confirmed failing on base too).
Make the boolean and null literals real tokens instead of bare WORDs, so the semantic-tokens classifier reads them by kind (the last text-match in the classifier's value-literal path is now backed by a real token). Updates the token-kind consumers the remap touches: - ast.rs: the block tail-expression accessor accepts KW_TRUE/FALSE/NULL (a trailing `false`/`true`/`null` is the block's value — without this a bool-returning function tripped E0029 "missing return value"). - baml_fmt: a KeywordLiteral token (spanning the three kinds) + a Literal::Keyword variant; Expression::from_cst routes the bare literal tokens to it (they were formatted as bare-WORD Paths before). - 39 parser CST snapshots regenerated — purely mechanical WORD -> KW_*. Validated: lsp 440/440, compiler2_ast 73/73, baml_tests 2661/2665 (the 4 generic_arg_soundness failures are pre-existing, fail on base).
Value-position literals are now KW_TRUE/KW_FALSE/KW_NULL (classified by kind) and type-position ones go through type_run, so the transitional WORD text match in token() is unreachable. The classifier no longer text-matches any literal.
Contributor
There was a problem hiding this comment.
Actionable comments posted: 2
🧹 Nitpick comments (1)
baml_language/crates/baml_lsp2_actions_tests/src/range_tokens_test.rs (1)
39-49: 📐 Maintainability & Code Quality | 🔵 Trivial | ⚡ Quick winExercise the new keyword remaps in this parity fixture.
This sample never emits
as,type,true,false, ornull, so the range/full equivalence check still skips several token kinds this PR reclassified. Adding one cast plus one boolean/null literal here would make the new range path much harder to regress.🤖 Prompt for AI Agents
Verify each finding against current code. Fix only still-valid issues, skip the rest with a brief reason, keep changes minimal, and validate. In `@baml_language/crates/baml_lsp2_actions_tests/src/range_tokens_test.rs` around lines 39 - 49, The parity fixture in range_equals_filtered_full still does not exercise the newly remapped keywords, so update the sample used by check to include at least one cast and boolean/null literals. Use the range_tokens_test::range_equals_filtered_full test and the existing sample block to add expressions that emit as, type, true, false, or null so the range/full token comparison covers the reclassified token kinds.
🤖 Prompt for all review comments with AI agents
Verify each finding against current code. Fix only still-valid issues, skip the
rest with a brief reason, keep changes minimal, and validate.
Inline comments:
In `@baml_language/crates/baml_compiler_syntax/src/ast.rs`:
- Around line 197-203: ObjectField::key() is only accepting SyntaxKind::WORD, so
it misses valid keys tokenized as KW_CLIENT. Update the key() accessor in ast.rs
to recognize KW_CLIENT alongside WORD when extracting the first non-trivia token
from self.syntax, so object fields named client are returned correctly and
downstream consumers can see them.
In `@baml_language/crates/baml_lsp2_actions/src/tokens/index.rs`:
- Around line 61-65: `resolve_token_class()` is caching on the raw
`scope_at_offset()` scope id, which can differ for sibling nested scopes that
still map to the same owning body. Update the memoization key to use the
inference owner scope returned by `scope_resolution_index()`/`scope_body(...)`
(the owning Function/Lambda/Let body) so identical ranges share one Salsa entry.
Keep the lookup flow in `resolve_token_class()` and `scope_resolution_index()`
aligned, and ensure any cache access in the range path uses the normalized owner
scope rather than the original scope id.
---
Nitpick comments:
In `@baml_language/crates/baml_lsp2_actions_tests/src/range_tokens_test.rs`:
- Around line 39-49: The parity fixture in range_equals_filtered_full still does
not exercise the newly remapped keywords, so update the sample used by check to
include at least one cast and boolean/null literals. Use the
range_tokens_test::range_equals_filtered_full test and the existing sample block
to add expressions that emit as, type, true, false, or null so the range/full
token comparison covers the reclassified token kinds.
🪄 Autofix (Beta)
Fix all unresolved CodeRabbit comments on this PR:
- Push a commit to this branch (recommended)
- Create a new PR with the fixes
ℹ️ Review info
⚙️ Run configuration
Configuration used: Repository UI
Review profile: CHILL
Plan: Pro
Run ID: 3de4b39f-568d-4701-b741-8daacf8f9631
⛔ Files ignored due to path filters (61)
baml_language/crates/baml_tests/snapshots/broken_syntax/optional_parameter_defaults/baml_tests__broken_syntax__optional_parameter_defaults__02_parser__function_type_defaults.snapis excluded by!**/*.snapbaml_language/crates/baml_tests/snapshots/broken_syntax/pending_greaters_fix/baml_tests__broken_syntax__pending_greaters_fix__02_parser__extra_greater.snapis excluded by!**/*.snapbaml_language/crates/baml_tests/snapshots/broken_syntax/test_invalid_contexts/baml_tests__broken_syntax__test_invalid_contexts__02_parser__main.snapis excluded by!**/*.snapbaml_language/crates/baml_tests/snapshots/broken_syntax/type_annotation_errors/baml_tests__broken_syntax__type_annotation_errors__02_parser__type_malformed.snapis excluded by!**/*.snapbaml_language/crates/baml_tests/snapshots/compiles/config_dictionary/baml_tests__compiles__config_dictionary__02_parser__valid_dictionary.snapis excluded by!**/*.snapbaml_language/crates/baml_tests/snapshots/compiles/json_alias_basic/baml_tests__compiles__json_alias_basic__02_parser__json_alias_basic.snapis excluded by!**/*.snapbaml_language/crates/baml_tests/snapshots/compiles/json_map_literal/baml_tests__compiles__json_map_literal__02_parser__json_map_literal.snapis excluded by!**/*.snapbaml_language/crates/baml_tests/snapshots/compiles/lambda_advanced/baml_tests__compiles__lambda_advanced__02_parser__lambda_advanced.snapis excluded by!**/*.snapbaml_language/crates/baml_tests/snapshots/compiles/lexical_scoping/baml_tests__compiles__lexical_scoping__02_parser__lexical_scoping.snapis excluded by!**/*.snapbaml_language/crates/baml_tests/snapshots/compiles/literal_union_arithmetic/baml_tests__compiles__literal_union_arithmetic__02_parser__main.snapis excluded by!**/*.snapbaml_language/crates/baml_tests/snapshots/compiles/method_explicit_type_args/baml_tests__compiles__method_explicit_type_args__02_parser__method_explicit_type_args.snapis excluded by!**/*.snapbaml_language/crates/baml_tests/snapshots/compiles/namespaces_type_resolution/baml_tests__compiles__namespaces_type_resolution__02_parser__main.snapis excluded by!**/*.snapbaml_language/crates/baml_tests/snapshots/compiles/namespaces_type_resolution/baml_tests__compiles__namespaces_type_resolution__02_parser__ns_auth_auth.snapis excluded by!**/*.snapbaml_language/crates/baml_tests/snapshots/compiles/namespaces_type_resolution/baml_tests__compiles__namespaces_type_resolution__02_parser__ns_llm_models.snapis excluded by!**/*.snapbaml_language/crates/baml_tests/snapshots/compiles/optional_function_parameters/baml_tests__compiles__optional_function_parameters__02_parser__main.snapis excluded by!**/*.snapbaml_language/crates/baml_tests/snapshots/compiles/parser_expressions/baml_tests__compiles__parser_expressions__02_parser__precedence.snapis excluded by!**/*.snapbaml_language/crates/baml_tests/snapshots/compiles/parser_statements/baml_tests__compiles__parser_statements__02_parser__break_continue.snapis excluded by!**/*.snapbaml_language/crates/baml_tests/snapshots/compiles/patterns_new/baml_tests__compiles__patterns_new__02_parser__patterns_new.snapis excluded by!**/*.snapbaml_language/crates/baml_tests/snapshots/compiles/stream_crossfile/baml_tests__compiles__stream_crossfile__02_parser__file_a.snapis excluded by!**/*.snapbaml_language/crates/baml_tests/snapshots/compiles/test_expr_name_concat/baml_tests__compiles__test_expr_name_concat__02_parser__main.snapis excluded by!**/*.snapbaml_language/crates/baml_tests/snapshots/compiles/test_raw_string_name/baml_tests__compiles__test_raw_string_name__02_parser__main.snapis excluded by!**/*.snapbaml_language/crates/baml_tests/snapshots/compiles/testset_basic/baml_tests__compiles__testset_basic__02_parser__main.snapis excluded by!**/*.snapbaml_language/crates/baml_tests/snapshots/compiles/testset_dynamic/baml_tests__compiles__testset_dynamic__02_parser__main.snapis excluded by!**/*.snapbaml_language/crates/baml_tests/snapshots/compiles/testset_nested/baml_tests__compiles__testset_nested__02_parser__main.snapis excluded by!**/*.snapbaml_language/crates/baml_tests/snapshots/compiles/type_annotation/baml_tests__compiles__type_annotation__02_parser__type_alias_interaction.snapis excluded by!**/*.snapbaml_language/crates/baml_tests/snapshots/compiles/type_annotation/baml_tests__compiles__type_annotation__02_parser__type_positions.snapis excluded by!**/*.snapbaml_language/crates/baml_tests/snapshots/compiles/type_builder_test/baml_tests__compiles__type_builder_test__02_parser__test.snapis excluded by!**/*.snapbaml_language/crates/baml_tests/snapshots/diagnostic_errors/attr_disambiguation/baml_tests__diagnostic_errors__attr_disambiguation__02_parser__non_field.snapis excluded by!**/*.snapbaml_language/crates/baml_tests/snapshots/diagnostic_errors/backtick_strict_types/baml_tests__diagnostic_errors__backtick_strict_types__02_parser__main.snapis excluded by!**/*.snapbaml_language/crates/baml_tests/snapshots/diagnostic_errors/basic_types/baml_tests__diagnostic_errors__basic_types__02_parser__types.snapis excluded by!**/*.snapbaml_language/crates/baml_tests/snapshots/diagnostic_errors/builtin_io/baml_tests__diagnostic_errors__builtin_io__02_parser__io_ops.snapis excluded by!**/*.snapbaml_language/crates/baml_tests/snapshots/diagnostic_errors/builtin_io/baml_tests__diagnostic_errors__builtin_io__02_parser__shell_ops.snapis excluded by!**/*.snapbaml_language/crates/baml_tests/snapshots/diagnostic_errors/catch_return_type_mismatch/baml_tests__diagnostic_errors__catch_return_type_mismatch__02_parser__catch_return_type_mismatch.snapis excluded by!**/*.snapbaml_language/crates/baml_tests/snapshots/diagnostic_errors/duplicate_class_span/baml_tests__diagnostic_errors__duplicate_class_span__02_parser__repro.snapis excluded by!**/*.snapbaml_language/crates/baml_tests/snapshots/diagnostic_errors/format_checks/baml_tests__diagnostic_errors__format_checks__02_parser__binary_expr.snapis excluded by!**/*.snapbaml_language/crates/baml_tests/snapshots/diagnostic_errors/format_checks/baml_tests__diagnostic_errors__format_checks__02_parser__config_decls.snapis excluded by!**/*.snapbaml_language/crates/baml_tests/snapshots/diagnostic_errors/format_checks/baml_tests__diagnostic_errors__format_checks__02_parser__loop_stmts.snapis excluded by!**/*.snapbaml_language/crates/baml_tests/snapshots/diagnostic_errors/format_checks/baml_tests__diagnostic_errors__format_checks__02_parser__match_exprs.snapis excluded by!**/*.snapbaml_language/crates/baml_tests/snapshots/diagnostic_errors/format_checks/baml_tests__diagnostic_errors__format_checks__02_parser__other_exprs.snapis excluded by!**/*.snapbaml_language/crates/baml_tests/snapshots/diagnostic_errors/format_checks/baml_tests__diagnostic_errors__format_checks__02_parser__type_alias_decls.snapis excluded by!**/*.snapbaml_language/crates/baml_tests/snapshots/diagnostic_errors/function_type_throws/baml_tests__diagnostic_errors__function_type_throws__02_parser__negative.snapis excluded by!**/*.snapbaml_language/crates/baml_tests/snapshots/diagnostic_errors/function_types/baml_tests__diagnostic_errors__function_types__02_parser__function_types.snapis excluded by!**/*.snapbaml_language/crates/baml_tests/snapshots/diagnostic_errors/generics/baml_tests__diagnostic_errors__generics__02_parser__classes.snapis excluded by!**/*.snapbaml_language/crates/baml_tests/snapshots/diagnostic_errors/headers_edge_cases/baml_tests__diagnostic_errors__headers_edge_cases__02_parser__edge_cases.snapis excluded by!**/*.snapbaml_language/crates/baml_tests/snapshots/diagnostic_errors/match_exhaustiveness/baml_tests__diagnostic_errors__match_exhaustiveness__02_parser__match_exhaustiveness.snapis excluded by!**/*.snapbaml_language/crates/baml_tests/snapshots/diagnostic_errors/null_handling/baml_tests__diagnostic_errors__null_handling__02_parser__null_handling.snapis excluded by!**/*.snapbaml_language/crates/baml_tests/snapshots/diagnostic_errors/optional_parameter_defaults/baml_tests__diagnostic_errors__optional_parameter_defaults__02_parser__unsupported_contexts.snapis excluded by!**/*.snapbaml_language/crates/baml_tests/snapshots/diagnostic_errors/parser_constructors/baml_tests__diagnostic_errors__parser_constructors__02_parser__array_constructor.snapis excluded by!**/*.snapbaml_language/crates/baml_tests/snapshots/diagnostic_errors/parser_constructors/baml_tests__diagnostic_errors__parser_constructors__02_parser__map_constructor.snapis excluded by!**/*.snapbaml_language/crates/baml_tests/snapshots/diagnostic_errors/stream_types/baml_tests__diagnostic_errors__stream_types__02_parser__complex.snapis excluded by!**/*.snapbaml_language/crates/baml_tests/snapshots/diagnostic_errors/stream_types/baml_tests__diagnostic_errors__stream_types__02_parser__main.snapis excluded by!**/*.snapbaml_language/crates/baml_tests/snapshots/diagnostic_errors/stream_types/baml_tests__diagnostic_errors__stream_types__02_parser__ns_foo_with_top_level_refs.snapis excluded by!**/*.snapbaml_language/crates/baml_tests/snapshots/diagnostic_errors/test_expr_name_type_error/baml_tests__diagnostic_errors__test_expr_name_type_error__02_parser__main.snapis excluded by!**/*.snapbaml_language/crates/baml_tests/snapshots/diagnostic_errors/test_expr_wrong_runner/baml_tests__diagnostic_errors__test_expr_wrong_runner__02_parser__main.snapis excluded by!**/*.snapbaml_language/crates/baml_tests/snapshots/diagnostic_errors/test_with_runner_ambiguity/baml_tests__diagnostic_errors__test_with_runner_ambiguity__02_parser__main.snapis excluded by!**/*.snapbaml_language/crates/baml_tests/snapshots/diagnostic_errors/type_aliases/baml_tests__diagnostic_errors__type_aliases__02_parser__type_aliases.snapis excluded by!**/*.snapbaml_language/crates/baml_tests/snapshots/diagnostic_errors/type_aliases/baml_tests__diagnostic_errors__type_aliases__02_parser__type_aliases_json.snapis excluded by!**/*.snapbaml_language/crates/baml_tests/snapshots/diagnostic_errors/unknown_type_error/baml_tests__diagnostic_errors__unknown_type_error__02_parser__unknown_type_error.snapis excluded by!**/*.snapbaml_language/crates/baml_tests/snapshots/diagnostic_errors/void_return_type/baml_tests__diagnostic_errors__void_return_type__02_parser__function_type_throws.snapis excluded by!**/*.snapbaml_language/crates/baml_tests/snapshots/diagnostic_errors/void_return_type/baml_tests__diagnostic_errors__void_return_type__02_parser__void_function_type.snapis excluded by!**/*.snapbaml_language/crates/baml_tests/snapshots/diagnostic_errors/void_return_type/baml_tests__diagnostic_errors__void_return_type__02_parser__void_type_position_errors.snapis excluded by!**/*.snap
📒 Files selected for processing (23)
baml_language/crates/baml_cli/src/paint.rsbaml_language/crates/baml_compiler2_ast/src/lower_expr_body.rsbaml_language/crates/baml_compiler_parser/src/parser.rsbaml_language/crates/baml_compiler_syntax/src/ast.rsbaml_language/crates/baml_compiler_syntax/src/syntax_kind.rsbaml_language/crates/baml_fmt/src/ast/declarations.rsbaml_language/crates/baml_fmt/src/ast/expressions.rsbaml_language/crates/baml_fmt/src/ast/tokens.rsbaml_language/crates/baml_fmt/src/ast/types.rsbaml_language/crates/baml_lsp2_actions/src/tokens.rsbaml_language/crates/baml_lsp2_actions/src/tokens/DESIGN.mdbaml_language/crates/baml_lsp2_actions/src/tokens/index.rsbaml_language/crates/baml_lsp2_actions_tests/src/lib.rsbaml_language/crates/baml_lsp2_actions_tests/src/range_tokens_test.rsbaml_language/crates/baml_lsp2_actions_tests/test_files/semantic_tokens/break_continue.bamlbaml_language/crates/baml_lsp2_actions_tests/test_files/semantic_tokens/cancel_token.bamlbaml_language/crates/baml_lsp2_actions_tests/test_files/semantic_tokens/config_dictionary.bamlbaml_language/crates/baml_lsp2_actions_tests/test_files/semantic_tokens/interfaces_inferred_generic_type_args.bamlbaml_language/crates/baml_lsp2_actions_tests/test_files/semantic_tokens/interfaces_iter_core.bamlbaml_language/crates/baml_lsp2_actions_tests/test_files/semantic_tokens/interfaces_sort_comparable.bamlbaml_language/crates/baml_lsp2_actions_tests/test_files/semantic_tokens/watch_let.bamlbaml_language/crates/bex_project/src/bex_lsp/multi_project/mod.rsbaml_language/crates/bex_project/src/bex_lsp/multi_project/request.rs
✅ Files skipped from review due to trivial changes (1)
- baml_language/crates/baml_lsp2_actions/src/tokens/DESIGN.md
🚧 Files skipped from review as they are similar to previous changes (8)
- baml_language/crates/baml_cli/src/paint.rs
- baml_language/crates/baml_lsp2_actions_tests/test_files/semantic_tokens/cancel_token.baml
- baml_language/crates/baml_lsp2_actions_tests/test_files/semantic_tokens/break_continue.baml
- baml_language/crates/baml_lsp2_actions_tests/test_files/semantic_tokens/config_dictionary.baml
- baml_language/crates/baml_compiler_syntax/src/syntax_kind.rs
- baml_language/crates/baml_lsp2_actions_tests/test_files/semantic_tokens/watch_let.baml
- baml_language/crates/baml_lsp2_actions_tests/test_files/semantic_tokens/interfaces_sort_comparable.baml
- baml_language/crates/baml_lsp2_actions/src/tokens.rs
- enum-variant (`Enum.Variant` patterns) and interface-field-link (`name as display_name`) resolve through the same package-resolution system as namespace/item lookup (resolve_enum_variant, resolve_field), verified against the type's actual variants/fields - builtin namespaces flagged defaultLibrary; primitives unified; named/ optional call args, bigint literals, and catch bindings classified - typing-robustness tests (never panic on incomplete/mid-edit input): curated + nested-scope always-run; full-fixture sweep #[ignore]d - parser: find_token_after_hashes returns None at EOF, fixing two index-out-of-bounds panics on incomplete raw strings
Contributor
There was a problem hiding this comment.
Actionable comments posted: 2
🤖 Prompt for all review comments with AI agents
Verify each finding against current code. Fix only still-valid issues, skip the
rest with a brief reason, keep changes minimal, and validate.
Inline comments:
In `@baml_language/crates/baml_lsp2_actions/src/completions.rs`:
- Around line 1319-1321: The `DefinitionSite::CatchBinding(_)` handling is still
incomplete in local-type consumers, so hover/type display can disagree with
completions. Update the `type_info.rs` logic that currently returns `"unknown"`
for `DefinitionSite::CatchBinding(_)` to resolve the catch binding type the same
way as `completions.rs` does, likely by reusing `find_binding_ty_for_local` or
the shared local-type lookup path used for `PatternBinding` and `CatchBinding`
in `find_binding_ty_for_local`/`DefinitionSite` matching.
In `@baml_language/crates/baml_lsp2_actions/src/tokens/classify.rs`:
- Around line 17-45: The builtin type allowlist in classify_primitive is
incomplete, so add the missing primitive names to PRIMITIVE_TYPES. Update the
PRIMITIVE_TYPES list in classify.rs to include void and type so
classify_primitive continues returning SemanticTokenType::Type with
ModifierSet::DEFAULT_LIBRARY for all builtin types.
🪄 Autofix (Beta)
Fix all unresolved CodeRabbit comments on this PR:
- Push a commit to this branch (recommended)
- Create a new PR with the fixes
ℹ️ Review info
⚙️ Run configuration
Configuration used: Repository UI
Review profile: CHILL
Plan: Pro
Run ID: 81e11b9c-3521-4821-96bc-4475180189f8
📒 Files selected for processing (39)
baml_language/crates/baml_compiler2_hir/src/builder.rsbaml_language/crates/baml_compiler2_hir/src/semantic_index.rsbaml_language/crates/baml_compiler2_mir/src/lower.rsbaml_language/crates/baml_compiler2_tir/src/resolve.rsbaml_language/crates/baml_compiler_parser/src/parser.rsbaml_language/crates/baml_compiler_syntax/src/ast.rsbaml_language/crates/baml_lsp2_actions/src/completions.rsbaml_language/crates/baml_lsp2_actions/src/definition.rsbaml_language/crates/baml_lsp2_actions/src/describe.rsbaml_language/crates/baml_lsp2_actions/src/tokens.rsbaml_language/crates/baml_lsp2_actions/src/tokens/classify.rsbaml_language/crates/baml_lsp2_actions/src/tokens/index.rsbaml_language/crates/baml_lsp2_actions/src/type_info.rsbaml_language/crates/baml_lsp2_actions_tests/src/lib.rsbaml_language/crates/baml_lsp2_actions_tests/src/range_tokens_test.rsbaml_language/crates/baml_lsp2_actions_tests/src/typing_robustness_test.rsbaml_language/crates/baml_lsp2_actions_tests/test_files/semantic_tokens/bigint_literals.bamlbaml_language/crates/baml_lsp2_actions_tests/test_files/semantic_tokens/call_named_args.bamlbaml_language/crates/baml_lsp2_actions_tests/test_files/semantic_tokens/cancel_token.bamlbaml_language/crates/baml_lsp2_actions_tests/test_files/semantic_tokens/catch_all_keyword.bamlbaml_language/crates/baml_lsp2_actions_tests/test_files/semantic_tokens/catch_param.bamlbaml_language/crates/baml_lsp2_actions_tests/test_files/semantic_tokens/catch_throw.bamlbaml_language/crates/baml_lsp2_actions_tests/test_files/semantic_tokens/exhaustive.bamlbaml_language/crates/baml_lsp2_actions_tests/test_files/semantic_tokens/field_alias.bamlbaml_language/crates/baml_lsp2_actions_tests/test_files/semantic_tokens/interfaces_inferred_generic_type_args.bamlbaml_language/crates/baml_lsp2_actions_tests/test_files/semantic_tokens/interfaces_sort_comparable.bamlbaml_language/crates/baml_lsp2_actions_tests/test_files/semantic_tokens/iterator.bamlbaml_language/crates/baml_lsp2_actions_tests/test_files/semantic_tokens/json_parse_stringify_intrinsics.bamlbaml_language/crates/baml_lsp2_actions_tests/test_files/semantic_tokens/ns_ansi.bamlbaml_language/crates/baml_lsp2_actions_tests/test_files/semantic_tokens/ns_game_clients.bamlbaml_language/crates/baml_lsp2_actions_tests/test_files/semantic_tokens/patterns_new.bamlbaml_language/crates/baml_lsp2_actions_tests/test_files/semantic_tokens/stream_llm_inferred_typeargs.bamlbaml_language/crates/baml_lsp2_actions_tests/test_files/semantic_tokens/task_group.bamlbaml_language/crates/baml_lsp2_actions_tests/test_files/semantic_tokens/testset.bamlbaml_language/crates/baml_lsp2_actions_tests/test_files/semantic_tokens/testset_vibes_nested.bamlbaml_language/crates/baml_lsp2_actions_tests/test_files/semantic_tokens/with_keyword.bamlbaml_language/crates/bex_project/src/bex_lsp/multi_project/request.rsbaml_language/crates/tools_semantic_tokens/src/server.rsbaml_language/crates/tools_semantic_tokens/src/staleness.rs
✅ Files skipped from review due to trivial changes (1)
- baml_language/crates/baml_lsp2_actions_tests/src/lib.rs
🚧 Files skipped from review as they are similar to previous changes (25)
- baml_language/crates/baml_lsp2_actions_tests/test_files/semantic_tokens/testset.baml
- baml_language/crates/baml_lsp2_actions_tests/src/range_tokens_test.rs
- baml_language/crates/baml_lsp2_actions_tests/test_files/semantic_tokens/field_alias.baml
- baml_language/crates/baml_lsp2_actions_tests/test_files/semantic_tokens/catch_throw.baml
- baml_language/crates/baml_lsp2_actions_tests/test_files/semantic_tokens/json_parse_stringify_intrinsics.baml
- baml_language/crates/baml_lsp2_actions_tests/test_files/semantic_tokens/testset_vibes_nested.baml
- baml_language/crates/baml_lsp2_actions_tests/test_files/semantic_tokens/with_keyword.baml
- baml_language/crates/baml_lsp2_actions_tests/test_files/semantic_tokens/catch_all_keyword.baml
- baml_language/crates/baml_lsp2_actions/src/definition.rs
- baml_language/crates/baml_lsp2_actions_tests/test_files/semantic_tokens/iterator.baml
- baml_language/crates/baml_lsp2_actions_tests/test_files/semantic_tokens/task_group.baml
- baml_language/crates/baml_lsp2_actions_tests/test_files/semantic_tokens/stream_llm_inferred_typeargs.baml
- baml_language/crates/baml_lsp2_actions_tests/test_files/semantic_tokens/ns_ansi.baml
- baml_language/crates/baml_lsp2_actions/src/tokens/index.rs
- baml_language/crates/baml_lsp2_actions_tests/test_files/semantic_tokens/exhaustive.baml
- baml_language/crates/baml_lsp2_actions_tests/test_files/semantic_tokens/ns_game_clients.baml
- baml_language/crates/baml_lsp2_actions_tests/test_files/semantic_tokens/cancel_token.baml
- baml_language/crates/tools_semantic_tokens/src/server.rs
- baml_language/crates/bex_project/src/bex_lsp/multi_project/request.rs
- baml_language/crates/baml_lsp2_actions_tests/test_files/semantic_tokens/interfaces_sort_comparable.baml
- baml_language/crates/baml_compiler_syntax/src/ast.rs
- baml_language/crates/tools_semantic_tokens/src/staleness.rs
- baml_language/crates/baml_compiler2_mir/src/lower.rs
- baml_language/crates/baml_lsp2_actions_tests/test_files/semantic_tokens/patterns_new.baml
- baml_language/crates/baml_lsp2_actions/src/tokens.rs
- builder.rs (tir): drop redundant InterfaceMethod resolution that is always clobbered by InterfaceDefaultMethod in the same iteration - ast.rs: ObjectField::key() accepts KW_CLIENT (client-named object fields) - definition.rs + item_tree/builder (hir): interface member go-to-def jumps to the member, not the interface header (interface field/method span plumbing mirroring the class-field/enum-variant pattern) + regression tests - tokens/index.rs: normalize the range-path resolution cache key to the inference-owner scope so sibling block/template scopes share one entry - viewer (tools_semantic_tokens): surface fixture load failures instead of empty results; count text-only snapshot drift as a diff; escape fixture names in HTML attributes; discard stale /api/tokens responses; clear state on load failure; re-enable Accept after a failed save; clamp port scan to u16::MAX; reject symlinked fixtures; watch the compiler crates - requires_clause fixture: exercise the transitive requires-chain member Skipped 5 stale/incorrect comments (classifier emits no token for the cited positions, or the flagged sections are genuine auto-generated output).
Contributor
There was a problem hiding this comment.
Actionable comments posted: 1
♻️ Duplicate comments (1)
baml_language/crates/tools_semantic_tokens/src/index.html (1)
498-498: 🎯 Functional Correctness | 🟡 Minor | ⚡ Quick winDon't overwrite the Accept state with
selected === SCRATCH.Line 498 clobbers the state that
select()/fixture rendering just computed. That can re-enable Accept after the load-failure path at Lines 463-472, and after a successful accept it can turn the button back on even when the refreshed fixture has no diffs.Suggested fix
} finally { - acceptEl.disabled = selected === SCRATCH; + acceptEl.disabled = + selected === SCRATCH || !detail || detail.diff_count === 0; }🤖 Prompt for AI Agents
Verify each finding against current code. Fix only still-valid issues, skip the rest with a brief reason, keep changes minimal, and validate. In `@baml_language/crates/tools_semantic_tokens/src/index.html` at line 498, The Accept button state in the fixture rendering flow is being overwritten by the `selected === SCRATCH` assignment, which clobbers the state already computed by `select()` and the load-failure handling. Update the logic around `select()`, the fixture rendering path, and the `acceptEl` state update so `acceptEl.disabled` reflects the real computed acceptability instead of being reset based on `SCRATCH`; keep the existing failure and post-accept refresh behavior intact.
🤖 Prompt for all review comments with AI agents
Verify each finding against current code. Fix only still-valid issues, skip the
rest with a brief reason, keep changes minimal, and validate.
Inline comments:
In `@baml_language/crates/baml_lsp2_actions/src/definition_at_tests.rs`:
- Around line 459-461: The definition-at tests are too permissive because
snippets like "-> fullname" and "-> encode" can match both the interface
declaration and other locations such as alias entries or impl methods. Update
the assertions in definition_at_tests to verify a unique target location/snippet
for each case, using the existing test helpers and descriptions around the
fullname and encode checks, so the tests only pass when navigation lands on the
interface declaration itself and not the impl site.
---
Duplicate comments:
In `@baml_language/crates/tools_semantic_tokens/src/index.html`:
- Line 498: The Accept button state in the fixture rendering flow is being
overwritten by the `selected === SCRATCH` assignment, which clobbers the state
already computed by `select()` and the load-failure handling. Update the logic
around `select()`, the fixture rendering path, and the `acceptEl` state update
so `acceptEl.disabled` reflects the real computed acceptability instead of being
reset based on `SCRATCH`; keep the existing failure and post-accept refresh
behavior intact.
🪄 Autofix (Beta)
Fix all unresolved CodeRabbit comments on this PR:
- Push a commit to this branch (recommended)
- Create a new PR with the fixes
ℹ️ Review info
⚙️ Run configuration
Configuration used: Repository UI
Review profile: CHILL
Plan: Pro
Run ID: b12c1d8f-fe97-4f01-bc94-68cbb9e92ef1
📒 Files selected for processing (14)
baml_language/crates/baml_compiler2_hir/src/builder.rsbaml_language/crates/baml_compiler2_hir/src/item_tree.rsbaml_language/crates/baml_compiler2_tir/src/builder.rsbaml_language/crates/baml_compiler2_tir/src/inference.rsbaml_language/crates/baml_compiler_syntax/src/ast.rsbaml_language/crates/baml_lsp2_actions/src/definition.rsbaml_language/crates/baml_lsp2_actions/src/definition_at_tests.rsbaml_language/crates/baml_lsp2_actions/src/tokens/index.rsbaml_language/crates/baml_lsp2_actions_tests/test_files/semantic_tokens/requires_clause.bamlbaml_language/crates/tools_semantic_tokens/src/analysis.rsbaml_language/crates/tools_semantic_tokens/src/index.htmlbaml_language/crates/tools_semantic_tokens/src/main.rsbaml_language/crates/tools_semantic_tokens/src/server.rsbaml_language/crates/tools_semantic_tokens/src/staleness.rs
💤 Files with no reviewable changes (1)
- baml_language/crates/baml_compiler2_tir/src/builder.rs
🚧 Files skipped from review as they are similar to previous changes (9)
- baml_language/crates/baml_lsp2_actions/src/definition.rs
- baml_language/crates/tools_semantic_tokens/src/main.rs
- baml_language/crates/tools_semantic_tokens/src/staleness.rs
- baml_language/crates/baml_compiler2_tir/src/inference.rs
- baml_language/crates/baml_lsp2_actions_tests/test_files/semantic_tokens/requires_clause.baml
- baml_language/crates/baml_lsp2_actions/src/tokens/index.rs
- baml_language/crates/tools_semantic_tokens/src/server.rs
- baml_language/crates/tools_semantic_tokens/src/analysis.rs
- baml_language/crates/baml_compiler_syntax/src/ast.rs
Resolved the semantic_tokens fixture conflicts by regenerating their snapshot blocks (//- sections only; fixture sources were identical on both sides). Post-merge suite green (745 passed).
⏭️ Performance benchmarks were skippedPerf benchmarks (CodSpeed) are opt-in on pull requests — they no longer run on every push. They always run automatically after merge to To run them on this PR, do any of the following, then push a commit (or re-run CI):
|
Binary size checks passed✅ 7 passed
Generated by |
Latest canary (catch/match-arm `return` support, #3881). Clean merge with no conflicts; workspace compiles and 750 affected-crate tests pass.
- classify.rs: add `void` to PRIMITIVE_TYPES so it highlights as a defaultLibrary builtin type like the other primitives (`type` is the KW_TYPE keyword, not a builtin type, so it is intentionally not added) - type_info.rs: resolve catch/pattern binding types in hover via the shared inference lookup (was always "unknown"), so hover agrees with completions - definition_at_tests.rs: assert the exact interface-declaration location (3:3 / 3:12) so the go-to-def tests can't pass on the alias/impl site - regenerate ns_game_clients, test_expr_throwing_body (void) and the hover_catch_binding fixture (resolved error-union type)
- stow.toml: approve `semantic` prefix for the tools namespace
- Cargo.toml: register baml_lsp2_actions_tests as a workspace dependency;
tools_semantic_tokens uses `{ workspace = true }` (stow validation)
- tokens.rs: fix two public->private intra-doc links so `cargo doc`
passes under `-D warnings`
- tokens.rs: classify value-position `null` through the shared builtin
classification (defaultLibrary `type`) so it matches its type position
and every other builtin instead of reading as a keyword
- regenerate semantic_tokens fixtures for the null change
DESIGN.md and GAPS.md were working notes for the semantic-tokens rework. validate-markdown only allows README.md or whitelisted long-term docs, so drop them rather than whitelist throwaway notes.
Contributor
There was a problem hiding this comment.
Actionable comments posted: 1
🤖 Prompt for all review comments with AI agents
Verify each finding against current code. Fix only still-valid issues, skip the
rest with a brief reason, keep changes minimal, and validate.
Inline comments:
In `@baml_language/crates/baml_lsp2_actions/src/type_info.rs`:
- Around line 708-717: The binding-type lookup in type_info.rs is starting from
the enclosing function scope via infer_scope_types, which can return a
same-index PatId from the wrong body before the nested scope is checked. Update
the hover/type resolution logic in the binding-type lookup path to prefer
find_binding_ty_in_scopes(db, index, scope_id, pat_id) as the primary source and
avoid using func_scope_id-first probing for body-local pattern/catch bindings.
Keep the existing display_local_binding_ty formatting, but ensure the lookup
follows the current scope chain so closures and nested blocks resolve the
correct binding type.
🪄 Autofix (Beta)
Fix all unresolved CodeRabbit comments on this PR:
- Push a commit to this branch (recommended)
- Create a new PR with the fixes
ℹ️ Review info
⚙️ Run configuration
Configuration used: Repository UI
Review profile: CHILL
Plan: Pro
Run ID: 2fa702f1-64ea-4318-a5c2-102218f8b5a5
📒 Files selected for processing (23)
baml_language/Cargo.tomlbaml_language/crates/baml_compiler2_ast/src/lower_expr_body.rsbaml_language/crates/baml_compiler2_hir/src/builder.rsbaml_language/crates/baml_compiler2_mir/src/lower.rsbaml_language/crates/baml_compiler2_tir/src/builder.rsbaml_language/crates/baml_compiler_parser/src/parser.rsbaml_language/crates/baml_compiler_syntax/src/ast.rsbaml_language/crates/baml_compiler_syntax/src/syntax_kind.rsbaml_language/crates/baml_fmt/src/ast/expressions.rsbaml_language/crates/baml_lsp2_actions/src/definition_at_tests.rsbaml_language/crates/baml_lsp2_actions/src/tokens.rsbaml_language/crates/baml_lsp2_actions/src/tokens/classify.rsbaml_language/crates/baml_lsp2_actions/src/type_info.rsbaml_language/crates/baml_lsp2_actions_tests/test_files/semantic_tokens/interfaces_iter_core.bamlbaml_language/crates/baml_lsp2_actions_tests/test_files/semantic_tokens/interfaces_sort_comparable.bamlbaml_language/crates/baml_lsp2_actions_tests/test_files/semantic_tokens/json_map_literal.bamlbaml_language/crates/baml_lsp2_actions_tests/test_files/semantic_tokens/lambda_advanced.bamlbaml_language/crates/baml_lsp2_actions_tests/test_files/semantic_tokens/method_explicit_type_args.bamlbaml_language/crates/baml_lsp2_actions_tests/test_files/semantic_tokens/ns_game_clients.bamlbaml_language/crates/baml_lsp2_actions_tests/test_files/semantic_tokens/test_expr_throwing_body.bamlbaml_language/crates/baml_lsp2_actions_tests/test_files/syntax/hover/catch_binding.bamlbaml_language/crates/tools_semantic_tokens/Cargo.tomlbaml_language/stow.toml
✅ Files skipped from review due to trivial changes (4)
- baml_language/crates/baml_lsp2_actions_tests/test_files/syntax/hover/catch_binding.baml
- baml_language/crates/baml_lsp2_actions_tests/test_files/semantic_tokens/test_expr_throwing_body.baml
- baml_language/stow.toml
- baml_language/crates/baml_compiler2_ast/src/lower_expr_body.rs
🚧 Files skipped from review as they are similar to previous changes (16)
- baml_language/crates/tools_semantic_tokens/Cargo.toml
- baml_language/crates/baml_lsp2_actions_tests/test_files/semantic_tokens/json_map_literal.baml
- baml_language/crates/baml_compiler2_tir/src/builder.rs
- baml_language/crates/baml_compiler2_hir/src/builder.rs
- baml_language/crates/baml_lsp2_actions/src/definition_at_tests.rs
- baml_language/crates/baml_compiler_syntax/src/syntax_kind.rs
- baml_language/crates/baml_lsp2_actions_tests/test_files/semantic_tokens/method_explicit_type_args.baml
- baml_language/crates/baml_lsp2_actions/src/tokens/classify.rs
- baml_language/crates/baml_fmt/src/ast/expressions.rs
- baml_language/crates/baml_lsp2_actions_tests/test_files/semantic_tokens/lambda_advanced.baml
- baml_language/crates/baml_lsp2_actions_tests/test_files/semantic_tokens/interfaces_sort_comparable.baml
- baml_language/crates/baml_lsp2_actions_tests/test_files/semantic_tokens/ns_game_clients.baml
- baml_language/crates/baml_compiler_syntax/src/ast.rs
- baml_language/crates/baml_compiler_parser/src/parser.rs
- baml_language/crates/baml_lsp2_actions/src/tokens.rs
- baml_language/crates/baml_compiler2_mir/src/lower.rs
Comment on lines
+708
to
+717
| let func_scope_id = index.scope_ids[enclosing_func_scope.index() as usize]; | ||
| let inference = baml_compiler2_tir::inference::infer_scope_types(db, func_scope_id); | ||
| let ty_str = inference | ||
| .binding_type(pat_id) | ||
| .map(|ty| display_local_binding_ty(db, file, ty)) | ||
| .or_else(|| { | ||
| find_binding_ty_in_scopes(db, index, scope_id, pat_id) | ||
| .map(|ty| display_local_binding_ty(db, file, &ty)) | ||
| }) | ||
| .unwrap_or_else(|| "unknown".to_string()); |
Contributor
There was a problem hiding this comment.
🎯 Functional Correctness | 🟠 Major | ⚡ Quick win
Start this binding-type lookup from the current scope chain.
PatId is body-local, so probing infer_scope_types(db, func_scope_id) first can pick up a same-index binding from the enclosing function body before we ever reach the real nested scope. That gives the wrong hover type for pattern/catch bindings inside closures or nested blocks. find_binding_ty_in_scopes(db, index, scope_id, pat_id) is already the collision-safe path here.
Suggested fix
- let func_scope_id = index.scope_ids[enclosing_func_scope.index() as usize];
- let inference = baml_compiler2_tir::inference::infer_scope_types(db, func_scope_id);
- let ty_str = inference
- .binding_type(pat_id)
- .map(|ty| display_local_binding_ty(db, file, ty))
- .or_else(|| {
- find_binding_ty_in_scopes(db, index, scope_id, pat_id)
- .map(|ty| display_local_binding_ty(db, file, &ty))
- })
+ let ty_str = find_binding_ty_in_scopes(db, index, scope_id, pat_id)
+ .map(|ty| display_local_binding_ty(db, file, &ty))
.unwrap_or_else(|| "unknown".to_string());📝 Committable suggestion
‼️ IMPORTANT
Carefully review the code before committing. Ensure that it accurately replaces the highlighted code, contains no missing lines, and has no issues with indentation. Thoroughly test & benchmark the code to ensure it meets the requirements.
Suggested change
| let func_scope_id = index.scope_ids[enclosing_func_scope.index() as usize]; | |
| let inference = baml_compiler2_tir::inference::infer_scope_types(db, func_scope_id); | |
| let ty_str = inference | |
| .binding_type(pat_id) | |
| .map(|ty| display_local_binding_ty(db, file, ty)) | |
| .or_else(|| { | |
| find_binding_ty_in_scopes(db, index, scope_id, pat_id) | |
| .map(|ty| display_local_binding_ty(db, file, &ty)) | |
| }) | |
| .unwrap_or_else(|| "unknown".to_string()); | |
| let ty_str = find_binding_ty_in_scopes(db, index, scope_id, pat_id) | |
| .map(|ty| display_local_binding_ty(db, file, &ty)) | |
| .unwrap_or_else(|| "unknown".to_string()); |
🤖 Prompt for AI Agents
Verify each finding against current code. Fix only still-valid issues, skip the
rest with a brief reason, keep changes minimal, and validate.
In `@baml_language/crates/baml_lsp2_actions/src/type_info.rs` around lines 708 -
717, The binding-type lookup in type_info.rs is starting from the enclosing
function scope via infer_scope_types, which can return a same-index PatId from
the wrong body before the nested scope is checked. Update the hover/type
resolution logic in the binding-type lookup path to prefer
find_binding_ty_in_scopes(db, index, scope_id, pat_id) as the primary source and
avoid using func_scope_id-first probing for body-local pattern/catch bindings.
Keep the existing display_local_binding_ty formatting, but ensure the lookup
follows the current scope chain so closures and nested blocks resolve the
correct binding type.
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Reworks the BAML semantic-tokens classifier to be resolution-driven, mirroring rust-analyzer: walk the lossless CST for token positions + syntactic tokens (keywords/operators/punctuation), and resolve identifier meaning through the HIR/inference instead of guessing from the CST.
What's here
tokens/index.rs— span-keyed resolution index over every inference-bearing scope (function / lambda / let) via the new uniformtir::scope_bodylookup, so identifiers insidespawn/block/closure bodies classify with their own scope's inference.resolve_interface_membernow recordsMemberResolution::InterfaceMethod/InterfaceField. So.as<I>.method(), interfaceSelfmethods, and chained interface calls classify through the normal path; typos stay neutral. MIR-safe (new variants →Noneitem-refs, fall through to existing interface dispatch; 323 runtime interface tests pass).as/with/iskeywords, generators, generic type args + params (typeParameter), associated types (decl + binding), self member accesses (no longernamespace), methods after.as<Interface>, string escapes (escapeSequence), byte strings, qualified type paths,true/false/null, object/map keys vs values.tools_semantic_tokens— standalone web viewer for the classifier (no VSCode needed).Tests
78 semantic-token fixtures; 439 LSP + 323 runtime-interface + 172 tir/mir tests pass; clippy-clean.
Next steps / gaps
See
crates/baml_lsp2_actions/src/tokens/GAPS.md— the priority is scaling like rust-analyzer (on-demand per-token resolution +semanticTokens/rangeviewport + delta), plus a couple remaining feature items (optional params at call site, abooleanliteral token type).Summary by CodeRabbit
EscapeSequencehighlighting, and improved full/delta/range legends/encoding.as,type,true/false/null) and enhancedcatchbinding typing/highlighting.