Consolidate Bolt PRs: optimize Context lock usage and eliminate redundant ContextValue clones

[Copilot]

21 overlapping AI-generated "⚡ Bolt:" PRs (#34–#57) targeting the same three areas (Value display, Context locking, token string allocations) were clogging the PR queue. This consolidates the remaining valid improvements into a single clean change.

Already on master (prior commit)

• Value::fmt streams directly to fmt::Formatter via write! — no intermediate String buffers
• DelimTokenType::as_str() returns &'static str; check_op() and tokenizer::expect() use it directly

This PR: src/context.rs

get_func / get_variable — previously delegated to self.get() which calls .cloned() on the full ContextValue enum regardless of variant. Now acquires the lock directly and matches on a borrowed reference, cloning only the specific inner value when the variant matches:

// Before: clones entire ContextValue (including Value or Arc) before variant check
pub fn get_variable(&self, name: &str) -> Option<Value> {
    let value = self.get(name)?;          // full ContextValue clone
    match value {
        ContextValue::Variable(v) => Some(v),
        ContextValue::Function(_) => None, // Arc was cloned and thrown away
    }
}

// After: borrows from the locked map, clones only if variant matches
pub fn get_variable(&self, name: &str) -> Option<Value> {
    let binding = self.0.lock().unwrap();
    match binding.get(name)? {
        ContextValue::Variable(v) => Some(v.clone()),
        ContextValue::Function(_) => None,
    }
}

value() — explicit lock scope block ensures MutexGuard is dropped before invoking any stored function, closing a potential deadlock window in reentrant contexts.

Original prompt

Triage and Close Redundant AI-Generated "Bolt" Pull Requests

The repository currently has a large backlog of AI-generated pull requests (all prefixed with "⚡ Bolt:") that are clogging the PR queue and making it difficult to find genuine community contributions. These PRs span from #34 to #57 and all target overlapping concerns: Value display allocations, Context lock contention, and token string allocations.

Task

Review all open "⚡ Bolt:" PRs and implement the best, non-overlapping performance improvements directly on the master branch in a single, clean PR. This consolidates the valid work while eliminating the noise.

The Bolt PRs to consolidate are:

• #57 — eliminate token string allocations
• #56 — Zero-allocation string evaluation for Token checking
• #55 — Optimize Display Formatting via Direct Stream Writes
• #54 — Optimize Value Display Allocations
• #53 — Avoid String heap allocation in DelimTokenType
• #52 — Optimize Display implementation for Value by removing heap allocations
• #51 — Optimize fmt::Display for Value to reduce memory allocations
• #50 — Optimize Value Display Formatting
• #49 — optimize Value enum Display allocation
• #48 — Optimize fmt::Display for Value collections
• #45 — Optimize Value enum Display to avoid string allocations
• #43 — Optimize Context state access and lock contention
• #42 — optimize Context map lookups and lock contention
• #41 — optimize Context map lookups and lock contention
• #40 — Optimize Context lookups and lock contention
• #39 — Optimize Context lookups to avoid double-lookups and unnecessary .clone()s
• #38 — Optimize Value Display formatting
• #37 — Optimize Context variable and function lookups
• #36 — Optimize Context value retrieval and lock duration
• #35 — Reduce Mutex lock contention in Context
• #34 — Optimize Context lookup and reduce Mutex lock contention

What to implement

Read the source files (src/value.rs, src/context.rs, src/token.rs, src/tokenizer.rs) and apply the best, correctness-preserving performance improvements from the Bolt PRs directly. Specifically:

1. src/value.rs — Optimize fmt::Display for Value to write directly to the formatter instead of building intermediate String allocations (e.g., avoid format!(...).fmt(f) patterns).

2. src/context.rs — Eliminate double-lookups in the Context maps (e.g., use entry() API or single get/insert calls instead of contains_key + insert), and minimize Mutex lock duration by dropping the guard early where possible.

3. src/token.rs / src/tokenizer.rs — Where token type comparisons build temporary Strings just to compare, replace with &str slices or direct char/pattern comparisons to avoid heap allocations.

Constraints

• All existing tests must continue to pass.
• Do not change the public API surface.
• Keep the changes minimal, correct, and idiomatic Rust.
• This is a consolidation — do NOT introduce speculative or unproven optimizations; only apply clear, safe improvements visible in the existing code.

The following is the prior conversation context from the user's chat exploration (may be truncated):

User: Review this repo

Assistant: Here's a comprehensive review of ashyanSpada/expression_engine_rs — a pure Rust expression/rule engine library.

---

📊 At a Glance

Metric	Value
Language	Rust (100%)
Version	0.7.0
License	Apache 2.0
Stars	⭐ 34
Forks	4
Created	January 2023
Last Push	April 5, 2026
Open Issues/PRs	26

---

✅ Strengths

1. Clean, Well-Structured Codebase

The `...

This pull request was created from Copilot chat.

[codecov]

Codecov Report

✅ All modified and coverable lines are covered by tests.
✅ Project coverage is 89.35%. Comparing base (f50ac5d) to head (3bc70e3).
⚠️ Report is 1 commits behind head on master.

Additional details and impacted files

@@            Coverage Diff             @@
##           master      #59      +/-   ##
==========================================
- Coverage   89.53%   89.35%   -0.18%     
==========================================
  Files          11       11              
  Lines        1061     1062       +1     
==========================================
- Hits          950      949       -1     
- Misses        111      113       +2     

☔ View full report in Codecov by Sentry.
📢 Have feedback on the report? Share it here.

🚀 New features to boost your workflow:

• ❄️ Test Analytics: Detect flaky tests, report on failures, and find test suite problems.

[Copilot]

Pull request overview

Consolidates remaining Bolt optimizations by improving Context read-path performance and correctness around mutex lock scope during function evaluation.

Changes:

• Updated get_func / get_variable to avoid cloning the full ContextValue enum when only one variant is needed.
• Refactored Context::value() to ensure the mutex guard is dropped before invoking stored functions (reducing contention and avoiding re-entrant deadlocks).

---

💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.

[Copilot]

Context::value now intentionally drops the MutexGuard before invoking a stored function (to avoid re-entrant deadlocks). Since this is a behavioral/concurrency fix, please add a regression test that would have deadlocked previously: store a function that calls back into the same Context (e.g., ctx.value("a")), call ctx.value("f") on another thread, and assert it completes via recv_timeout within a short duration.