fix: remove capacity pre-allocation in mergeFetchRefs to avoid overflow (CodeQL #555)

[Copilot]

mergeFetchRefs used len(existing)+len(newRefs) directly as a make capacity argument. On pathologically large inputs this addition overflows int, producing a negative capacity and a runtime panic.

Change

Removed the capacity pre-allocation entirely:

// before
result := make([]string, 0, len(existing)+len(newRefs))

// after
result := make([]string, 0)

append grows the slice as needed, eliminating the overflow risk without any guard logic.

---

💬 Send tasks to Copilot coding agent from Slack and Teams to turn conversations into code. Copilot posts an update in your thread when it's finished.

[pelikhan]

@copilot do not pre-allocate size

[Copilot]

Done in 6c2f7df — replaced make([]string, 0, capacity) with make([]string, 0) and removed the math import.

[Copilot]

Pull request overview

Removes slice capacity pre-allocation in mergeFetchRefs to eliminate an int overflow risk that could cause a runtime panic on extreme input sizes (CodeQL #555).

Changes:

• Remove len(existing)+len(newRefs) from make(..., cap) in mergeFetchRefs to prevent int overflow.
• Rely on append to grow the result slice dynamically.

---

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

[Copilot]

Dropping pre-allocation entirely fixes the overflow, but it also guarantees extra realloc/copy work for typical inputs. You can keep the fix and still reduce allocations by preallocating to len(existing) (safe since it doesn’t involve an addition) or by using an overflow-checked sum before setting capacity.

Suggested change

	result := make([]string, 0)
	result := make([]string, 0, len(existing))