Claude Code transcript - page 1/2

gh issue view 43

git log --oneline -20 main

gh issue view 43 --comments

git log --oneline main..fix/chan-array-dir-params

go build -o occam2go .

ls kroc/modules/course/examples/*.occ

for f in kroc/modules/course/examples/*.occ; do
  base=$(basename "$f" .occ)
  out="/tmp/course_${base}.go"
  echo "=== $base ==="
  if ./occam2go -I kroc/modules/course/libsrc -D TARGET.BITS.PER.WORD=32 -o "$out" "$f" 2>&1; then
    echo "  TRANSPILE: OK"
    if go vet "$out" 2>&1; then
      echo "  GO VET: OK"
    else
      echo "  GO VET: FAIL"
    fi
  else
    echo "  TRANSPILE: FAIL"
  fi
  echo ""
done

gh issue view 56 --json state,title -q '.state + " - " + .title' && gh issue view 57 --json state,title -q '.state + " - " + .title'

gh issue list --state open --limit 20

gh issue comment 43 --body "$(cat <<'EOF'
## Status Update — After PRs #55, #56, #57, #58

Four codegen bugs have been fixed since the last update:

- **boolVars scoping** (#56, closed) — scoped per proc/function body to prevent cross-proc leakage
- **Channel array direction covariance** (#57, closed via `fix/chan-array-dir-params`) — direction dropped from `[]CHAN OF TYPE` params since Go slices are invariant
- **Typed abbreviation type loss** (#55, closed) — already noted in previous update
- **boolVars per-proc scoping** (#58, merged) — related follow-up to #56

### Current results: 10/16 transpile, 10/16 pass `go vet`

| File | Transpile | `go vet` | Remaining blockers |
|------|-----------|----------|--------------------|
| `hello_world.occ` | OK | OK | — |
| `hello_seq_world.occ` | OK | OK | — |
| `hello_raw_world.occ` | OK | OK | — |
| `echoing.occ` | OK | OK | — |
| `double_echo.occ` | OK | OK | — |
| `commstime.occ` | OK | OK | — |
| `cast.occ` | OK | **OK** | — *(was blocked by boolVars scoping)* |
| `casting.occ` | OK | **OK** | — *(was blocked by boolVars scoping)* |
| `sort_pump.occ` | OK | **OK** | — *(was blocked by chan array direction)* |
| `sort_pump_2.occ` | OK | **OK** | — *(was blocked by chan array direction)* |
| `bar.occ` | FAIL | — | PRI ALT, SHARED/CLAIM, dotted protocol tags, `tim ? AFTER`, guarded ALT, multi-dim arrays |
| `demo.occ` | FAIL | — | `tim ? AFTER`, MOBILE |
| `sort_inside.occ` | FAIL | — | Expression-sized arrays (`[expr]TYPE`) |
| `sort_inside_2.occ` | FAIL | — | `SIZE monitor?`, `tim ? AFTER` |
| `test_bell.occ` | FAIL | — | Multi-value CASE labels |
| `test_utils.occ` | FAIL | — | Multi-dim arrays (`[][n]TYPE`), `*"` string escape |

### Changes from previous update

- **Newly passing `go vet`:** `cast.occ`, `casting.occ`, `sort_pump.occ`, `sort_pump_2.occ` (4 new, 10 total)
- **All codegen bugs from the previous update are resolved** — no files transpile but fail vet
- **Still failing to parse:** 6 files (unchanged from previous update)

### Progress since issue was opened

| Milestone | Transpile | `go vet` |
|-----------|-----------|----------|
| Original report | 5/16 | 5/16 |
| After #44, #45, #46 | 10/16 | 6/16 |
| After #53, #54, #55 | 10/16 | 7/16 |
| **Current** (after #56, #57, #58) | **10/16** | **10/16** |

### Remaining work — new issues filed

The remaining 6 files are all blocked at parse time by unimplemented language features. Individual issues have been filed:

| Feature | Affected files | Issue |
|---------|---------------|-------|
| `tim ? AFTER expr` | `bar.occ`, `demo.occ`, `sort_inside_2.occ` | #59 |
| Multi-value CASE labels | `test_bell.occ` | #60 |
| Expression-sized arrays (`[expr]TYPE`) | `sort_inside.occ` | #61 |
| `SIZE` of direction-annotated name | `sort_inside_2.occ` | #62 |
| Multi-dimensional arrays (`[][n]TYPE`) | `bar.occ`, `test_utils.occ` | #63 |
| `*"` string escape | `test_utils.occ` | #64 |
| PRI ALT | `bar.occ` | #65 |
| Guarded ALT with boolean conditions | `bar.occ` | #66 |
| Dotted protocol tags | `bar.occ` | #67 |

SHARED/CLAIM and MOBILE are tracked in #40.
EOF
)"

gh issue create --title "Support timer AFTER input (tim ? AFTER expr)" --body "$(cat <<'EOF'
## Summary

Occam's `tim ? AFTER expr` construct waits until the timer value exceeds `expr`. This is used for timed delays and is distinct from `tim ? t` (which just reads the current time).

## Occam syntax

```occam
TIMER tim:
INT t:
SEQ
  tim ? t              -- read current time
  tim ? AFTER t PLUS delay  -- wait until time passes t + delay
```

## Proposed Go mapping

```go
t = time.Now().UnixMicro()
time.Sleep(time.Duration(t + delay - time.Now().UnixMicro()) * time.Microsecond)
```

Or possibly using `AFTER` comparison semantics (modular time comparison).

## Affected files

- `bar.occ` (lines 176, 189, 225, 373)
- `demo.occ` (line 16)
- `sort_inside_2.occ` (line 323)

## Work required

1. **Parser**: Detect `AFTER` keyword after `?` in channel/timer input and parse the delay expression
2. **AST**: Add an `AfterExpr` field (or similar) to the input node
3. **Codegen**: Generate `time.Sleep(...)` or equivalent

Part of #43.
EOF
)"

gh issue create --title "Support multi-value CASE labels" --body "$(cat <<'EOF'
## Summary

Occam CASE statements can have multiple comma-separated values on a single label. Currently only single-value labels are parsed.

## Occam syntax

```occam
CASE ch
  '*n', '*c'
    SKIP
  ELSE
    out ! ch
```

## Proposed Go mapping

```go
switch ch {
case '\n', '\r':
    // SKIP
default:
    out <- ch
}
```

## Affected files

- `test_bell.occ` (lines 39, 77)

## Work required

1. **Parser**: After parsing the first case value, check for comma and parse additional values
2. **AST**: Change `CaseOption.Value` from single expression to a list
3. **Codegen**: Emit comma-separated values in Go `case` clause

Part of #43.
EOF
)"

gh issue create --title "Support expression-sized array declarations" --body "$(cat <<'EOF'
## Summary

Occam allows array sizes to be arbitrary expressions (typically referencing variables or constants), not just integer literals. Currently the parser only accepts literal integers as array sizes.

## Occam syntax

```occam
VAL INT max.delay IS 100:
[max.delay]BYTE buffer:

[total - 1]BYTE temp:
```

## Proposed Go mapping

```go
maxDelay := 100
buffer := make([]byte, maxDelay)

temp := make([]byte, total - 1)
```

Since Go arrays require compile-time constant sizes, expression-sized arrays should map to slices via `make()`.

## Affected files

- `sort_inside.occ` (lines 309, 333, 336)

## Work required

1. **Parser**: Parse the array size as a full expression instead of requiring an integer literal
2. **Codegen**: When array size is not a literal, generate `make([]type, expr)` instead of a fixed-size array

Part of #43.
EOF
)"

gh issue create --title "Support SIZE of direction-annotated channel name" --body "$(cat <<'EOF'
## Summary

When a channel parameter has a direction annotation (e.g., `monitor?`), the `SIZE` operator should work on it by stripping the direction suffix. Currently `SIZE monitor?` fails to parse.

## Occam syntax

```occam
PROC foo([]CHAN OF INT monitor?)
  SEQ i = 0 FOR SIZE monitor?
    ...
```

## Proposed Go mapping

```go
func foo(monitor []chan int) {
    for i := 0; i < len(monitor); i++ {
        ...
    }
}
```

The `?` suffix is purely a direction annotation and should be stripped when generating the `len()` call.

## Affected files

- `sort_inside_2.occ` (line 294)

## Work required

1. **Parser**: When parsing `SIZE`, handle the case where the operand identifier has a trailing `?` or `!` direction annotation
2. **Codegen**: Generate `len(name)` with the direction suffix stripped

Part of #43.
EOF
)"

gh issue create --title "Support multi-dimensional arrays ([][n]TYPE)" --body "$(cat <<'EOF'
## Summary

Occam supports multi-dimensional arrays such as `[][2]BYTE` (open first dimension, fixed second) and `[n][m]TYPE` (both fixed). These are currently not parsed.

## Occam syntax

```occam
VAL [][2]BYTE pairs IS [['A', 'a'], ['B', 'b']]:

[10][20]INT grid:
```

## Proposed Go mapping

```go
var pairs = [][2]byte{{'A', 'a'}, {'B', 'b'}}

var grid [10][20]int
```

Or using slices for open dimensions:
```go
var pairs [][]byte = [][]byte{{'A', 'a'}, {'B', 'b'}}
```

## Affected files

- `bar.occ` (multi-dim array params/declarations)
- `test_utils.occ` (line 19: `VAL [][2]BYTE`)

## Work required

1. **Parser**: After parsing `[n]`, check for another `[` to handle nested array dimensions
2. **AST**: Extend array type representation to support multiple dimensions
3. **Codegen**: Generate nested Go array/slice types

Part of #43.
EOF
)"

gh issue create --title 'Support *" string escape sequence' --body "$(cat <<'EOF'
## Summary

Occam uses `*"` inside string literals to represent a literal double-quote character. Currently the lexer does not handle this escape sequence, causing parse failures.

## Occam syntax

```occam
VAL []BYTE msg IS "He said *"hello*"":
```

## Proposed Go mapping

```go
var msg []byte = []byte("He said \"hello\"")
```

## Affected files

- `test_utils.occ` (line 75)

## Work required

1. **Lexer**: In string literal scanning, recognize `*"` as an escape sequence that produces a `"` character (rather than terminating the string)

This is a small addition to the existing occam escape sequence handling (`*n`, `*c`, `*t`, etc.).

Part of #43.
EOF
)"

gh issue create --title "Support PRI ALT (prioritised alternation)" --body "$(cat <<'EOF'
## Summary

`PRI ALT` is a prioritised version of `ALT` where earlier guards have priority over later ones when multiple are ready simultaneously. Currently only `ALT` is supported.

## Occam syntax

```occam
PRI ALT
  in ? x
    ... handle input
  tim ? AFTER timeout
    ... handle timeout
```

## Proposed Go mapping

Go's `select` does not have built-in priority. Options:
1. **Simple approach**: Map `PRI ALT` to `select` (same as `ALT`), accepting the loss of priority semantics. Add a comment noting the limitation.
2. **Faithful approach**: Use nested `select` with `default` clauses to check higher-priority channels first.

## Affected files

- `bar.occ` (multiple PRI ALT blocks)

## Work required

1. **Lexer**: Recognize `PRI` keyword (if not already)
2. **Parser**: Parse `PRI ALT` as a variant of ALT
3. **AST**: Add a `Priority` flag to the ALT node
4. **Codegen**: Generate appropriate Go select construct

Part of #43.
EOF
)"

gh issue create --title "Support guarded ALT with boolean pre-conditions" --body "$(cat <<'EOF'
## Summary

Occam ALT cases can have boolean guard pre-conditions using the `&` operator. A guard that evaluates to FALSE disables that ALT branch. Currently the parser does not support this syntax.

## Occam syntax

```occam
ALT
  running & in ? x
    ... only considered if running is TRUE
  (NOT paused) & tim ? AFTER timeout
    ... only considered if paused is FALSE
  TRUE & stop ? any
    ... always considered
```

## Proposed Go mapping

```go
select {
case x = <-in:   // wrap in: if running { ... }
case <-time.After(...):  // wrap in: if !paused { ... }
case any = <-stop:       // always active
}
```

For `reflect.Select`-based ALT replicators, disabled guards can be handled by setting the channel to `nil` (which makes a select case block forever, effectively disabling it).

## Affected files

- `bar.occ` (lines 327, 338, 352, 399, 402)

## Work required

1. **Parser**: Before parsing a channel input in ALT, check for `expr &` guard prefix
2. **AST**: Add a `Guard` expression field to ALT case nodes
3. **Codegen**: Conditionally enable/disable select cases based on guard value

Part of #43.
EOF
)"

gh issue create --title "Support dotted protocol tags (e.g., bar.data)" --body "$(cat <<'EOF'
## Summary

Occam variant protocol tags can contain dots (e.g., `bar.data`, `bar.terminate`, `bar.blank`). Currently the parser treats the dot as a field access operator rather than part of the tag name.

## Occam syntax

```occam
PROTOCOL BAR.PROTO
  CASE
    bar.data ; INT ; BYTE
    bar.terminate
    bar.blank ; INT
:
```

## Proposed Go mapping

Dots in tag names would be replaced with underscores (consistent with `goIdent()`):

```go
type _proto_BAR_PROTO interface{ _tag_BAR_PROTO() }
type _proto_BAR_PROTO_bar_data struct { _0 int; _1 byte }
type _proto_BAR_PROTO_bar_terminate struct{}
type _proto_BAR_PROTO_bar_blank struct { _0 int }
```

## Affected files

- `bar.occ` (protocol declaration and usage throughout)

## Work required

1. **Parser**: When parsing protocol tag names, allow dotted identifiers (consume `IDENT.IDENT` as a single tag name)
2. **Codegen**: Use `goIdent()` to convert dots to underscores in generated Go identifiers

Part of #43.
EOF
)"

gh issue list --state open --limit 20 --json number,title -q '.[] | "#\(.number) \(.title)"'

gh issue comment 43 --edit-last --body "$(cat <<'EOF'
## Status Update — After PRs #55, #56, #57, #58

Four codegen bugs have been fixed since the last update:

- **boolVars scoping** (#56, closed) — scoped per proc/function body to prevent cross-proc leakage
- **Channel array direction covariance** (#57, closed via `fix/chan-array-dir-params`) — direction dropped from `[]CHAN OF TYPE` params since Go slices are invariant
- **Typed abbreviation type loss** (#55, closed) — already noted in previous update
- **boolVars per-proc scoping** (#58, merged) — related follow-up to #56

### Current results: 10/16 transpile, 10/16 pass `go vet`

| File | Transpile | `go vet` | Remaining blockers |
|------|-----------|----------|--------------------|
| `hello_world.occ` | OK | OK | — |
| `hello_seq_world.occ` | OK | OK | — |
| `hello_raw_world.occ` | OK | OK | — |
| `echoing.occ` | OK | OK | — |
| `double_echo.occ` | OK | OK | — |
| `commstime.occ` | OK | OK | — |
| `cast.occ` | OK | **OK** | — *(was blocked by boolVars scoping)* |
| `casting.occ` | OK | **OK** | — *(was blocked by boolVars scoping)* |
| `sort_pump.occ` | OK | **OK** | — *(was blocked by chan array direction)* |
| `sort_pump_2.occ` | OK | **OK** | — *(was blocked by chan array direction)* |
| `bar.occ` | FAIL | — | PRI ALT, SHARED/CLAIM, dotted protocol tags, `tim ? AFTER`, guarded ALT, multi-dim arrays |
| `demo.occ` | FAIL | — | `tim ? AFTER`, MOBILE |
| `sort_inside.occ` | FAIL | — | Expression-sized arrays (`[expr]TYPE`) |
| `sort_inside_2.occ` | FAIL | — | `SIZE monitor?`, `tim ? AFTER` |
| `test_bell.occ` | FAIL | — | Multi-value CASE labels |
| `test_utils.occ` | FAIL | — | Multi-dim arrays (`[][n]TYPE`), `*"` string escape |

### Changes from previous update

- **Newly passing `go vet`:** `cast.occ`, `casting.occ`, `sort_pump.occ`, `sort_pump_2.occ` (4 new, 10 total)
- **All codegen bugs from the previous update are resolved** — no files transpile but fail vet
- **Still failing to parse:** 6 files (unchanged from previous update)

### Progress since issue was opened

| Milestone | Transpile | `go vet` |
|-----------|-----------|----------|
| Original report | 5/16 | 5/16 |
| After #44, #45, #46 | 10/16 | 6/16 |
| After #53, #54, #55 | 10/16 | 7/16 |
| **Current** (after #56, #57, #58) | **10/16** | **10/16** |

### Remaining work — new issues filed

The remaining 6 files are all blocked at parse time by unimplemented language features. Individual issues have been filed:

| Feature | Affected files | Issue |
|---------|---------------|-------|
| `tim ? AFTER expr` | `bar.occ`, `demo.occ`, `sort_inside_2.occ` | #60 |
| Multi-value CASE labels | `test_bell.occ` | #61 |
| Expression-sized arrays (`[expr]TYPE`) | `sort_inside.occ` | #62 |
| `SIZE` of direction-annotated name | `sort_inside_2.occ` | #63 |
| Multi-dimensional arrays (`[][n]TYPE`) | `bar.occ`, `test_utils.occ` | #64 |
| `*"` string escape | `test_utils.occ` | #65 |
| PRI ALT | `bar.occ` | #66 |
| Guarded ALT with boolean conditions | `bar.occ` | #67 |
| Dotted protocol tags | `bar.occ` | #68 |

SHARED/CLAIM and MOBILE are tracked in #40.
EOF
)"

gh issue comment 43 --edit-last --body "$(cat <<'EOF'
## Status Update — After PRs #55, #56, #57, #58

Four codegen bugs have been fixed since the last update:

- **boolVars scoping** (#56, closed) — scoped per proc/function body to prevent cross-proc leakage
- **Channel array direction covariance** (#57, closed via `fix/chan-array-dir-params`) — direction dropped from `[]CHAN OF TYPE` params since Go slices are invariant
- **Typed abbreviation type loss** (#55, closed) — already noted in previous update
- **boolVars per-proc scoping** (#58, merged) — related follow-up to #56

### Current results: 10/16 transpile, 10/16 pass `go vet`

| File | Transpile | `go vet` | Remaining blockers |
|------|-----------|----------|--------------------|
| `hello_world.occ` | OK | OK | — |
| `hello_seq_world.occ` | OK | OK | — |
| `hello_raw_world.occ` | OK | OK | — |
| `echoing.occ` | OK | OK | — |
| `double_echo.occ` | OK | OK | — |
| `commstime.occ` | OK | OK | — |
| `cast.occ` | OK | **OK** | — *(was blocked by boolVars scoping)* |
| `casting.occ` | OK | **OK** | — *(was blocked by boolVars scoping)* |
| `sort_pump.occ` | OK | **OK** | — *(was blocked by chan array direction)* |
| `sort_pump_2.occ` | OK | **OK** | — *(was blocked by chan array direction)* |
| `bar.occ` | FAIL | — | PRI ALT, SHARED/CLAIM, dotted protocol tags, `tim ? AFTER`, guarded ALT, multi-dim arrays |
| `demo.occ` | FAIL | — | `tim ? AFTER`, MOBILE |
| `sort_inside.occ` | FAIL | — | Expression-sized arrays (`[expr]TYPE`) |
| `sort_inside_2.occ` | FAIL | — | `SIZE monitor?`, `tim ? AFTER` |
| `test_bell.occ` | FAIL | — | Multi-value CASE labels |
| `test_utils.occ` | FAIL | — | Multi-dim arrays (`[][n]TYPE`), `*"` string escape |

### Changes from previous update

- **Newly passing `go vet`:** `cast.occ`, `casting.occ`, `sort_pump.occ`, `sort_pump_2.occ` (4 new, 10 total)
- **All codegen bugs from the previous update are resolved** — no files transpile but fail vet
- **Still failing to parse:** 6 files (unchanged from previous update)

### Progress since issue was opened

| Milestone | Transpile | `go vet` |
|-----------|-----------|----------|
| Original report | 5/16 | 5/16 |
| After #44, #45, #46 | 10/16 | 6/16 |
| After #53, #54, #55 | 10/16 | 7/16 |
| **Current** (after #56, #57, #58) | **10/16** | **10/16** |

### Remaining work — new issues filed

The remaining 6 files are all blocked at parse time by unimplemented language features. Individual issues have been filed, with estimated difficulty:

| Feature | Affected files | Difficulty | Issue |
|---------|---------------|------------|-------|
| `tim ? AFTER expr` | `bar.occ`, `demo.occ`, `sort_inside_2.occ` | Medium — parser, AST, and codegen changes across timer input handling | #60 |
| Multi-value CASE labels | `test_bell.occ` | Easy — extend case label parsing to accept comma-separated values | #61 |
| Expression-sized arrays (`[expr]TYPE`) | `sort_inside.occ` | Medium — parser must accept expressions as array sizes; codegen must emit `make()` for non-literal sizes | #62 |
| `SIZE` of direction-annotated name | `sort_inside_2.occ` | Easy — strip trailing `?`/`!` direction suffix when parsing SIZE operand | #63 |
| Multi-dimensional arrays (`[][n]TYPE`) | `bar.occ`, `test_utils.occ` | Medium — parser, AST, and codegen must all support nested array dimensions | #64 |
| `*"` string escape | `test_utils.occ` | Easy — small addition to existing escape sequence handling in the lexer | #65 |
| PRI ALT | `bar.occ` | Medium — new keyword, AST flag, and codegen strategy (Go `select` has no native priority) | #66 |
| Guarded ALT with boolean conditions | `bar.occ` | Medium — parser must handle `expr &` prefix on ALT cases; codegen must conditionally enable/disable select cases | #67 |
| Dotted protocol tags | `bar.occ` | Easy — allow dotted identifiers in protocol tag positions; `goIdent()` already converts dots to underscores | #68 |

SHARED/CLAIM and MOBILE are tracked in #40 (hard — significant language extension).

### Suggested implementation order

Easiest wins first, maximizing files unblocked per effort:

1. **#61** (multi-value CASE) — easy, unblocks `test_bell.occ`
2. **#65** (`*"` escape) + **#64** (multi-dim arrays) — unblocks `test_utils.occ`
3. **#63** (SIZE direction) + **#60** (timer AFTER) — unblocks `sort_inside_2.occ` and `demo.occ`
4. **#62** (expression-sized arrays) — unblocks `sort_inside.occ`
5. **#68** (dotted tags) + **#67** (guarded ALT) + **#66** (PRI ALT) + **#40** (SHARED/CLAIM/MOBILE) — chipping away at `bar.occ`
EOF
)"

gh issue edit 60 --body "$(cat <<'EOF'
**Difficulty: Medium** — Parser, AST, and codegen changes across timer input handling.

## Summary

Occam's `tim ? AFTER expr` construct waits until the timer value exceeds `expr`. This is used for timed delays and is distinct from `tim ? t` (which just reads the current time).

## Occam syntax

```occam
TIMER tim:
INT t:
SEQ
  tim ? t              -- read current time
  tim ? AFTER t PLUS delay  -- wait until time passes t + delay
```

## Proposed Go mapping

```go
t = time.Now().UnixMicro()
time.Sleep(time.Duration(t + delay - time.Now().UnixMicro()) * time.Microsecond)
```

Or possibly using `AFTER` comparison semantics (modular time comparison).

## Affected files

- `bar.occ` (lines 176, 189, 225, 373)
- `demo.occ` (line 16)
- `sort_inside_2.occ` (line 323)

## Work required

1. **Parser**: Detect `AFTER` keyword after `?` in channel/timer input and parse the delay expression
2. **AST**: Add an `AfterExpr` field (or similar) to the input node
3. **Codegen**: Generate `time.Sleep(...)` or equivalent

Part of #43.
EOF
)"

gh issue edit 61 --body "$(cat <<'EOF'
**Difficulty: Easy** — Extend case label parsing to accept comma-separated values; small AST and codegen changes.

## Summary

Occam CASE statements can have multiple comma-separated values on a single label. Currently only single-value labels are parsed.

## Occam syntax

```occam
CASE ch
  '*n', '*c'
    SKIP
  ELSE
    out ! ch
```

## Proposed Go mapping

```go
switch ch {
case '\n', '\r':
    // SKIP
default:
    out <- ch
}
```

## Affected files

- `test_bell.occ` (lines 39, 77)

## Work required

1. **Parser**: After parsing the first case value, check for comma and parse additional values
2. **AST**: Change `CaseOption.Value` from single expression to a list
3. **Codegen**: Emit comma-separated values in Go `case` clause

Part of #43.
EOF
)"

gh issue edit 62 --body "$(cat <<'EOF'
**Difficulty: Medium** — Parser must accept expressions as array sizes; codegen must emit `make()` for non-literal sizes since Go arrays require compile-time constants.

## Summary

Occam allows array sizes to be arbitrary expressions (typically referencing variables or constants), not just integer literals. Currently the parser only accepts literal integers as array sizes.

## Occam syntax

```occam
VAL INT max.delay IS 100:
[max.delay]BYTE buffer:

[total - 1]BYTE temp:
```

## Proposed Go mapping

```go
maxDelay := 100
buffer := make([]byte, maxDelay)

temp := make([]byte, total - 1)
```

Since Go arrays require compile-time constant sizes, expression-sized arrays should map to slices via `make()`.

## Affected files

- `sort_inside.occ` (lines 309, 333, 336)

## Work required

1. **Parser**: Parse the array size as a full expression instead of requiring an integer literal
2. **Codegen**: When array size is not a literal, generate `make([]type, expr)` instead of a fixed-size array

Part of #43.
EOF
)"

gh issue edit 63 --body "$(cat <<'EOF'
**Difficulty: Easy** — Strip trailing `?`/`!` direction suffix when parsing SIZE operand.

## Summary

When a channel parameter has a direction annotation (e.g., `monitor?`), the `SIZE` operator should work on it by stripping the direction suffix. Currently `SIZE monitor?` fails to parse.

## Occam syntax

```occam
PROC foo([]CHAN OF INT monitor?)
  SEQ i = 0 FOR SIZE monitor?
    ...
```

## Proposed Go mapping

```go
func foo(monitor []chan int) {
    for i := 0; i < len(monitor); i++ {
        ...
    }
}
```

The `?` suffix is purely a direction annotation and should be stripped when generating the `len()` call.

## Affected files

- `sort_inside_2.occ` (line 294)

## Work required

1. **Parser**: When parsing `SIZE`, handle the case where the operand identifier has a trailing `?` or `!` direction annotation
2. **Codegen**: Generate `len(name)` with the direction suffix stripped

Part of #43.
EOF
)"

gh issue edit 64 --body "$(cat <<'EOF'
**Difficulty: Medium** — Parser, AST, and codegen must all support nested array dimensions.

## Summary

Occam supports multi-dimensional arrays such as `[][2]BYTE` (open first dimension, fixed second) and `[n][m]TYPE` (both fixed). These are currently not parsed.

## Occam syntax

```occam
VAL [][2]BYTE pairs IS [['A', 'a'], ['B', 'b']]:

[10][20]INT grid:
```

## Proposed Go mapping

```go
var pairs = [][2]byte{{'A', 'a'}, {'B', 'b'}}

var grid [10][20]int
```

Or using slices for open dimensions:
```go
var pairs [][]byte = [][]byte{{'A', 'a'}, {'B', 'b'}}
```

## Affected files

- `bar.occ` (multi-dim array params/declarations)
- `test_utils.occ` (line 19: `VAL [][2]BYTE`)

## Work required

1. **Parser**: After parsing `[n]`, check for another `[` to handle nested array dimensions
2. **AST**: Extend array type representation to support multiple dimensions
3. **Codegen**: Generate nested Go array/slice types

Part of #43.
EOF
)"

gh issue edit 65 --body "$(cat <<'EOF'
**Difficulty: Easy** — Small addition to existing escape sequence handling in the lexer.

## Summary

Occam uses `*"` inside string literals to represent a literal double-quote character. Currently the lexer does not handle this escape sequence, causing parse failures.

## Occam syntax

```occam
VAL []BYTE msg IS "He said *"hello*"":
```

## Proposed Go mapping

```go
var msg []byte = []byte("He said \"hello\"")
```

## Affected files

- `test_utils.occ` (line 75)

## Work required

1. **Lexer**: In string literal scanning, recognize `*"` as an escape sequence that produces a `"` character (rather than terminating the string)

This is a small addition to the existing occam escape sequence handling (`*n`, `*c`, `*t`, etc.).

Part of #43.
EOF
)"

gh issue edit 66 --body "$(cat <<'EOF'
**Difficulty: Medium** — New keyword, AST flag, and codegen strategy needed. Go `select` has no native priority semantics, so a faithful implementation requires nested selects with `default` clauses or a similar workaround.

## Summary

`PRI ALT` is a prioritised version of `ALT` where earlier guards have priority over later ones when multiple are ready simultaneously. Currently only `ALT` is supported.

## Occam syntax

```occam
PRI ALT
  in ? x
    ... handle input
  tim ? AFTER timeout
    ... handle timeout
```

## Proposed Go mapping

Go's `select` does not have built-in priority. Options:
1. **Simple approach**: Map `PRI ALT` to `select` (same as `ALT`), accepting the loss of priority semantics. Add a comment noting the limitation.
2. **Faithful approach**: Use nested `select` with `default` clauses to check higher-priority channels first.

## Affected files

- `bar.occ` (multiple PRI ALT blocks)

## Work required

1. **Lexer**: Recognize `PRI` keyword (if not already)
2. **Parser**: Parse `PRI ALT` as a variant of ALT
3. **AST**: Add a `Priority` flag to the ALT node
4. **Codegen**: Generate appropriate Go select construct

Part of #43.
EOF
)"

gh issue edit 67 --body "$(cat <<'EOF'
**Difficulty: Medium** — Parser must handle `expr &` prefix on ALT cases; codegen must conditionally enable/disable select cases (e.g., by setting channels to `nil` when the guard is false).

## Summary

Occam ALT cases can have boolean guard pre-conditions using the `&` operator. A guard that evaluates to FALSE disables that ALT branch. Currently the parser does not support this syntax.

## Occam syntax

```occam
ALT
  running & in ? x
    ... only considered if running is TRUE
  (NOT paused) & tim ? AFTER timeout
    ... only considered if paused is FALSE
  TRUE & stop ? any
    ... always considered
```

## Proposed Go mapping

```go
select {
case x = <-in:   // wrap in: if running { ... }
case <-time.After(...):  // wrap in: if !paused { ... }
case any = <-stop:       // always active
}
```

For `reflect.Select`-based ALT replicators, disabled guards can be handled by setting the channel to `nil` (which makes a select case block forever, effectively disabling it).

## Affected files

- `bar.occ` (lines 327, 338, 352, 399, 402)

## Work required

1. **Parser**: Before parsing a channel input in ALT, check for `expr &` guard prefix
2. **AST**: Add a `Guard` expression field to ALT case nodes
3. **Codegen**: Conditionally enable/disable select cases based on guard value

Part of #43.
EOF
)"

gh issue edit 68 --body "$(cat <<'EOF'
**Difficulty: Easy** — Allow dotted identifiers in protocol tag positions. `goIdent()` already converts dots to underscores, so codegen should need minimal changes.

## Summary

Occam variant protocol tags can contain dots (e.g., `bar.data`, `bar.terminate`, `bar.blank`). Currently the parser treats the dot as a field access operator rather than part of the tag name.

## Occam syntax

```occam
PROTOCOL BAR.PROTO
  CASE
    bar.data ; INT ; BYTE
    bar.terminate
    bar.blank ; INT
:
```

## Proposed Go mapping

Dots in tag names would be replaced with underscores (consistent with `goIdent()`):

```go
type _proto_BAR_PROTO interface{ _tag_BAR_PROTO() }
type _proto_BAR_PROTO_bar_data struct { _0 int; _1 byte }
type _proto_BAR_PROTO_bar_terminate struct{}
type _proto_BAR_PROTO_bar_blank struct { _0 int }
```

## Affected files

- `bar.occ` (protocol declaration and usage throughout)

## Work required

1. **Parser**: When parsing protocol tag names, allow dotted identifiers (consume `IDENT.IDENT` as a single tag name)
2. **Codegen**: Use `goIdent()` to convert dots to underscores in generated Go identifiers

Part of #43.
EOF
)"