-
fix: #1868:
- Adds logic to include the 3 new builtins in
builtin_segments
when serializing the output cairo pie's metadata.
- Adds logic to include the 3 new builtins in
-
fix: #1855:
- Adds logic to skip pedersen additional data comparison when checking pie compatibility.
-
serde: add
size
field toIdentifier
[#1861]#1861
-
fix: #1864:
- Runner: include data from constants segment to the bytecode when assembling program
-
chore: bump
cairo-lang-
dependencies to 2.9.0-dev.0 #1858 -
chore: update Rust required version to 1.81.0 #1857
-
- Add support for dynamic layout
- CLI change(BREAKING): The flag
cairo_layout_params_file
must be specified when using dynamic layout. - Signature change(BREAKING): Both
CairoRunner::new
andCairoRunner::new_v2
now receive anOption<CairoLayoutParams>
, used only with dynamic layout.
-
fix: #1841:
- Fix modulo builtin to comply with prover constraints
-
chore: bump pip
cairo-lang
0.13.2 #1827 -
chore: bump
cairo-lang-
dependencies to 2.8.0 #1833- chore: update Rust required version to 1.80.0
-
fix: Added the following VM fixes: #1820
- Fix zero segment location.
- Fix has_zero_segment naming.
- Fix prover input.
- Fix version reading when no version is supplied.
-
chore: bump
cairo-lang-
dependencies to 2.7.1 #1823
-
fix(BREAKING): #1818:
- Fix
MemorySegmentManager::add_zero_segment
function when resizing a segment - Signature change(BREAKING):
MemorySegmentManager::get_memory_holes
now receivesbuiltin_segment_indexes: HashSet<usize>
- Fix
-
fix(BREAKING): Replace
CairoRunner
methodinitialize_all_builtins
withinitialize_program_builtins
. Now it only initializes program builtins instead of all of them
-
chore: bump
cairo-lang-
dependencies to 2.7.0 #1813 -
fix(BREAKING): Don't assume output builtin is first when counting memory holes
- Logic change: Memory hole counting no longer asumes that the output builtin ocuppies the first builtin segment if present
- Signature change:
MemorySegmentManager
methodget_memory_holes
now receives the index of the output builtin (as anOption<usize>
) instead of the boolean argumenthas_output_builtin
#1811
-
fix: ambiguous keccak module name use on external contexts #1809
- chore: bump
cairo-lang-
dependencies to 2.7.0-rc.3 #1807- chore: update Rust required version to 1.76.0
- fix: Fixed deserialization of negative numbers in scientific notation #1804
-
chore: bump
cairo-lang-
dependencies to 2.6.4 #1799- fix: revert breaking change on public input serialization
-
fix: Remove validation of CairoPie memory values #1783
-
fix: Handle
GasBuiltin
in cairo1-run crate #1789- Load
initial_gas
into vm instead of creating it via instructions. - Fix bug affecting programs with input arguments and gas builtin.
- Load
-
fix: Change (de)serialization of CairoPie's
OutputBuiltinAdditionalData
'sPublicMemoryPage
to vectors of length 2. #1781 -
fix: Fixed deserialization issue when signature additional data is empty, and the name of the builtin range_check96 #1785
-
refactor + bugfix: Improve arg handling for cairo1-run #1782
- Now uses ascii whitespace as separator, preventing errors when using newlines in args file
- No longer gets stuck on improperly-formatted arrays
- Returns an informative clap error upon invalid felt strings instead of unwrapping
-
fix: Ignore memory order when comparing instances of
CairoPieMemory
#1780 -
feat: Add
EXCESS_BALANCE
hint #1777 -
feat(BREAKING): Use a cheatcode to relocate all dicts + Make temporary segment usage configurable #1776
- Add the flags
segment_arena_validation
&use_temporary_segments
to theCairo1HintProcessor
&DictManagerExecScope
respectively. These flags will determine if real segments or temporary segments will be used when creating dictionaries. DictManagerExecScope::finalize_segment
no longer performs relocation and is ignored ifuse_temporary_segments
is set to false.- Add method
DictManagerExecScope::relocate_all_dictionaries
that adds relocation rules for all tracked dictionaries, relocating them one next to the other in a new segment. - Add cheatcode
RelocateAllDictionaries
to theCairo1HintProcessor
, which calls the aforementioned method. - Add casm instruction to call the aforementioned cheatcode in
create_entry_code
if eitherproof_mode
orappend_return_values
are set to true, and segment arena is present.
- Add the flags
-
Bump
starknet-types-core
version + Use the lib's pedersen hash #1734 -
refactor: Add boolean method Cairo1RunConfig::copy_to_output + Update Doc #1778
-
feat: Filter implicit arguments from return value in cairo1-run crate #1775
-
feat(BREAKING): Serialize inputs into output segment in cairo1-run crate:
-
Checks that only
Array<Felt252>
can be received by the program main function when running with with either--proof_mode
or--append_return_values
. -
Copies the input value to the output segment right after the output in the format
[array_len, arr[0], arr[1],.., arr[n]]
.* feat: specify initial value for `exec_scopes` in `cairo_run_program` [1772](https://github.com/lambdaclass/cairo-vm/pull/1772)
-
-
fix: make MemorySegmentManager.finalize() public #1771
-
feat: load Cairo PIE from bytes #1773
-
feat(BREAKING): Serialize
Array<Felt252>
return value into output segment in cairo1-run crate:- Checks that only
PanicResult<Array<Felt252>>
orArray<Felt252>
can be returned by the program when running with either--proof_mode
or--append_return_values
. - Serializes return values into the output segment under the previous conditions following the format:
PanicResult<Array<Felt252>>
->[panic_flag, array_len, arr[0], arr[1],.., arr[n]]
<Array<Felt252>
->[array_len, arr[0], arr[1],.., arr[n]]
- Checks that only
-
feat: Handle
BoundedInt
variant inserialize_output
,cairo1-run
crate #1768 -
fix: make
OutputBuiltinState
public #1769 -
feat: Load arguments into VM instead of creating them via instructions in cairo1-run #1759
-
bugfix: Fix handling of return values wrapped in
PanicResult
in cairo1-run crate #1763 -
refactor(BREAKING): Move the VM back to the CairoRunner #1743
CairoRunner
has a new public fieldvm: VirtualMachine
CairoRunner
no longer derivesDebug
CairoRunner
methodsnew_v2
&new
take an extra boolean argumenttrace_enabled
.- Functions
cairo_run
,cairo_run_program
&cairo_run_fuzzed_program
fromvm
crate andcairo_run_program
fromcairo1-run
crate now retun onlyCairoRunner
instead of(CairoRunner, VirtualMachine)
CairoRunner
methods no longer take a reference toVirtualMachine
. Methods that took an immutable reference to self and a mutable reference to the VM now take a mutable reference to self. Affected methods:initialize
initialize_builtins
initialize_all_builtins
initialize_segments
initialize_state
initialize_function_entrypoint
initialize_state
initialize_main_entrypoint
initialize_vm
run_until_pc
run_for_steps
run_until_steps
run_until_power_of_2
get_perm_range_check_limits
check_range_check_usage
get_memory_holes
check_diluted_check_usage
end_run
relocate_trace
relocate_memory
relocate
get_builtin_segments_info
get_builtin_segments_info_for_pie
get_execution_resources
finalize_segments
run_from_entrypoint
check_used_cells
check_memory_usage
initialize_function_runner_cairo_1
initialize_function_runner
read_return_values
get_builtins_final_stack
get_cairo_pie
get_air_public_input
get_air_private_input
get_memory_segment_addresses
- Functions & methods taking a reference to
CairoRunner
&VirtualMachine
now only take a reference toCairoRunner
:start_tracer
VmException::from_vm_error
get_error_attr_value
get_traceback
verify_secure_runner
- [hooks feature]
BeforeFirstStepHookFunc
dyn Fn no longer takes a mutable reference toCairoRunner
, along withVirtualMachine::execute_before_first_step
.
-
fix: add support for arrays shorter than 2 as arguments for cairo1-run #1737
-
bugfix: Fix BuiltinRunner::final_stack for SegmentArena#1747
-
feat: unify
arbitrary
,hooks
,print
andskip_next_instruction_hint
features as a singletest_utils
feature #1755- BREAKING: removed the above features
-
bugfix: cairo1-run CLI: Set finalize_builtins to true when using --air_public_input flag #1744
-
feat: Add hint
U256InvModN
toCairo1HintProcessor
#1744 -
perf: use a more compact representation for
MemoryCell
#1672- BREAKING:
Memory::get_value
will now always returnCow::Owned
variants, code that relied onCow::Borrowed
may break
- BREAKING:
-
cairo1-run
CLI: Allow loading arguments from file#1739 -
BREAKING: Remove unused
CairoRunner
fieldoriginal_steps
#1742 -
feat: Add
--run_from_cairo_pie
tocairo-vm-cli
+ workflow #1730 -
Serialize directly into writer in
CairoPie::write_zip_file
#1736 -
feat: Add support for cairo1 run with segements arena validation.
- Refactored the runner CASM code generation to user a more high level builder.
- Added segment merging of the dictionary segments.
- Added validation of the generated segment arena in cairo1 run.
-
refactor: Add
lib.rs
to cairo1-run#1714 -
feat: Implement
CairoPie::read_zip_file
#1729 -
feat: Bump to 2.6.3 + Remove gas checks#1709
- Bump cairo_lang crates & corelib to v2.6.3
- Disable gas checks when compiling to sierra & casm
- Add
Known bugs & issues
segment to README, poining out issues derived from the removal of gas checks and cairo v2.6.3
-
feat: Implement running from
CairoPie
#1720- Add function
cairo_run_pie
- Add
CairoPie
methodsrun_validity_checks
&check_pie_compatibility
- Add
Program
methodfrom_stripped_program
- Add function
-
bugfix: Don't assume outer deref when fetching integer values from references#1732
-
feat: Implement
extend_additional_data
forBuiltinRunner
#1726 -
BREAKING: Set dynamic params as null by default on air public input #1716
PublicInput
fieldlayout_params
renamed todynamic_params
& type changed from&'a CairoLayout
to()
.
-
feat:
cairo1-run
accepts Sierra programs #1719 -
refactor(BREAKING): Use
BuiltinName
enum instead of string representation #1722BuiltinName
moved fromcrate::serde::deserialize_program
module tocrate::types::builtin_name
.- Implement
BuiltinName
methodsto_str
,to_str_with_suffix
,from_str
&from_str_with_suffix
.
- Implement
- Remove
BuiltinName
methodname
. - All builtin-related error variants now store
BuiltinName
instead of&'static str
orString
. - Remove constants:
OUTPUT_BUILTIN_NAME
,HASH_BUILTIN_NAME
,RANGE_CHECK_BUILTIN_NAME
,RANGE_CHECK_96_BUILTIN_NAME
,SIGNATURE_BUILTIN_NAME
,BITWISE_BUILTIN_NAME
,EC_OP_BUILTIN_NAME
,KECCAK_BUILTIN_NAME
,POSEIDON_BUILTIN_NAME
,SEGMENT_ARENA_BUILTIN_NAME
,ADD_MOD_BUILTIN_NAME
&MUL_MOD_BUILTIN_NAME
. - Remove
BuiltinRunner
&ModBuiltinRunner
methodidentifier
- Structs containing string representation of builtin names now use
BuiltinName
instead:AirPrivateInput(pub HashMap<&'static str, Vec<PrivateInput>>)
->AirPrivateInput(pub HashMap<BuiltinName, Vec<PrivateInput>>)
.CairoPieMetadata
fieldadditional_data
:HashMap<String, BuiltinAdditionalData>,
->CairoPieAdditionalData
withCairoPieAdditionalData(pub HashMap<BuiltinName, BuiltinAdditionalData>)
CairoPieMetadata
fieldbuiltin_segments
:HashMap<String, SegmentInfo>
->HashMap<BuiltinName, SegmentInfo>
.ExecutiobResources
fieldbuiltin_instance_counter
:HashMap<String, usize>
->HashMap<BuiltinName, usize>
- Methods returning string representation of builtin names now use
BuiltinName
instead:BuiltinRunner
,ModBuiltinRunner
&RangeCheckBuiltinRunner
methodname
:&'static str
->BuiltinName
.CairoRunner
methodget_builtin_segment_info_for_pie
:Result<HashMap<String, cairo_pie::SegmentInfo>, RunnerError>
->Result<HashMap<BuiltinName, cairo_pie::SegmentInfo>, RunnerError>
Notes: Serialization of vm outputs that now contain
BuiltinName
&Display
implementation ofBuiltinName
have not been affected by this PR -
feat: Add
recursive_with_poseidon
layout#1724 -
refactor(BREAKING): Use an enum to represent layout name#1715
- Add enum
LayoutName
to represent cairo layout names. CairoRunConfig
,Cairo1RunConfig
&CairoRunner
fieldlayout
type changed fromString
toLayoutName
.CairoLayout
fieldname
type changed fromString
toLayoutName
.
- Add enum
-
fix(BREAKING): Remove unsafe impl of
Add<usize> for &'a Relocatable
#1718 -
fix(BREAKING): Handle triple dereference references#1708
- Replace
ValueAddress
boolean fielddereference
with boolean fieldsouter_dereference
&inner_dereference
- Replace
HintReference
boolean fielddereference
with boolean fieldsouter_dereference
&inner_dereference
- Reference parsing now handles the case of dereferences inside the cast. Aka references of type
cast([A + B], type)
such ascast([[fp + 2] + 2], felt)
.
- Replace
-
Bump
starknet-types-core
version + Use the lib's pedersen hash #1692 -
refactor: Remove unused code & use constants whenever possible for builtin instance definitions#1707
-
feat: missing EC hints for Starknet OS 0.13.1 #1706
-
fix(BREAKING): Use program builtins in
initialize_main_entrypoint
&read_return_values
#1703initialize_main_entrypoint
now iterates over the program builtins when building the stack & inserts 0 for any missing builtinread_return_values
now only computes the final stack of the builtins in the program- BREAKING:
read_return_values
now takes a boolean argumentallow_missing_builtins
- Added method
BuiltinRunner::identifier
to get theBuiltinName
of each builtin - BREAKING:
OutputBuiltinRunner::get_public_memory
now takes a reference toMemorySegmentManager
- BREAKING: method
VirtualMachine::get_memory_segment_addresses
moved toCairoRunner::get_memory_segment_addresses
-
feat(BREAKING): Add range_check96 builtin#1698
- Add the new
range_check96
builtin to theall_cairo
layout. RangeCheckBuiltinRunner
changes:- Remove field
n_parts
, replacing it with const genericN_PARTS
. - Remome
n_parts
argument form methodnew
. - Remove field
_bound
, replacing it with public methodbound
. - Add public methods
name
&n_parts
.
- Remove field
- Add the new
-
feat(BREAKING): Add mod builtin #1673
Main Changes:
- Add the new
ModBuiltinRunner
, implementing the builtinsadd_mod
&mul_mod
- Adds
add_mod
&mul_mod
to theall_cairo
&dynamic
layouts under themod_builtin
feature flag. This will be added to the main code in a future update. - Add method
VirtualMachine::fill_memory
in order to perform the new builtin's main logic from within hints - Add hints to run arithmetic circuits using
add_mod
and/ormul_mod
builtins
Other Changes:
- BREAKING: BuiltinRunner method signature change from
air_private_input(&self, memory: &Memory) -> Vec<PrivateInput>
topub fn air_private_input(&self, segments: &MemorySegmentManager) -> Vec<PrivateInput>
- Add
MayleRelocatable::sub_usize
- Implement
Add<u32> for Relocatable
- Add
Memory::get_usize
- BREAKING: Clean up unused/duplicated code from builtins module:
- Remove unused method
get_memory_segment_addresses
from all builtin runners & the enum - Remove empty implementations of
deduce_memory_cell
&add_validation_rules
from all builtin runners - Remove duplicated implementation of
final_stack
from all builtin runners except output and move it to the enum implementation
- Remove unused method
- Add the new
-
bugfix(BREAKING): Handle off2 immediate case in
get_integer_from_reference
#1701get_integer_from_reference
&get_integer_from_var_name
output changed fromResult<Cow<'a, Felt252>, HintError>
toResult<Felt252, HintError>
-
feat: Reorganized builtins to be in the top of stack at the end of a run (Cairo1).
-
BREAKING: Remove
CairoRunner::add_additional_hash_builtin
&VirtualMachine::disable_trace
#1658 -
feat: output builtin add_attribute method #1691
-
feat: add a method to retrieve the output builtin from the VM #1690
-
feat: Add zero segment #1668
-
feat: Bump cairo_lang to 0.13.1 in testing env #1687
-
feat(BREAKING): Use return type info from sierra when serializing return values in cairo1-run crate #1665
- Removed public function
serialize_output
. - Add field
serialize_output
toCairo1RunConfig
. - Function
cairo_run_program
now returns an extraOption<String>
value with the serialized output ifserialize_output
is enabled in the config. - Output serialization improved as it now uses the sierra program data to identify return value's types.
- Removed public function
-
feat: Create hyper_threading crate to benchmark the
cairo-vm
in a hyper-threaded environment #1679 -
feat: add a
--tracer
option which hosts a web server that shows the line by line execution of cairo code along with memory registers #1265 -
feat: Fix error handling in
initialize_state
#1657 -
feat: Make air public inputs deserializable #1657
-
feat: Show only layout builtins in air private input #1651
-
feat: Sort builtin segment info upon serialization for Cairo PIE #1654
-
feat: Fix output serialization for cairo 1 #1645
- Reverts changes added by #1630
- Extends the serialization of Arrays added by the
print_output
flag to Spans and Dictionaries - Now dereferences references upon serialization
-
feat: Add flag to append return values to output segment when not running in proof_mode #1646
- Adds the flag
append_return_values
to both the CLI andCairo1RunConfig
struct. - Enabling flag will add the output builtin and the necessary instructions to append the return values to the output builtin's memory segment.
- Adds the flag
-
feat: Compute program hash chain #1647
-
feat: Add cairo1-run output pretty-printing for felts, arrays/spans and dicts #1630
-
feat: output builtin features for bootloader support #1580
-
Bump
starknet-types-core
dependency version to 0.0.9 #1628 -
feat: Implement
Display
forMemorySegmentManager
#1606 -
fix: make Felt252DictEntryUpdate work with MaybeRelocatable instead of only Felt #1624.
-
chore: bump
cairo-lang-
dependencies to 2.5.4 #1629 -
chore: bump
cairo-lang-
dependencies to 2.5.3 #1596 -
refactor: Refactor
cairo1-run
crate #1601- Add function
cairo_run_program
& structCairo1RunConfig
incairo1-run::cairo_run
module. - Function
serialize_output
& structsFuncArg
andError
in cratecairo1-run
are now public.
- Add function
-
feat(BREAKING): Add
allow_missing_builtins
flag #1600This new flag will skip the check that all builtins used by the program need to be present in the selected layout if enabled. It will also be enabled by default when running in proof_mode.
- Add
allow_missing_builtins
flag tocairo-vm-cli
crate - Add
allow_missing_builtins
field toCairoRunConfig
struct - Add
allow_missing_builtins
boolean argument toCairoRunner
methodsinitialize
&initialize_builtins
- Add
-
feat: Append return values to the output segment when running cairo1-run in proof_mode #1597
- Add instructions to the proof_mode header to copy return values to the output segment before initiating the infinite loop
- Output builtin is now always included when running cairo 1 programs in proof_mode
-
feat: deserialize AIR private input #1589
-
feat(BREAKING): Remove unecessary conversion functions between
Felt
&BigUint
/BigInt
#1562- Remove the following functions:
- felt_from_biguint
- felt_from_bigint
- felt_to_biguint
- felt_to_bigint
- Remove the following functions:
-
perf: optimize instruction cache allocations by using
VirtualMachine::load_data
#1441 -
feat: Add
print_output
flag tocairo-1
crate [#1575] (#1575) -
bugfixes(BREAKING): Fix memory hole count inconsistencies #[1585] (#1585)
- Output builtin memory segment is no longer skipped when counting memory holes
- Temporary memory cells now keep their accessed status when relocated
- BREAKING: Signature change:
get_memory_holes(&self, builtin_count: usize) -> Result<usize, MemoryError>
->get_memory_holes(&self, builtin_count: usize, has_output_builtin: bool) -> Result<usize, MemoryError>
-
feat: Add
cairo_pie_output
flag tocairo1-run
[#1581] (#1581) -
feat: Add
cairo_pie_output
flag tocairo_vm_cli
[#1578] (#1578)- Fix serialization of CairoPie to be fully compatible with the python version
- Add
CairoPie::write_zip_file
- Move handling of required and exclusive arguments in
cairo-vm-cli
to struct definition using clap derives
-
feat: Add doc + default impl for ResourceTracker trait [#1576] (#1576)
-
feat: Add
air_private_input
flag tocairo1-run
[#1559] (#1559) -
feat: Add
args
flag tocairo1-run
[#1551] (#1551) -
feat: Add
air_public_input
flag tocairo1-run
[#1539] (#1539) -
feat: Implement air_private_input #1552
-
feat: Add
proof_mode
flag tocairo1-run
[#1537] (#1537)- The cairo1-run crate no longer compiles and executes in proof_mode by default
- Add flag
proof_mode
to cairo1-run crate. Activating this flag will enable proof_mode compilation and execution
-
dev: bump cairo 1 compiler dep to 2.4 #1530
-
feat: Use
ProjectivePoint
from types-rs in ec_op builtin impl #1532 -
feat(BREAKING): Replace
cairo-felt
crate withstarknet-types-core
(0.0.5) #1408 -
feat(BREAKING): Add Cairo 1 proof mode compilation and execution [#1517] (#1517)
- In the cairo1-run crate, now the Cairo 1 Programs are compiled and executed in proof-mode
- BREAKING: Remove
CairoRunner.proof_mode: bool
field and replace it withCairoRunner.runner_mode: RunnerMode
-
perf: Add
extensive_hints
feature to prevent performance regression for the common use-case [#1503] (#1503)- Gates changes added by #1491 under the feature flag
extensive_hints
- Gates changes added by #1491 under the feature flag
-
chore: remove cancel-duplicates workflow #1497
-
feat: Handle
pc
s outside of program segment inVmException
[#1501] (#1501)VmException
now shows the full pc value instead of just the offset (VmException.pc
field type changed toRelocatable
)VmException.traceback
now shows the full pc value for each entry instead of hardcoding its index to 0.- Disable debug information for errors produced when
pc
is outside of the program segment (segment_index != 0).VmException
fieldsinst_location
&error_attr_value
will beNone
in such case.
-
feat: Allow running instructions from pcs outside the program segement #1493
-
BREAKING: Partially Revert
Optimize trace relocation #906
#1492- Remove methods
VirtualMachine::get_relocated_trace
&VirtualMachine::relocate_trace
. - Add
relocated_trace
field &relocate_trace
method toCairoRunner
. - Swap
TraceEntry
forRelocatedTraceEntry
type inwrite_encoded_trace
&PublicInput::new
signatures. - Now takes into account the program counter's segment index when building the execution trace instead of assuming it to be 0.
- Remove methods
-
feat: Add HintProcessor::execute_hint_extensive + refactor hint_ranges #1491
-
Add trait method
HintProcessorLogic::execute_hint_extensive
:- This method has a similar behaviour to
HintProcessorLogic::execute_hint
but it also returns aHintExtension
(type alias forHashMap<Relocatable, Vec<Box<dyn Any>>>
) that can be used to extend the current map of hints used by the VM. This behaviour achieves what thevm_load_data
primitive does for cairo-lang, and is needed to implement os hints. - This method is now used by the VM to execute hints instead of
execute_hint
, but it's default implementation callsexecute_hint
, so current implementors of theHintProcessor
trait won't notice any change.
- This method has a similar behaviour to
-
Signature changes:
pub fn step_hint(&mut self, hint_executor: &mut dyn HintProcessor, exec_scopes: &mut ExecutionScopes, hint_datas: &mut Vec<Box<dyn Any>>, constants: &HashMap<String, Felt252>) -> Result<(), VirtualMachineError>
->pub fn step_hint(&mut self, hint_processor: &mut dyn HintProcessor, exec_scopes: &mut ExecutionScopes, hint_datas: &mut Vec<Box<dyn Any>>, hint_ranges: &mut HashMap<Relocatable, HintRange>, constants: &HashMap<String, Felt252>) -> Result<(), VirtualMachineError>
pub fn step(&mut self, hint_executor: &mut dyn HintProcessor, exec_scopes: &mut ExecutionScopes, hint_data: &[Box<dyn Any>], constants: &HashMap<String, Felt252>) -> Result<(), VirtualMachineError>
->pub fn step(&mut self, hint_processor: &mut dyn HintProcessor, exec_scopes: &mut ExecutionScopes, hint_datas: &mut Vec<Box<dyn Any>>, hint_ranges: &mut HashMap<Relocatable, HintRange>, constants: &HashMap<String, Felt252>) -> Result<(), VirtualMachineError>
-
-
feat: add debugging capabilities behind
print
feature flag. #1476 -
feat: add
cairo_run_program
function that takes aProgram
as an arg. #1496
-
feat: Make PublicInput fields public #1474
-
chore: bump starknet-crypto to v0.6.1 #1469
-
feat: Implement the Serialize and Deserialize methods for the Program struct #1458
-
feat: Use only program builtins when running cairo 1 programs #1457
-
feat: Use latest cairo-vm version in cairo1-run crate #1455
-
feat: Implement a CLI to run cairo 1 programs #1370
-
fix: Fix string code of
BLAKE2S_ADD_UINT256
hint #1454
-
fix: Default to empty attributes vector when the field is missing from the program JSON #1450
-
fix: Change serialization of CairoPieMemory to match Python's binary format #1447
-
fix: Remove Deserialize derive from CairoPie and fix Serialize implementation to match Python's #1444
-
fix: ec_recover hints no longer panic when divisor is 0 #1433
-
feat: Implement the Serialize and Deserialize traits for the CairoPie struct #1438
-
fix: Using UINT256_HINT no longer panics when b is greater than 2^256 #1430
-
feat: Added a differential fuzzer for programs with whitelisted hints #1358
-
fix(breaking): Change return type of
get_execution_resources
toRunnerError
#1398 -
Don't build wasm-demo in
build
target + add ci job to run the wasm demo #1393- Adds default-members to workspace
- Crate
examples/wasm-demo
is no longer built duringmake build
make check
no longer compiles the cairo file used in the wasm-demo- Removes Makefile targets
examples/wasm-demo/src/array_sum.json
&example_program
wasm-demo
now uses the compiled cairo file incairo_programs
directory instead of its own copy
-
feat: Add
Program::new_for_proof
#1396
-
Add REDUCE_V2 hint #1420:
- Implement REDUCE_V2 hint
- Rename hint REDUCE -> REDUCE_V1
-
BREAKING: Add
disable_trace_padding
toCairoRunConfig
#1233 -
feat: Implement
CairoRunner.get_cairo_pie
#1375 -
fix: Compare air_public_inputs against python vm + Fix how public memory is built #391
BugFixes:
CairoRunner.finalize_segments
now builds the output builtin's public memory (if applicable).MemorySegmentManager.get_public_memory_addresses
logic fixed.MemorySegmentManager.finalize
no longer skips segments when their public memory is None
Minor changes:
VirtualMachine.get_public_memory_addresses
now strips the "_builtin" suffix from builtin namesMemorySegmentAddresses.stop_address
renamed tostop_ptr
Overall these changes make the the air public input file (obtained through the --air_public_input flag) equivalent to the ones outputted by the cairo-lang version
-
fix: Fix
SPLIT_FELT
hint #1387 -
refactor: combine
Program.hints
andProgram.hints_ranges
into custom collection #1366 -
fix: Fix div_mod #1383
- Fixes
div_mod
function so that it behaves like the cairo-lang version - Various functions in the
math_utils
crate can now return aMathError
:div_mod
,ec_add
,line_slope
,ec_double
,ec_double_slope
. - Fixes
UINT256_MUL_INV_MOD_P
hint so that it behaves like the python code.
- Fixes
-
fix: Handle error in hint
UINT256_MUL_DIV_MOD
when divides by zero #1367 -
Add HintError::SyscallError and VmErrors::HINT_ERROR_STR constant #1357
-
feat: make arbitrary feature also enable a
proptest::arbitrary::Arbitrary
implementation forFelt252
#1355 -
fix: correctly display invalid signature error message #1361
-
fix:
Program
comparison depending onhints_ranges
ordering #1351 -
feat: implement the
--air_public_input
flag to the runner for outputting public inputs into a file #1268 -
fix: CLI errors bad formatting and handling
-
perf: replace insertion with bit-setting in validated addresses #1208
-
fix: return error when a parsed hint's PC is invalid #1340
-
chore(deps): bump cairo-lang dependencies to v2.1.0-rc2 #1345
-
chore(examples): remove wee_alloc dependency from wasm-demo example and ensure-no_std dummy crate #1337
-
docs: improved crate documentation #1334
-
chore!: made
deserialize_utils
module private #1334 BREAKING:deserialize_utils
is no longer exported- functions
maybe_add_padding
,parse_value
, andtake_until_unbalanced
are no longer exported ReferenceParseError
is no more
-
perf: changed
ok_or
usage forok_or_else
in expensive cases #1332 -
feat: updated the old WASM example and moved it to
examples/wasm-demo
#1315 -
feat(fuzzing): add
arbitrary
feature to enable arbitrary derive inProgram
andCairoRunConfig
#1306 #1330 -
perf: remove pointless iterator from rc limits tracking #1316
-
feat(felt): add
from_bytes_le
andfrom_bytes_ne
methods toFelt252
#1326 -
perf: change
Program::shared_program_data::hints
fromHashMap<usize, Vec<Box<dyn Any>>>
toVec<Box<dyn Any>>
and refer to them as ranges stored in aVec<_>
indexed by PC with run time reductions of up to 12% #931 BREAKING:get_hint_dictionary(&self, &[HintReference], &mut dyn HintProcessor) -> Result<HashMap<usize, Vec<Box<dyn Any>>, VirtualMachineError>
->get_hint_data(self, &[HintReference], &mut dyn HintProcessor) -> Result<Vec<Box<dyn Any>, VirtualMachineError>
- Hook methods receive
&[Box<dyn Any>]
rather than&HashMap<usize, Vec<Box<dyn Any>>>
YANKED
YANKED
-
chore: update dependencies, particularly lamdaworks 0.1.2 -> 0.1.3 #1323
-
fix: fix
UINT256_MUL_DIV_MOD
hint #1320 -
feat: add dependency installation script
install.sh
#1298 -
fix: specify resolver version 2 in the virtual workspace's manifest #1311
-
feat: add
lambdaworks-felt
feature tocairo-vm-cli
#1308 -
chore: update dependencies, particularly clap 3.2 -> 4.3 #1309
- this removes dependency on atty, that's no longer mantained
-
chore: remove unused dependencies #1307
- rand_core
- serde_bytes
- rusty-hook (dev-dependency)
-
chore: bump
cairo-lang-starknet
andcairo-lang-casm
dependencies to 2.0.0 #1313
-
chore: change mentions of cairo-rs-py to cairo-vm-py #1296
-
rename github repo from https://github.com/lambdaclass/cairo-rs to https://github.com/lambdaclass/cairo-vm #1289
-
fix(security): avoid OOM crashes when programs jump to very high invalid addresses #1285
-
fix: add
to_bytes_be
to the felt whenlambdaworks-felt
feature is active #1290 -
chore: mark
modpow
andto_signed_bytes_le
as deprecated #1290 -
fix: bump lambdaworks-math to latest version, that fixes no-std support #1293
-
build: remove dependency to
thiserror
(usethiserror-no-std/std
instead) -
chore: use LambdaWorks' implementation of bit operations for
Felt252
#1291 -
update
cairo-lang-starknet
andcairo-lang-casm
dependencies to v2.0.0-rc6 #1299
-
feat: Add feature
lambdaworks-felt
tofelt
&cairo-vm
crates #1281Changes under this feature:
Felt252
now uses LambdaWorks'FieldElement
internally- BREAKING: some methods of
Felt252
were removed, namely:modpow
andto_signed_bytes_le
-
BREAKING: Integrate
RunResources
logic intoHintProcessor
trait #1274- Rename trait
HintProcessor
toHintProcessorLogic
- Add trait
ResourceTracker
- Trait
HintProcessor
is nowHintProcessor: HintProcessorLogic + ResourceTracker
BuiltinHintProcessor::new
&Cairo1HintProcessor::new
now receive the argumetrun_resources: RunResources
HintProcessorLogic::execute_hint
no longer receivesrun_resources: &mut RunResources
- Remove argument
run_resources: &mut RunResources
fromCairoRunner::run_until_pc
&CairoRunner::run_from_entrypoint
- Rename trait
-
build: remove unused implicit features from cairo-vm #1266
-
fix: updated the
custom_hint_example
and added it to the workspace #1258 -
Add path to cairo-vm README.md #1276
-
fix: change error returned when subtracting two
MaybeRelocatable
s to better reflect the cause #1271 -
fix: CLI error message when using --help #1270
-
fix:
dibit
hint no longer fails when called with anm
of zero #1247 -
fix(security): avoid denial of service on malicious input exploiting the scientific notation parser #1239
-
BREAKING: Change
RunResources
usage:-
Modify field type
RunResources.n_steps: Option<usize>,
-
Public Api Changes:
- CairoRunner::run_until_pc: Now receive a
&mut RunResources
instead of an&mut Option<RunResources>
- CairoRunner::run_from_entrypoint: Now receive a
&mut RunResources
instead of an&mut Option<RunResources>
- VirtualMachine::Step: Add
&mut RunResources
as input - Trait HintProcessor::execute_hint: Add
&mut RunResources
as an input
- CairoRunner::run_until_pc: Now receive a
-
-
perf: accumulate
min
andmax
instruction offsets during run to speed up range check #1080 BREAKING:Cairo_runner::get_perm_range_check_limits
no longer returns an error when called without trace enabled, as it no longer depends on it -
perf: process reference list on
Program
creation only #1214 Also keep them in aVec<_>
instead of aHashMap<_, _>
since it will be continuous anyway. BREAKING:HintProcessor::compile_hint
now receies a&[HintReference]
rather than&HashMap<usize, HintReference>
- Public
CairoRunner::get_reference_list
has been removed
-
BREAKING: Add no_std compatibility to cairo-vm (cairo-1-hints feature still not supported)
-
Move the vm to its own directory and crate, different from the workspace #1215
-
Add an
ensure_no_std
crate that the CI will use to check that new changes don't revertno_std
support #1215 #1232 -
replace the use of
num-prime::is_prime
by a custom implementation, therefore restoringno_std
compatibility #1238
-
-
BREAKING: Compute
ExecutionResources.n_steps
without requiring trace #1222CairoRunner::get_execution_resources
return'sn_steps
field value is now set tovm.current_step
instead of0
if bothoriginal_steps
andtrace
are set toNone
-
Add
RunResources::get_n_steps
method #1225 -
refactor: simplify
mem_eq
-
fix: pin Cairo compiler version #1220
-
perf: make
inner_rc_bound
a constant, improving performance of the range-check builtin -
fix: substraction of
MaybeRelocatable
always behaves as signed #1218
-
fix: fix overflow for
QUAD_BIT
andDI_BIT
hints #1209 Fixes #1205 -
fix: fix hints
UINT256_UNSIGNED_DIV_REM
&&UINT256_EXPANDED_UNSIGNED_DIV_REM
#1203 -
bugfix: fix deserialization of scientific notation with fractional values #1202
-
feat: implement
mem_eq
function to test for equality of two ranges in memory #1198 -
perf: use
mem_eq
inset_add
#1198 -
feat: wrap big variants of
HintError
,VirtualMachineError
,RunnerError
,MemoryError
,MathError
,InsufficientAllocatedCellsError
inBox
#1193- BREAKING: all tuple variants of
HintError
with a singleFelt252
or multiple elements now receive a singleBox
- BREAKING: all tuple variants of
-
Add
Program::builtins_len method
#1194 -
fix: Handle the deserialization of serde_json::Number with scientific notation (e.g.: Number(1e27)) in felt_from_number function #1188
-
feat: Add RunResources Struct #1175
- BREAKING: Modify
CairoRunner::run_until_pc
arity. Addrun_resources: &mut Option<RunResources>
input - BREAKING: Modify
CairoRunner::run_from_entrypoint
arity. Addrun_resources: &mut Option<RunResources>
input
- BREAKING: Modify
-
fix: Fix 'as_int' conversion usage in hints
ASSERT_250_BIT
&SIGNED_DIV_REM
#1191 -
bugfix: Use cairo constants in
ASSERT_250_BIT
hint #1187 -
bugfix: Fix
EC_DOUBLE_ASSIGN_NEW_X_V2
hint not takingSECP_P
value from the current execution scope #1186 -
fix: Fix hint
BIGINT_PACK_DIV_MOD
#1189 -
fix: Fix possible subtraction overflow in
QUAD_BIT
&DI_BIT
hints #1185- These hints now return an error when ids.m equals zero
-
fix: felt_from_number not properly returning parse errors #1012
-
fix: Fix felt sqrt and Signed impl #1150
- BREAKING: Fix
Felt252
methodsabs
,signum
,is_positive
,is_negative
andsqrt
- BREAKING: Remove function
math_utils::sqrt
(Now moved toFelt252::sqrt
)
- BREAKING: Fix
-
feat: Add method
CairoRunner::initialize_function_runner_cairo_1
#1151-
Add method
pub fn initialize_function_runner_cairo_1( &mut self, vm: &mut VirtualMachine, program_builtins: &[BuiltinName], ) -> Result<(), RunnerError>
toCairoRunner
-
BREAKING: Move field
builtins
fromSharedProgramData
toProgram
-
BREAKING: Remove argument
add_segment_arena_builtin
fromCairoRunner::initialize_function_runner
, it is now always false -
BREAKING: Add
segment_arena
enum variant toBuiltinName
-
-
Fix implementation of
InitSquashData
andShouldSkipSquashLoop
-
Add more hints to
Cairo1HintProcessor
#1171 #1143Cairo1HintProcessor
can now run the following hints:- Felt252DictEntryInit
- Felt252DictEntryUpdate
- GetCurrentAccessDelta
- InitSquashData
- AllocConstantSize
- GetCurrentAccessIndex
- ShouldContinueSquashLoop
- FieldSqrt
- Uint512DivMod
-
Add some small considerations regarding Cairo 1 programs #1144:
- Ignore Casm and Sierra files
- Add special flag to compile Cairo 1 programs
-
Make the VM able to run
CasmContractClass
files undercairo-1-hints
feature #1098- Implement
TryFrom<CasmContractClass> for Program
- Add
Cairo1HintProcessor
- Implement
YANKED
-
perf: insert elements from the tail in
load_data
so reallocation happens only once #1117 -
Add
CairoRunner::get_program method
#1123 -
Use to_signed_felt as function for felt252 as BigInt within [-P/2, P/2] range and use to_bigint as function for representation as BigInt. #1100
-
Implement hint on field_arithmetic lib #1090
BuiltinHintProcessor
now supports the following hints:%{ def split(num: int, num_bits_shift: int, length: int): a = [] for _ in range(length): a.append( num & ((1 << num_bits_shift) - 1) ) num = num >> num_bits_shift return tuple(a) def pack(z, num_bits_shift: int) -> int: limbs = (z.d0, z.d1, z.d2) return sum(limb << (num_bits_shift * i) for i, limb in enumerate(limbs)) a = pack(ids.a, num_bits_shift = 128) b = pack(ids.b, num_bits_shift = 128) p = pack(ids.p, num_bits_shift = 128) res = (a - b) % p res_split = split(res, num_bits_shift=128, length=3) ids.res.d0 = res_split[0] ids.res.d1 = res_split[1] ids.res.d2 = res_split[2] %}
-
Add missing hint on cairo_secp lib #1089:
BuiltinHintProcessor
now supports the following hint:from starkware.cairo.common.cairo_secp.secp_utils import pack slope = pack(ids.slope, PRIME) x0 = pack(ids.point0.x, PRIME) x1 = pack(ids.point1.x, PRIME) y0 = pack(ids.point0.y, PRIME) value = new_x = (pow(slope, 2, SECP_P) - x0 - x1) % SECP_P
-
Add missing hint on vrf.json whitelist #1055:
BuiltinHintProcessor
now supports the following hint:%{ PRIME = 2**255 - 19 II = pow(2, (PRIME - 1) // 4, PRIME) xx = ids.xx.low + (ids.xx.high<<128) x = pow(xx, (PRIME + 3) // 8, PRIME) if (x * x - xx) % PRIME != 0: x = (x * II) % PRIME if x % 2 != 0: x = PRIME - x ids.x.low = x & ((1<<128)-1) ids.x.high = x >> 128 %}
-
Implement hint variant for finalize_blake2s#1072
BuiltinHintProcessor
now supports the following hint:%{ # Add dummy pairs of input and output. from starkware.cairo.common.cairo_blake2s.blake2s_utils import IV, blake2s_compress _n_packed_instances = int(ids.N_PACKED_INSTANCES) assert 0 <= _n_packed_instances < 20 _blake2s_input_chunk_size_felts = int(ids.BLAKE2S_INPUT_CHUNK_SIZE_FELTS) assert 0 <= _blake2s_input_chunk_size_felts < 100 message = [0] * _blake2s_input_chunk_size_felts modified_iv = [IV[0] ^ 0x01010020] + IV[1:] output = blake2s_compress( message=message, h=modified_iv, t0=0, t1=0, f0=0xffffffff, f1=0, ) padding = (message + modified_iv + [0, 0xffffffff] + output) * (_n_packed_instances - 1) segments.write_arg(ids.blake2s_ptr_end, padding) %} ```
-
Implement fast_ec_add hint variant #1087
BuiltinHintProcessor
now supports the following hint:
```python
%{
from starkware.cairo.common.cairo_secp.secp_utils import SECP_P, pack
slope = pack(ids.slope, PRIME)
x0 = pack(ids.pt0.x, PRIME)
x1 = pack(ids.pt1.x, PRIME)
y0 = pack(ids.pt0.y, PRIME)
value = new_x = (pow(slope, 2, SECP_P) - x0 - x1) % SECP_P
%}
```
-
feat(hints): Add alternative string for hint IS_ZERO_PACK_EXTERNAL_SECP #1082
BuiltinHintProcessor
now supports the following hint:%{ from starkware.cairo.common.cairo_secp.secp_utils import pack x = pack(ids.x, PRIME) % SECP_P %}
-
Add alternative hint code for ec_double hint #1083
BuiltinHintProcessor
now supports the following hint:%{ from starkware.cairo.common.cairo_secp.secp_utils import SECP_P, pack slope = pack(ids.slope, PRIME) x = pack(ids.pt.x, PRIME) y = pack(ids.pt.y, PRIME) value = new_x = (pow(slope, 2, SECP_P) - 2 * x) % SECP_P %}
-
fix(security)!: avoid DoS on malicious insertion to memory #1099
- A program could crash the library by attempting to insert a value at an address with a big offset; fixed by trying to reserve to check for allocation failure
- A program could crash the program by exploiting an integer overflow when attempting to insert a value at an address with offset
usize::MAX
BREAKING: added a new error variant
MemoryError::VecCapacityExceeded
-
perf: specialize addition for
u64
andFelt252
#932- Avoids the creation of a new
Felt252
instance for additions with a very restricted valid range - This impacts specially the addition of
Relocatable
withFelt252
values inupdate_pc
, which take a significant amount of time in some benchmarks
- Avoids the creation of a new
-
fix(starknet-crypto): bump version to
0.5.0
#1088 -
feat(hints): Add alternative string for hint IS_ZERO_PACK #1081
BuiltinHintProcessor
now supports the following hint:%{ from starkware.cairo.common.cairo_secp.secp_utils import SECP_P, pack x = pack(ids.x, PRIME) % SECP_P %}
-
Add missing hints
NewHint#55
,NewHint#56
, andNewHint#57
#1077BuiltinHintProcessor
now supports the following hints:from starkware.cairo.common.cairo_secp.secp_utils import pack SECP_P=2**255-19 x = pack(ids.x, PRIME) % SECP_P
from starkware.cairo.common.cairo_secp.secp_utils import pack SECP_P=2**255-19 value = pack(ids.x, PRIME) % SECP_P
SECP_P=2**255-19 from starkware.python.math_utils import div_mod value = x_inv = div_mod(1, x, SECP_P)
-
Implement hint for
starkware.cairo.common.cairo_keccak.keccak._copy_inputs
as described by whiteliststarknet/security/whitelists/cairo_keccak.json
#1058BuiltinHintProcessor
now supports the following hint:%{ ids.full_word = int(ids.n_bytes >= 8) %}
-
perf: cache decoded instructions #944
- Creates a new cache field in
VirtualMachine
that stores theInstruction
instances as they get decoded from memory, significantly reducing decoding overhead, with gains up to 9% in runtime according to benchmarks in the performance server
- Creates a new cache field in
-
Add alternative hint code for nondet_bigint3 hint #1071
BuiltinHintProcessor
now supports the following hint:%{ from starkware.cairo.common.cairo_secp.secp_utils import split segments.write_arg(ids.res.address_, split(value)) %}
-
Add missing hint on vrf.json lib #1052:
BuiltinHintProcessor
now supports the following hint:%{ from starkware.cairo.common.cairo_secp.secp_utils import pack SECP_P = 2**255-19 slope = pack(ids.slope, PRIME) x0 = pack(ids.point0.x, PRIME) x1 = pack(ids.point1.x, PRIME) y0 = pack(ids.point0.y, PRIME) value = new_x = (pow(slope, 2, SECP_P) - x0 - x1) % SECP_P %}
-
Implement hint for cairo_sha256_arbitrary_input_length whitelist #1091
BuiltinHintProcessor
now supports the following hint:%{ from starkware.cairo.common.cairo_sha256.sha256_utils import ( compute_message_schedule, sha2_compress_function) _sha256_input_chunk_size_felts = int(ids.SHA256_INPUT_CHUNK_SIZE_FELTS) assert 0 <= _sha256_input_chunk_size_felts < 100 _sha256_state_size_felts = int(ids.SHA256_STATE_SIZE_FELTS) assert 0 <= _sha256_state_size_felts < 100 w = compute_message_schedule(memory.get_range( ids.sha256_start, _sha256_input_chunk_size_felts)) new_state = sha2_compress_function(memory.get_range(ids.state, _sha256_state_size_felts), w) segments.write_arg(ids.output, new_state) %}
-
Add missing hint on vrf.json lib #1053:
BuiltinHintProcessor
now supports the following hint:%{ from starkware.cairo.common.cairo_secp.secp_utils import SECP_P, pack SECP_P = 2**255-19 slope = pack(ids.slope, PRIME) x = pack(ids.point.x, PRIME) y = pack(ids.point.y, PRIME) value = new_x = (pow(slope, 2, SECP_P) - 2 * x) % SECP_P %}
-
Implement hint on 0.6.0.json whitelist #1044:
BuiltinHintProcessor
now supports the following hints:%{ ids.a_lsb = ids.a & 1 ids.b_lsb = ids.b & 1 %}
-
Implement hint for
starkware.cairo.common.cairo_keccak.keccak._block_permutation
as described by whiteliststarknet/security/whitelists/cairo_keccak.json
#1046BuiltinHintProcessor
now supports the following hint:%{ from starkware.cairo.common.cairo_keccak.keccak_utils import keccak_func _keccak_state_size_felts = int(ids.KECCAK_STATE_SIZE_FELTS) assert 0 <= _keccak_state_size_felts < 100 output_values = keccak_func(memory.get_range( ids.keccak_ptr_start, _keccak_state_size_felts)) segments.write_arg(ids.output, output_values) %}
-
Implement hint on cairo_blake2s whitelist #1040
BuiltinHintProcessor
now supports the following hint:%{ from starkware.cairo.common.cairo_blake2s.blake2s_utils import IV, blake2s_compress _blake2s_input_chunk_size_felts = int(ids.BLAKE2S_INPUT_CHUNK_SIZE_FELTS) assert 0 <= _blake2s_input_chunk_size_felts < 100 new_state = blake2s_compress( message=memory.get_range(ids.blake2s_start, _blake2s_input_chunk_size_felts), h=[IV[0] ^ 0x01010020] + IV[1:], t0=ids.n_bytes, t1=0, f0=0xffffffff, f1=0, ) segments.write_arg(ids.output, new_state) %}
-
Implement hint on cairo_blake2s whitelist #1039
BuiltinHintProcessor
now supports the following hint:%{ # Add dummy pairs of input and output. from starkware.cairo.common.cairo_blake2s.blake2s_utils import IV, blake2s_compress _n_packed_instances = int(ids.N_PACKED_INSTANCES) assert 0 <= _n_packed_instances < 20 _blake2s_input_chunk_size_felts = int(ids.BLAKE2S_INPUT_CHUNK_SIZE_FELTS) assert 0 <= _blake2s_input_chunk_size_felts < 100 message = [0] * _blake2s_input_chunk_size_felts modified_iv = [IV[0] ^ 0x01010020] + IV[1:] output = blake2s_compress( message=message, h=modified_iv, t0=0, t1=0, f0=0xffffffff, f1=0, ) padding = (modified_iv + message + [0, 0xffffffff] + output) * (_n_packed_instances - 1) segments.write_arg(ids.blake2s_ptr_end, padding) %}
-
Add
Program::iter_identifiers(&self) -> Iterator<Item = (&str, &Identifier)>
to get an iterator over the program's identifiers #1079 -
Implement hint on
assert_le_felt
for versions 0.6.0 and 0.8.2 #1047:BuiltinHintProcessor
now supports the following hints:%{ from starkware.cairo.common.math_utils import assert_integer assert_integer(ids.a) assert_integer(ids.b) assert (ids.a % PRIME) <= (ids.b % PRIME), \ f'a = {ids.a % PRIME} is not less than or equal to b = {ids.b % PRIME}.' %}
%{ from starkware.cairo.common.math_utils import assert_integer assert_integer(ids.a) assert_integer(ids.b) a = ids.a % PRIME b = ids.b % PRIME assert a <= b, f'a = {a} is not less than or equal to b = {b}.' ids.small_inputs = int( a < range_check_builtin.bound and (b - a) < range_check_builtin.bound) %}
-
Add missing hints on whitelist #1073:
BuiltinHintProcessor
now supports the following hints:ids.is_250 = 1 if ids.addr < 2**250 else 0
# Verify the assumptions on the relationship between 2**250, ADDR_BOUND and PRIME. ADDR_BOUND = ids.ADDR_BOUND % PRIME assert (2**250 < ADDR_BOUND <= 2**251) and (2 * 2**250 < PRIME) and ( ADDR_BOUND * 2 > PRIME), \ 'normalize_address() cannot be used with the current constants.' ids.is_small = 1 if ids.addr < ADDR_BOUND else 0
-
Implement hint on ec_recover.json whitelist #1038:
BuiltinHintProcessor
now supports the following hint:%{ value = k = product // m %}
-
Implement hint on ec_recover.json whitelist #1037:
BuiltinHintProcessor
now supports the following hint:%{ from starkware.cairo.common.cairo_secp.secp_utils import pack from starkware.python.math_utils import div_mod, safe_div a = pack(ids.a, PRIME) b = pack(ids.b, PRIME) product = a * b m = pack(ids.m, PRIME) value = res = product % m %}
-
Implement hint for
starkware.cairo.common.cairo_keccak.keccak.finalize_keccak
as described by whiteliststarknet/security/whitelists/cairo_keccak.json
#1041BuiltinHintProcessor
now supports the following hint:%{ # Add dummy pairs of input and output. _keccak_state_size_felts = int(ids.KECCAK_STATE_SIZE_FELTS) _block_size = int(ids.BLOCK_SIZE) assert 0 <= _keccak_state_size_felts < 100 assert 0 <= _block_size < 1000 inp = [0] * _keccak_state_size_felts padding = (inp + keccak_func(inp)) * _block_size segments.write_arg(ids.keccak_ptr_end, padding) %}
-
Implement hint on ec_recover.json whitelist #1036:
BuiltinHintProcessor
now supports the following hint:%{ from starkware.cairo.common.cairo_secp.secp_utils import pack from starkware.python.math_utils import div_mod, safe_div a = pack(ids.a, PRIME) b = pack(ids.b, PRIME) value = res = a - b %}
-
Add missing hint on vrf.json lib #1054:
BuiltinHintProcessor
now supports the following hint:from starkware.cairo.common.cairo_secp.secp_utils import pack SECP_P = 2**255-19 y = pack(ids.point.y, PRIME) % SECP_P # The modulo operation in python always returns a nonnegative number. value = (-y) % SECP_P
-
Implement hint on ec_recover.json whitelist #1032:
BuiltinHintProcessor
now supports the following hint:%{ from starkware.cairo.common.cairo_secp.secp_utils import pack from starkware.python.math_utils import div_mod, safe_div N = pack(ids.n, PRIME) x = pack(ids.x, PRIME) % N s = pack(ids.s, PRIME) % N, value = res = div_mod(x, s, N) %}
-
Implement hints on field_arithmetic lib (Part 2) #1004
BuiltinHintProcessor
now supports the following hint:%{ from starkware.python.math_utils import div_mod def split(num: int, num_bits_shift: int, length: int): a = [] for _ in range(length): a.append( num & ((1 << num_bits_shift) - 1) ) num = num >> num_bits_shift return tuple(a) def pack(z, num_bits_shift: int) -> int: limbs = (z.d0, z.d1, z.d2) return sum(limb << (num_bits_shift * i) for i, limb in enumerate(limbs)) a = pack(ids.a, num_bits_shift = 128) b = pack(ids.b, num_bits_shift = 128) p = pack(ids.p, num_bits_shift = 128) # For python3.8 and above the modular inverse can be computed as follows: # b_inverse_mod_p = pow(b, -1, p) # Instead we use the python3.7-friendly function div_mod from starkware.python.math_utils b_inverse_mod_p = div_mod(1, b, p) b_inverse_mod_p_split = split(b_inverse_mod_p, num_bits_shift=128, length=3) ids.b_inverse_mod_p.d0 = b_inverse_mod_p_split[0] ids.b_inverse_mod_p.d1 = b_inverse_mod_p_split[1] ids.b_inverse_mod_p.d2 = b_inverse_mod_p_split[2] %}
-
Optimizations for hash builtin #1029:
- Track the verified addresses by offset in a
Vec<bool>
rather than storing the address in aVec<Relocatable>
- Track the verified addresses by offset in a
-
Add missing hint on vrf.json whitelist #1056:
BuiltinHintProcessor
now supports the following hint:%{ from starkware.python.math_utils import ec_double_slope from starkware.cairo.common.cairo_secp.secp_utils import pack SECP_P = 2**255-19 # Compute the slope. x = pack(ids.point.x, PRIME) y = pack(ids.point.y, PRIME) value = slope = ec_double_slope(point=(x, y), alpha=42204101795669822316448953119945047945709099015225996174933988943478124189485, p=SECP_P) %}
-
Add missing hint on vrf.json whitelist #1035:
BuiltinHintProcessor
now supports the following hint:%{ from starkware.python.math_utils import line_slope from starkware.cairo.common.cairo_secp.secp_utils import pack SECP_P = 2**255-19 # Compute the slope. x0 = pack(ids.point0.x, PRIME) y0 = pack(ids.point0.y, PRIME) x1 = pack(ids.point1.x, PRIME) y1 = pack(ids.point1.y, PRIME) value = slope = line_slope(point1=(x0, y0), point2=(x1, y1), p=SECP_P) %}
-
Add missing hint on vrf.json whitelist #1035:
BuiltinHintProcessor
now supports the following hint:%{ from starkware.cairo.common.cairo_secp.secp_utils import pack SECP_P = 2**255-19 to_assert = pack(ids.val, PRIME) q, r = divmod(pack(ids.val, PRIME), SECP_P) assert r == 0, f"verify_zero: Invalid input {ids.val.d0, ids.val.d1, ids.val.d2}." ids.q = q % PRIME %}
-
Add missing hint on vrf.json whitelist #1000:
BuiltinHintProcessor
now supports the following hint:def pack_512(u, num_bits_shift: int) -> int: limbs = (u.d0, u.d1, u.d2, u.d3) return sum(limb << (num_bits_shift * i) for i, limb in enumerate(limbs)) x = pack_512(ids.x, num_bits_shift = 128) p = ids.p.low + (ids.p.high << 128) x_inverse_mod_p = pow(x,-1, p) x_inverse_mod_p_split = (x_inverse_mod_p & ((1 << 128) - 1), x_inverse_mod_p >> 128) ids.x_inverse_mod_p.low = x_inverse_mod_p_split[0] ids.x_inverse_mod_p.high = x_inverse_mod_p_split[1]
-
BREAKING CHANGE: Fix
CairoRunner::get_memory_holes
#1027:- Skip builtin segements when counting memory holes
- Check amount of memory holes for all tests in cairo_run_test
- Remove duplicated tests in cairo_run_test
- BREAKING CHANGE:
MemorySegmentManager.get_memory_holes
now also receives the amount of builtins in the vm. Signature is nowpub fn get_memory_holes(&self, builtin_count: usize) -> Result<usize, MemoryError>
-
Add missing hints on cairo_secp lib #1026:
BuiltinHintProcessor
now supports the following hints:from starkware.cairo.common.cairo_secp.secp256r1_utils import SECP256R1_ALPHA as ALPHA
and:
from starkware.cairo.common.cairo_secp.secp256r1_utils import SECP256R1_N as N
-
Add missing hint on vrf.json lib #1043:
BuiltinHintProcessor
now supports the following hint:from starkware.python.math_utils import div_mod def split(a: int): return (a & ((1 << 128) - 1), a >> 128) def pack(z, num_bits_shift: int) -> int: limbs = (z.low, z.high) return sum(limb << (num_bits_shift * i) for i, limb in enumerate(limbs)) a = pack(ids.a, 128) b = pack(ids.b, 128) p = pack(ids.p, 128) # For python3.8 and above the modular inverse can be computed as follows: # b_inverse_mod_p = pow(b, -1, p) # Instead we use the python3.7-friendly function div_mod from starkware.python.math_utils b_inverse_mod_p = div_mod(1, b, p) b_inverse_mod_p_split = split(b_inverse_mod_p) ids.b_inverse_mod_p.low = b_inverse_mod_p_split[0] ids.b_inverse_mod_p.high = b_inverse_mod_p_split[1]
-
Add missing hints
NewHint#35
andNewHint#36
#975BuiltinHintProcessor
now supports the following hint:from starkware.cairo.common.cairo_secp.secp_utils import pack from starkware.cairo.common.math_utils import as_int from starkware.python.math_utils import div_mod, safe_div p = pack(ids.P, PRIME) x = pack(ids.x, PRIME) + as_int(ids.x.d3, PRIME) * ids.BASE ** 3 + as_int(ids.x.d4, PRIME) * ids.BASE ** 4 y = pack(ids.y, PRIME) value = res = div_mod(x, y, p)
k = safe_div(res * y - x, p) value = k if k > 0 else 0 - k ids.flag = 1 if k > 0 else 0
-
Add missing hint on cairo_secp lib #1057:
BuiltinHintProcessor
now supports the following hint:from starkware.cairo.common.cairo_secp.secp_utils import pack from starkware.python.math_utils import ec_double_slope # Compute the slope. x = pack(ids.point.x, PRIME) y = pack(ids.point.y, PRIME) value = slope = ec_double_slope(point=(x, y), alpha=ALPHA, p=SECP_P)
-
Add missing hint on uint256_improvements lib #1025:
BuiltinHintProcessor
now supports the following hint:from starkware.python.math_utils import isqrt n = (ids.n.high << 128) + ids.n.low root = isqrt(n) assert 0 <= root < 2 ** 128 ids.root = root
-
Add missing hint on vrf.json lib #1045:
BuiltinHintProcessor
now supports the following hint:from starkware.python.math_utils import is_quad_residue, sqrt def split(a: int): return (a & ((1 << 128) - 1), a >> 128) def pack(z) -> int: return z.low + (z.high << 128) generator = pack(ids.generator) x = pack(ids.x) p = pack(ids.p) success_x = is_quad_residue(x, p) root_x = sqrt(x, p) if success_x else None success_gx = is_quad_residue(generator*x, p) root_gx = sqrt(generator*x, p) if success_gx else None # Check that one is 0 and the other is 1 if x != 0: assert success_x + success_gx == 1 # `None` means that no root was found, but we need to transform these into a felt no matter what if root_x == None: root_x = 0 if root_gx == None: root_gx = 0 ids.success_x = int(success_x) ids.success_gx = int(success_gx) split_root_x = split(root_x) # print('split root x', split_root_x) split_root_gx = split(root_gx) ids.sqrt_x.low = split_root_x[0] ids.sqrt_x.high = split_root_x[1] ids.sqrt_gx.low = split_root_gx[0] ids.sqrt_gx.high = split_root_gx[1]
-
Add missing hint on uint256_improvements lib #1024:
BuiltinHintProcessor
now supports the following hint:res = ids.a + ids.b ids.carry = 1 if res >= ids.SHIFT else 0
-
BREAKING CHANGE: move
Program::identifiers
toSharedProgramData::identifiers
#1023- Optimizes
CairoRunner::new
, needed for sequencers and other workflows reusing the sameProgram
instance acrossCairoRunner
s - Breaking change: make all fields in
Program
andSharedProgramData
pub(crate)
, since we break by moving the field let's make it the last break for this struct - Add
Program::get_identifier(&self, id: &str) -> &Identifier
to get a single identifier by name
- Optimizes
-
Implement hints on field_arithmetic lib#985
BuiltinHintProcessor
now supports the following hint:%{ from starkware.python.math_utils import is_quad_residue, sqrt def split(num: int, num_bits_shift: int = 128, length: int = 3): a = [] for _ in range(length): a.append( num & ((1 << num_bits_shift) - 1) ) num = num >> num_bits_shift return tuple(a) def pack(z, num_bits_shift: int = 128) -> int: limbs = (z.d0, z.d1, z.d2) return sum(limb << (num_bits_shift * i) for i, limb in enumerate(limbs)) generator = pack(ids.generator) x = pack(ids.x) p = pack(ids.p) success_x = is_quad_residue(x, p) root_x = sqrt(x, p) if success_x else None success_gx = is_quad_residue(generator*x, p) root_gx = sqrt(generator*x, p) if success_gx else None # Check that one is 0 and the other is 1 if x != 0: assert success_x + success_gx ==1 # `None` means that no root was found, but we need to transform these into a felt no matter what if root_x == None: root_x = 0 if root_gx == None: root_gx = 0 ids.success_x = int(success_x) ids.success_gx = int(success_gx) split_root_x = split(root_x) split_root_gx = split(root_gx) ids.sqrt_x.d0 = split_root_x[0] ids.sqrt_x.d1 = split_root_x[1] ids.sqrt_x.d2 = split_root_x[2] ids.sqrt_gx.d0 = split_root_gx[0] ids.sqrt_gx.d1 = split_root_gx[1] ids.sqrt_gx.d2 = split_root_gx[2] %}
-
Add missing hint on vrf.json lib #1050:
BuiltinHintProcessor
now supports the following hint:sum_low = ids.a.low + ids.b.low ids.carry_low = 1 if sum_low >= ids.SHIFT else 0
-
Add missing hint on uint256_improvements lib #1016:
BuiltinHintProcessor
now supports the following hint:def split(num: int, num_bits_shift: int = 128, length: int = 2): a = [] for _ in range(length): a.append( num & ((1 << num_bits_shift) - 1) ) num = num >> num_bits_shift return tuple(a) def pack(z, num_bits_shift: int = 128) -> int: limbs = (z.low, z.high) return sum(limb << (num_bits_shift * i) for i, limb in enumerate(limbs)) a = pack(ids.a) b = pack(ids.b) res = (a - b)%2**256 res_split = split(res) ids.res.low = res_split[0] ids.res.high = res_split[1]
-
Implement hint on vrf.json lib #1049
BuiltinHintProcessor
now supports the following hint:def split(num: int, num_bits_shift: int, length: int): a = [] for _ in range(length): a.append( num & ((1 << num_bits_shift) - 1) ) num = num >> num_bits_shift return tuple(a) def pack(z, num_bits_shift: int) -> int: limbs = (z.d0, z.d1, z.d2) return sum(limb << (num_bits_shift * i) for i, limb in enumerate(limbs)) def pack_extended(z, num_bits_shift: int) -> int: limbs = (z.d0, z.d1, z.d2, z.d3, z.d4, z.d5) return sum(limb << (num_bits_shift * i) for i, limb in enumerate(limbs)) a = pack_extended(ids.a, num_bits_shift = 128) div = pack(ids.div, num_bits_shift = 128) quotient, remainder = divmod(a, div) quotient_split = split(quotient, num_bits_shift=128, length=6) ids.quotient.d0 = quotient_split[0] ids.quotient.d1 = quotient_split[1] ids.quotient.d2 = quotient_split[2] ids.quotient.d3 = quotient_split[3] ids.quotient.d4 = quotient_split[4] ids.quotient.d5 = quotient_split[5] remainder_split = split(remainder, num_bits_shift=128, length=3) ids.remainder.d0 = remainder_split[0] ids.remainder.d1 = remainder_split[1] ids.remainder.d2 = remainder_split[2]
Note: this hint is similar to the one in #983, but with some trailing whitespace removed
-
Add missing hint on vrf.json whitelist #1030:
BuiltinHintProcessor
now supports the following hint:def split(num: int, num_bits_shift: int, length: int): a = [] for _ in range(length): a.append( num & ((1 << num_bits_shift) - 1) ) num = num >> num_bits_shift return tuple(a) def pack(z, num_bits_shift: int) -> int: limbs = (z.low, z.high) return sum(limb << (num_bits_shift * i) for i, limb in enumerate(limbs)) def pack_extended(z, num_bits_shift: int) -> int: limbs = (z.d0, z.d1, z.d2, z.d3) return sum(limb << (num_bits_shift * i) for i, limb in enumerate(limbs)) x = pack_extended(ids.x, num_bits_shift = 128) div = pack(ids.div, num_bits_shift = 128) quotient, remainder = divmod(x, div) quotient_split = split(quotient, num_bits_shift=128, length=4) ids.quotient.d0 = quotient_split[0] ids.quotient.d1 = quotient_split[1] ids.quotient.d2 = quotient_split[2] ids.quotient.d3 = quotient_split[3] remainder_split = split(remainder, num_bits_shift=128, length=2) ids.remainder.low = remainder_split[0] ids.remainder.high = remainder_split[1]
-
Add method
Program::data_len(&self) -> usize
to get the number of data cells in a given program #1022 -
Add missing hint on uint256_improvements lib #1013:
BuiltinHintProcessor
now supports the following hint:a = (ids.a.high << 128) + ids.a.low div = (ids.div.b23 << 128) + ids.div.b01 quotient, remainder = divmod(a, div) ids.quotient.low = quotient & ((1 << 128) - 1) ids.quotient.high = quotient >> 128 ids.remainder.low = remainder & ((1 << 128) - 1) ids.remainder.high = remainder >> 128
-
Add missing hint on cairo_secp lib #1010:
BuiltinHintProcessor
now supports the following hint:memory[ap] = int(x == 0)
-
Implement hint on
get_felt_bitlength
#993BuiltinHintProcessor
now supports the following hint:x = ids.x ids.bit_length = x.bit_length()
Used by the
Garaga
library functionget_felt_bitlength
-
Add missing hint on cairo_secp lib #1009:
BuiltinHintProcessor
now supports the following hint:ids.dibit = ((ids.scalar_u >> ids.m) & 1) + 2 * ((ids.scalar_v >> ids.m) & 1)
-
Add getters to read properties of a
Program
#1017:prime(&self) -> &str
: get the prime associated to data in hex representationiter_data(&self) -> Iterator<Item = &MaybeRelocatable>
: get an iterator over all elements in the program dataiter_builtins(&self) -> Iterator<Item = &BuiltinName>
: get an iterator over the names of required builtins
-
Add missing hint on cairo_secp lib #1008:
BuiltinHintProcessor
now supports the following hint:ids.len_hi = max(ids.scalar_u.d2.bit_length(), ids.scalar_v.d2.bit_length())-1
-
Update
starknet-crypto
to version0.4.3
#1011- The new version carries an 85% reduction in execution time for ECDSA signature verification
-
BREAKING CHANGE: refactor
Program
to optimizeProgram::clone
#999- Breaking change: many fields that were (unnecessarily) public become hidden by the refactor.
-
BREAKING CHANGE: Add _builtin suffix to builtin names e.g.: output -> output_builtin #1005
-
Implement hint on uint384_extension lib #983
BuiltinHintProcessor
now supports the following hint:def split(num: int, num_bits_shift: int, length: int): a = [] for _ in range(length): a.append( num & ((1 << num_bits_shift) - 1) ) num = num >> num_bits_shift return tuple(a) def pack(z, num_bits_shift: int) -> int: limbs = (z.d0, z.d1, z.d2) return sum(limb << (num_bits_shift * i) for i, limb in enumerate(limbs)) def pack_extended(z, num_bits_shift: int) -> int: limbs = (z.d0, z.d1, z.d2, z.d3, z.d4, z.d5) return sum(limb << (num_bits_shift * i) for i, limb in enumerate(limbs)) a = pack_extended(ids.a, num_bits_shift = 128) div = pack(ids.div, num_bits_shift = 128) quotient, remainder = divmod(a, div) quotient_split = split(quotient, num_bits_shift=128, length=6) ids.quotient.d0 = quotient_split[0] ids.quotient.d1 = quotient_split[1] ids.quotient.d2 = quotient_split[2] ids.quotient.d3 = quotient_split[3] ids.quotient.d4 = quotient_split[4] ids.quotient.d5 = quotient_split[5] remainder_split = split(remainder, num_bits_shift=128, length=3) ids.remainder.d0 = remainder_split[0] ids.remainder.d1 = remainder_split[1] ids.remainder.d2 = remainder_split[2]
-
BREAKING CHANGE: optimization for instruction decoding #942:
- Avoids copying immediate arguments to the
Instruction
structure, as they get inferred from the offset anyway - Breaking: removal of the field
Instruction::imm
- Avoids copying immediate arguments to the
-
Add missing
\n
character in traceback string #997- BugFix: Add missing
\n
character after traceback lines when the filename is missing ("Unknown Location")
- BugFix: Add missing
-
0.11 Support
- Add missing hints #1014:
BuiltinHintProcessor
now supports the following hints:and:from starkware.cairo.common.cairo_secp.secp256r1_utils import SECP256R1_P as SECP_P
from starkware.cairo.common.cairo_secp.secp_utils import pack from starkware.python.math_utils import line_slope # Compute the slope. x0 = pack(ids.point0.x, PRIME) y0 = pack(ids.point0.y, PRIME) x1 = pack(ids.point1.x, PRIME) y1 = pack(ids.point1.y, PRIME) value = slope = line_slope(point1=(x0, y0), point2=(x1, y1), p=SECP_P)
- Add missing hints on cairo_secp lib #991:
BuiltinHintProcessor
now supports the following hints:and:from starkware.cairo.common.cairo_secp.secp_utils import pack from starkware.python.math_utils import div_mod, safe_div N = 0xfffffffffffffffffffffffffffffffebaaedce6af48a03bbfd25e8cd0364141 x = pack(ids.x, PRIME) % N s = pack(ids.s, PRIME) % N value = res = div_mod(x, s, N)
value = k = safe_div(res * s - x, N)
- Layouts update #874
- Keccak builtin updated #873, #883
- Changes to
ec_op
#876 - Poseidon builtin #875
- Renamed Felt to Felt252 #899
- Added SegmentArenaBuiltinRunner #913
- Added
program_segment_size
argument toverify_secure_runner
&run_from_entrypoint
#928 - Added dynamic layout #879
get_segment_size
was exposed #934
- Add missing hints #1014:
-
Add missing hint on cairo_secp lib #1006:
BuiltinHintProcessor
now supports the following hint:ids.quad_bit = ( 8 * ((ids.scalar_v >> ids.m) & 1) + 4 * ((ids.scalar_u >> ids.m) & 1) + 2 * ((ids.scalar_v >> (ids.m - 1)) & 1) + ((ids.scalar_u >> (ids.m - 1)) & 1) )
-
Add missing hint on cairo_secp lib #1003:
BuiltinHintProcessor
now supports the following hint:from starkware.cairo.common.cairo_secp.secp_utils import pack x = pack(ids.x, PRIME) % SECP_P
-
Add missing hint on cairo_secp lib #996:
BuiltinHintProcessor
now supports the following hint:from starkware.python.math_utils import div_mod value = x_inv = div_mod(1, x, SECP_P)
-
Add missing hints on cairo_secp lib #994:
BuiltinHintProcessor
now supports the following hints:from starkware.cairo.common.cairo_secp.secp_utils import pack from starkware.python.math_utils import div_mod, safe_div a = pack(ids.a, PRIME) b = pack(ids.b, PRIME) value = res = div_mod(a, b, N)
value = k_plus_one = safe_div(res * b - a, N) + 1
-
Add missing hint on cairo_secp lib #992:
BuiltinHintProcessor
now supports the following hint:from starkware.cairo.common.cairo_secp.secp_utils import pack q, r = divmod(pack(ids.val, PRIME), SECP_P) assert r == 0, f"verify_zero: Invalid input {ids.val.d0, ids.val.d1, ids.val.d2}." ids.q = q % PRIME
-
Add missing hint on cairo_secp lib #990:
BuiltinHintProcessor
now supports the following hint:from starkware.cairo.common.cairo_secp.secp_utils import pack slope = pack(ids.slope, PRIME) x = pack(ids.point.x, PRIME) y = pack(ids.point.y, PRIME) value = new_x = (pow(slope, 2, SECP_P) - 2 * x) % SECP_P
-
Add missing hint on cairo_secp lib #989:
BuiltinHintProcessor
now supports the following hint:from starkware.cairo.common.cairo_secp.secp_utils import SECP_P q, r = divmod(pack(ids.val, PRIME), SECP_P) assert r == 0, f"verify_zero: Invalid input {ids.val.d0, ids.val.d1, ids.val.d2}." ids.q = q % PRIME
-
Add missing hint on cairo_secp lib #986:
BuiltinHintProcessor
now supports the following hint:from starkware.cairo.common.cairo_secp.secp_utils import SECP_P, pack from starkware.python.math_utils import div_mod # Compute the slope. x = pack(ids.pt.x, PRIME) y = pack(ids.pt.y, PRIME) value = slope = div_mod(3 * x ** 2, 2 * y, SECP_P)
-
Add missing hint on cairo_secp lib #984:
BuiltinHintProcessor
now supports the following hint:from starkware.cairo.common.cairo_secp.secp_utils import SECP_P, pack from starkware.python.math_utils import div_mod # Compute the slope. x0 = pack(ids.pt0.x, PRIME) y0 = pack(ids.pt0.y, PRIME) x1 = pack(ids.pt1.x, PRIME) y1 = pack(ids.pt1.y, PRIME) value = slope = div_mod(y0 - y1, x0 - x1, SECP_P)
-
Implement hints on uint384 lib (Part 2) #971
BuiltinHintProcessor
now supports the following hint:memory[ap] = 1 if 0 <= (ids.a.d2 % PRIME) < 2 ** 127 else 0
-
Add alternative hint code for hint on _block_permutation used by 0.10.3 whitelist #958
BuiltinHintProcessor
now supports the following hint:from starkware.cairo.common.keccak_utils.keccak_utils import keccak_func _keccak_state_size_felts = int(ids.KECCAK_STATE_SIZE_FELTS) assert 0 <= _keccak_state_size_felts < 100 output_values = keccak_func(memory.get_range( ids.keccak_ptr - _keccak_state_size_felts, _keccak_state_size_felts)) segments.write_arg(ids.keccak_ptr, output_values)
-
Make hints code
src/hint_processor/builtin_hint_processor/hint_code.rs
public #988 -
Implement hints on uint384 lib (Part 1) #960
BuiltinHintProcessor
now supports the following hints:def split(num: int, num_bits_shift: int, length: int): a = [] for _ in range(length): a.append( num & ((1 << num_bits_shift) - 1) ) num = num >> num_bits_shift return tuple(a) def pack(z, num_bits_shift: int) -> int: limbs = (z.d0, z.d1, z.d2) return sum(limb << (num_bits_shift * i) for i, limb in enumerate(limbs)) a = pack(ids.a, num_bits_shift = 128) div = pack(ids.div, num_bits_shift = 128) quotient, remainder = divmod(a, div) quotient_split = split(quotient, num_bits_shift=128, length=3) assert len(quotient_split) == 3 ids.quotient.d0 = quotient_split[0] ids.quotient.d1 = quotient_split[1] ids.quotient.d2 = quotient_split[2] remainder_split = split(remainder, num_bits_shift=128, length=3) ids.remainder.d0 = remainder_split[0] ids.remainder.d1 = remainder_split[1] ids.remainder.d2 = remainder_split[2]
ids.low = ids.a & ((1<<128) - 1) ids.high = ids.a >> 128
sum_d0 = ids.a.d0 + ids.b.d0 ids.carry_d0 = 1 if sum_d0 >= ids.SHIFT else 0 sum_d1 = ids.a.d1 + ids.b.d1 + ids.carry_d0 ids.carry_d1 = 1 if sum_d1 >= ids.SHIFT else 0 sum_d2 = ids.a.d2 + ids.b.d2 + ids.carry_d1 ids.carry_d2 = 1 if sum_d2 >= ids.SHIFT else 0
from starkware.python.math_utils import isqrt def split(num: int, num_bits_shift: int, length: int): a = [] for _ in range(length): a.append( num & ((1 << num_bits_shift) - 1) ) num = num >> num_bits_shift return tuple(a) def pack(z, num_bits_shift: int) -> int: limbs = (z.d0, z.d1, z.d2) return sum(limb << (num_bits_shift * i) for i, limb in enumerate(limbs)) a = pack(ids.a, num_bits_shift=128) root = isqrt(a) assert 0 <= root < 2 ** 192 root_split = split(root, num_bits_shift=128, length=3) ids.root.d0 = root_split[0] ids.root.d1 = root_split[1] ids.root.d2 = root_split[2]
-
Re-export the
cairo-felt
crate ascairo_vm::felt
#981- Removes the need of explicitly importing
cairo-felt
in downstream projects and helps ensure there is no version mismatch caused by that
- Removes the need of explicitly importing
-
Implement hint on
uint256_mul_div_mod
#957BuiltinHintProcessor
now supports the following hint:a = (ids.a.high << 128) + ids.a.low b = (ids.b.high << 128) + ids.b.low div = (ids.div.high << 128) + ids.div.low quotient, remainder = divmod(a * b, div) ids.quotient_low.low = quotient & ((1 << 128) - 1) ids.quotient_low.high = (quotient >> 128) & ((1 << 128) - 1) ids.quotient_high.low = (quotient >> 256) & ((1 << 128) - 1) ids.quotient_high.high = quotient >> 384 ids.remainder.low = remainder & ((1 << 128) - 1) ids.remainder.high = remainder >> 128"
Used by the common library function
uint256_mul_div_mod
-
Derive Deserialize for ExecutionResources #922
-
Remove builtin names from VirtualMachine.builtin_runners #921
-
Implemented hints on common/ec.cairo #888
-
Changed
Memory.insert
argument types #902 -
feat: implemented
Deserialize
on Program by changing builtins field type to enum #896 -
Effective size computation from the VM exposed #887
-
MathError
added for math operation #855 -
Check for overflows in relocatable operations #859
-
Use
Relocatable
instead of&MaybeRelocatable
inload_data
andget_range
#860 #867 -
Memory-related errors moved to
MemoryError
#854- Removed unused error variants
- Moved memory-related error variants to
MemoryError
- Changed memory getters to return
MemoryError
instead ofVirtualMachineError
- Changed all memory-related errors in hint from
HintError::Internal(VmError::...
toHintError::Memory(MemoryError::...
-
feat: Builder pattern for
VirtualMachine
#820 -
Simplified
Memory::get
return type toOption
#852 -
Improved idenitifier variable error handling #851
-
CairoRunner::write_output
now prints missing and relocatable values #853 -
VirtualMachineError::FailedToComputeOperands
error message expanded #848 -
Builtin names made public #849
-
secure_run
flag moved toCairoRunConfig
struct #832 -
vm_core
error types revised and iimplementedAddAssign
forRelocatable
#837 -
to_bigint
andto_biguint
deprecated #757 -
Memory
moved intoMemorySegmentManager
#830- To reduce the complexity of the VM's memory and enforce proper usage (as the memory and its segment manager are now a "unified" entity)
- Removed
memory
field fromVirtualMachine
- Added
memory
field toMemorySegmentManager
- Removed
Memory
argument from methods whereMemorySegmentManager
is also an argument - Added test macro
segments
(an extension of thememory
macro)
-
Display
trait added to Memory struct #812 -
feat: Extensible VirtualMachineError and removed PartialEq trait #783
VirtualMachineError::Other(anyhow::Error)
was added to allow to returning custom errors when usingcairo-vm
- The
PartialEq
trait was removed from theVirtualMachineError
enum
-
VM hooks added as a conditional feature #761
- Cairo-vm based testing tools such as cairo-foundry or those built by FuzzingLabs need access to the state of the VM at specific points during the execution.
- This PR adds the possibility for users of the cairo-vm lib to execute their custom additional code during the program execution.
- The Rust "feature" mechanism was used in order to guarantee that this ability is only available when the lib user needs it, and is not compiled when it's not required.
- Three hooks were created:
- before the first step
- before each step
- after each step
-
ExecutionResource operations: add and substract #774, multiplication #908 , and
AddAssign
#914 -
Move
Memory
intoMemorySegmentManager
#830- Structural changes:
- Remove
memory: Memory
field fromVirtualMachine
- Add
memory: Memory
field toMemorySegmentManager
- Remove
- As a result of this, multiple public methods' signatures changed:
BuiltinRunner
(and its inner enum types):initialize_segments(&mut self, segments: &mut MemorySegmentManager, memory: &mut Memory)
->initialize_segments(&mut self, segments: &mut MemorySegmentManager)
final_stack(&mut self, segments: &MemorySegmentManager, memory: &Memory, stack_pointer: Relocatable) -> Result<Relocatable, RunnerError>
->final_stack(&mut self, segments: &MemorySegmentManager, stack_pointer: Relocatable) -> Result<Relocatable, RunnerError>
MemorySegmentManager
add(&mut self, memory: &mut Memory) -> Relocatable
->add(&mut self) -> Relocatable
add_temporary_segment(&mut self, memory: &mut Memory) -> Relocatable
->add_temporary_segment(&mut self) -> Relocatable
load_data(&mut self, memory: &mut Memory, ptr: &MaybeRelocatable, data: &Vec<MaybeRelocatable>) -> Result<MaybeRelocatable, MemoryError>
->load_data(&mut self, ptr: &MaybeRelocatable, data: &Vec<MaybeRelocatable>) -> Result<MaybeRelocatable, MemoryError>
compute_effective_sizes(&mut self, memory: &Memory) -> &Vec<usize>
->compute_effective_sizes(&mut self) -> &Vec<usize>
gen_arg(&mut self, arg: &dyn Any, memory: &mut Memory) -> Result<MaybeRelocatable, VirtualMachineError>
->gen_arg(&mut self, arg: &dyn Any) -> Result<MaybeRelocatable, VirtualMachineError>
gen_cairo_arg(&mut self, arg: &CairoArg, memory: &mut Memory) -> Result<MaybeRelocatable, VirtualMachineError>
->gen_cairo_arg(&mut self, arg: &CairoArg) -> Result<MaybeRelocatable, VirtualMachineError>
write_arg(&mut self, memory: &mut Memory, ptr: &Relocatable, arg: &dyn Any) -> Result<MaybeRelocatable, MemoryError>
->write_arg(&mut self, ptr: &Relocatable, arg: &dyn Any) -> Result<MaybeRelocatable, MemoryError>
- Structural changes:
-
Refactor
Memory::relocate memory
#784- Bugfixes:
Memory::relocate_memory
now moves data in the temporary memory relocated by a relocation rule to the real memory
- Aditional Notes:
- When relocating temporary memory produces clashes with pre-existing values in the real memory, an InconsistentMemory error is returned instead of keeping the last inserted value. This differs from the original implementation.
- Bugfixes:
-
Restrict addresses to Relocatable + fix some error variants used in signature.rs #792
- Public Api Changes:
- Change
ValidationRule
inner type toBox<dyn Fn(&Memory, &Relocatable) -> Result<Vec<Relocatable>, MemoryError>>
. - Change
validated_addresses
field ofMemory
toHashSet<Relocatable>
. - Change
validate_memory_cell(&mut self, address: &MaybeRelocatable) -> Result<(), MemoryError>
tovalidate_memory_cell(&mut self, addr: &Relocatable) -> Result<(), MemoryError>
.
- Change
- Public Api Changes:
-
Add
VmException
toCairoRunner::run_from_entrypoint
#775- Public Api Changes:
- Change error return type of
CairoRunner::run_from_entrypoint
toCairoRunError
. - Convert
VirtualMachineError
s outputed during the vm run toVmException
inCairoRunner::run_from_entrypoint
. - Make
VmException
fields public
- Change error return type of
- Public Api Changes:
-
Fix
BuiltinRunner::final_stack
and remove quick fix #778- Public Api changes:
- Various changes to public
BuiltinRunner
method's signatures:final_stack(&self, vm: &VirtualMachine, pointer: Relocatable) -> Result<(Relocatable, usize), RunnerError>
tofinal_stack(&mut self, segments: &MemorySegmentManager, memory: &Memory, pointer: Relocatable) -> Result<Relocatable,RunnerError>
.get_used_cells(&self, vm: &VirtualMachine) -> Result<usize, MemoryError>
toget_used_cells(&self, segments: &MemorySegmentManager) -> Result<usize, MemoryError>
.get_used_instances(&self, vm: &VirtualMachine) -> Result<usize, MemoryError>
toget_used_instances(&self, segments: &MemorySegmentManager) -> Result<usize, MemoryError>
.
- Various changes to public
- Bugfixes:
BuiltinRunner::final_stack
now updates the builtin's stop_ptr instead of returning it. This replaces the bugfix on PR #768.
- Public Api changes:
-
Add secure_run flag + integrate verify_secure_runner into cairo-run #771
- Public Api changes:
- Add command_line argument
secure_run
- Add argument
secure_run: Option<bool>
tocairo_run
verify_secure_runner
is now called insidecairo-run
whensecure_run
is set to true or when it not set and the run is not onproof_mode
- Add command_line argument
- Bugfixes:
EcOpBuiltinRunner::deduce_memory_cell
now checks that both points are on the curve instead of only the first oneEcOpBuiltinRunner::deduce_memory_cell
now returns the values of the point coordinates instead of the indices when aPointNotOnCurve
error is returned
- Public Api changes:
-
Refactor
Refactor verify_secure_runner
#768- Public Api changes:
- Remove builtin name from the return value of
BuiltinRunner::get_memory_segment_addresses
- Simplify the return value of
CairoRunner::get_builtin_segments_info
toVec<(usize, usize)>
- CairoRunner::read_return_values now receives a mutable reference to VirtualMachine
- Remove builtin name from the return value of
- Bugfixes:
- CairoRunner::read_return_values now updates the
stop_ptr
of each builtin after callingBuiltinRunner::final_stack
- CairoRunner::read_return_values now updates the
- Public Api changes:
-
Use CairoArg enum instead of Any in CairoRunner::run_from_entrypoint #686
- Public Api changes:
- Remove
Result
fromMaybeRelocatable::mod_floor
, it now returns aMaybeRelocatable
- Add struct
CairoArg
- Change
arg
argument ofCairoRunner::run_from_entrypoint
fromVec<&dyn Any>
to&[&CairoArg]
- Remove argument
typed_args
fromCairoRunner::run_from_entrypoint
- Remove no longer used method
gen_typed_arg
fromVirtualMachine
&MemorySegmentManager
- Add methods
MemorySegmentManager::gen_cairo_arg
&MemorySegmentManager::write_simple_args
as typed counterparts toMemorySegmentManager::gen_arg
&MemorySegmentManager::write_arg
- Remove
- Public Api changes:
-
Add input file contents to traceback #666
- Public Api changes:
VirtualMachineError
enum variants containingMaybeRelocatable
and/orRelocatable
values now use theDisplay
format instead ofDebug
in theirDisplay
implementationget_traceback
now adds the source code line to each traceback entry
- Public Api changes:
-
Use hint location instead of instruction location when building VmExceptions from hint failure #673
- Public Api changes:
hints
field added toInstructionLocation
Program.instruction_locations
type changed fromOption<HashMap<usize, Location>>
toOption<HashMap<usize, InstructionLocation>>
VirtualMachineError
s produced byHintProcessor::execute_hint()
will be wrapped in aVirtualMachineError::Hint
error containing their hint_indexget_location()
now receives an an optional usize valuehint_index
, used to obtain hint locations
- Public Api changes:
-
Default implementation of compile_hint #680
- Internal changes:
- Make the
compile_hint
implementation which was in theBuiltinHintProcessor
the default implementation in the trait.
- Make the
- Internal changes:
-
Add new error type
HintError
#676- Public Api changes:
HintProcessor::execute_hint()
now returns aHintError
instead of aVirtualMachineError
- Helper functions on
hint_processor_utils.rs
now return aHintError
- Public Api changes:
-
Change the Dictionary used in dict hints to store MaybeRelocatable instead of BigInt #687
- Public Api changes:
DictManager
, its dictionaries, and all dict module hints implemented in rust now useMaybeRelocatable
for keys and values instead ofBigInt
- Add helper functions that allow extracting ids variables as
MaybeRelocatable
:get_maybe_relocatable_from_var_name
&get_maybe_relocatable_from_reference
- Change inner value type of dict-related
HintError
variants toMaybeRelocatable
- Public Api changes:
-
Implement
substitute_error_message_attribute_references
[#689] (#689)- Public Api changes:
- Remove
error_message_attributes
field fromVirtualMachine
, andVirtualMachine::new
- Add
flow_tracking_data
field toAttribute
get_error_attr_value
now replaces the references in the error message with the corresponding cairo values.- Remove duplicated handling of error attribute messages leading to duplicated into in the final error display.
- Remove
- Public Api changes:
-
Fix multiplicative inverse bug #697 #698. The VM was using integer division rather than prime field inverse when deducing
op0
orop1
for the multiplication opcode
- Add traceback to VmException #657
- Public API changes:
traceback
field added toVmException
structpub fn from_vm_error(runner: &CairoRunner, error: VirtualMachineError, pc: usize) -> Self
is nowpub fn from_vm_error(runner: &CairoRunner, vm: &VirtualMachine, error: VirtualMachineError) -> Self
pub fn get_location(pc: &usize, runner: &CairoRunner) -> Option<Location>
is nowpub fn get_location(pc: usize, runner: &CairoRunner) -> Option<Location>
pub fn decode_instruction(encoded_instr: i64, mut imm: Option<BigInt>) -> Result<instruction::Instruction, VirtualMachineError>
is nowpub fn decode_instruction(encoded_instr: i64, mut imm: Option<&BigInt>) -> Result<instruction::Instruction, VirtualMachineError>
VmException
fields' string format now mirrors their cairo-lang counterparts.
- Public API changes: