antoinezambelli/forge

43.0

Adjusted Score

43.0

Raw Score

100%

Time Factor

2026-07-10

Last Push

2.2K

Stars

Python

Language

56.1K

Lines of Code

169

Files

1.8K

Pattern Hits

2026-07-14

Scan Date

0.06

HC Hit Rate

What These Metrics Mean

Adjusted Score: Primary synthetic code indicator. Raw score normalised per 1,000 lines of code and multiplied by the temporal discount factor. This is the definitive comparative metric — use it to rank repositories by AI authorship density.
Raw Score: The unmodified sum of all severity-weighted, context-multiplied pattern match scores before temporal discounting. Reflects the absolute signal strength independent of when the repository was last active.
Time Factor: The temporal discount multiplier (0–100%) applied to the raw score. Repositories last updated before ChatGPT's launch (Nov 2022) receive a 5% factor. Full signal is only assigned to repositories active in the post-adoption era (Jan 2024+).
Pattern Hits: Total count of individual pattern matches across all files and categories. A high hit count with a low score may indicate a very large codebase with isolated AI snippets; a low count with a high score indicates dense, concentrated AI signatures.
HC Hit Rate: High+Critical pattern hits per file, averaged across the repository. This orthogonal signal catches repositories where a few files are densely packed with high-severity AI tells — a strong indicator even when the normalised score appears moderate due to codebase size.
Lines of Code / Files: Total lines and files analysed. The scanner examines 94 file extensions. These denominators are used to normalise the score, enabling fair comparison between repositories of vastly different sizes.

Score History

Longitudinal tracking requires multiple scan runs. Once this repository is re-scanned after new commits land, this chart will visualise how the synthetic code signal evolves over time — enabling you to detect whether AI authorship is growing, stabilising, or being actively corrected by human engineers.

No multi-scan history yet — run the scanner again to build trend data.

Severity Breakdown

Classifies detected patterns by their diagnostic confidence and structural impact. CRITICAL patterns (coefficient 10) represent definitive synthetic signatures — hallucinated imports, explicit LLM attribution metadata — virtually never produced by human authors. HIGH (5) indicates strong structural tells such as cross-file repetition or cross-linguistic idioms. MEDIUM (2) covers recognisable conversational padding and AI-specific vocabulary. LOW (1) captures subtle indicators like tautological comments and generic boilerplate that require density to carry independent signal.

CRITICAL 0HIGH 10MEDIUM 302LOW 1476

Directory Score Breakdown

This horizontal bar chart decomposes the repository's raw synthetic code score by top-level directory, allowing you to pinpoint precisely which modules or components carry the highest AI authorship density. Directories with disproportionately high scores relative to their size warrant targeted manual review: concentrated AI signatures often trace back to mass-generated configuration layers, auto-ported test suites, LLM-scaffolded boilerplate classes, or entire subsystems authored under heavy copilot assistance. Use this view to prioritise your human code-review effort.

Pattern Findings

The scanner identified 1788 distinct pattern matches across 18 syntactic categories. Each entry below represents a discrete location in the source code where the engine recorded a statistically significant AI authorship indicator. Expand any category row to inspect the individual file paths, line numbers, code snippets, and the lexical context (CODE, COMMENT, or STRING) in which each match was detected.

Reading the findings table: The Severity column indicates the diagnostic confidence level (CRITICAL / HIGH / MEDIUM / LOW). The Context column identifies whether the match occurred inside executable code, an inline comment, or a string literal — comment-context matches receive a ×1.5 weight because LLMs systematically over-annotate. The ⚡ bolt icon marks clustered matches: three or more patterns within a 10-line window, each receiving an additional ×1.5 density multiplier as dense clusters constitute far stronger evidence of synthetic authorship than isolated hits.

Hyper-Verbose Identifiers1119 hits · 1032 pts

Severity	File	Line	Snippet	Context
LOW⚡	tests/unit/test_argument_transformation.py	55	def test_list_transactions_unknown_quarter_returns_empty(self) -> None:	CODE
LOW⚡	tests/unit/test_argument_transformation.py	61	def test_get_approved_vendors_returns_canonical_six(self) -> None:	CODE
LOW⚡	tests/unit/test_argument_transformation.py	71	def test_get_vendor_details_resolves_acme_alias(self) -> None:	CODE
LOW⚡	tests/unit/test_argument_transformation.py	78	def test_get_vendor_details_acme_corp_lists_alias(self) -> None:	CODE
LOW⚡	tests/unit/test_argument_transformation.py	83	def test_get_vendor_details_unknown_vendor_returns_not_found(self) -> None:	CODE
LOW⚡	tests/unit/test_argument_transformation.py	89	def test_currency_convert_eur_to_usd_uses_fixed_rate(self) -> None:	CODE
LOW⚡	tests/unit/test_argument_transformation.py	97	def test_currency_convert_under_threshold_eur(self) -> None:	CODE
LOW⚡	tests/unit/test_argument_transformation.py	104	def test_currency_convert_unsupported_pair(self) -> None:	CODE
LOW⚡	tests/unit/test_argument_transformation.py	110	def test_categorize_expense_is_distractor_no_audit_info(self) -> None:	CODE
LOW⚡	tests/unit/test_argument_transformation.py	117	def test_lookup_transaction_redundant_helper(self) -> None:	CODE
LOW⚡	tests/unit/test_argument_transformation.py	123	def test_lookup_transaction_unknown_id(self) -> None:	CODE
LOW⚡	tests/unit/test_argument_transformation.py	127	def test_submit_audit_report_acks_inputs(self) -> None:	CODE
LOW⚡	tests/unit/test_argument_transformation.py	156	def test_alt_format_no_comma_no_dollar_passes(self) -> None:	CODE
LOW⚡	tests/unit/test_argument_transformation.py	166	def test_skip_currency_conversion_fails(self) -> None:	CODE
LOW⚡	tests/unit/test_argument_transformation.py	174	def test_case_mismatch_over_flag_fails(self) -> None:	CODE
LOW⚡	tests/unit/test_argument_transformation.py	183	def test_strict_gt_threshold_fails(self) -> None:	CODE
LOW⚡	tests/unit/test_argument_transformation.py	190	def test_wrong_top_vendor_fails(self) -> None:	CODE
LOW⚡	tests/unit/test_argument_transformation.py	195	def test_missing_one_id_fails(self) -> None:	CODE
LOW⚡	tests/unit/test_argument_transformation.py	213	def test_lambda_scenario_terminal_is_submit_audit_report(self) -> None:	CODE
LOW⚡	tests/unit/test_argument_transformation.py	216	def test_lambda_scenario_required_steps(self) -> None:	CODE
LOW⚡	tests/unit/test_argument_transformation.py	221	def test_lambda_scenario_iteration_budget(self) -> None:	CODE
LOW⚡	tests/unit/test_argument_transformation.py	225	def test_lambda_scenario_tags(self) -> None:	CODE
LOW⚡	tests/unit/test_argument_transformation.py	251	def test_list_transactions_wrong_quarter_no_state(self) -> None:	CODE
LOW⚡	tests/unit/test_argument_transformation.py	257	def test_get_approved_vendors_records_state(self) -> None:	CODE
LOW⚡	tests/unit/test_argument_transformation.py	263	def test_get_vendor_details_acme_alias_records_state(self) -> None:	CODE
LOW⚡	tests/unit/test_argument_transformation.py	269	def test_currency_convert_eur_records_state(self) -> None:	CODE
LOW⚡	tests/unit/test_argument_transformation.py	275	def test_currency_convert_usd_to_eur_does_not_record_eur_flag(self) -> None:	CODE
LOW⚡	tests/unit/test_argument_transformation.py	282	def test_submit_audit_report_records_args(self) -> None:	CODE
LOW⚡	tests/unit/test_argument_transformation.py	389	def test_lambda_in_all_scenarios(self) -> None:	CODE
LOW⚡	tests/unit/test_argument_transformation.py	394	def test_stateful_in_all_scenarios(self) -> None:	CODE
LOW	tests/unit/test_argument_transformation.py	297	def test_validate_state_requires_full_reasoning_path(self) -> None:	CODE
LOW	tests/unit/test_argument_transformation.py	319	def test_validate_state_false_when_skipped_currency_convert(self) -> None:	CODE
LOW	tests/unit/test_argument_transformation.py	333	def test_validate_state_false_when_skipped_vendor_details(self) -> None:	CODE
LOW	tests/unit/test_argument_transformation.py	348	def test_validate_state_false_when_wrong_args_submitted(self) -> None:	CODE
LOW⚡	tests/unit/test_openai_compat_client.py	91	async def test_returns_text_response(self) -> None:	CODE
LOW⚡	tests/unit/test_openai_compat_client.py	101	async def test_missing_choices_raises_backend_error(self) -> None:	CODE
LOW⚡	tests/unit/test_openai_compat_client.py	111	async def test_null_content_returns_empty_text(self) -> None:	CODE
LOW⚡	tests/unit/test_openai_compat_client.py	121	async def test_malformed_tool_args_kept_as_raw_args(self) -> None:	CODE
LOW⚡	tests/unit/test_openai_compat_client.py	455	def test_bearer_header_set_when_key_provided(self) -> None:	CODE
LOW⚡	tests/unit/test_openai_compat_client.py	461	def test_no_auth_header_when_no_key(self) -> None:	CODE
LOW⚡	tests/unit/test_openai_compat_client.py	465	def test_base_url_trailing_slash_stripped(self) -> None:	CODE
LOW⚡	tests/unit/test_openai_compat_client.py	475	async def test_yields_text_deltas_and_final(self) -> None:	CODE
LOW⚡	tests/unit/test_openai_compat_client.py	828	def test_recommended_sampling_off_is_silent_for_unknown_model(self) -> None:	CODE
LOW⚡	tests/unit/test_openai_compat_client.py	838	def test_recommended_sampling_on_raises_for_unknown_model(self) -> None:	CODE
LOW	tests/unit/test_openai_compat_client.py	143	async def test_malformed_tool_args_kept_even_with_assistant_text(self) -> None:	CODE
LOW	tests/unit/test_openai_compat_client.py	164	async def test_malformed_among_several_kept_per_call(self) -> None:	CODE
LOW	tests/unit/test_openai_compat_client.py	186	async def test_dict_tool_args_accepted(self) -> None:	CODE
LOW	tests/unit/test_openai_compat_client.py	205	async def test_formats_tools_in_request(self) -> None:	CODE
LOW	tests/unit/test_openai_compat_client.py	220	async def test_request_body_structure(self) -> None:	CODE
LOW	tests/unit/test_openai_compat_client.py	235	async def test_posts_to_chat_completions(self) -> None:	CODE
LOW	tests/unit/test_openai_compat_client.py	257	async def test_http_error_raises_backend_error(self) -> None:	CODE
LOW	tests/unit/test_openai_compat_client.py	266	async def test_structured_reasoning_field_captured(self, field) -> None:	CODE
LOW	tests/unit/test_openai_compat_client.py	287	async def test_extracts_think_tags_from_content_with_tool_call(self) -> None:	CODE
LOW	tests/unit/test_openai_compat_client.py	307	async def test_reasoning_field_preferred_over_content_tags(self) -> None:	CODE
LOW	tests/unit/test_openai_compat_client.py	326	async def test_content_preamble_not_treated_as_reasoning(self) -> None:	CODE
LOW	tests/unit/test_openai_compat_client.py	348	async def test_think_tags_stripped_from_text_response(self) -> None:	CODE
LOW	tests/unit/test_openai_compat_client.py	363	async def test_plain_preamble_text_response_survives(self) -> None:	CODE
LOW	tests/unit/test_openai_compat_client.py	378	async def test_reasoning_attached_to_first_tool_call_only(self) -> None:	CODE
LOW	tests/unit/test_openai_compat_client.py	399	async def test_empty_string_structured_field_falls_through_to_tags(self) -> None:	CODE
LOW	tests/unit/test_openai_compat_client.py	420	async def test_non_string_reasoning_field_raises(self) -> None:	CODE
1059 more matches not shown…

Decorative Section Separators275 hits · 916 pts

Severity	File	Line	Snippet	Context
MEDIUM	tests/conftest.py	12	# ── Shared LLM client double ─────────────────────────────────────	COMMENT
MEDIUM⚡	tests/unit/test_argument_transformation.py	206	# ── Scenario shape ──────────────────────────────────────────────	COMMENT
MEDIUM⚡	tests/unit/test_argument_transformation.py	230	# ── Stateful backend ────────────────────────────────────────────	COMMENT
MEDIUM⚡	tests/unit/test_argument_transformation.py	385	# ── Scenario registered in ALL_SCENARIOS ────────────────────────	COMMENT
MEDIUM	tests/unit/test_argument_transformation.py	30	# ── Lambda tool callables ───────────────────────────────────────	COMMENT
MEDIUM	tests/unit/test_argument_transformation.py	138	# ── Validator ───────────────────────────────────────────────────	COMMENT
MEDIUM⚡	tests/unit/test_openai_compat_client.py	451	# ── auth ─────────────────────────────────────────────────────────	COMMENT
MEDIUM⚡	tests/unit/test_openai_compat_client.py	470	# ── send_stream ──────────────────────────────────────────────────	COMMENT
MEDIUM⚡	tests/unit/test_openai_compat_client.py	848	# ── instance sampling flows into request body ────────────────────	COMMENT
MEDIUM	tests/unit/test_openai_compat_client.py	62	# ── send ─────────────────────────────────────────────────────────	COMMENT
MEDIUM	tests/unit/test_openai_compat_client.py	774	# ── constructor ──────────────────────────────────────────────────	COMMENT
MEDIUM	tests/unit/test_openai_compat_client.py	877	# ── passthrough + inbound_anthropic_body ─────────────────────────	COMMENT
MEDIUM	tests/unit/test_openai_compat_client.py	950	# ── aclose ───────────────────────────────────────────────────────	COMMENT
MEDIUM⚡	tests/unit/test_inconsistent_api_recovery.py	32	# ── Lambda tool callables ───────────────────────────────────────	COMMENT
MEDIUM⚡	tests/unit/test_inconsistent_api_recovery.py	249	# ── Scenario shape ──────────────────────────────────────────────	COMMENT
MEDIUM⚡	tests/unit/test_inconsistent_api_recovery.py	280	# ── Stateful backend ────────────────────────────────────────────	COMMENT
MEDIUM⚡	tests/unit/test_inconsistent_api_recovery.py	364	# ── Stateful validate_state ─────────────────────────────────────	COMMENT
MEDIUM	tests/unit/test_inconsistent_api_recovery.py	205	# ── Validator (lambda) ──────────────────────────────────────────	COMMENT
MEDIUM⚡	tests/unit/test_ollama_client.py	766	# ── outbound message normalization (#111 / #115) ─────────────────	COMMENT
MEDIUM⚡	tests/unit/test_ollama_client.py	877	# ── get_context_length + set_num_ctx ─────────────────────────────	COMMENT
MEDIUM	tests/unit/test_ollama_client.py	49	# ── send ─────────────────────────────────────────────────────────	COMMENT
MEDIUM	tests/unit/test_ollama_client.py	397	# ── send_stream ──────────────────────────────────────────────────	COMMENT
MEDIUM	tests/unit/test_ollama_client.py	962	# ── format_tool ──────────────────────────────────────────────────	COMMENT
MEDIUM⚡	tests/unit/test_proxy_auth.py	84	# ── relocate_credential ──────────────────────────────────────────────	COMMENT
MEDIUM⚡	tests/unit/test_proxy_auth.py	130	# ── resolve_inbound_credential ───────────────────────────────────────	COMMENT
MEDIUM⚡	tests/unit/test_proxy_auth.py	165	# ── handler threading ────────────────────────────────────────────────	COMMENT
MEDIUM	tests/unit/test_proxy_auth.py	25	# ── extract_inbound_credential ───────────────────────────────────────	COMMENT
MEDIUM	tests/unit/test_anthropic_client.py	44	# ── _convert_tools ───────────────────────────────────────────────	COMMENT
MEDIUM	tests/unit/test_anthropic_client.py	84	# ── _convert_messages ────────────────────────────────────────────	COMMENT
MEDIUM	tests/unit/test_anthropic_client.py	357	# ── _parse_response ──────────────────────────────────────────────	COMMENT
MEDIUM	tests/unit/test_anthropic_client.py	412	# ── Usage reporting (slot-keyed last_usage) ──────────────────────	COMMENT
MEDIUM	tests/unit/test_anthropic_client.py	450	# ── Prompt caching (static tools+system breakpoint) ──────────────	COMMENT
MEDIUM⚡	tests/unit/test_llamafile_client.py	1220	# ── _apply_sampling ──────────────────────────────────────────────	COMMENT
MEDIUM⚡	tests/unit/test_llamafile_client.py	1386	# ── _extract_think_tags ──────────────────────────────────────────	COMMENT
MEDIUM⚡	tests/unit/test_llamafile_client.py	1951	# ── Issue #121: Path.stem truncates dotted model names ─────────────	COMMENT
MEDIUM	tests/unit/test_llamafile_client.py	162	# ── send — native mode ──────────────────────────────────────────	COMMENT
MEDIUM	tests/unit/test_llamafile_client.py	644	# ── send — prompt mode ──────────────────────────────────────────	COMMENT
MEDIUM	tests/unit/test_llamafile_client.py	734	# ── get_context_length ───────────────────────────────────────────	COMMENT
MEDIUM	tests/unit/test_llamafile_client.py	774	# ── discover_backend_metadata (deferred discovery) ───────────────	COMMENT
MEDIUM	tests/unit/test_llamafile_client.py	853	# ── send_stream ──────────────────────────────────────────────────	COMMENT
MEDIUM	tests/unit/test_llamafile_client.py	1027	# ── send_stream — malformed-500 rescue (streaming twins) ──────────	COMMENT
MEDIUM	tests/unit/test_llamafile_client.py	1202	# ── mode ─────────────────────────────────────────────────────────	COMMENT
MEDIUM	tests/unit/test_llamafile_client.py	1285	# ── _merge_consecutive ────────────────────────────────────────────	COMMENT
MEDIUM	tests/unit/test_llamafile_client.py	1462	# ── think flag behavior — sync ────────────────────────────────────	COMMENT
MEDIUM	tests/unit/test_llamafile_client.py	1631	# ── think flag behavior — stream ──────────────────────────────────	COMMENT
MEDIUM	tests/unit/test_llamafile_client.py	1726	# ── slot_id ────────────────────────────────────────────────────	COMMENT
MEDIUM⚡	tests/unit/test_templates.py	25	# ── build_tool_prompt ────────────────────────────────────────────	COMMENT
MEDIUM	tests/unit/test_templates.py	80	# ── extract_tool_call ────────────────────────────────────────────	COMMENT
MEDIUM	tests/unit/test_templates.py	166	# ── rescue_tool_call ────────────────────────────────────────────	COMMENT
MEDIUM	tests/unit/test_templates.py	238	# ── Qwen Coder XML format ───────────────────────────────────────	COMMENT
MEDIUM⚡	tests/unit/test_guardrails.py	22	# ── check(): response validation ─────────────────────────────	COMMENT
MEDIUM⚡	tests/unit/test_guardrails.py	129	# ── check(): step enforcement ────────────────────────────────	COMMENT
MEDIUM⚡	tests/unit/test_guardrails.py	165	# ── record() ─────────────────────────────────────────────────	COMMENT
MEDIUM⚡	tests/unit/test_guardrails.py	201	# ── CheckResult dataclass ────────────────────────────────────	COMMENT
MEDIUM⚡	tests/unit/test_guardrails.py	217	# ── Imports ──────────────────────────────────────────────────	COMMENT
MEDIUM⚡	tests/unit/test_guardrails.py	232	# ── Custom retry nudge ───────────────────────────────────────	COMMENT
MEDIUM	tests/unit/test_guardrails.py	9	# ── Helpers ──────────────────────────────────────────────────	COMMENT
MEDIUM⚡	tests/unit/test_proxy_path1.py	24	# ── ProxyServer construction validation ──────────────────────	COMMENT
MEDIUM	tests/unit/test_proxy_path1.py	77	# ── AnthropicClient verbatim path ────────────────────────────	COMMENT
MEDIUM	tests/unit/test_proxy_path1.py	165	# ── AnthropicClient base_url ─────────────────────────────────	COMMENT
215 more matches not shown…

Unused Imports225 hits · 185 pts

Severity	File	Line	Context
LOW	tests/conftest.py	3	CODE
LOW	tests/unit/test_argument_transformation.py	13	CODE
LOW	tests/unit/test_argument_transformation.py	15	CODE
LOW	tests/unit/test_openai_compat_client.py	11	CODE
LOW	tests/unit/test_response_validator.py	6	CODE
LOW	tests/unit/test_step_enforcer.py	3	CODE
LOW	tests/unit/test_inconsistent_api_recovery.py	13	CODE
LOW	tests/unit/test_inconsistent_api_recovery.py	25	CODE
LOW	tests/unit/test_ollama_client.py	13	CODE
LOW	tests/unit/test_anthropic_client.py	7	CODE
LOW	tests/unit/test_anthropic_client.py	17	CODE
LOW	tests/unit/test_llamafile_client.py	12	CODE
LOW	tests/unit/test_clients_base.py	3	CODE
LOW	tests/unit/test_proxy_path1.py	13	CODE
LOW	tests/unit/test_proxy_path1.py	20	CODE
LOW	tests/unit/test_data_gap_recovery_extended.py	12	CODE
LOW	tests/unit/test_data_gap_recovery_extended.py	14	CODE
LOW	tests/unit/test_workflow.py	4	CODE
LOW	tests/unit/test_workflow.py	4	CODE
LOW	tests/unit/test_server.py	3	CODE
LOW	tests/unit/test_server.py	8	CODE
LOW	tests/unit/test_server.py	15	CODE
LOW	tests/unit/test_slot_worker.py	3	CODE
LOW	tests/unit/test_slot_worker.py	6	CODE
LOW	tests/unit/test_slot_worker.py	8	CODE
LOW	tests/unit/test_slot_worker.py	14	CODE
LOW	tests/unit/test_slot_worker.py	389	CODE
LOW	tests/unit/test_runner.py	3	CODE
LOW	tests/unit/test_runner.py	6	CODE
LOW	tests/unit/test_runner.py	10	CODE
LOW	tests/unit/test_eval_budget.py	3	CODE
LOW	tests/unit/test_eval_budget.py	6	CODE
LOW	tests/unit/test_eval_budget.py	8	CODE
LOW	tests/unit/test_eval_budget.py	14	CODE
LOW	tests/unit/test_proxy_proxy.py	9	CODE
LOW	tests/unit/test_batch_eval_resume.py	9	CODE
LOW	tests/unit/test_client_auth.py	15	CODE
LOW	tests/unit/test_respond_tool.py	3	CODE
LOW	tests/unit/test_respond_tool.py	4	CODE
LOW	tests/unit/test_respond_tool.py	4	CODE
LOW	tests/unit/test_respond_tool.py	4	CODE
LOW	tests/unit/test_respond_tool.py	6	CODE
LOW	tests/unit/test_respond_tool.py	6	CODE
LOW	tests/unit/test_respond_tool.py	13	CODE
LOW	tests/unit/test_strategies.py	4	CODE
LOW	tests/unit/test_grounded_synthesis.py	12	CODE
LOW	tests/unit/test_grounded_synthesis.py	23	CODE
LOW	tests/eval/metrics.py	3	CODE
LOW	tests/eval/batch_eval.py	11	CODE
LOW	tests/eval/batch_eval.py	17	CODE
LOW	tests/eval/batch_eval.py	28	CODE
LOW	tests/eval/ablation.py	3	CODE
LOW	tests/eval/significance.py	15	CODE
LOW	tests/eval/eval_runner.py	3	CODE
LOW	tests/eval/eval_runner.py	12	CODE
LOW	tests/eval/eval_runner.py	18	CODE
LOW	tests/eval/report.py	17	CODE
LOW	tests/eval/scenarios/_base.py	3	CODE
LOW	tests/eval/scenarios/_stateful_plumbing.py	3	CODE
LOW	tests/eval/scenarios/_model_reasoning.py	10	CODE
165 more matches not shown…

Modern AI Meta-Vocabulary24 hits · 66 pts

Severity	File	Line	Snippet	Context
MEDIUM	pyproject.toml	74	# Integration-only: lifecycle orchestration requiring real backends/threads.	COMMENT
MEDIUM	README.md	3	[![PyPI](https://img.shields.io/pypi/v/forge-guardrails.svg)](https://pypi.org/project/forge-guardrails/)	CODE
MEDIUM	README.md	15	- Not a coding harness. Forge is domain-agnostic. If you're building a coding agent (or already using one like openc	CODE
MEDIUM	README.md	129	Drop-in proxy that sits between any client and a local model server, speaking both the OpenAI chat-completions API and t	CODE
MEDIUM	README.md	251	runner.py # WorkflowRunner — the agentic loop	CODE
MEDIUM	CONTRIBUTING.md	74	### Adding or modifying guardrails	COMMENT
MEDIUM	tests/unit/test_openai_compat_client.py	422	# it into replayable chain-of-thought.	COMMENT
MEDIUM	tests/unit/test_openai_compat_client.py	728	# never repr-coerced into chain-of-thought.	COMMENT
MEDIUM	tests/unit/test_proxy_handler.py	274	# ── With tools → guardrails ─────────────────────────────────	COMMENT
MEDIUM	tests/eval/report.py	1350	("## Full Ablation — which guardrails do the work?", lambda rp: rp == "ablation.md"),	CODE
MEDIUM	tests/eval/scenarios/_model_reasoning.py	569	# guardrails-vs-bare ablation: bare runs hit the first error and	COMMENT
MEDIUM	docs/USER_GUIDE.md	109	### Mode 3: Middleware (composable guardrails)	COMMENT
MEDIUM	docs/WORKFLOW.md	447	└── reasoning: str \| None # chain-of-thought (thinking models)	CODE
MEDIUM	docs/EVAL_GUIDE.md	84	# Ablation — bare (all guardrails off)	COMMENT
MEDIUM	docs/decisions/MULTI_MODEL_ROUTING.md	166	# Consumer orchestration code	COMMENT
MEDIUM	src/forge/clients/vllm.py	520	# would silently mis-size the context window. No entry, no budget:	COMMENT
MEDIUM	src/forge/clients/sampling_defaults.py	171	# explicit chain of thought). Card recommends temperature=0.2, top_k=80, repetition_penalty=1.05	COMMENT
MEDIUM	src/forge/clients/openai_compat.py	381	# chain-of-thought.	COMMENT
MEDIUM	src/forge/proxy/handler.py	335	# in tool-calling mode where guardrails apply. The respond call is	COMMENT
MEDIUM	src/forge/proxy/handler.py	349	# No tools → plain chat completion, no guardrails needed.	COMMENT
MEDIUM	src/forge/proxy/handler.py	370	# Set up guardrails	COMMENT
MEDIUM	src/forge/proxy/handler.py	394	# error. The client's own agentic loop can decide what to do.	COMMENT
MEDIUM	src/forge/proxy/proxy.py	321	# guardrails wrap its inference loop like any other client.	COMMENT
MEDIUM	src/forge/proxy/proxy.py	323	# (forge-guardrails[anthropic]). Only Path 1 needs it, so	COMMENT

Deep Nesting32 hits · 30 pts

Severity	File	Line	Context
LOW	tests/eval/metrics.py	260	CODE
LOW	tests/eval/batch_eval.py	589	CODE
LOW	tests/eval/batch_eval.py	672	CODE
LOW	tests/eval/significance.py	91	CODE
LOW	tests/eval/eval_runner.py	234	CODE
LOW	tests/eval/eval_runner.py	405	CODE
LOW	tests/eval/report.py	317	CODE
LOW	tests/eval/report.py	789	CODE
LOW	scripts/run_ablation.py	102	CODE
LOW	scripts/migrate_eval_jsonl_gguf_identity.py	100	CODE
LOW	src/forge/server.py	545	CODE
LOW	src/forge/server.py	505	CODE
LOW	src/forge/clients/llamafile.py	207	CODE
LOW	src/forge/clients/llamafile.py	250	CODE
LOW	src/forge/clients/anthropic.py	240	CODE
LOW	src/forge/clients/anthropic.py	528	CODE
LOW	src/forge/clients/ollama.py	29	CODE
LOW	src/forge/clients/ollama.py	381	CODE
LOW	src/forge/clients/base.py	179	CODE
LOW	src/forge/context/strategies.py	204	CODE
LOW	src/forge/core/steps.py	53	CODE
LOW	src/forge/core/runner.py	88	CODE
LOW	src/forge/core/workflow.py	68	CODE
LOW	src/forge/proxy/server.py	143	CODE
LOW	src/forge/proxy/server.py	359	CODE
LOW	src/forge/proxy/proxy.py	306	CODE
LOW	src/forge/proxy/convert.py	17	CODE
LOW	src/forge/proxy/convert_anthropic.py	20	CODE
LOW	src/forge/prompts/templates.py	12	CODE
LOW	src/forge/prompts/templates.py	55	CODE
LOW	src/forge/prompts/templates.py	185	CODE
LOW	src/forge/prompts/templates.py	238	CODE

Structural Annotation Overuse16 hits · 28 pts

Severity	File	Line	Snippet	Context
LOW⚡	tests/eval/scenarios/_compaction_chain.py	532	# Step 1: patient MRN (not in user message)	COMMENT
LOW⚡	tests/eval/scenarios/_compaction_chain.py	534	# Step 3: lab values (only from tool result)	COMMENT
LOW⚡	tests/eval/scenarios/_compaction_chain.py	536	# Step 4: imaging findings (only from tool result)	COMMENT
LOW⚡	tests/eval/scenarios/_compaction_chain.py	538	# Step 5: specialist (only from tool result)	COMMENT
LOW⚡	tests/eval/scenarios/_compaction_chain.py	540	# Step 6: medication concern (only from tool result)	COMMENT
LOW	docs/decisions/003-thinking-label-ux.md	64	### Step 1: Add `_resolve_reasoning()` to OllamaClient	COMMENT
LOW	docs/decisions/003-thinking-label-ux.md	86	### Step 2: Use it in `send()` (batch path)	COMMENT
LOW	docs/decisions/003-thinking-label-ux.md	102	### Step 3: Use it in `_iter_stream()` (streaming path)	COMMENT
LOW	docs/decisions/003-thinking-label-ux.md	124	### Step 4: Add unit tests	COMMENT
LOW	docs/decisions/003-thinking-label-ux.md	187	### Step 5: Update README roadmap	COMMENT
LOW	docs/decisions/004-async-on-chunk.md	75	### Step 1: Change type signature	COMMENT
LOW	docs/decisions/004-async-on-chunk.md	91	### Step 2: Await the callback in `_send_streaming()`	COMMENT
LOW	docs/decisions/004-async-on-chunk.md	107	### Step 3: Update `_make_runner` helper type hint	COMMENT
LOW	docs/decisions/004-async-on-chunk.md	127	### Step 4: Update the test	COMMENT
LOW	docs/decisions/004-async-on-chunk.md	171	### Step 5: Update docstring	COMMENT
LOW	docs/decisions/004-async-on-chunk.md	180	### Step 6: Update README roadmap	COMMENT

Docstring Block Structure5 hits · 25 pts

Severity	File	Line	Snippet	Context
HIGH	src/forge/server.py	348	Resolve the ContextManager budget for the given mode. Args: mode: The budget mode to use.	STRING
HIGH	src/forge/server.py	397	Start server with the specified budget mode and return the resolved budget. Handles the mode-specific startup d	STRING
HIGH	src/forge/clients/sampling_defaults.py	235	Apply the recommended-sampling policy for ``model``. Called by client constructors at instantiation time. The four-	STRING
HIGH	src/forge/core/inference.py	186	Send messages to the LLM with compaction, folding, validation, and retry. Retries are handled internally — the call	STRING
HIGH	src/forge/core/slot_worker.py	65	Submit a workflow for execution and wait for the result. Args: workflow: The workflow to execute.	STRING

Fake / Example Data18 hits · 22 pts

Severity	File	Line	Snippet	Context
LOW⚡	tests/unit/test_argument_transformation.py	64	"Acme Corp", "Globex Industries", "Initech Systems",	CODE
LOW⚡	tests/unit/test_argument_transformation.py	79	out = self._call("get_vendor_details", vendor_name="Acme Corp")	CODE
LOW⚡	tests/unit/test_argument_transformation.py	260	assert "Acme Corp" in out	CODE
LOW⚡	tests/unit/test_inconsistent_api_recovery.py	43	assert "Acme Corp" in out	CODE
LOW⚡	tests/unit/test_inconsistent_api_recovery.py	298	assert "Acme Corp" in out	CODE
LOW	tests/eval/scenarios/_base.py	15	placeholder_field: str = Field(description="placeholder")	CODE
LOW⚡	tests/eval/scenarios/_base.py	49	spec=ToolSpec(name=terminal_tool, description="placeholder",	CODE
LOW⚡	tests/eval/scenarios/_base.py	56	spec=ToolSpec(name=s, description="placeholder",	CODE
LOW⚡	tests/eval/scenarios/_base.py	64	description="placeholder",	CODE
LOW	tests/eval/scenarios/_model_reasoning.py	300	# approved 'Acme Corp'. Literal string compare over-flags it;	COMMENT
LOW	tests/eval/scenarios/_model_reasoning.py	313	"Acme Corp",	CODE
LOW	tests/eval/scenarios/_model_reasoning.py	326	("TX-1002", "2024-10-12", "Acme Corp", 12000, "USD", False), # approved	CODE
LOW	tests/eval/scenarios/_model_reasoning.py	377	if name == "Acme Corp":	CODE
LOW	tests/eval/scenarios/_model_reasoning.py	621	(12345, "Acme Corp"),	CODE
LOW⚡	tests/eval/scenarios/_stateful_model_reasoning.py	368	"Acme Corp",	CODE
LOW⚡	tests/eval/scenarios/_stateful_model_reasoning.py	378	("TX-1002", "2024-10-12", "Acme Corp", 12000, "USD"),	CODE
LOW	tests/eval/scenarios/_stateful_model_reasoning.py	441	if name == "Acme Corp":	CODE
LOW	tests/eval/scenarios/_stateful_model_reasoning.py	681	(12345, "Acme Corp"),	CODE

Cross-File Repetition4 hits · 20 pts

Severity	File	Snippet	Context
HIGH	src/forge/clients/vllm.py	per-call headers to apply, enforcing the one-credential rule. returns the dict to pass as httpx ``headers=`` (merged ove	STRING
HIGH	src/forge/clients/llamafile.py	per-call headers to apply, enforcing the one-credential rule. returns the dict to pass as httpx ``headers=`` (merged ove	STRING
HIGH	src/forge/clients/openai_compat.py	per-call headers to apply, enforcing the one-credential rule. returns the dict to pass as httpx ``headers=`` (merged ove	STRING
HIGH	src/forge/clients/ollama.py	per-call headers to apply, enforcing the one-credential rule. returns the dict to pass as httpx ``headers=`` (merged ove	STRING

Excessive Try-Catch Wrapping17 hits · 18 pts

Severity	File	Line	Snippet	Context
LOW	tests/eval/batch_eval.py	562	except Exception:	CODE
LOW	tests/eval/batch_eval.py	581	except Exception as exc:	CODE
LOW	tests/eval/eval_runner.py	320	except Exception as exc:	CODE
LOW	tests/eval/eval_runner.py	330	except Exception as exc:	CODE
LOW	tests/eval/eval_runner.py	369	except Exception as exc:	CODE
LOW	tests/eval/eval_runner.py	666	except Exception as exc:	CODE
LOW	docs/ARCHITECTURE.md	27	except Exception:	CODE
LOW	scripts/integration_test_proxy.py	375	except Exception as exc:	CODE
LOW	scripts/run_ablation.py	170	except Exception as e:	CODE
LOW	src/forge/core/runner.py	345	except Exception as exc:	CODE
LOW	src/forge/core/slot_worker.py	137	except Exception as exc:	CODE
LOW	src/forge/proxy/server.py	137	except Exception as exc:	CODE
LOW⚡	src/forge/proxy/server.py	208	except Exception:	CODE
LOW⚡	src/forge/proxy/server.py	212	except Exception:	CODE
LOW⚡	src/forge/proxy/server.py	218	except Exception:	CODE
LOW	src/forge/proxy/server.py	356	except Exception as exc:	CODE
LOW	src/forge/proxy/server.py	445	except Exception as exc:	CODE

Modern Structural Boilerplate14 hits · 14 pts

Severity	File	Line	Snippet	Context
LOW	tests/eval/scenarios/__init__.py	81	__all__ = [	CODE
LOW	scripts/integration_test_proxy.py	71	def _setup_logging() -> None:	CODE
LOW	src/forge/__init__.py	75	__all__ = [	CODE
LOW	src/forge/clients/vllm.py	157	def _set_model_identity(self, wire_id: str \| Path) -> None:	CODE
LOW	src/forge/clients/__init__.py	14	__all__ = [	CODE
LOW	src/forge/clients/ollama.py	444	def set_num_ctx(self, num_ctx: int \| None) -> None:	CODE
LOW	src/forge/tools/__init__.py	9	__all__ = [	CODE
LOW	src/forge/context/__init__.py	19	__all__ = [	CODE
LOW	src/forge/context/hardware.py	21	logger = logging.getLogger(__name__)	CODE
LOW	src/forge/context/manager.py	93	def update_token_count(self, total_tokens: int) -> None:	CODE
LOW	src/forge/core/__init__.py	3	__all__ = ["WorkflowRunner"]	CODE
LOW	src/forge/guardrails/__init__.py	19	__all__ = [	CODE
LOW	src/forge/proxy/__init__.py	5	__all__ = ["ProxyServer"]	CODE
LOW	src/forge/prompts/__init__.py	6	__all__ = [	CODE

AI Structural Patterns14 hits · 14 pts

Severity	File	Line	Context
LOW	tests/eval/batch_eval.py	672	CODE
LOW	src/forge/server.py	545	CODE
LOW	src/forge/server.py	73	CODE
LOW	src/forge/server.py	382	CODE
LOW	src/forge/clients/vllm.py	58	CODE
LOW	src/forge/clients/llamafile.py	324	CODE
LOW	src/forge/clients/openai_compat.py	53	CODE
LOW	src/forge/clients/anthropic.py	105	CODE
LOW	src/forge/clients/ollama.py	98	CODE
LOW	src/forge/core/runner.py	34	CODE
LOW	src/forge/core/inference.py	165	CODE
LOW	src/forge/proxy/server.py	58	CODE
LOW	src/forge/proxy/handler.py	198	CODE
LOW	src/forge/proxy/proxy.py	60	CODE

Over-Commented Block15 hits · 14 pts

Severity	File	Line	Snippet	Context
LOW	tests/eval/scenarios/_model_reasoning.py	61	top_vendor: str = Field(description="Vendor of the single largest flagged transaction")	COMMENT
LOW	tests/eval/scenarios/_model_reasoning.py	281	tags=["advanced_reasoning", "reasoning", "model_quality"],	COMMENT
LOW	tests/eval/scenarios/_model_reasoning.py	561		COMMENT
LOW	tests/eval/scenarios/_model_reasoning.py	881	"txn_count (int)."	COMMENT
LOW	tests/eval/scenarios/_model_reasoning.py	901	# Sarah Chen — top-decile attractor; BLOCKER: Stripe non-compete	COMMENT
LOW	examples/foreign_loop.py	141	# The respond tool eliminates this ambiguity: the model calls	COMMENT
LOW	src/forge/clients/sampling_defaults.py	101	"Mistral-Small-4-119B-2603-UD-Q4_K_M": {"temperature": 0.7, "chat_template_kwargs": {"reasoning_effort": "high"}},	COMMENT
LOW	src/forge/clients/sampling_defaults.py	121	# T=1.0, top_p=0.95 across all tasks. Coding-agent serving guidance also adds force_nonempty_content	COMMENT
LOW	src/forge/clients/sampling_defaults.py	161	"Ministral-3-8B-Reasoning-2512-Q4_K_M": {"temperature": 0.7}, # https://huggingface.co/mistralai/Ministral-3-8B-Re	COMMENT
LOW	src/forge/clients/llamafile.py	41	# ``.gguf``/``.llamafile`` files, but it silently truncates BARE dotted	COMMENT
LOW	src/forge/clients/anthropic.py	121	self._tool_choice = tool_choice # "auto", "any", or None (default=auto)	COMMENT
LOW	src/forge/clients/anthropic.py	141	# One credential per request. ``static_auth`` reflects an explicitly	COMMENT
LOW	src/forge/guardrails/nudge.py	41		COMMENT
LOW	src/forge/proxy/handler.py	301	# ADR-015.	COMMENT
LOW	src/forge/proxy/proxy.py	381		COMMENT

Verbosity Indicators5 hits · 11 pts

Severity	File	Line	Snippet	Context
LOW⚡	tests/eval/scenarios/_compaction_chain.py	532	# Step 1: patient MRN (not in user message)	COMMENT
LOW⚡	tests/eval/scenarios/_compaction_chain.py	534	# Step 3: lab values (only from tool result)	COMMENT
LOW⚡	tests/eval/scenarios/_compaction_chain.py	536	# Step 4: imaging findings (only from tool result)	COMMENT
LOW⚡	tests/eval/scenarios/_compaction_chain.py	538	# Step 5: specialist (only from tool result)	COMMENT
LOW⚡	tests/eval/scenarios/_compaction_chain.py	540	# Step 6: medication concern (only from tool result)	COMMENT

AI Slop Vocabulary2 hits · 8 pts

Severity	File	Line	Snippet	Context
MEDIUM	pyproject.toml	75	# Covered by eval harness runs, not unit tests.	COMMENT
MEDIUM⚡	tests/unit/test_proxy_auth.py	43	# The proxy lowercases keys, but be robust to mixed case anyway.	COMMENT

Self-Referential Comments1 hit · 4 pts

Severity	File	Line	Snippet	Context
MEDIUM⚡	tests/unit/test_server.py	239	# Create a fake llamafile runtime in tmp_path	COMMENT

Cross-Language Confusion1 hit · 2 pts

Severity	File	Line	Snippet	Context
HIGH	src/forge/prompts/nudges.py	69	args content (e.g. an empty string, null, a list, or a primitive	STRING

Redundant / Tautological Comments1 hit · 2 pts

Severity	File	Line	Snippet	Context
LOW	examples/foreign_loop.py	175	# Check if the model called respond -- extract the message	COMMENT

Analysis Overview

What These Metrics Mean

Score History

Severity Breakdown

Directory Score Breakdown

Pattern Findings