feat: make TokenUsage.total_tokens a computed field#118
Conversation
Convert `total_tokens` from a stored `Field` with `@model_validator` to a `@computed_field` property. This eliminates redundant storage and the impossible-to-fail validator, and removes `total_tokens=...` from all 22 call sites. Closes #109 Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Pre-reviewed by 9 agents, 5 findings addressed: - CLAUDE.md: mark @computed_field as Adopted (was stale Planned) - Add serialization roundtrip + computed-always-wins tests - Add explanatory comment for type: ignore[prop-decorator] - Rename test_maintains_total_invariant → test_total_tokens_is_sum_of_parts - Clarify add_token_usage docstring re: computed total_tokens Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Dependency Review✅ No vulnerabilities or license issues or OpenSSF Scorecard issues found.Scanned FilesNone |
|
Caution Review failedPull request was closed or merged during review No actionable comments were generated in the recent review. 🎉 ℹ️ Recent review info⚙️ Run configurationConfiguration used: Organization UI Review profile: ASSERTIVE Plan: Pro Run ID: 📒 Files selected for processing (3)
📜 Recent review details⏰ Context from checks skipped due to timeout of 90000ms. You can increase the timeout in your CodeRabbit configuration to a maximum of 15 minutes (900000ms). (1)
🧰 Additional context used📓 Path-based instructions (3)DESIGN_SPEC.md📄 CodeRabbit inference engine (CLAUDE.md)
Files:
tests/**/*.py📄 CodeRabbit inference engine (CLAUDE.md)
Files:
src/**/*.py📄 CodeRabbit inference engine (CLAUDE.md)
Files:
🧠 Learnings (10)📓 Common learnings📚 Learning: 2026-03-06T07:08:12.974ZApplied to files:
📚 Learning: 2026-03-06T07:08:12.974ZApplied to files:
📚 Learning: 2026-03-06T07:08:12.974ZApplied to files:
📚 Learning: 2026-03-06T07:08:12.974ZApplied to files:
📚 Learning: 2026-03-06T07:08:12.974ZApplied to files:
📚 Learning: 2026-01-26T08:59:32.818ZApplied to files:
📚 Learning: 2026-03-06T07:08:12.974ZApplied to files:
📚 Learning: 2026-03-06T07:08:12.974ZApplied to files:
📚 Learning: 2026-03-06T07:08:12.974ZApplied to files:
🪛 LanguageToolDESIGN_SPEC.md[style] ~860-~860: This word has been used in one of the immediately preceding sentences. Using a synonym could make your text more interesting to read, unless the repetition is intentional. (EN_REPEATEDWORDS_NEED) 🔇 Additional comments (5)
📝 WalkthroughSummary by CodeRabbit
WalkthroughThis PR replaces the stored Changes
Estimated code review effort🎯 3 (Moderate) | ⏱️ ~20 minutes 🚥 Pre-merge checks | ✅ 4 | ❌ 1❌ Failed checks (1 warning)
✅ Passed checks (4 passed)
✏️ Tip: You can configure your own custom pre-merge checks in the settings. ✨ Finishing Touches
🧪 Generate unit tests (beta)
Thanks for using CodeRabbit! It's free for OSS, and your support helps us grow. If you like it, consider giving us a shout-out. Comment |
Summary of ChangesHello, I'm Gemini Code Assist1! I'm currently reviewing this pull request and will post my feedback shortly. In the meantime, here's a summary to help you and other reviewers quickly get up to speed! This pull request refactors the Highlights
Changelog
Activity
Using Gemini Code AssistThe full guide for Gemini Code Assist can be found on our documentation page, here are some quick tips. Invoking Gemini You can request assistance from Gemini at any point by creating a comment using either
Customization To customize Gemini Code Assist for GitHub experience, repository maintainers can create a configuration file and/or provide a custom code review style guide (such as PEP-8 for Python) by creating and adding files to a Limitations & Feedback Gemini Code Assist may make mistakes. Please leave feedback on any instances where its feedback is incorrect or counter productive. You can react with 👍 and 👎 on @gemini-code-assist comments. If you're interested in giving your feedback about your experience with Gemini Code Assist for Github and other Google products, sign up here. You can also get AI-powered code generation, chat, as well as code reviews directly in the IDE at no cost with the Gemini Code Assist IDE Extension. Footnotes
|
Greptile SummaryThis PR completes the migration of Key changes:
Confidence Score: 5/5
Last reviewed commit: 2faff4d |
There was a problem hiding this comment.
Pull request overview
This PR migrates TokenUsage.total_tokens from a stored/validated Pydantic field to a @computed_field, removing redundant state and simplifying construction/aggregation across the provider and engine layers.
Changes:
- Convert
TokenUsage.total_tokensto a@computed_fieldand drop the (now unnecessary) validator and stored field. - Remove
total_tokens=from allTokenUsage(...)call sites and fixtures; simplifyadd_token_usage. - Update unit tests and documentation (DESIGN_SPEC.md, CLAUDE.md) to reflect the adopted derived-field convention.
Reviewed changes
Copilot reviewed 10 out of 10 changed files in this pull request and generated no comments.
Show a summary per file
| File | Description |
|---|---|
src/ai_company/providers/models.py |
Implements total_tokens as a computed field; updates ZERO_TOKEN_USAGE and add_token_usage. |
src/ai_company/providers/base.py |
Removes redundant total_tokens construction in compute_cost. |
tests/unit/providers/test_models.py |
Replaces invariant-validator test with computed-field, serialization, and roundtrip tests. |
tests/unit/providers/test_base_provider.py |
Updates provider test helper to construct TokenUsage without total_tokens. |
tests/unit/providers/conftest.py |
Updates TokenUsageFactory and sample_token_usage fixture to omit total_tokens. |
tests/unit/engine/test_task_execution.py |
Updates engine aggregation tests and renames invariant test to reflect computed behavior. |
tests/unit/engine/test_context.py |
Updates context tests to construct TokenUsage without total_tokens. |
tests/unit/engine/conftest.py |
Updates engine fixture to omit total_tokens. |
DESIGN_SPEC.md |
Updates design notes/conventions to mark computed derived fields as adopted. |
CLAUDE.md |
Updates modeling conventions to include computed_field as adopted practice. |
💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.
There was a problem hiding this comment.
Code Review
This pull request refactors TokenUsage.total_tokens to be a @computed_field, improving data integrity and code simplicity by ensuring the total token count is always consistent with the sum of input and output tokens, eliminating the need for manual validation and reducing redundant storage. No security vulnerabilities were identified during the audit. The changes are applied consistently, and the new tests are thorough. I suggest implementing the __add__ operator in the TokenUsage model for more idiomatic summation, which would allow for removing the add_token_usage helper function.
| def add_token_usage(a: TokenUsage, b: TokenUsage) -> TokenUsage: | ||
| """Create a new ``TokenUsage`` with summed token counts and cost. | ||
|
|
||
| Computes ``total_tokens`` from the summed parts to maintain the | ||
| ``total_tokens == input_tokens + output_tokens`` invariant. | ||
|
|
||
| Args: | ||
| a: First usage record. | ||
| b: Second usage record. | ||
|
|
||
| Returns: | ||
| New ``TokenUsage`` with summed token counts and cost. | ||
| New ``TokenUsage`` with summed token counts and cost | ||
| (``total_tokens`` is computed automatically). | ||
| """ | ||
| input_tokens = a.input_tokens + b.input_tokens | ||
| output_tokens = a.output_tokens + b.output_tokens | ||
| return TokenUsage( | ||
| input_tokens=input_tokens, | ||
| output_tokens=output_tokens, | ||
| total_tokens=input_tokens + output_tokens, | ||
| input_tokens=a.input_tokens + b.input_tokens, | ||
| output_tokens=a.output_tokens + b.output_tokens, | ||
| cost_usd=a.cost_usd + b.cost_usd, | ||
| ) |
There was a problem hiding this comment.
While this function works correctly, consider implementing operator overloading by adding an __add__ method to the TokenUsage class. This would allow for more idiomatic and readable code, like usage_a + usage_b, instead of add_token_usage(usage_a, usage_b). This would make TokenUsage behave more like a numeric type where addition is a natural operation.
Example implementation inside TokenUsage class:
from typing import Self
# ...
def __add__(self, other: Self) -> Self:
if not isinstance(other, TokenUsage):
return NotImplemented
return TokenUsage(
input_tokens=self.input_tokens + other.input_tokens,
output_tokens=self.output_tokens + other.output_tokens,
cost_usd=self.cost_usd + other.cost_usd,
)With this change, this add_token_usage function would no longer be necessary and could be removed, and call sites could be updated to use the + operator.
| total_tokens=30, | ||
| cost_usd=0.02, | ||
| ) | ||
| result = add_token_usage(a, b) |
There was a problem hiding this comment.
If you implement __add__ on TokenUsage as suggested in src/ai_company/providers/models.py, this call can be simplified.
| result = add_token_usage(a, b) | |
| result = a + b |
| total_tokens=20, | ||
| cost_usd=0.0, | ||
| ) | ||
| result = add_token_usage(a, b) |
There was a problem hiding this comment.
If you implement __add__ on TokenUsage as suggested in src/ai_company/providers/models.py, this call can be simplified.
| result = add_token_usage(a, b) | |
| result = a + b |
| total_tokens=75, | ||
| cost_usd=0.05, | ||
| ) | ||
| result = add_token_usage(ZERO_TOKEN_USAGE, usage) |
There was a problem hiding this comment.
If you implement __add__ on TokenUsage as suggested in src/ai_company/providers/models.py, this call can be simplified.
| result = add_token_usage(ZERO_TOKEN_USAGE, usage) | |
| result = ZERO_TOKEN_USAGE + usage |
There was a problem hiding this comment.
Actionable comments posted: 1
🤖 Prompt for all review comments with AI agents
Verify each finding against the current code and only fix it if needed.
Inline comments:
In `@tests/unit/providers/test_models.py`:
- Around line 82-92: Replace the hand-written dict with a real serialized
payload from TokenUsage.model_dump to perform a true round-trip: create a
TokenUsage instance with input_tokens and output_tokens, call model_dump() to
get the serialized dict, mutate the serialized dict's "total_tokens" to 999,
then pass that dict into TokenUsage.model_validate(...) and assert that
usage.total_tokens == 15; reference the test function
test_total_tokens_roundtrip and methods TokenUsage.model_dump and
TokenUsage.model_validate when locating the change.
ℹ️ Review info
⚙️ Run configuration
Configuration used: Organization UI
Review profile: ASSERTIVE
Plan: Pro
Run ID: a7ab4640-be95-4f24-bc27-dc5fbd4fed2f
📒 Files selected for processing (10)
CLAUDE.mdDESIGN_SPEC.mdsrc/ai_company/providers/base.pysrc/ai_company/providers/models.pytests/unit/engine/conftest.pytests/unit/engine/test_context.pytests/unit/engine/test_task_execution.pytests/unit/providers/conftest.pytests/unit/providers/test_base_provider.pytests/unit/providers/test_models.py
💤 Files with no reviewable changes (5)
- src/ai_company/providers/base.py
- tests/unit/engine/test_context.py
- tests/unit/providers/conftest.py
- tests/unit/engine/conftest.py
- tests/unit/providers/test_base_provider.py
📜 Review details
⏰ Context from checks skipped due to timeout of 90000ms. You can increase the timeout in your CodeRabbit configuration to a maximum of 15 minutes (900000ms). (2)
- GitHub Check: Agent
- GitHub Check: Greptile Review
🧰 Additional context used
📓 Path-based instructions (3)
tests/**/*.py
📄 CodeRabbit inference engine (CLAUDE.md)
tests/**/*.py: Mark test functions with@pytest.mark.unit,@pytest.mark.integration,@pytest.mark.e2e, or@pytest.mark.slow
Maintain minimum 80% code coverage (enforced in CI)
Useasyncio_mode = 'auto'in pytest configuration — no manual@pytest.mark.asyncioneeded on async tests
Set 30-second timeout per test
Use fake/test model IDs and provider names in tests (e.g.test-haiku-001,test-provider), never real vendor model IDs — tests must not be coupled to external providers
Files:
tests/unit/providers/test_models.pytests/unit/engine/test_task_execution.py
DESIGN_SPEC.md
📄 CodeRabbit inference engine (CLAUDE.md)
Update
DESIGN_SPEC.mdto reflect approved deviations from the original design
Files:
DESIGN_SPEC.md
src/**/*.py
📄 CodeRabbit inference engine (CLAUDE.md)
src/**/*.py: Always readDESIGN_SPEC.mdbefore implementing any feature or planning any issue — it is the starting point for architecture, data models, and behavior
If implementation deviates fromDESIGN_SPEC.md, alert the user and explain why — user decides whether to proceed or update the spec. Do NOT silently diverge.
When a spec section is referenced (e.g. 'Section 10.2'), read that section verbatim before coding
Every implementation plan must be presented to the user for accept/deny before coding starts
At every phase of planning and implementation, be critical and actively look for ways to improve the design in the spirit of what we're building (robustness, correctness, simplicity, future-proofing where it's free). Surface improvements as suggestions, not silent changes.
Do NOT usefrom __future__ import annotations— Python 3.14 has PEP 649 native lazy annotations
Useexcept A, B:syntax without parentheses for multiple exception handling (PEP 758) — ruff enforces this on Python 3.14
All public functions must have type hints and pass mypy strict mode
All public classes and functions must have Google-style docstrings, enforced by ruff D rules
Never mutate existing objects — create new objects instead. For non-Pydantic internal collections (registries,BaseTool), usecopy.deepcopy()at construction +MappingProxyTypewrapping for read-only enforcement.
Fordict/listfields in frozen Pydantic models, rely onfrozen=Truefor field reassignment prevention and usecopy.deepcopy()at system boundaries (tool execution, LLM provider serialization, inter-agent delegation, serializing for persistence)
Use frozen Pydantic models for config/identity; use separate mutable-via-copy models (usingmodel_copy(update=...)) for runtime state that evolves (e.g. agent execution state, task progress). Never mix static config fields with mutable runtime fields in one model.
Use Pydantic v2 withBaseModel,model_validator, andConfigDict
Use `@computed...
Files:
src/ai_company/providers/models.py
🧠 Learnings (15)
📓 Common learnings
Learnt from: CR
Repo: Aureliolo/ai-company PR: 0
File: CLAUDE.md:0-0
Timestamp: 2026-03-06T07:08:12.933Z
Learning: Applies to src/**/*.py : Use `computed_field` for derived values instead of storing + validating redundant fields in Pydantic models
📚 Learning: 2026-03-06T07:08:12.933Z
Learnt from: CR
Repo: Aureliolo/ai-company PR: 0
File: CLAUDE.md:0-0
Timestamp: 2026-03-06T07:08:12.933Z
Learning: Applies to src/**/*.py : Use `computed_field` for derived values instead of storing + validating redundant fields in Pydantic models
Applied to files:
CLAUDE.mdDESIGN_SPEC.mdsrc/ai_company/providers/models.py
📚 Learning: 2026-02-26T17:43:50.902Z
Learnt from: CR
Repo: Aureliolo/story-factory PR: 0
File: CLAUDE.md:0-0
Timestamp: 2026-02-26T17:43:50.902Z
Learning: When making changes that affect architecture, services, key files, settings, or workflows, update the relevant sections of existing documentation (CLAUDE.md, README.md, etc.) to reflect those changes.
Applied to files:
CLAUDE.md
📚 Learning: 2026-01-26T08:59:32.818Z
Learnt from: CR
Repo: Aureliolo/story-factory PR: 0
File: .github/copilot-instructions.md:0-0
Timestamp: 2026-01-26T08:59:32.818Z
Learning: Applies to docs/MODELS.md : Update docs/MODELS.md when adding model recommendations
Applied to files:
CLAUDE.md
📚 Learning: 2026-03-06T07:08:12.933Z
Learnt from: CR
Repo: Aureliolo/ai-company PR: 0
File: CLAUDE.md:0-0
Timestamp: 2026-03-06T07:08:12.933Z
Learning: Applies to src/**/*.py : Use frozen Pydantic models for config/identity; use separate mutable-via-copy models (using `model_copy(update=...)`) for runtime state that evolves (e.g. agent execution state, task progress). Never mix static config fields with mutable runtime fields in one model.
Applied to files:
CLAUDE.mdDESIGN_SPEC.md
📚 Learning: 2026-03-06T07:08:12.933Z
Learnt from: CR
Repo: Aureliolo/ai-company PR: 0
File: CLAUDE.md:0-0
Timestamp: 2026-03-06T07:08:12.933Z
Learning: Applies to src/**/*.py : All public classes and functions must have Google-style docstrings, enforced by ruff D rules
Applied to files:
CLAUDE.md
📚 Learning: 2026-03-06T07:08:12.933Z
Learnt from: CR
Repo: Aureliolo/ai-company PR: 0
File: CLAUDE.md:0-0
Timestamp: 2026-03-06T07:08:12.933Z
Learning: Applies to src/**/*.py : For `dict`/`list` fields in frozen Pydantic models, rely on `frozen=True` for field reassignment prevention and use `copy.deepcopy()` at system boundaries (tool execution, LLM provider serialization, inter-agent delegation, serializing for persistence)
Applied to files:
CLAUDE.mdDESIGN_SPEC.md
📚 Learning: 2026-03-06T07:08:12.933Z
Learnt from: CR
Repo: Aureliolo/ai-company PR: 0
File: CLAUDE.md:0-0
Timestamp: 2026-03-06T07:08:12.933Z
Learning: Applies to src/**/*.py : Never mutate existing objects — create new objects instead. For non-Pydantic internal collections (registries, `BaseTool`), use `copy.deepcopy()` at construction + `MappingProxyType` wrapping for read-only enforcement.
Applied to files:
CLAUDE.mdDESIGN_SPEC.md
📚 Learning: 2026-01-26T08:59:32.818Z
Learnt from: CR
Repo: Aureliolo/story-factory PR: 0
File: .github/copilot-instructions.md:0-0
Timestamp: 2026-01-26T08:59:32.818Z
Learning: Applies to **/*.py : Line length: 100 characters (enforced by Ruff)
Applied to files:
CLAUDE.md
📚 Learning: 2026-01-26T08:59:32.818Z
Learnt from: CR
Repo: Aureliolo/story-factory PR: 0
File: .github/copilot-instructions.md:0-0
Timestamp: 2026-01-26T08:59:32.818Z
Learning: Applies to **/*.py : Use type hints where appropriate. Use Pydantic models for data validation in `src/memory/story_state.py`, dataclasses in `src/settings.py`.
Applied to files:
CLAUDE.mdDESIGN_SPEC.md
📚 Learning: 2026-03-06T07:08:12.933Z
Learnt from: CR
Repo: Aureliolo/ai-company PR: 0
File: CLAUDE.md:0-0
Timestamp: 2026-03-06T07:08:12.933Z
Learning: Applies to src/**/*.py : At every phase of planning and implementation, be critical and actively look for ways to improve the design in the spirit of what we're building (robustness, correctness, simplicity, future-proofing where it's free). Surface improvements as suggestions, not silent changes.
Applied to files:
CLAUDE.mdDESIGN_SPEC.md
📚 Learning: 2026-03-06T07:08:12.933Z
Learnt from: CR
Repo: Aureliolo/ai-company PR: 0
File: CLAUDE.md:0-0
Timestamp: 2026-03-06T07:08:12.933Z
Learning: Applies to src/**/*.py : Maximum line length is 88 characters (enforced by ruff)
Applied to files:
CLAUDE.md
📚 Learning: 2026-03-06T07:08:12.933Z
Learnt from: CR
Repo: Aureliolo/ai-company PR: 0
File: CLAUDE.md:0-0
Timestamp: 2026-03-06T07:08:12.933Z
Learning: Applies to src/**/*.py : Use Pydantic v2 with `BaseModel`, `model_validator`, and `ConfigDict`
Applied to files:
CLAUDE.mdsrc/ai_company/providers/models.py
📚 Learning: 2026-03-06T07:08:12.933Z
Learnt from: CR
Repo: Aureliolo/ai-company PR: 0
File: CLAUDE.md:0-0
Timestamp: 2026-03-06T07:08:12.933Z
Learning: Applies to src/**/*.py : Always read `DESIGN_SPEC.md` before implementing any feature or planning any issue — it is the starting point for architecture, data models, and behavior
Applied to files:
CLAUDE.md
📚 Learning: 2026-03-06T07:08:12.933Z
Learnt from: CR
Repo: Aureliolo/ai-company PR: 0
File: CLAUDE.md:0-0
Timestamp: 2026-03-06T07:08:12.933Z
Learning: Applies to DESIGN_SPEC.md : Update `DESIGN_SPEC.md` to reflect approved deviations from the original design
Applied to files:
DESIGN_SPEC.md
🪛 LanguageTool
DESIGN_SPEC.md
[style] ~860-~860: This word has been used in one of the immediately preceding sentences. Using a synonym could make your text more interesting to read, unless the repetition is intentional.
Context: ..._tokens — no stored field or validator needed. Spending summary models (AgentSpendin...
(EN_REPEATEDWORDS_NEED)
- Add description="Total token count" to @computed_field for consistency - Improve test_total_tokens_roundtrip to use model_dump() + mutate pattern - Add JSON roundtrip assertion (model_dump_json/model_validate_json) - Add test_total_tokens_not_assignable for computed property immutability - Fix DESIGN_SPEC.md §15.3: CompletionRequest → CompletionConfig Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
🤖 I have created a release *beep* *boop* --- ## [0.1.1](ai-company-v0.1.0...ai-company-v0.1.1) (2026-03-10) ### Features * add autonomy levels and approval timeout policies ([#42](#42), [#126](#126)) ([#197](#197)) ([eecc25a](eecc25a)) * add CFO cost optimization service with anomaly detection, reports, and approval decisions ([#186](#186)) ([a7fa00b](a7fa00b)) * add code quality toolchain (ruff, mypy, pre-commit, dependabot) ([#63](#63)) ([36681a8](36681a8)) * add configurable cost tiers and subscription/quota-aware tracking ([#67](#67)) ([#185](#185)) ([9baedfa](9baedfa)) * add container packaging, Docker Compose, and CI pipeline ([#269](#269)) ([435bdfe](435bdfe)), closes [#267](#267) * add coordination error taxonomy classification pipeline ([#146](#146)) ([#181](#181)) ([70c7480](70c7480)) * add cost-optimized, hierarchical, and auction assignment strategies ([#175](#175)) ([ce924fa](ce924fa)), closes [#173](#173) * add design specification, license, and project setup ([8669a09](8669a09)) * add env var substitution and config file auto-discovery ([#77](#77)) ([7f53832](7f53832)) * add FastestStrategy routing + vendor-agnostic cleanup ([#140](#140)) ([09619cb](09619cb)), closes [#139](#139) * add HR engine and performance tracking ([#45](#45), [#47](#47)) ([#193](#193)) ([2d091ea](2d091ea)) * add issue auto-search and resolution verification to PR review skill ([#119](#119)) ([deecc39](deecc39)) * add memory retrieval, ranking, and context injection pipeline ([#41](#41)) ([873b0aa](873b0aa)) * add pluggable MemoryBackend protocol with models, config, and events ([#180](#180)) ([46cfdd4](46cfdd4)) * add pluggable MemoryBackend protocol with models, config, and events ([#32](#32)) ([46cfdd4](46cfdd4)) * add pluggable PersistenceBackend protocol with SQLite implementation ([#36](#36)) ([f753779](f753779)) * add progressive trust and promotion/demotion subsystems ([#43](#43), [#49](#49)) ([3a87c08](3a87c08)) * add retry handler, rate limiter, and provider resilience ([#100](#100)) ([b890545](b890545)) * add SecOps security agent with rule engine, audit log, and ToolInvoker integration ([#40](#40)) ([83b7b6c](83b7b6c)) * add shared org memory and memory consolidation/archival ([#125](#125), [#48](#48)) ([4a0832b](4a0832b)) * design unified provider interface ([#86](#86)) ([3e23d64](3e23d64)) * expand template presets, rosters, and add inheritance ([#80](#80), [#81](#81), [#84](#84)) ([15a9134](15a9134)) * implement agent runtime state vs immutable config split ([#115](#115)) ([4cb1ca5](4cb1ca5)) * implement AgentEngine core orchestrator ([#11](#11)) ([#143](#143)) ([f2eb73a](f2eb73a)) * implement basic tool system (registry, invocation, results) ([#15](#15)) ([c51068b](c51068b)) * implement built-in file system tools ([#18](#18)) ([325ef98](325ef98)) * implement communication foundation — message bus, dispatcher, and messenger ([#157](#157)) ([8e71bfd](8e71bfd)) * implement company template system with 7 built-in presets ([#85](#85)) ([cbf1496](cbf1496)) * implement conflict resolution protocol ([#122](#122)) ([#166](#166)) ([e03f9f2](e03f9f2)) * implement core entity and role system models ([#69](#69)) ([acf9801](acf9801)) * implement crash recovery with fail-and-reassign strategy ([#149](#149)) ([e6e91ed](e6e91ed)) * implement engine extensions — Plan-and-Execute loop and call categorization ([#134](#134), [#135](#135)) ([#159](#159)) ([9b2699f](9b2699f)) * implement enterprise logging system with structlog ([#73](#73)) ([2f787e5](2f787e5)) * implement graceful shutdown with cooperative timeout strategy ([#130](#130)) ([6592515](6592515)) * implement hierarchical delegation and loop prevention ([#12](#12), [#17](#17)) ([6be60b6](6be60b6)) * implement LiteLLM driver and provider registry ([#88](#88)) ([ae3f18b](ae3f18b)), closes [#4](#4) * implement LLM decomposition strategy and workspace isolation ([#174](#174)) ([aa0eefe](aa0eefe)) * implement meeting protocol system ([#123](#123)) ([ee7caca](ee7caca)) * implement message and communication domain models ([#74](#74)) ([560a5d2](560a5d2)) * implement model routing engine ([#99](#99)) ([d3c250b](d3c250b)) * implement parallel agent execution ([#22](#22)) ([#161](#161)) ([65940b3](65940b3)) * implement per-call cost tracking service ([#7](#7)) ([#102](#102)) ([c4f1f1c](c4f1f1c)) * implement personality injection and system prompt construction ([#105](#105)) ([934dd85](934dd85)) * implement single-task execution lifecycle ([#21](#21)) ([#144](#144)) ([c7e64e4](c7e64e4)) * implement subprocess sandbox for tool execution isolation ([#131](#131)) ([#153](#153)) ([3c8394e](3c8394e)) * implement task assignment subsystem with pluggable strategies ([#172](#172)) ([c7f1b26](c7f1b26)), closes [#26](#26) [#30](#30) * implement task decomposition and routing engine ([#14](#14)) ([9c7fb52](9c7fb52)) * implement Task, Project, Artifact, Budget, and Cost domain models ([#71](#71)) ([81eabf1](81eabf1)) * implement tool permission checking ([#16](#16)) ([833c190](833c190)) * implement YAML config loader with Pydantic validation ([#59](#59)) ([ff3a2ba](ff3a2ba)) * implement YAML config loader with Pydantic validation ([#75](#75)) ([ff3a2ba](ff3a2ba)) * initialize project with uv, hatchling, and src layout ([39005f9](39005f9)) * initialize project with uv, hatchling, and src layout ([#62](#62)) ([39005f9](39005f9)) * Litestar REST API, WebSocket feed, and approval queue (M6) ([#189](#189)) ([29fcd08](29fcd08)) * make TokenUsage.total_tokens a computed field ([#118](#118)) ([c0bab18](c0bab18)), closes [#109](#109) * parallel tool execution in ToolInvoker.invoke_all ([#137](#137)) ([58517ee](58517ee)) * testing framework, CI pipeline, and M0 gap fixes ([#64](#64)) ([f581749](f581749)) * wire all modules into observability system ([#97](#97)) ([f7a0617](f7a0617)) ### Bug Fixes * address Greptile post-merge review findings from PRs [#170](https://github.com/Aureliolo/ai-company/issues/170)-[#175](https://github.com/Aureliolo/ai-company/issues/175) ([#176](#176)) ([c5ca929](c5ca929)) * address post-merge review feedback from PRs [#164](https://github.com/Aureliolo/ai-company/issues/164)-[#167](https://github.com/Aureliolo/ai-company/issues/167) ([#170](#170)) ([3bf897a](3bf897a)), closes [#169](#169) * enforce strict mypy on test files ([#89](#89)) ([aeeff8c](aeeff8c)) * harden Docker sandbox, MCP bridge, and code runner ([#50](#50), [#53](#53)) ([d5e1b6e](d5e1b6e)) * harden git tools security + code quality improvements ([#150](#150)) ([000a325](000a325)) * harden subprocess cleanup, env filtering, and shutdown resilience ([#155](#155)) ([d1fe1fb](d1fe1fb)) * incorporate post-merge feedback + pre-PR review fixes ([#164](#164)) ([c02832a](c02832a)) * pre-PR review fixes for post-merge findings ([#183](#183)) ([26b3108](26b3108)) * strengthen immutability for BaseTool schema and ToolInvoker boundaries ([#117](#117)) ([7e5e861](7e5e861)) ### Performance * harden non-inferable principle implementation ([#195](#195)) ([02b5f4e](02b5f4e)), closes [#188](#188) ### Refactoring * adopt NotBlankStr across all models ([#108](#108)) ([#120](#120)) ([ef89b90](ef89b90)) * extract _SpendingTotals base class from spending summary models ([#111](#111)) ([2f39c1b](2f39c1b)) * harden BudgetEnforcer with error handling, validation extraction, and review fixes ([#182](#182)) ([c107bf9](c107bf9)) * harden personality profiles, department validation, and template rendering ([#158](#158)) ([10b2299](10b2299)) * pre-PR review improvements for ExecutionLoop + ReAct loop ([#124](#124)) ([8dfb3c0](8dfb3c0)) * split events.py into per-domain event modules ([#136](#136)) ([e9cba89](e9cba89)) ### Documentation * add ADR-001 memory layer evaluation and selection ([#178](#178)) ([db3026f](db3026f)), closes [#39](#39) * add agent scaling research findings to DESIGN_SPEC ([#145](#145)) ([57e487b](57e487b)) * add CLAUDE.md, contributing guide, and dev documentation ([#65](#65)) ([55c1025](55c1025)), closes [#54](#54) * add crash recovery, sandboxing, analytics, and testing decisions ([#127](#127)) ([5c11595](5c11595)) * address external review feedback with MVP scope and new protocols ([#128](#128)) ([3b30b9a](3b30b9a)) * expand design spec with pluggable strategy protocols ([#121](#121)) ([6832db6](6832db6)) * finalize 23 design decisions (ADR-002) ([#190](#190)) ([8c39742](8c39742)) * update project docs for M2.5 conventions and add docs-consistency review agent ([#114](#114)) ([99766ee](99766ee)) ### Tests * add e2e single agent integration tests ([#24](#24)) ([#156](#156)) ([f566fb4](f566fb4)) * add provider adapter integration tests ([#90](#90)) ([40a61f4](40a61f4)) ### CI/CD * add Release Please for automated versioning and GitHub Releases ([#278](#278)) ([a488758](a488758)) * bump actions/checkout from 4 to 6 ([#95](#95)) ([1897247](1897247)) * bump actions/upload-artifact from 4 to 7 ([#94](#94)) ([27b1517](27b1517)) * harden CI/CD pipeline ([#92](#92)) ([ce4693c](ce4693c)) * split vulnerability scans into critical-fail and high-warn tiers ([#277](#277)) ([aba48af](aba48af)) ### Maintenance * add /worktree skill for parallel worktree management ([#171](#171)) ([951e337](951e337)) * add design spec context loading to research-link skill ([8ef9685](8ef9685)) * add post-merge-cleanup skill ([#70](#70)) ([f913705](f913705)) * add pre-pr-review skill and update CLAUDE.md ([#103](#103)) ([92e9023](92e9023)) * add research-link skill and rename skill files to SKILL.md ([#101](#101)) ([651c577](651c577)) * bump aiosqlite from 0.21.0 to 0.22.1 ([#191](#191)) ([3274a86](3274a86)) * bump pyyaml from 6.0.2 to 6.0.3 in the minor-and-patch group ([#96](#96)) ([0338d0c](0338d0c)) * bump ruff from 0.15.4 to 0.15.5 ([a49ee46](a49ee46)) * fix M0 audit items ([#66](#66)) ([c7724b5](c7724b5)) * pin setup-uv action to full SHA ([#281](#281)) ([4448002](4448002)) * post-audit cleanup — PEP 758, loggers, bug fixes, refactoring, tests, hookify rules ([#148](#148)) ([c57a6a9](c57a6a9)) --- This PR was generated with [Release Please](https://github.com/googleapis/release-please). See [documentation](https://github.com/googleapis/release-please#release-please).
🤖 I have created a release *beep* *boop* --- ## [0.1.0](v0.0.0...v0.1.0) (2026-03-11) ### Features * add autonomy levels and approval timeout policies ([#42](#42), [#126](#126)) ([#197](#197)) ([eecc25a](eecc25a)) * add CFO cost optimization service with anomaly detection, reports, and approval decisions ([#186](#186)) ([a7fa00b](a7fa00b)) * add code quality toolchain (ruff, mypy, pre-commit, dependabot) ([#63](#63)) ([36681a8](36681a8)) * add configurable cost tiers and subscription/quota-aware tracking ([#67](#67)) ([#185](#185)) ([9baedfa](9baedfa)) * add container packaging, Docker Compose, and CI pipeline ([#269](#269)) ([435bdfe](435bdfe)), closes [#267](#267) * add coordination error taxonomy classification pipeline ([#146](#146)) ([#181](#181)) ([70c7480](70c7480)) * add cost-optimized, hierarchical, and auction assignment strategies ([#175](#175)) ([ce924fa](ce924fa)), closes [#173](#173) * add design specification, license, and project setup ([8669a09](8669a09)) * add env var substitution and config file auto-discovery ([#77](#77)) ([7f53832](7f53832)) * add FastestStrategy routing + vendor-agnostic cleanup ([#140](#140)) ([09619cb](09619cb)), closes [#139](#139) * add HR engine and performance tracking ([#45](#45), [#47](#47)) ([#193](#193)) ([2d091ea](2d091ea)) * add issue auto-search and resolution verification to PR review skill ([#119](#119)) ([deecc39](deecc39)) * add mandatory JWT + API key authentication ([#256](#256)) ([c279cfe](c279cfe)) * add memory retrieval, ranking, and context injection pipeline ([#41](#41)) ([873b0aa](873b0aa)) * add pluggable MemoryBackend protocol with models, config, and events ([#180](#180)) ([46cfdd4](46cfdd4)) * add pluggable MemoryBackend protocol with models, config, and events ([#32](#32)) ([46cfdd4](46cfdd4)) * add pluggable output scan response policies ([#263](#263)) ([b9907e8](b9907e8)) * add pluggable PersistenceBackend protocol with SQLite implementation ([#36](#36)) ([f753779](f753779)) * add progressive trust and promotion/demotion subsystems ([#43](#43), [#49](#49)) ([3a87c08](3a87c08)) * add retry handler, rate limiter, and provider resilience ([#100](#100)) ([b890545](b890545)) * add SecOps security agent with rule engine, audit log, and ToolInvoker integration ([#40](#40)) ([83b7b6c](83b7b6c)) * add shared org memory and memory consolidation/archival ([#125](#125), [#48](#48)) ([4a0832b](4a0832b)) * design unified provider interface ([#86](#86)) ([3e23d64](3e23d64)) * expand template presets, rosters, and add inheritance ([#80](#80), [#81](#81), [#84](#84)) ([15a9134](15a9134)) * implement agent runtime state vs immutable config split ([#115](#115)) ([4cb1ca5](4cb1ca5)) * implement AgentEngine core orchestrator ([#11](#11)) ([#143](#143)) ([f2eb73a](f2eb73a)) * implement AuditRepository for security audit log persistence ([#279](#279)) ([94bc29f](94bc29f)) * implement basic tool system (registry, invocation, results) ([#15](#15)) ([c51068b](c51068b)) * implement built-in file system tools ([#18](#18)) ([325ef98](325ef98)) * implement communication foundation — message bus, dispatcher, and messenger ([#157](#157)) ([8e71bfd](8e71bfd)) * implement company template system with 7 built-in presets ([#85](#85)) ([cbf1496](cbf1496)) * implement conflict resolution protocol ([#122](#122)) ([#166](#166)) ([e03f9f2](e03f9f2)) * implement core entity and role system models ([#69](#69)) ([acf9801](acf9801)) * implement crash recovery with fail-and-reassign strategy ([#149](#149)) ([e6e91ed](e6e91ed)) * implement engine extensions — Plan-and-Execute loop and call categorization ([#134](#134), [#135](#135)) ([#159](#159)) ([9b2699f](9b2699f)) * implement enterprise logging system with structlog ([#73](#73)) ([2f787e5](2f787e5)) * implement graceful shutdown with cooperative timeout strategy ([#130](#130)) ([6592515](6592515)) * implement hierarchical delegation and loop prevention ([#12](#12), [#17](#17)) ([6be60b6](6be60b6)) * implement LiteLLM driver and provider registry ([#88](#88)) ([ae3f18b](ae3f18b)), closes [#4](#4) * implement LLM decomposition strategy and workspace isolation ([#174](#174)) ([aa0eefe](aa0eefe)) * implement meeting protocol system ([#123](#123)) ([ee7caca](ee7caca)) * implement message and communication domain models ([#74](#74)) ([560a5d2](560a5d2)) * implement model routing engine ([#99](#99)) ([d3c250b](d3c250b)) * implement parallel agent execution ([#22](#22)) ([#161](#161)) ([65940b3](65940b3)) * implement per-call cost tracking service ([#7](#7)) ([#102](#102)) ([c4f1f1c](c4f1f1c)) * implement personality injection and system prompt construction ([#105](#105)) ([934dd85](934dd85)) * implement single-task execution lifecycle ([#21](#21)) ([#144](#144)) ([c7e64e4](c7e64e4)) * implement subprocess sandbox for tool execution isolation ([#131](#131)) ([#153](#153)) ([3c8394e](3c8394e)) * implement task assignment subsystem with pluggable strategies ([#172](#172)) ([c7f1b26](c7f1b26)), closes [#26](#26) [#30](#30) * implement task decomposition and routing engine ([#14](#14)) ([9c7fb52](9c7fb52)) * implement Task, Project, Artifact, Budget, and Cost domain models ([#71](#71)) ([81eabf1](81eabf1)) * implement tool permission checking ([#16](#16)) ([833c190](833c190)) * implement YAML config loader with Pydantic validation ([#59](#59)) ([ff3a2ba](ff3a2ba)) * implement YAML config loader with Pydantic validation ([#75](#75)) ([ff3a2ba](ff3a2ba)) * initialize project with uv, hatchling, and src layout ([39005f9](39005f9)) * initialize project with uv, hatchling, and src layout ([#62](#62)) ([39005f9](39005f9)) * Litestar REST API, WebSocket feed, and approval queue (M6) ([#189](#189)) ([29fcd08](29fcd08)) * make TokenUsage.total_tokens a computed field ([#118](#118)) ([c0bab18](c0bab18)), closes [#109](#109) * parallel tool execution in ToolInvoker.invoke_all ([#137](#137)) ([58517ee](58517ee)) * testing framework, CI pipeline, and M0 gap fixes ([#64](#64)) ([f581749](f581749)) * wire all modules into observability system ([#97](#97)) ([f7a0617](f7a0617)) ### Bug Fixes * address Greptile post-merge review findings from PRs [#170](https://github.com/Aureliolo/ai-company/issues/170)-[#175](https://github.com/Aureliolo/ai-company/issues/175) ([#176](#176)) ([c5ca929](c5ca929)) * address post-merge review feedback from PRs [#164](https://github.com/Aureliolo/ai-company/issues/164)-[#167](https://github.com/Aureliolo/ai-company/issues/167) ([#170](#170)) ([3bf897a](3bf897a)), closes [#169](#169) * enforce strict mypy on test files ([#89](#89)) ([aeeff8c](aeeff8c)) * harden Docker sandbox, MCP bridge, and code runner ([#50](#50), [#53](#53)) ([d5e1b6e](d5e1b6e)) * harden git tools security + code quality improvements ([#150](#150)) ([000a325](000a325)) * harden subprocess cleanup, env filtering, and shutdown resilience ([#155](#155)) ([d1fe1fb](d1fe1fb)) * incorporate post-merge feedback + pre-PR review fixes ([#164](#164)) ([c02832a](c02832a)) * pre-PR review fixes for post-merge findings ([#183](#183)) ([26b3108](26b3108)) * resolve circular imports, bump litellm, fix release tag format ([#286](#286)) ([a6659b5](a6659b5)) * strengthen immutability for BaseTool schema and ToolInvoker boundaries ([#117](#117)) ([7e5e861](7e5e861)) ### Performance * harden non-inferable principle implementation ([#195](#195)) ([02b5f4e](02b5f4e)), closes [#188](#188) ### Refactoring * adopt NotBlankStr across all models ([#108](#108)) ([#120](#120)) ([ef89b90](ef89b90)) * extract _SpendingTotals base class from spending summary models ([#111](#111)) ([2f39c1b](2f39c1b)) * harden BudgetEnforcer with error handling, validation extraction, and review fixes ([#182](#182)) ([c107bf9](c107bf9)) * harden personality profiles, department validation, and template rendering ([#158](#158)) ([10b2299](10b2299)) * pre-PR review improvements for ExecutionLoop + ReAct loop ([#124](#124)) ([8dfb3c0](8dfb3c0)) * split events.py into per-domain event modules ([#136](#136)) ([e9cba89](e9cba89)) ### Documentation * add ADR-001 memory layer evaluation and selection ([#178](#178)) ([db3026f](db3026f)), closes [#39](#39) * add agent scaling research findings to DESIGN_SPEC ([#145](#145)) ([57e487b](57e487b)) * add CLAUDE.md, contributing guide, and dev documentation ([#65](#65)) ([55c1025](55c1025)), closes [#54](#54) * add crash recovery, sandboxing, analytics, and testing decisions ([#127](#127)) ([5c11595](5c11595)) * address external review feedback with MVP scope and new protocols ([#128](#128)) ([3b30b9a](3b30b9a)) * expand design spec with pluggable strategy protocols ([#121](#121)) ([6832db6](6832db6)) * finalize 23 design decisions (ADR-002) ([#190](#190)) ([8c39742](8c39742)) * update project docs for M2.5 conventions and add docs-consistency review agent ([#114](#114)) ([99766ee](99766ee)) ### Tests * add e2e single agent integration tests ([#24](#24)) ([#156](#156)) ([f566fb4](f566fb4)) * add provider adapter integration tests ([#90](#90)) ([40a61f4](40a61f4)) ### CI/CD * add Release Please for automated versioning and GitHub Releases ([#278](#278)) ([a488758](a488758)) * bump actions/checkout from 4 to 6 ([#95](#95)) ([1897247](1897247)) * bump actions/upload-artifact from 4 to 7 ([#94](#94)) ([27b1517](27b1517)) * bump anchore/scan-action from 6.5.1 to 7.3.2 ([#271](#271)) ([80a1c15](80a1c15)) * bump docker/build-push-action from 6.19.2 to 7.0.0 ([#273](#273)) ([dd0219e](dd0219e)) * bump docker/login-action from 3.7.0 to 4.0.0 ([#272](#272)) ([33d6238](33d6238)) * bump docker/metadata-action from 5.10.0 to 6.0.0 ([#270](#270)) ([baee04e](baee04e)) * bump docker/setup-buildx-action from 3.12.0 to 4.0.0 ([#274](#274)) ([5fc06f7](5fc06f7)) * bump sigstore/cosign-installer from 3.9.1 to 4.1.0 ([#275](#275)) ([29dd16c](29dd16c)) * harden CI/CD pipeline ([#92](#92)) ([ce4693c](ce4693c)) * split vulnerability scans into critical-fail and high-warn tiers ([#277](#277)) ([aba48af](aba48af)) ### Maintenance * add /worktree skill for parallel worktree management ([#171](#171)) ([951e337](951e337)) * add design spec context loading to research-link skill ([8ef9685](8ef9685)) * add post-merge-cleanup skill ([#70](#70)) ([f913705](f913705)) * add pre-pr-review skill and update CLAUDE.md ([#103](#103)) ([92e9023](92e9023)) * add research-link skill and rename skill files to SKILL.md ([#101](#101)) ([651c577](651c577)) * bump aiosqlite from 0.21.0 to 0.22.1 ([#191](#191)) ([3274a86](3274a86)) * bump pyyaml from 6.0.2 to 6.0.3 in the minor-and-patch group ([#96](#96)) ([0338d0c](0338d0c)) * bump ruff from 0.15.4 to 0.15.5 ([a49ee46](a49ee46)) * fix M0 audit items ([#66](#66)) ([c7724b5](c7724b5)) * **main:** release ai-company 0.1.1 ([#282](#282)) ([2f4703d](2f4703d)) * pin setup-uv action to full SHA ([#281](#281)) ([4448002](4448002)) * post-audit cleanup — PEP 758, loggers, bug fixes, refactoring, tests, hookify rules ([#148](#148)) ([c57a6a9](c57a6a9)) --- This PR was generated with [Release Please](https://github.com/googleapis/release-please). See [documentation](https://github.com/googleapis/release-please#release-please). --------- Signed-off-by: Aurelio <19254254+Aureliolo@users.noreply.github.com>
Summary
TokenUsage.total_tokensfrom a storedField+@model_validatorto a@computed_fieldproperty — eliminates redundant storage and impossible-to-fail validatortotal_tokens=kwarg from all constructor call sites (compute_cost,add_token_usage,ZERO_TOKEN_USAGE, all test fixtures/factories)add_token_usageby inlining expressions (no intermediate variables needed)@computed_fieldas an adopted conventionReview coverage
Pre-reviewed by 9 agents (code-reviewer, python-reviewer, pr-test-analyzer, silent-failure-hunter, comment-analyzer, type-design-analyzer, logging-audit, resilience-audit, docs-consistency). 5 findings addressed:
@computed_fieldas Adopted (was stale "Planned")type: ignore[prop-decorator]test_maintains_total_invariant→test_total_tokens_is_sum_of_partsadd_token_usagedocstring re: computedtotal_tokensTest plan
uv run ruff check src/ tests/— all checks passeduv run mypy src/ tests/— no issues in 199 source filesuv run pytest tests/ -n auto --cov=ai_company --cov-fail-under=80— 1788 passed, 95.35% coveragetest_total_tokens_is_always_computed,test_total_tokens_in_serialization,test_total_tokens_roundtripCloses #109