feat: Python SDK feature parity — core types, hooks, tools, triggers, interactive loop

[codeitlikemiley]

Summary

Implements full feature parity between the Rust and Python Antigravity SDKs, closing all identified gaps from the SDK comparison analysis.

Changes

New Modules (5 files)

File	Description
src/error.rs	Typed error hierarchy: AntigravityError (Connection, Execution, Validation)
src/context.rs	Hierarchical HookContext state store (Session→Turn→Operation)
src/tool_context.rs	Session-scoped ToolContext with state store and agent communication
src/trigger_helpers.rs	every() periodic trigger factory
src/interactive.rs	run_interactive_loop() REPL utility (native only)

Extended Modules (4 files)

File	Changes
src/hooks.rs	Added on_session_end, post_turn, on_compaction hooks + dispatchers + tests
src/tools.rs	Added needs_context() / call_with_context() for context-aware tools
src/types.rs	Added multimodal pipeline (Media, Content, MimeType — 32 extensions), trigger types
src/lib.rs	Wired all new modules into public API

Documentation

File	Changes
README.md	Added 7 new sections: Error Handling, Multimodal Content, Lifecycle Hooks, Hook Context, Context-Aware Tools, Trigger Helpers, Interactive Loop

Python SDK Feature Mapping

Python Feature	Rust Implementation	Status
AntigravityConnectionError / AntigravityValidationError	AntigravityError::Connection / AntigravityError::Validation	✅
Image, Document, Audio, Video, Content	Media, Content, MimeType enums	✅
SessionContext → TurnContext → OperationContext	HookContext::new() / HookContext::child()	✅
ToolContext with get_state/set_state	ToolContext struct	✅
on_session_end, post_turn, on_compaction	Hook trait methods	✅
every() trigger helper	trigger_helpers::every()	✅
run_interactive_loop()	interactive::run_interactive_loop()	✅

Testing

• 90 unit tests — all pass
• 4 integration tests — all pass
• 4 doc-tests — all pass (including new modules)
• cargo clippy --all-targets -- -D warnings — 0 warnings

Backwards Compatibility

All changes are fully backwards compatible:

• New hook methods have default no-op implementations
• Tool::needs_context() defaults to false
• Existing PolicyEnforcer uses defaults automatically
• No breaking changes to public API

[codeitlikemiley]

/ecc-tools analyze

[ecc-tools]

Analysis Queued

Analyzing codeitlikemiley/antigravity-sdk-rust on pull request head c945a43b3130

Analysis Pipeline

Stage	Description	Status
Compare Snapshot	Resolving PR head/base diff before branch fallback	pending
Commit History	Fetching up to 200 commits (queued-mode cap)	pending
File Sampling	Extracting code patterns and structure	pending
Pattern Detection	AI analysis of conventions and workflows	pending
Bundle Generation	Creating skills, rules, commands, identity, and instincts	pending
Pull Request	Opening PR with generated files	pending

Estimated time: 2-5 minutes depending on repository size.

---

_{10/10 analyses remaining this month (free tier) | ECC Tools}

[ecc-tools]

Analyzing 200 commits...

[ecc-tools]

Analysis Complete

Generated ECC bundle from 6 commits | Confidence: 55%

View Pull Request #6

Repository Profile

Attribute	Value
Language	Rust
Framework	Not detected
Commit Convention	conventional
Test Directory	separate

Changed Files (20)

Metric	Value
Files changed	20
Additions	4438
Deletions	5

Top hotspots

Path	Status	+/-
docs/agent.md	added	+696 / -0
docs/hooks.md	added	+608 / -0
src/types.rs	modified	+531 / -0
docs/conversation.md	added	+408 / -0
docs/connections.md	added	+386 / -0

Top directories

Directory	Files	Total changes
docs	7	2961
src	11	1243
.	1	238
tests	1	1

Analysis Depth Readiness (commit-history, 14%)

ECC Tools uses this to decide whether recommendations should stay at commit-history/setup guidance or expand into CI, security, harness, reference-set, AI-routing, and team backlog work.

Area	Status	Evidence / Next Step
Commit history	Ready	6 commits sampled
CI/CD signals	Missing	Add workflow files or CI troubleshooting evidence so ECC Tools can reason about pipeline setup.
Security evidence	Missing	Add AgentShield, audit, SARIF, SBOM, or security review evidence so recommendations can cover security posture.
Harness configuration	Missing	Add Claude, Codex, OpenCode, Zed, dmux, MCP, plugin, or cross-harness config evidence for harness-agnostic recommendations.
Reference/eval evidence	Missing	Add fixtures, golden traces, reference sets, or evaluator benchmarks so deeper recommendations have regression evidence.
AI routing and cost controls	Missing	Add model-routing, budget, usage, or cost-control files before relying on AI-heavy automation recommendations.
Team handoff and project tracking	Missing	Add roadmap, runbook, project, Linear, or follow-up tracking docs so generated work can land in a team queue.

Reference Set Readiness (0/7, 0%)

Area	Status	Evidence / Next Step
Deep analyzer corpus	Missing	Add analyzer fixture, golden, benchmark, or reference-set files that can catch analyzer regressions.
RAG/evaluator comparison	Missing	Add retrieval or evaluator reference-set comparison fixtures with expected ranking behavior.
PR salvage/review corpus	Missing	Add stale-PR, review-thread, reopen-flow, or salvage reference cases for queue cleanup automation.
Discussion triage corpus	Missing	Add public discussion triage fixtures, golden cases, or reference sets for informational, answered, and no-response classifications.
Harness compatibility	Missing	Add cross-harness, adapter-compliance, or harness-audit evidence for Claude, Codex, OpenCode, Zed, dmux, and agent surfaces.
Security evidence	Missing	Attach security evidence such as SBOMs, SARIF, audit reports, or AgentShield evidence packs.
CI failure-mode evidence	Missing	Add captured CI failure logs, dry-run fixtures, or troubleshooting docs for common workflow failure modes.

Likely Future Issues (1)

Severity	Signal	Why it may show up
HIGH	Security-sensitive changes may ship without scanner evidence	1 security-sensitive paths changed; 0 security scanner or security-focused validation artifacts changed

• Security-sensitive changes may ship without scanner evidence: The PR touches billing, secrets, auth, webhooks, agent, or CI-sensitive surfaces without adding obvious security scanner, code scanning, or security-focused validation evidence.

Suggested Follow-up Work (1)

Type	Suggested title	Targets
PR	security: add scanner evidence for src/agent.rs	src/agent.rs

• security: add scanner evidence for src/agent.rs: Backfill explicit scanner or code-scanning evidence before another security-sensitive change lands on the touched surface.

Copy-ready bodies

security: add scanner evidence for src/agent.rs

## Summary
- Add security scanner or code-scanning evidence for the recently changed security-sensitive surface.

## Why
- Backfill explicit scanner or code-scanning evidence before another security-sensitive change lands on the touched surface.

## Touched paths
- `src/agent.rs`

## Validation
- Run or add the relevant security scanner, code scanning, secret scanning, or dependency/security review check for the touched surface.
- Attach the scanner output, SARIF/code-scanning result, or focused security regression test to the follow-up PR.
- Confirm the changed auth, billing, webhook, secret-handling, agent, or CI surface has an explicit pass/fail gate.

Detected Workflows (3)

Workflow	Description
feature-development	Standard feature implementation workflow
feature-implementation-and-wiring	Implements a new core feature or module, then wires it into the main library entry point and supporting files.
documentation-update-after-feature	Updates documentation files and README to reflect new features, components, or API changes.

Generated Instincts (21)

Domain	Count
git	3
code-style	9
testing	3
workflow	6

After merging, import with:

/instinct-import .claude/homunculus/instincts/inherited/antigravity-sdk-rust-instincts.yaml

Files

• .claude/ecc-tools.json
• .claude/skills/antigravity-sdk-rust/SKILL.md
• .agents/skills/antigravity-sdk-rust/SKILL.md
• .agents/skills/antigravity-sdk-rust/agents/openai.yaml
• .claude/identity.json
• .codex/config.toml
• .codex/AGENTS.md
• .codex/agents/explorer.toml
• .codex/agents/reviewer.toml
• .codex/agents/docs-researcher.toml
• .claude/homunculus/instincts/inherited/antigravity-sdk-rust-instincts.yaml
• .claude/commands/feature-development.md
• .claude/commands/feature-implementation-and-wiring.md
• .claude/commands/documentation-update-after-feature.md

---

_{ECC Tools | Everything Claude Code}