anuragg-saxenaa
f471f27658
fix: address CodeRabbit review — dependency versions, risk wording, style, security audit rec
...
- Fix dependency table: update outdated versions, remove unused git2
- Fix "No...No...No" repetitive sentence in Config section
- Add task string security audit to Section 7 recommendations
- Fix risk assessment: dashboard 1,273 lines (not >1500) — mark as projected
- Renumber P3 items after inserting new recommendation
2026-03-26 17:31:09 -04:00
Toast (gastown)
925d830c53
docs: add ECC2 codebase analysis research report
...
Covers architecture overview, code quality metrics, identified gaps,
test coverage analysis, security observations, dependency health,
and prioritized recommendations. Key findings: comms module has send
without receive, new-session dialog is a stub, git2 dependency is
unused, dashboard.rs at 1273 lines needs extraction.
2026-03-26 16:20:57 +00:00
Affaan Mustafa
678fb6f0d3
Merge pull request #846 from pythonstrup/feat/desktop-notify-hook
...
feat: add macOS desktop notification Stop hook
2026-03-25 03:19:13 -07:00
Affaan Mustafa
401e26a45a
Merge pull request #880 from affaan-m/dependabot/cargo/ecc2/cargo-3169503097
...
chore(deps): bump git2 from 0.19.0 to 0.20.4 in /ecc2 in the cargo group across 1 directory
2026-03-25 03:04:43 -07:00
Affaan Mustafa
eb934afbb5
Merge pull request #888 from affaan-m/feat/ecc2-risk-scoring
...
feat(ecc2): add tool risk scoring and actions
2026-03-25 03:01:12 -07:00
Affaan Mustafa
8303970258
feat(ecc2): add tool risk scoring and actions
2026-03-25 06:00:34 -04:00
Affaan Mustafa
319f9efafb
Merge pull request #887 from affaan-m/feat/ecc2-tool-logging
...
feat(ecc2): add tool call logging and history
2026-03-25 02:51:20 -07:00
Affaan Mustafa
6c2a3a2bae
feat(ecc2): add tool call logging and history
2026-03-25 05:50:31 -04:00
Affaan Mustafa
adaeab9dba
Merge pull request #886 from affaan-m/feat/ecc2-split-pane
...
feat(ecc2): add split-pane dashboard resizing
2026-03-25 02:46:08 -07:00
Affaan Mustafa
8981dd6067
feat(ecc2): add split-pane dashboard resizing
2026-03-25 05:45:43 -04:00
Affaan Mustafa
4105a2f36c
Merge pull request #885 from affaan-m/feat/ecc2-crash-resume
...
feat(ecc2): add crash resume session recovery
2026-03-25 01:37:35 -07:00
Affaan Mustafa
0166231ddb
feat(ecc2): add crash resume session recovery
2026-03-25 04:36:12 -04:00
Affaan Mustafa
cf439dd481
Merge pull request #882 from affaan-m/feat/ecc2-live-streaming
...
feat(ecc2): live output streaming per agent
2026-03-25 01:31:53 -07:00
Affaan Mustafa
9903ae528b
fix: restore antigravity install target metadata
2026-03-25 04:24:19 -04:00
Affaan Mustafa
44c2bf6f7b
feat(ecc2): implement live output streaming per agent ( #774 )
...
- PTY output capture via tokio::process with stdout/stderr piping
- Ring buffer (1000 lines) per session
- Output pane wired to show selected session with auto-scroll
- Broadcast channel for output events
2026-03-25 04:19:50 -04:00
Affaan Mustafa
e78c092499
fix(ci): restore validation and antigravity target safety
2026-03-25 04:19:50 -04:00
Affaan Mustafa
61f70de479
Merge pull request #903 from affaan-m/fix/session-manager-843-supersede-853
...
fix: fold blocker-lane session and hook hardening into one PR
2026-03-25 01:16:28 -07:00
Affaan Mustafa
776ac439f3
test: cover canonical session duplicate precedence
2026-03-25 04:01:23 -04:00
Affaan Mustafa
b19b4c6b5e
fix: finish blocker lane hook and install regressions
2026-03-25 04:00:50 -04:00
Affaan Mustafa
b5157f4ed1
test: relax sync-ecc shell parsing
2026-03-25 03:56:10 -04:00
Affaan Mustafa
2d1e384eef
test: isolate suggest-compact counter fixtures
2026-03-25 03:51:15 -04:00
Affaan Mustafa
9c5ca92e6e
fix: finish hook fallback and canonical session follow-ups
2026-03-25 03:44:03 -04:00
Affaan Mustafa
7b510c886e
fix: harden session hook guards and session ID handling
2026-03-25 03:36:36 -04:00
Affaan Mustafa
c1b47ac9db
Merge pull request #883 from affaan-m/feat/ecc2-status-panel
...
feat(ecc2): agent status panel with Table widget
2026-03-25 00:18:05 -07:00
Affaan Mustafa
3f02fa439a
feat(ecc2): implement agent status panel with Table widget ( #773 )
...
- Table widget with columns: ID, Agent, State, Branch, Tokens, Duration
- Color-coded states: green=Running, yellow=Idle, red=Failed, gray=Stopped, blue=Completed
- Summary bar with running/completed/failed counts
- Row selection highlighting
2026-03-25 03:07:51 -04:00
Jonghyeok Park
f6b10481f3
fix: add spawnSync error logging and restore 5s timeout
...
- Check spawnSync result and log warning on failure via stderr
- Restore osascript timeout to 5000ms, increase hook deadline to 10s
for sufficient headroom
2026-03-25 16:03:21 +09:00
Jonghyeok Park
d3699f9010
fix: use AppleScript-safe escaping and reduce spawnSync timeout
...
- Replace JSON.stringify with curly quote substitution for AppleScript
compatibility (AppleScript does not support \" backslash escapes)
- Reduce spawnSync timeout from 5000ms to 3000ms to leave headroom
within the 5s hook deadline
2026-03-25 16:03:21 +09:00
Jonghyeok Park
445ae5099d
feat: add macOS desktop notification Stop hook
...
Add a new Stop hook that sends a native macOS notification with the
task summary (first line of last_assistant_message) when Claude finishes
responding. Uses osascript via spawnSync for shell injection safety.
Supports run-with-flags fast require() path. Only active on standard
and strict profiles; silently skips on non-macOS platforms.
2026-03-25 16:03:21 +09:00
Affaan Mustafa
00bc7f30be
fix: resolve blocker PR validation regressions
2026-03-25 01:34:29 -04:00
Affaan Mustafa
1d0aa5ac2a
fix: fold session manager blockers into one candidate
2026-03-24 23:08:27 -04:00
Affaan Mustafa
7f7e319d9f
Merge pull request #884 from affaan-m/feat/ecc2-token-meter
...
feat(ecc2): token/cost meter widget
2026-03-24 19:53:59 -07:00
Affaan Mustafa
d7bcc92007
feat(ecc2): add token/cost meter widget ( #775 )
...
- TokenMeter widget using ratatui Gauge with color gradient (green->yellow->red)
- Budget fields (cost_budget_usd, token_budget) in Config
- Aggregate cost display in status bar
- Warning state at 80%+ budget consumption
- Tests for gradient, config fallback, and meter rendering
2026-03-24 22:52:52 -04:00
dependabot[bot]
e883385ab0
chore(deps): bump git2 in /ecc2 in the cargo group across 1 directory
...
Bumps the cargo group with 1 update in the /ecc2 directory: [git2](https://github.com/rust-lang/git2-rs ).
Updates `git2` from 0.19.0 to 0.20.4
- [Changelog](https://github.com/rust-lang/git2-rs/blob/git2-0.20.4/CHANGELOG.md )
- [Commits](https://github.com/rust-lang/git2-rs/compare/git2-0.19.0...git2-0.20.4 )
---
updated-dependencies:
- dependency-name: git2
dependency-version: 0.20.4
dependency-type: direct:production
dependency-group: cargo
...
Signed-off-by: dependabot[bot] <support@github.com >
2026-03-25 02:45:34 +00:00
Affaan Mustafa
e7d827548c
Merge pull request #881 from affaan-m/feat/ecc2-session-lifecycle
...
feat(ecc2): session create/destroy lifecycle
2026-03-24 19:44:28 -07:00
Affaan Mustafa
2787b8e92f
feat(ecc2): implement session create/destroy lifecycle ( #764 )
...
- Process spawning via tokio::process::Command
- Session state transitions with guards (Pending->Running->Completed/Failed/Stopped)
- Stop with process kill and optional worktree cleanup
- Latest alias resolver in get_status
- SQLite store migrations for state tracking
2026-03-24 03:56:23 -07:00
Affaan Mustafa
2166d80d58
Merge pull request #762 from affaan-m/feat/ecc2-tui-scaffold
...
feat: ECC 2.0 — Rust TUI agentic IDE control plane
2026-03-24 03:54:54 -07:00
Affaan Mustafa
67306c22cd
test: align antigravity manifest expectations
2026-03-24 03:50:46 -07:00
Affaan Mustafa
b2407ab3f5
fix(ecc2): sync catalog counts for scaffold CI
2026-03-24 03:43:48 -07:00
Affaan Mustafa
00dce30d3b
feat: scaffold ECC 2.0 Rust TUI — agentic IDE control plane
...
Initial scaffold for ECC 2.0, a terminal-native agentic IDE built with
Ratatui. Compiles to a 3.4MB single binary.
Core modules:
- Session manager with SQLite-backed state store
- TUI dashboard with split-pane layout (sessions, output, metrics)
- Worktree orchestration (auto-create per agent session)
- Observability with tool call risk scoring
- Inter-agent communication via SQLite mailbox
- Background daemon with heartbeat monitoring
- CLI with start/stop/sessions/status/daemon subcommands
Tech stack: Rust + Ratatui + Crossterm + Tokio + rusqlite + git2 + clap
2026-03-24 03:43:05 -07:00
Affaan Mustafa
7726c25e46
fix(ci): restore validation and antigravity target safety
2026-03-23 14:29:21 -07:00
Affaan Mustafa
df4f2df297
feat: add 6 gap-closing skills — browser QA, design system, product lens, canary watch, benchmark, safety guard
...
Closes competitive gaps with gstack:
- browser-qa: automated visual testing via browser MCP
- design-system: generate, audit, and detect AI slop in UI
- product-lens: product diagnostic, founder review, feature prioritization
- canary-watch: post-deploy monitoring with alert thresholds
- benchmark: performance baseline and regression detection
- safety-guard: prevent destructive operations in autonomous sessions
2026-03-23 04:31:17 -07:00
Himanshu Sharma
bacc585b87
Add Kiro steering files, hooks, and scripts ( #812 )
...
Co-authored-by: Sungmin Hong <hsungmin@amazon.com >
2026-03-22 21:55:47 -07:00
Himanshu Sharma
535120d6b1
Add Kiro skills (18 SKILL.md files) ( #811 )
...
Co-authored-by: Sungmin Hong <hsungmin@amazon.com >
2026-03-22 21:55:45 -07:00
Himanshu Sharma
bf4a22f082
Add Kiro agents (16 JSON + 16 MD) ( #810 )
...
Co-authored-by: Sungmin Hong <hsungmin@amazon.com >
2026-03-22 21:55:43 -07:00
Himanshu Sharma
2c23ff54d1
Add Kiro base structure, install script, and docs ( #809 )
...
Co-authored-by: Sungmin Hong <hsungmin@amazon.com >
2026-03-22 21:55:40 -07:00
Charlie Tonneslan
a411da9122
fix(commands): replace py_compile with compileall in build-fix ( #804 )
...
py_compile requires explicit filenames and exits with status 2 when
invoked without them. compileall -q . recursively validates Python
syntax across the entire project, which is what the build-fix
command actually needs.
Fixes #759
2026-03-22 21:55:38 -07:00
Affaan Mustafa
264396a616
fix: add antigravity to platform-configs targets
...
Fixes #813 . The platform-configs module was missing antigravity from its
targets array, causing all 13+ dependent modules to be skipped when
installing with --target antigravity --profile full.
2026-03-22 21:54:48 -07:00
Shimo
a2e465c74d
feat(skills): add skill-comply — automated behavioral compliance measurement ( #724 )
...
* feat(skills): add skill-comply — automated behavioral compliance measurement
Automated compliance measurement for skills, rules, and agent definitions.
Generates behavioral specs, runs scenarios at 3 strictness levels,
classifies tool calls via LLM, and produces self-contained reports.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com >
* fix(skill-comply): address bot review feedback
- AGENTS.md: fix stale skill count (115 → 117) in project structure
- run.py: replace remaining print() with logger, add zero-division guard,
create parent dirs for --output path
- runner.py: add returncode check for claude subprocess, clarify
relative_to path traversal validation
- parser.py: use is_file() instead of exists(), catch KeyError for
missing trace fields, add file check in parse_spec
- classifier.py: log warnings on malformed classification output,
guard against non-dict JSON responses
- grader.py: filter negative indices from LLM classification
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com >
---------
Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com >
2026-03-22 21:51:49 -07:00
Affaan Mustafa
0f22cb4450
docs: add ECC 2.0 reference architecture from competitor research
...
Summarizes patterns from superset-sh/superset (Electron, 7.7K stars),
standardagents/dmux (Ink TUI, 1.2K stars), and others. Defines the
three-layer architecture (daemon + runtime + TUI) and patterns to adopt.
2026-03-22 15:50:32 -07:00
Pixiu Media holdings
6f13b057af
feat(skills): add santa-method - multi-agent adversarial verification ( #760 )
...
* feat(skills): add santa-method
Multi-agent adversarial verification with convergence loop. Two independent review agents evaluate output against a shared rubric. Both must pass before shipping. Includes architecture diagram, implementation patterns (subagent, inline, batch sampling), domain-specific rubric extensions, failure mode mitigations, and integration guidance with existing ECC skills.
* Enhance SKILL.md with detailed Santa Method documentation
Expanded the SKILL.md documentation for the Santa Method, detailing architecture, phases, implementation patterns, failure modes, integration with other skills, metrics, and cost analysis.
2026-03-22 15:41:04 -07:00