Skip to content

Commit 920c0a3

Browse files
tbitcsoz-agent
tbitcs
and
oz-agent
committed
chore: specsmith upgrade --full to 0.11.3; switch to develop branch
Regenerated AGENTS.md with Session Bootstrap section, updated CI configs, and governance files to specsmith 0.11.3. Establishing develop as the default working branch for all governed projects. Co-Authored-By: Oz <oz-agent@warp.dev>
1 parent 99c5070 commit 920c0a3

36 files changed

Lines changed: 1565 additions & 32 deletions

‎.editorconfig‎

Lines changed: 25 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,25 @@
1+
# EditorConfig — https://editorconfig.org
2+
root = true
3+
4+
[*]
5+
charset = utf-8
6+
end_of_line = lf
7+
insert_final_newline = true
8+
trim_trailing_whitespace = true
9+
indent_style = space
10+
indent_size = 4
11+
12+
[*.{yml,yaml}]
13+
indent_size = 2
14+
15+
[*.md]
16+
trim_trailing_whitespace = false
17+
18+
[Makefile]
19+
indent_style = tab
20+
21+
[*.{cmd,bat}]
22+
end_of_line = crlf
23+
24+
[*.{ps1,psm1}]
25+
end_of_line = crlf

‎.gitattributes‎

Lines changed: 24 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,24 @@
1+
# Auto-detect text files and normalize line endings
2+
* text=auto
3+
4+
# Common text files
5+
*.md text eol=lf
6+
*.txt text eol=lf
7+
*.yml text eol=lf
8+
*.yaml text eol=lf
9+
*.json text eol=lf
10+
*.toml text eol=lf
11+
*.cfg text eol=lf
12+
*.ini text eol=lf
13+
*.xml text eol=lf
14+
.gitignore text eol=lf
15+
.gitattributes text eol=lf
16+
.editorconfig text eol=lf
17+
18+
# Shell scripts
19+
*.sh text eol=lf
20+
*.bash text eol=lf
21+
*.cmd text eol=crlf
22+
*.bat text eol=crlf
23+
*.ps1 text eol=crlf
24+
*.psm1 text eol=crlf

‎.github/ISSUE_TEMPLATE/bug_report.md‎

Lines changed: 34 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,34 @@
1+
---
2+
name: Bug Report
3+
about: Report a bug in specsmith-test
4+
title: "bug: "
5+
labels: bug
6+
---
7+
8+
## Description
9+
10+
<!-- Clear description of the bug -->
11+
12+
## Steps to Reproduce
13+
14+
1.
15+
2.
16+
3.
17+
18+
## Expected Behavior
19+
20+
<!-- What should happen -->
21+
22+
## Actual Behavior
23+
24+
<!-- What actually happens -->
25+
26+
## Environment
27+
28+
- OS:
29+
- Python version:
30+
- specsmith-test version:
31+
32+
## Additional Context
33+
34+
<!-- Logs, screenshots, or other relevant information -->

‎.github/ISSUE_TEMPLATE/feature_request.md‎

Lines changed: 26 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,26 @@
1+
---
2+
name: Feature Request
3+
about: Suggest an enhancement for specsmith-test
4+
title: "feat: "
5+
labels: enhancement
6+
---
7+
8+
## Summary
9+
10+
<!-- Brief description of the feature -->
11+
12+
## Motivation
13+
14+
<!-- Why is this needed? What problem does it solve? -->
15+
16+
## Proposed Solution
17+
18+
<!-- How should this work? -->
19+
20+
## Alternatives Considered
21+
22+
<!-- Other approaches you've thought about -->
23+
24+
## Additional Context
25+
26+
<!-- Mockups, references, or related issues -->

‎.github/PULL_REQUEST_TEMPLATE.md‎

Lines changed: 21 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,21 @@
1+
## Description
2+
3+
<!-- Brief description of what this PR does -->
4+
5+
Closes #
6+
7+
## Changes
8+
9+
-
10+
11+
## Governance Checklist
12+
13+
- [ ] Read `AGENTS.md` and followed the workflow
14+
- [ ] Changes proposed in `LEDGER.md` before implementation
15+
- [ ] `docs/REQUIREMENTS.md` updated (if new/changed requirements)
16+
- [ ] `docs/TESTS.md` updated (if new/changed tests)
17+
- [ ] Lint passes: `ruff check`
18+
- [ ] Type check passes: `mypy`
19+
- [ ] Tests pass: `pytest`
20+
- [ ] Security scan passes: `pip-audit`
21+
- [ ] `LEDGER.md` entry recorded

‎.specsmith/agent-tools.json‎

Lines changed: 20 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,20 @@
1+
{
2+
"schema_version": 1,
3+
"primary_governance_command": "specsmith_run",
4+
"slash_prefix": "/specsmith",
5+
"verb_shortcuts": [
6+
"audit",
7+
"commit",
8+
"doctor",
9+
"load",
10+
"pull",
11+
"push",
12+
"run",
13+
"save",
14+
"status",
15+
"sync",
16+
"validate",
17+
"watch"
18+
],
19+
"description": "Use specsmith_run() or /specsmith <args> in the Nexus REPL for all governance operations (save, load, push, pull, audit, status, \u2026). REQ-SM-001: agents must not invoke the specsmith binary directly via run_shell when specsmith_run is available."
20+
}

‎.specsmith/compliance/README.md‎

Lines changed: 26 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,26 @@
1+
# .specsmith/compliance/
2+
3+
Project-specific compliance overlays for AI regulation.
4+
5+
## Structure
6+
7+
Each file overrides the built-in regulation status for this project:
8+
eu-ai-act.yaml — EU AI Act (Regulation 2024/1689)
9+
nist-rmf.yaml — NIST AI RMF 1.0 + AI 600-1
10+
omb-m-24-10.yaml — OMB M-24-10
11+
colorado-sb24-205.yaml — Colorado AI Act (effective Feb 2026)
12+
texas-hb1709.yaml — Texas AI Transparency Act
13+
etc.
14+
15+
## Usage
16+
17+
# Check compliance for all regulations
18+
specsmith compliance check
19+
20+
# Generate compliance report
21+
specsmith compliance report --format html --output compliance-report.html
22+
23+
# Store results to ESDB audit trail
24+
specsmith compliance audit
25+
26+
See: https://specsmith.readthedocs.io/en/stable/compliance/

‎.specsmith/compliance/eu-ai-act.yaml‎

Lines changed: 17 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,17 @@
1+
# EU AI Act (Regulation 2024/1689) — project overlay
2+
#
3+
# This file allows overriding compliance status for this specific project.
4+
# Leave fields empty to use specsmith's auto-detection.
5+
#
6+
# regulation_id: eu-ai-act
7+
# project notes:
8+
9+
risk_tier: minimal_risk # prohibited | high_risk | gpai | minimal_risk
10+
is_gpai: false # true if this is a General Purpose AI model
11+
gpai_systemic_risk: false # true if > 10^25 FLOP training compute
12+
13+
# Override specific article status (auto-detected if absent):
14+
# article_overrides:
15+
# Art.9:
16+
# status: compliant
17+
# notes: "Risk management system via specsmith AEE pipeline"

‎.specsmith/credit-budget.json‎

Lines changed: 12 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,12 @@
1+
{
2+
"monthly_cap_usd": 0.0,
3+
"alert_threshold_pct": 80,
4+
"alert_watermarks_usd": [
5+
5.0,
6+
10.0,
7+
25.0,
8+
50.0
9+
],
10+
"enabled": true,
11+
"enforcement_mode": "soft"
12+
}

‎.specsmith/governance/context-budget.yaml‎

Lines changed: 120 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,120 @@
1+
# Generated by specsmith migrate m001
2+
# Edit this file; original MD kept as view.
3+
4+
content: '# Context Window Management and Credit Optimization
5+
6+
7+
## Core principle
8+
9+
Treat unnecessary credit consumption as a process defect.
10+
11+
12+
## Session load protocol (lazy loading)
13+
14+
On session start, load only:
15+
16+
- `AGENTS.md` (in full)
17+
18+
- `docs/governance/RULES.md`
19+
20+
- `docs/governance/CONTEXT-BUDGET.md`
21+
22+
- Last ~300 lines of `LEDGER.md`
23+
24+
25+
Load on demand:
26+
27+
- `docs/governance/SESSION-PROTOCOL.md` — when preparing proposals or ledger entries
28+
29+
- `docs/governance/LIFECYCLE.md` — when checking phase readiness or advancing
30+
31+
- `docs/governance/ROLES.md` — when role boundaries are relevant
32+
33+
- `docs/governance/VERIFICATION.md` — when testing or accepting work
34+
35+
- `docs/governance/DRIFT-METRICS.md` — when running `audit`
36+
37+
- `docs/REQUIREMENTS.md` — first ~200 lines, expand by section
38+
39+
- `docs/TESTS.md` — first ~200 lines, expand by section
40+
41+
- `docs/ARCHITECTURE.md` — first ~40 lines, expand by section
42+
43+
44+
## During a session
45+
46+
- NEVER re-read a file already in context unless modified since last read
47+
48+
- Use line ranges for files > ~200 lines
49+
50+
- Prefer grep/semantic search over reading entire files
51+
52+
- Batch file reads into a single call
53+
54+
- Summarize rather than echo file contents
55+
56+
- Do not repeat proposals after creating them
57+
58+
59+
## Conversation summarization recovery
60+
61+
If the conversation is summarized or truncated, re-read AGENTS.md in full before
62+
any further actions.
63+
64+
65+
## Response economy
66+
67+
- No echoing file contents back
68+
69+
- No repeating proposal content after creation
70+
71+
- No "status theater" messages that add no information
72+
73+
- Provide only evidence needed to support conclusions
74+
75+
76+
## Efficient verification order
77+
78+
1. Static validation / lint / syntax (cheapest)
79+
80+
2. Type checks / unit tests
81+
82+
3. Integration tests
83+
84+
4. Expensive builds / hardware flows (most expensive)
85+
86+
87+
If a cheaper check fails, fix that before running more expensive checks.
88+
89+
90+
## Cost tiers
91+
92+
- **low** — docs-only, single-file edits, small scaffolds
93+
94+
- **medium** — multi-file implementation, routine refactors, standard test runs
95+
96+
- **high** — architecture changes, large builds, broad audits
97+
98+
99+
## Credit tracking
100+
101+
102+
This project tracks AI credit spend automatically. At the end of each session:
103+
104+
105+
1. Record usage: `specsmith credits record --model <model> --provider <provider>
106+
--tokens-in <N> --tokens-out <N> --task "<description>"`
107+
108+
2. Check budget: `specsmith credits summary`
109+
110+
3. If budget alerts appear, review with: `specsmith credits analyze`
111+
112+
113+
Budget configuration: `specsmith credits budget --cap <USD> --alert-pct 80`
114+
115+
Credit data stored in `.specsmith/credits.json` (gitignored).
116+
117+
'
118+
generated_by: specsmith migrate (m001)
119+
kind: context-budget
120+
source_md: docs/governance/CONTEXT-BUDGET.md

0 commit comments

Comments
 (0)