coulomb/markitect-main
2
0
Fork 0
Code Issues 61 Pull Requests Actions Projects 12 Releases 1 Wiki Activity
639 Commits 1 Branch 12 Tags
b7e9edbb4b2fc61b87cbf8a26fc7d03d3023d573
Commit Graph

39 Commits

Author SHA1 Message Date
tegwick
f325f89dc9 feat(infospace): evaluate 3 missing WoN entities (C.1)
Some checks failed
Test Suite / unit-tests (3.11) (push) Has been cancelled
Details
Test Suite / unit-tests (3.12) (push) Has been cancelled
Details
Test Suite / integration-tests (push) Has been cancelled
Details
Test Suite / e2e-tests (push) Has been cancelled
Details
Test Suite / performance-tests (push) Has been cancelled
Details
Test Suite / code-quality (push) Has been cancelled
Details
Test Suite / security-scan (push) Has been cancelled
Details
Test Suite / test-summary (push) Has been cancelled
Details 
Fills the 988 entity / 985 evaluation gap in the Wealth of Nations
infospace. Entities advanced_state_of_society, bank_notes, and
bank_systemic_risk_management had no evaluation files; runs through
Gemini (2.5-flash / 2.5-flash-lite for the last one, which hit the
free-tier RPM limit) bring the eval count to 988.

per_entity_mean nudged from 3.955635 to 3.95668; viability still
6/6 PASS.

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
 2026-04-21 23:52:04 +02:00
tegwick
d1f57272a4 feat(example): add L2 classifications for 823/988 WoN entities (S3.4) 
Batch classification via OpenRouter (claude-sonnet-4). 165 entities
remain unclassified due to credit exhaustion; incremental skip means
a follow-up run will complete them automatically.

Type × VSM matrix (823 entities):
                  S1   S2   S3  S3*   S4   S5
  Element         86   75   58   21   43   32  (315 total, 38%)
  Process         39   42   37   17   67   24  (226 total, 28%)
  Institution      4   12   30   24    .   52  (122 total, 15%)
  Principle        3    7   15    2   43   32  (102 total, 12%)
  Relation         2   14    5    5   22   10   (58 total,  7%)
  Matrix fill: 29/30 cells (Institution/S4 empty — expected)

Metrics updated: type_entropy=2.0936, vsm_type_matrix_cells=29

Also:
- BatchEvaluator gains delay_seconds param for rate-limited providers
- classify CLI gains --rpm option (--rpm 10 for Gemini free tier)
- history.write_metrics_file now handles non-float metric values
  (type_distribution is a dict, was crashing round())
- run_entity_classification forwards delay_seconds to BatchEvaluator
- classify-links and graph commands added by user (entities --by-type,
  graph --format mermaid/dot, classify-links for Relation enrichment)

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
 2026-02-23 12:49:11 +01:00
tegwick
a9ca0adfcf feat(example): add per-entity LLM evaluations for 985 WoN entities (S3.3) 
Batch evaluation of all 988 entities via OpenRouter. 984 succeeded on
first pass; 3 failed (network errors). eval-summary --update-metrics
written with per_entity_mean=3.9556.

Viability dashboard: 6/6 PASS
  redundancy_ratio   0.0061  (max 0.10)
  coverage_ratio     0.6190  (min 0.40)
  coherence_comps    0.0000  (max 3)
  consistency_cycles 0.0000  (max 0)
  granularity_entropy 2.6748 (min 1.0)
  per_entity_mean    3.9556  (min 3.5)

Dimension breakdown (mean across 985 entities):
  definition_precision  3.62
  source_grounding      4.36
  domain_placement      4.56
  vsm_relevance         3.31
  explanatory_value     3.94

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
 2026-02-23 09:36:46 +01:00
tegwick
7f1eecbdb2 feat(infospace): add eval-summary command and improve evaluate pipeline (S3.3) 
- Fix evaluate dimensions to match template file:
  definition_precision, source_grounding, domain_placement,
  vsm_relevance, explanatory_value (was domain_relevance,
  discipline_alignment, conceptual_clarity)
- Add VSM background context to evaluation prompt so LLM can
  score vsm_relevance without macro injection
- Fix model_name bug: was sending literal "default" to API (HTTP 400)
- Refactor run_entity_evaluation to write files incrementally via
  callback rather than all at once after the batch — long runs are
  now resumable if interrupted
- Add incremental skip in CLI: entities with existing eval files
  are skipped automatically on re-run (acts as resume)
- Add eval-summary command: reads all eval files, shows per-dimension
  means, optionally writes per_entity_mean to metrics.yaml
- Fix record_check_results to merge rather than overwrite metrics.yaml
  so per_entity_mean survives subsequent check runs
- Add per_entity_mean viability threshold (min: 3.5) to infospace.yaml

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
 2026-02-23 01:26:45 +01:00
tegwick
0f54f094e4 chore(example): final metrics snapshot — all 35 chapters processed 
1021 entities extracted across all Books 1-5 of The Wealth of Nations.
Final metrics: coverage=0.4424, granularity=2.9533, redundancy=0.0059.

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
 2026-02-19 22:54:54 +01:00
tegwick
4a15a50337 infospace: process book-5-chapter-03 
Extract entities, map to VSM, and synthesize analysis.
 2026-02-19 22:54:40 +01:00
tegwick
92dfe367c7 infospace: process book-5-chapter-02 
Extract entities, map to VSM, and synthesize analysis.
 2026-02-19 22:46:32 +01:00
tegwick
23c397e46a infospace: process book-5-chapter-01 
Extract entities, map to VSM, and synthesize analysis.
 2026-02-19 22:36:06 +01:00
tegwick
e695ddfbbd infospace: process book-4-chapter-09 
Extract entities, map to VSM, and synthesize analysis.
 2026-02-19 22:32:07 +01:00
tegwick
5245dbbfc8 infospace: process book-4-chapter-08 
Extract entities, map to VSM, and synthesize analysis.
 2026-02-19 22:25:52 +01:00
tegwick
4319d2a32b infospace: process book-4-chapter-07 
Extract entities, map to VSM, and synthesize analysis.
 2026-02-19 22:14:18 +01:00
tegwick
efdaa884c8 infospace: process book-4-chapter-06 
Extract entities, map to VSM, and synthesize analysis.
 2026-02-19 22:01:44 +01:00
tegwick
2804de3d24 infospace: process book-4-chapter-05 
Extract entities, map to VSM, and synthesize analysis.
 2026-02-19 21:47:52 +01:00
tegwick
3e96ac7b8d infospace: process book-4-chapter-04 
Extract entities, map to VSM, and synthesize analysis.
 2026-02-19 21:36:17 +01:00
tegwick
a687e508f3 infospace: process book-4-chapter-03 
Extract entities, map to VSM, and synthesize analysis.
 2026-02-19 21:31:40 +01:00
tegwick
da9c5fce80 infospace: process book-4-chapter-02 
Extract entities, map to VSM, and synthesize analysis.
 2026-02-19 21:19:39 +01:00
tegwick
cd87ebfdc0 infospace: process book-4-chapter-01 
Extract entities, map to VSM, and synthesize analysis.
 2026-02-19 21:13:08 +01:00
tegwick
666f78d1ba infospace: process book-4-introduction 
Extract entities, map to VSM, and synthesize analysis.
 2026-02-19 21:02:00 +01:00
tegwick
579e02989b infospace: process book-3-chapter-04 
Extract entities, map to VSM, and synthesize analysis.
 2026-02-19 20:46:20 +01:00
tegwick
8401c69ff2 infospace: process book-3-chapter-03 
Extract entities, map to VSM, and synthesize analysis.
 2026-02-19 20:40:35 +01:00
tegwick
06e904ccf5 infospace: process book-3-chapter-02 
Extract entities, map to VSM, and synthesize analysis.
 2026-02-19 20:30:22 +01:00
tegwick
59d42b1665 infospace: process book-3-chapter-01 
Extract entities, map to VSM, and synthesize analysis.
 2026-02-19 20:18:15 +01:00
tegwick
8c11e13fef infospace: process book-2-chapter-05 
Extract entities, map to VSM, and synthesize analysis.
 2026-02-19 20:03:11 +01:00
tegwick
ac4e508aff infospace: process book-2-chapter-04 
Extract entities, map to VSM, and synthesize analysis.
 2026-02-19 19:57:59 +01:00
tegwick
8e1943afdb infospace: process book-2-chapter-03 
Extract entities, map to VSM, and synthesize analysis.
 2026-02-19 19:50:53 +01:00
tegwick
05711e541d infospace: process book-2-chapter-02 
Extract entities, map to VSM, and synthesize analysis.
 2026-02-19 19:43:19 +01:00
tegwick
8cb9ee6f6e infospace: process book-2-chapter-01 
Extract entities, map to VSM, and synthesize analysis.
 2026-02-19 19:26:57 +01:00
tegwick
db129fde6b infospace: process book-1-chapter-11 
Extract entities, map to VSM, and synthesize analysis.
 2026-02-19 19:19:20 +01:00
tegwick
6d9ec4e34b infospace: process book-1-chapter-10 
Extract entities, map to VSM, and synthesize analysis.
 2026-02-19 18:59:36 +01:00
tegwick
368571905a infospace: process book-1-chapter-09 
Extract entities, map to VSM, and synthesize analysis.
 2026-02-19 15:58:08 +01:00
tegwick
9c95912d68 infospace: process book-1-chapter-08 
Extract entities, map to VSM, and synthesize analysis.
 2026-02-19 15:47:12 +01:00
tegwick
0828581269 infospace: process book-1-chapter-07 
Extract entities, map to VSM, and synthesize analysis.
 2026-02-19 15:40:24 +01:00
tegwick
283abac378 infospace: process book-1-chapter-06 
Extract entities, map to VSM, and synthesize analysis.
 2026-02-19 15:29:59 +01:00
tegwick
098b781f92 infospace: process book-1-chapter-05 
Extract entities, map to VSM, and synthesize analysis.
 2026-02-19 15:20:35 +01:00
tegwick
7615beb139 chore(example): update metrics after chapter-03 collection check 
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
 2026-02-19 15:06:03 +01:00
tegwick
c2e06c15d7 infospace: process book-1-chapter-03 
Extract entities, map to VSM, and synthesize analysis.
 2026-02-19 15:04:57 +01:00
tegwick
715ef19d1c infospace: remove example output — will replay chapter by chapter 
This commit clears the tangled example output so each chapter
can be re-committed cleanly via S3.2.
 2026-02-19 09:22:55 +01:00
tegwick
3ac8447c10 feat(example): add baseline metrics snapshot from collection checks run
Some checks failed
Test Suite / unit-tests (3.11) (push) Has been cancelled
Details
Test Suite / unit-tests (3.12) (push) Has been cancelled
Details
Test Suite / code-quality (push) Has been cancelled
Details
Test Suite / security-scan (push) Has been cancelled
Details
Test Suite / integration-tests (push) Has been cancelled
Details
Test Suite / e2e-tests (push) Has been cancelled
Details
Test Suite / performance-tests (push) Has been cancelled
Details
Test Suite / test-summary (push) Has been cancelled
Details 
Initial metrics from S2.4 checks on 85 entities (7 of 35 chapters):
coverage_ratio=0.361, redundancy=0.0, coherence_components=0.0,
consistency_cycles=0.0, granularity_entropy=2.69

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
 2026-02-19 07:44:01 +01:00
tegwick
fecc2fd4fa feat(llm): add LLM integration module with OpenRouter and Claude Code adapters 
Implements markitect/llm/ package with concrete LLMAdapter implementations:
- OpenRouterAdapter: HTTP via urllib with retry/backoff on 429/5xx
- ClaudeCodeAdapter: subprocess-based Claude CLI with stdin piping
- Factory pattern: create_adapter("openrouter") or create_adapter("claude-code")
- API key resolution chain: constructor > env var > project-root key file
- 42 unit tests, 2 integration tests (gated on API key / CLI availability)

Also adds the infospace-with-history example with Wealth of Nations VSM
analysis pipeline, templates, schemas, source chapters, and processed
output for chapters 1-2. process_chapters.py now supports --provider
and --model flags for automatic LLM-driven processing.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
 2026-02-11 01:17:58 +01:00