15 commits

Author	SHA1	Message	Date
tegwick	e1ca67e509	Resolve the OpenRouter key from OpenBao before the environment ... auto tries platform/suppliers/openrouter/llm-connect, then the live activity-core workload lane, then OPENROUTER_API_KEY. A denied token falls back to the environment. LLM_CONNECT_KEY_SOURCE selects env or openbao alone. Assistant: grok Assistant-Session: 01a11ab6-1534-7d63-8606-662b92a80ed6	2026-10-08 19:35:00 +02:00
tegwick	c0b7e54ed1	Render a hall portrait only for the entry about to be published ... render-hall requires --entry and no longer walks the corpus. image plan without --entry stays an inventory. LLM-WP-0010 records that existing seats are historic and that the cooldown publisher comes later. Assistant: grok Assistant-Session: 01a11ab6-1534-7d63-8606-662b92a80ed6	2026-10-08 16:57:26 +02:00
tegwick	e1bab67bd1	Apply the image decision tree to missing hall portraits ... A hall visual that stays on the general branch uses the Efficient model from the 2026-10-08 intelligence-radar tree. render-hall writes only portraits whose files are still absent. Assistant: grok Assistant-Session: 01a11ab6-1534-7d63-8606-662b92a80ed6	2026-10-08 16:44:43 +02:00
tegwick	7073d2543c	Add image-model selection guide from the intelligence-radar digest ... Maps the 2026-10-08 image-generation decision tree onto OpenRouter model IDs with per-image quotes and caps for llm_connect.images, and documents the anchor-win-rate scoring that makes Elo leaderboards usable for Topnotch. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com> Assistant: claude-code Assistant-Model: opus Assistant-Process: 197486@bnt-lap001 Assistant-Session: 8e588643-5640-4ad7-9309-4ed3e12b2423	2026-10-08 16:33:32 +02:00
tegwick	e3ab268d6e	Add square text-to-image rendering with a spend gate ... Hall of Helix needs a credential-safe render that returns a provenance receipt and refuses a batch before the quote exceeds its cap. OpenRouter is the only client; the model and the live budget stay with the founder. Assistant: grok Assistant-Session: 01a11ab6-1534-7d63-8606-662b92a80ed6	2026-10-08 11:01:49 +02:00
tegwick	7cd633986e	Close local release-quality gaps and reconcile workplan status ... Assistant: codex Assistant-Model: gpt-6-astra Assistant-Session: 01a0e332-3365-77c0-8491-084e9ea33ac1	2026-09-27 17:36:27 +02:00
tegwick	718e6730e4	Provide a private Unix listener for owner-metered Messages ... Assistant: codex Assistant-Model: gpt-6-astra Assistant-Session: 01a07ff8-19d0-7820-b4d0-1353833cb7fc	2026-09-09 22:20:55 +02:00
tegwick	526e073e28	Add owner-metered Messages transport with conservative admission ... Assistant: codex Assistant-Model: gpt-5.6-luna Assistant-Session: 01a07ff8-19d0-7820-b4d0-1353833cb7fc	2026-09-09 21:25:52 +02:00
tegwick	ed7c632155	Implement LLM-WP-0008: provider-scoped account balance CLI ... Add pluggable balance registry, OpenRouter credits/key limit client, and llm-connect balance with one-shot --provider that does not change library defaults.	2026-08-03 23:49:01 +02:00
tegwick	09aa1f3604	Implement LLM-WP-0007: Kimi K3 default and EUR spend reporting ... Add moonshotai/kimi-k3 as OpenRouter basemodel default after live smoke, USD→EUR cost conversion, append-only usage ledger, and CLI run/cost/spend week commands with token and euro reporting.	2026-08-03 22:00:34 +02:00
tegwick	14ba47c129	Add activity-core LLM endpoint support	2026-06-07 19:24:45 +02:00
tegwick	c11c6afa3f	Implement-LLM-WP-0005-cost-model-estimators	2026-05-19 05:02:20 +02:00
tegwick	c4ad4bb9f2	Add adaptive cost-quality routing primitives	2026-05-17 21:32:27 +02:00
Bernd Worsch	d51d6303e2	feat: WP-0003 — RoutingPolicy (FR-2) and HTTP serve mode (FR-1) ... FR-2 RoutingPolicy: - RoutingPolicy + RoutingRule dataclasses in llm_connect/routing.py - resolve(task_type, estimated_cost_per_1k=None) with cost-cap fallback - Exported from llm_connect.__init__; contract doc at contracts/functional/routing-policy.md - 11 tests covering rule match, cost-cap, fallback, unknown type, no-match FR-1 HTTP serve mode: - LLMServer in llm_connect/server.py (stdlib http.server, zero extra deps) - POST /execute + GET /health; CLI via python -m llm_connect.server - [server] optional-dep group added to pyproject.toml - Contract doc at contracts/functional/server.md - 9 tests: health, round-trip, 400/404/500 errors, config forwarding - Added "mock" provider to factory for CLI default All 101 tests pass. Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>	2026-04-01 22:34:00 +00:00
Bernd Worsch	d71f4114d1	feat: WP-0001 foundation + WP-0002 core extensions ... WP-0001 — Foundation & GAAF Baseline - SCOPE.md, ARCHITECTURE-LAYERS.md, contracts/ tree - .claude/rules/ stubs filled (architecture, stack, boundary) - 57 tests (pytest), pyproject.toml with ruff+mypy, CI workflow WP-0002 — Core Extensions (FR-4 + FR-3) - FR-4: BudgetTracker (thread-safe) + LLMBudgetExceededError + optional RunConfig.budget_tracker + enforcement in all adapters - FR-3: async_execute_prompt on LLMAdapter ABC (asyncio.to_thread fallback) + native asyncio.create_subprocess_exec in ClaudeCodeAdapter 81 tests passing. Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>	2026-04-01 22:24:14 +00:00