Commit Graph

35 Commits

Author SHA1 Message Date
3f4fd230b9 Implemented support for loading configuration from nested subdirectories 2026-05-26 07:36:10 -05:00
2091b58066 Completed the documentation update and removed the completed roadmap 2026-05-26 07:15:36 -05:00
77134c3c78 Rationalized the default configuration file path and updated documentation
All checks were successful
ci/woodpecker/tag/release Pipeline was successful
2026-05-14 20:48:12 -05:00
f3e8c960af Added support for OpenAI-compatible structured output 2026-05-08 07:32:54 -05:00
8677f7947d Stabilize application config support 2026-05-06 16:51:36 +00:00
7be543a541 Allow CLI paths to come from config 2026-05-06 16:48:35 +00:00
0fca5611d6 Wire config loading into CLI setup 2026-05-06 16:46:33 +00:00
2a40dc1030 Add application config loading 2026-05-06 16:42:27 +00:00
03cdd2416e Updated documentation and tests to reflect the new render command 2026-05-06 15:59:22 +00:00
ea27763320 Add scriptorium render command with shared run/request parsing and text/json prepared output 2026-05-06 15:20:22 +00:00
5328f04f6d Add modular PreparedRun text/json formatters with role-grouped text output and secret-safety tests 2026-05-06 15:15:52 +00:00
44056d7b8f Add Runner.Prepare and refactor Runner.Run to reuse pre-LLM prepare flow 2026-05-06 15:12:58 +00:00
48c06218dc Add PreparedRun model and render formatters (text/json) with tests 2026-05-06 14:27:38 +00:00
bf058a046e Documentation cleanup and bugfixes 2026-05-05 20:01:45 -05:00
ddb4254124 Centralize remaining runtime constants and add precedence/default fallback coverage 2026-05-05 11:01:44 -05:00
d82bcd0581 Migrate repo fixtures to separated prompts/ and execution profiles/ with file-backed prompt templates 2026-05-05 10:58:22 -05:00
6142bd88ee Refactor http adapter to enforce strict run request JSON, expand prompt/profile error mapping, and harden api_key handling 2026-05-05 10:54:35 -05:00
e66763f2a7 Split prompt/profile dirs, adopt --prompt/--profile flags, and add override/selection integration tests 2026-05-05 10:49:33 -05:00
8818796b8b Refactor: separate prompt/profile run resolution with explicit precedence, centralized defaults, and api_key_env validation 2026-05-05 10:44:56 -05:00
a2459931b6 Expand PromptDefinition renderer coverage and tighten missing/nil input handling 2026-05-05 10:39:10 -05:00
f6692dd4bb Refactor: enforce canonical messages/output YAML, normalize content_file, and expand fixture-based validation tests 2026-05-05 10:35:39 -05:00
7fffdaede3 Refactor: load execution profiles from YAML and split prompt definitions into promptdef repository 2026-05-05 10:18:28 -05:00
a633c67538 Refactor: split prompt definition from execution settings and migrate run contracts to prompt_* + execution_target 2026-05-05 10:09:31 -05:00
ca4d939fdc Relaxed CLI requirements when defaults are specified in the profile or application defaults 2026-05-05 08:41:07 -05:00
281202e313 Architectural improvements in the http adapter 2026-05-05 08:25:32 -05:00
c5ce270090 Added a configurable timeout knob 2026-05-04 22:38:20 -05:00
ea05945457 Add bounded structured-output repair 2026-05-04 21:35:31 -05:00
328703df36 Add example profiles, schemas, and an end-to-end local fixture 2026-05-04 21:23:48 -05:00
eac6b69217 Add a minimal HTTP API 2026-05-04 21:19:29 -05:00
526ee463f2 Add a minimal CLI 2026-05-04 21:08:40 -05:00
fd78f2c883 Implement OpenAI-compatible LLM client 2026-05-04 21:02:27 -05:00
eb7ac84c51 Implement basic, JSON, and JSON Schema validation 2026-05-04 20:57:21 -05:00
ff7e5d3190 Implement the core Run use case with a fake LLM path 2026-05-04 20:57:08 -05:00
fa070a296d Bugfixes and improved alignment with architecture blueprint 2026-05-04 20:36:12 -05:00
c07320f9d0 Implement the initial framework skeleton 2026-05-04 20:14:31 -05:00