Matthew Meszaros 6501cb599c feat: fix the "Edit with AI" rewrite in the campaign body and the unibox composer for issue #432 by running /generation/edit on a new generation.BuildEditRules system prompt through AIProvider.Complete instead of the cold-outreach writer prompt that redefined the model's role, capped it at 80 words and imposed a five-part email skeleton on every instruction, raising the completion cap so a full-body rewrite is no longer truncated at 1024 tokens and counting the request limits in runes rather than bytes, carrying merge variables, AI blocks, conditionals, form links and link destinations through the round trip in web/src/components/app/ai/richTextPassage.ts instead of deleting every atom node via doc.textBetween, replacing the passage with paste semantics so a phrase rewritten inside a sentence stops splitting its paragraph into three, saying "No change" when the model hands the passage back untouched, and clamping the floating AI card to the surface it is editing so it no longer draws outside the step drawer over the flow canvas

2026-09-11 20:04:32 -07:00

..

anthropic_provider.go

feat: sweep stale OPENAI_API_KEY/AI_LOCAL_MODEL mentions out of comments, the provider-not-configured and warmup-admin error strings, env.example, and the deployment guide now that AI_* is the only config surface

2026-07-16 06:39:07 +02:00

anthropic.go

feat: sweep stale OPENAI_API_KEY/AI_LOCAL_MODEL mentions out of comments, the provider-not-configured and warmup-admin error strings, env.example, and the deployment guide now that AI_* is the only config surface

2026-07-16 06:39:07 +02:00

batch_test.go

feat: count only readable messages in the warmup batch failure suffix, so a blank provider error entry no longer renders "(+1 more)" and sends the operator hunting for a second reason that does not exist, and condense the new BatchState, batchFailureReason and failed-batch comments to the one-line form the repo convention asks for

2026-08-28 20:03:07 -07:00

batch.go

feat: count only readable messages in the warmup batch failure suffix, so a blank provider error entry no longer renders "(+1 more)" and sends the operator hunting for a second reason that does not exist, and condense the new BatchState, batchFailureReason and failed-batch comments to the one-line form the repo convention asks for

2026-08-28 20:03:07 -07:00

conversation.go

feat: automate warmup conversation generation, coherent replies, adaptive rotation, and admin observability

2026-07-22 12:11:19 +02:00

generation.go

feat: reflect the structured-output schema inline and anonymously so OpenAI stops rejecting every warmup generation request with "$ref cannot have keywords {'$id'}", which made AI warmup content impossible to generate on any install

2026-08-25 20:46:27 +00:00

model.go

feat: automate warmup conversation generation, coherent replies, adaptive rotation, and admin observability

2026-07-22 12:11:19 +02:00

openai_provider.go

feat: stream the dashboard agent's text token by token: the OpenAI-compatible provider now runs chat completions with stream=true whenever a listener is attached, forwarding content deltas as a new EventTextDelta (SSE text_delta) while stitching tool-call fragments by index, capturing usage via stream_options with a sticky compatibility fallback, tolerating backends that ignore streaming, and always closing each block with the authoritative full-text event (now also emitted for commentary alongside tool calls)

2026-07-19 10:41:45 +02:00

provider.go

feat: rework automation AI steps to mirror campaign step types with one agentic AI step plus an AI switch, per-case switch handles on the canvas, a Stop node, and a step-type add menu

2026-07-22 10:58:35 +02:00

resolve.go

feat: drop the legacy OPENAI_*/ANTHROPIC_API_KEY/AI_LOCAL_MODEL env fallbacks (no prod deployments exist): AI_PROVIDER/AI_API_KEY/AI_MODEL/AI_BASE_URL/AI_FREE are the only AI vars, empty provider means openai, the anthropic preset and writing client key off AI_API_KEY, and the warmup Batch generator runs only when the selected provider is OpenAI

2026-07-16 06:39:06 +02:00

search.go

feat: provider-agnostic LLM agent-loop layer (OpenAI-first, Anthropic self-host connector) with RunAgent tool-use loop, approval/resume contract, pluggable web search, and extracted voice-rules builder - generation.Provider.RunAgent executes Go tool handlers over a resumable transcript with a read-auto/write-approve gate, openAIProvider drives it via a lean HTTP client retargetable with OPENAI_BASE_URL for any OpenAI-compatible endpoint and also serves the writing assistant, anthropicProvider mirrors it with tool_use/tool_result multi-turn plus hosted web_search, NewProvider prefers OPENAI_API_KEY, SearchClient supports Serper/SearXNG with a clean not-configured error, and BuildVoiceRules extracts the humanizer prompt for reuse; refreshed stale model ids to sonnet-4-6 and haiku-4-5

2026-07-13 17:52:09 +02:00

thread_test.go

Fix truncated, unformatted and mis-encoded email content in the unibox (#137)

2026-08-21 18:45:09 +02:00

thread.go

Fix truncated, unformatted and mis-encoded email content in the unibox (#137)

2026-08-21 18:45:09 +02:00

voice.go

feat: fix the "Edit with AI" rewrite in the campaign body and the unibox composer for issue #432 by running /generation/edit on a new generation.BuildEditRules system prompt through AIProvider.Complete instead of the cold-outreach writer prompt that redefined the model's role, capped it at 80 words and imposed a five-part email skeleton on every instruction, raising the completion cap so a full-body rewrite is no longer truncated at 1024 tokens and counting the request limits in runes rather than bytes, carrying merge variables, AI blocks, conditionals, form links and link destinations through the round trip in web/src/components/app/ai/richTextPassage.ts instead of deleting every atom node via doc.textBetween, replacing the passage with paste semantics so a phrase rewritten inside a sentence stops splitting its paragraph into three, saying "No change" when the model hands the passage back untouched, and clamping the floating AI card to the surface it is editing so it no longer draws outside the step drawer over the flow canvas

2026-09-11 20:04:32 -07:00

writing.go

feat: sweep stale OPENAI_API_KEY/AI_LOCAL_MODEL mentions out of comments, the provider-not-configured and warmup-admin error strings, env.example, and the deployment guide now that AI_* is the only config surface

2026-07-16 06:39:07 +02:00