Bring docs current with 1.37.1#149
Merged
Merged
Conversation
…rovider set) Audited the full docs surface against the shipped 1.37.1 code and fixed stale or inaccurate claims: - Document the `primr render` verb (RUN_MODES mode matrix, ARTIFACTS, AGENTS output handling, AGENT_INTEGRATION zero-cost flow, docs index). - Reframe AI news / vendor research as grounded-lite by default (~$0.30, Gemini + Google Search) with Deep Research opt-in via --deep-research; update README, ROADMAP, CONFIG, RUN_MODES. - Note --ai-strategy-only defaults to the ~$1 lite engine; correct the stale INTERNALS claim that it lacks an estimate/approval gate. - Add AWS Bedrock and Azure Foundry to provider lists and key docs (SECURITY, ARCHITECTURE, CONFIG, API_KEYS, provider-expansion). - Correct the Bedrock/Foundry example READMEs: those providers are wired for `keys test`/`doctor`, not model->provider routing; point custom endpoints at the OpenAI-compatible gateway seam. - Fix output path (flat output/), AI Strategy default framing, company-brief citation format ([cite: N]) and DOCX-is-free-via-render, and cost drift (~$0.89 full) in the Copilot guides; refresh SECURITY supported versions.
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Audited the entire docs surface (README, ROADMAP, AGENTS, docs/*, skills, examples/deploy) against the shipped 1.37.1 code and corrected stale or inaccurate claims. No code changes — docs only.
mkdocs build --strictis clean; skill + release-integrity tests pass (2456 passed).What changed
New
primr renderverb documented where a user or agent would look for it: RUN_MODES mode matrix + Output Locations, ARTIFACTS, AGENTS output handling, AGENT_INTEGRATION zero-cost flow, docs index.AI news / vendor research reframed to reality — defaults to a grounded-lite engine (
$0.30, one Gemini + Google Search grounded call, live/cited); Deep Research ($2.50/task) is the--deep-researchopt-in; freshness-aware. Updated README, ROADMAP §13, CONFIG, RUN_MODES.--ai-strategy-onlynow documented as defaulting to the ~$1 lite engine with--deep-researchopt-in; corrected the false INTERNALS claim that it lacks an estimate/approval gate (it is estimate- and budget-gated).Provider set — added AWS Bedrock and Azure AI Foundry to SECURITY, ARCHITECTURE, CONFIG (keys table), API_KEYS (
keys set), and provider-expansion.Corrected a genuinely misleading instruction in the Bedrock/Foundry example READMEs: those providers are wired for
primr keys test/doctoronly, not into model→provider routing —AI_REASONING_MODEL=<bedrock/foundry model>would silently fall through to xAI. Point custom-endpoint inference at the OpenAI-compatible gateway seam (LOCAL_LLM_BASE_URL).Smaller accuracy fixes — flat
output/path (nooutput/<company>/subfolder), AI Strategy is a default not opt-in, company-brief[cite: N]citation format + DOCX-is-free-via-render,~$0.89full-run cost in the Copilot guides, SECURITY supported-versions table → 1.37.x.How it was verified
Findings came from a parallel audit of the docs against source (
cli_parser.pyepilog,cli_render.py,config/env.py,config/models.py,ai/providers/*,vendor_research.py), then applied as surgical edits. Gates run locally:mkdocs build --strictclean, 2456 skill/doc/release tests pass.