docs: LLM-first quickstart + GET /v1/models and chat-completions reference (#3)

[longnhp12]

Context

Workstream 3/4 (Docs) of the Deva LLM API v1 epic (Bitplanet-L1/cross-eco-internal-docs#248). Per #3: docs led with agent identity/registration and had no LLM on-ramp; the API reference listed POST /v1/chat/completions only as a table row and didn't document GET /v1/models at all.

Part of #3 — covers the three active checkboxes (LLM-first quickstart, canonical path + /v1/models reference, SDK separation). The deferred deva.me/docs hosting checkbox stays open, so this PR intentionally does not close the issue.

What

• docs/quickstart.md — restructured to lead with "Call the Deva LLM API" (OpenRouter-style 3 steps): get a key via POST /agents/register, make a chat completion (cURL + official OpenAI Python/JS SDKs with base_url = https://api.deva.me/v1), and read costs (usage.cost, usage.deva.karma_cost/karma_balance, X-Deva-Karma-* headers, streaming final-chunk usage). The agent-platform quickstart is preserved below under its own heading.
• docs/api-reference.md — new full GET /v1/models subsection (query params, list envelope, all model fields incl. description, input/output_modalities, USD-per-token + karma pricing strings, capabilities, cache headers, detail route) and an expanded POST /v1/chat/completions subsection (canonical path per D1, request shape, streaming usage chunk, karma billing surfaces, 402 insufficient_quota). AI-resources table updated.
• SDK separation (README + quickstart): @deva-ai/sdk (Deva-me-AI/deva-agent-sdk, native LLM/agent-resources SDK — on GitHub, npm publish pending) vs @bitplanet/deva-sdk ("Login with Deva" auth SDK). Since the native SDK is unpublished, the quickstart deliberately uses the OpenAI SDKs and has no npm install @deva-ai/sdk instructions.
• README.md — "Call any LLM" added as quickstart step 2 + SDKs section; docs/pricing.md points at GET /v1/models / deva.me/models as the live per-model pricing source.

Verification

• GET /v1/models example JSON copied from the live production endpoint (34 models, post-Bitplanet-L1/content-server#1959 contract with descriptions/modalities/real capabilities).
• Chat-completion usage/402 shapes validated against content-server source (app/schemas/ai_completions.py, app/apis/ai_completions.py).
• All intra-repo anchors resolve; no stale /v1/ai/chat/completions references; no install instructions for the unpublished SDK.

🤖 Generated with Claude Code

[longnhp12]

Superseded — reopening as a regular same-repo PR (branch docs/3-llm-first, identical content) once write access is sorted; fork PRs can't run the claude-review check (no OIDC for forks).