packages/llm/README.md

# llm/ — LLM capability family

The LLM seam and its provider adapters. The interface package (`llm`) owns the abstract service, the content-block vocabulary, and the stream-chunk assembler; the adapters are concrete implementations that register on `ctx.llm`. All **product** packages.

| Package | Role | ctx key |
|---|---|---|
| `llm/` | Abstract LLM service + content-block vocabulary + chunk assembler | `ctx.llm` |
| `token-meter/` | Replay-aware request and surface token measurement | `ctx.tokenMeter` |
| `llm-retry/` | Bounded transient request retry policy | (listens to `agent/request-error`) |
| `llm-deepseek/` | DeepSeek API adapter (hand-rolled fetch/SSE) | (registers on `ctx.llm`) |
| `llm-pi-ai/` | Multi-provider adapter via `@earendil-works/pi-ai` | (registers on `ctx.llm`) |

The interface lives at `llm/llm/`; adapters, retry policy, and reusable token meter are flat siblings under the group. Requests route by `provider`, while `model` is passed through to the selected adapter. A new provider adapter joins here and registers one or more provider routes on `ctx.llm` without touching the interface. See [twin LLM adapters](../../.agents/notes/implemented/architecture/2026-06-13-twin-llm-adapters.md) for the contract-validation origin of the two shipping implementations and the [replay token meter Agent Note](../../.agents/notes/implemented/architecture/2026-07-15-replay-token-meter-service.md) for measurement ownership.
Document the package hierarchy and finalize the RFC 2026-06-20 23:25:33 +08:00			`# llm/ — LLM capability family`

			The LLM seam and its provider adapters. The interface package (`llm`) owns the abstract service, the content-block vocabulary, and the stream-chunk assembler; the adapters are concrete implementations that register on `ctx.llm`. All product packages.

			`\| Package \| Role \| ctx key \|`
			`\|---\|---\|---\|`
			\| `llm/` \| Abstract LLM service + content-block vocabulary + chunk assembler \| `ctx.llm` \|
refactor(token-meter): simplify singleton service (round 1) 2026-07-16 12:58:07 +08:00			\| `token-meter/` \| Replay-aware request and surface token measurement \| `ctx.tokenMeter` \|
feat: implement bounded LLM request recovery 2026-07-20 03:34:19 +08:00			\| `llm-retry/` \| Bounded transient request retry policy \| (listens to `agent/request-error`) \|
Document the package hierarchy and finalize the RFC 2026-06-20 23:25:33 +08:00			\| `llm-deepseek/` \| DeepSeek API adapter (hand-rolled fetch/SSE) \| (registers on `ctx.llm`) \|
feat(llm): route adapters by provider 2026-07-14 21:57:52 +08:00			\| `llm-pi-ai/` \| Multi-provider adapter via `@earendil-works/pi-ai` \| (registers on `ctx.llm`) \|
Document the package hierarchy and finalize the RFC 2026-06-20 23:25:33 +08:00
feat: implement bounded LLM request recovery 2026-07-20 03:34:19 +08:00			The interface lives at `llm/llm/`; adapters, retry policy, and reusable token meter are flat siblings under the group. Requests route by `provider`, while `model` is passed through to the selected adapter. A new provider adapter joins here and registers one or more provider routes on `ctx.llm` without touching the interface. See [twin LLM adapters](../../.agents/notes/implemented/architecture/2026-06-13-twin-llm-adapters.md) for the contract-validation origin of the two shipping implementations and the [replay token meter Agent Note](../../.agents/notes/implemented/architecture/2026-07-15-replay-token-meter-service.md) for measurement ownership.