coulomb/llm-connect
4
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

chore: hub IDs for LLM-WP-0007 and WORK-RECORDS index

Browse source 
Write back state_hub task/workstream IDs from fix-consistency and add
the generated WORK-RECORDS.md index.
This commit is contained in:
tegwick 2026-08-03 21:53:02 +02:00
parent 79c7969705
commit f3121c3f1f
2 changed files with 113 additions and 0 deletions
Download patch file Download diff file Expand all files Collapse all files

9
workplans/LLM-WP-0007-kimi-k3-default-and-spend-reporting.md
View file

@ -15,6 +15,7 @@ depends_on_workplans:
- LLM-WP-0005
related_workplans:
- LLM-WP-0006
state_hub_workstream_id: "a93d226a-f5c4-4656-b584-a783840b10fe"
---
# LLM-WP-0007 — Kimi K3 default via OpenRouter + EUR spend reporting
@ -174,6 +175,7 @@ print clear `unknown` when not.
id: LLM-WP-0007-T01
status: todo
priority: high
state_hub_task_id: "af12101d-bcd5-4d6f-9507-c81de79a0685"
```
**Validate Kimi K3 via OpenRouter.** Confirm `moonshotai/kimi-k3` is callable
@ -186,6 +188,7 @@ or README providers table. Gate for T02.
id: LLM-WP-0007-T02
status: todo
priority: high
state_hub_task_id: "ca836db8-9041-42e5-87ce-7c3ace1298a3"
```
**Promote Kimi K3 to OpenRouter basemodel default** after T01 smoke passes.
@ -198,6 +201,7 @@ leave default unchanged and record the blocker in the task notes.
id: LLM-WP-0007-T03
status: todo
priority: high
state_hub_task_id: "f379d09b-ea03-44f5-82fa-171da4681cef"
```
**USD→EUR cost conversion.** Add `fx` helper + extend `CostEstimate` with EUR
@ -209,6 +213,7 @@ model still yields `cost_usd=None` / `cost_eur=None`.
id: LLM-WP-0007-T04
status: todo
priority: high
state_hub_task_id: "cadf1b0c-fdea-4446-8d01-964b2706540d"
```
**Usage ledger.** Implement `UsageEvent` + append-only JSONL `UsageLedger`
@ -221,6 +226,7 @@ effort flock), and range aggregation.
id: LLM-WP-0007-T05
status: todo
priority: high
state_hub_task_id: "8956fd74-cad4-435c-ae66-6b19088691e4"
```
**CLI `run` with per-call cost footer.** Extend `llm-connect` with a `run`
@ -232,6 +238,7 @@ estimation from response usage + rate table + FX. Tests with mock adapter.
id: LLM-WP-0007-T06
status: todo
priority: high
state_hub_task_id: "ac5e4322-cd00-4034-b162-a0e1c481180e"
```
**CLI weekly spend views.** `llm-connect spend week` and `spend week --last`
@ -243,6 +250,7 @@ fixed timezone.
id: LLM-WP-0007-T07
status: todo
priority: medium
state_hub_task_id: "a05761b9-d91c-4b6d-9e90-296aadadaf16"
```
**Optional library/server recording.** When `LLM_CONNECT_USAGE_LEDGER` is set,
@ -254,6 +262,7 @@ opt-in so library consumers are not surprised by home-dir writes.
id: LLM-WP-0007-T08
status: todo
priority: medium
state_hub_task_id: "94ce6aee-2835-46c0-a3e6-3d0345e7715f"
```
**Docs + acceptance polish.** README: new default model, CLI examples for