docs(platform-credits): address audit findings

- Reframe Platform Credits intro to lead with the rule (every cloud agent
  run, plus Business/Enterprise local agent runs with customer-supplied
  inference) instead of the negative 'when Warp isn't paying' framing.
- Align cross-file framing in credits.mdx and plans-pricing-refunds.mdx so
  all three pages describe Platform Credits in the same terms.
- Replace 'Workflow autofill' with linked 'AI Autofill'.
- Replace 'Local Oz runs' with 'local agent runs' (Oz run is cloud-only).
- Deduplicate the second BYOK parenthetical and normalize BYOLLM wording.
- Clarify that self-hosted cloud workers count as cloud agents for
  Platform Credits purposes.

Co-Authored-By: Oz <oz-agent@warp.dev>

Author: hongyi-chen

src/content/docs/support-and-community/plans-and-billing/credits.mdx

@@ -16,7 +16,7 @@ Warp meters credits across three types of infrastructure — inference, compute,
 
 * **AI credits** - Charged for inference infrastructure Warp pays for. Consumed by Agent conversations and other AI features that route through Warp-managed model providers.
 * **Cloud Agent Credits** - Charged for compute infrastructure when cloud agents run on Warp-hosted compute. See [Cloud Agent Credits](/support-and-community/plans-and-billing/credits/#cloud-agent-credits).
-* **Platform Credits** - Charged for platform infrastructure (run lifecycle, integrations, dashboard, APIs, and observability) when Warp isn't paying for inference or compute. Applies to every cloud agent run, plus local runs on Business and Enterprise plans that use customer-supplied inference (BYOK or BYOLLM via Amazon Bedrock or Google Vertex). See [Platform Credits](/support-and-community/plans-and-billing/platform-credits/).
+* **Platform Credits** - Charged for Warp's platform infrastructure (run lifecycle, integrations, dashboard, APIs, and observability). Applies to every cloud agent run, plus local agent runs on Business and Enterprise plans that use customer-supplied inference (BYOK or BYOLLM via Amazon Bedrock or Google Vertex). See [Platform Credits](/support-and-community/plans-and-billing/platform-credits/).
 
 All three buckets draw from the same plan credit pool and [Add-on Credits](/support-and-community/plans-and-billing/add-on-credits/), so you can manage them as a single balance in **Settings** > **Billing and usage**.
 
@@ -141,14 +141,14 @@ The following scenarios do **not** use Cloud Agent Credits:
 
 ### Platform Credits
 
-Platform Credits charge for Warp's platform infrastructure — run lifecycle, scheduling, integrations, dashboard, APIs, and observability — when Warp isn't paying for the inference or compute.
+Platform Credits charge for Warp's platform infrastructure — run lifecycle, scheduling, integrations, dashboard, APIs, and observability — for every cloud agent run, plus local agent runs on Business and Enterprise plans that use customer-supplied inference.
 
 #### Eligible for Platform Credits
 
 The following scenarios use Platform Credits:
 
 * **Cloud agents on any plan** — Every cloud agent run, regardless of harness or inference source
-* **Local agents on Business or Enterprise with customer-supplied inference** — Local Oz runs on a Business or Enterprise plan that use [Bring Your Own API Key (BYOK)](/support-and-community/plans-and-billing/bring-your-own-api-key/) or BYOLLM via Amazon Bedrock or Google Vertex
+* **Local agents on Business or Enterprise with customer-supplied inference** — Local agent runs on a Business or Enterprise plan that use [Bring Your Own API Key (BYOK)](/support-and-community/plans-and-billing/bring-your-own-api-key/) or BYOLLM via Amazon Bedrock or Google Vertex
 
 #### Not eligible for Platform Credits
 

src/content/docs/support-and-community/plans-and-billing/plans-pricing-refunds.mdx

@@ -20,7 +20,7 @@ Visit [warp.dev/pricing](https://warp.dev/pricing) to see the latest plans and w
 
 * [Credits](/support-and-community/plans-and-billing/credits/) — learn how credits are used and calculated across AI features.
 * [Add-on Credits](/support-and-community/plans-and-billing/add-on-credits/) — purchase additional credits or enable automatic reloads at discounted rates.
-* [Platform Credits](/support-and-community/plans-and-billing/platform-credits/) — the third credit bucket, which covers Oz orchestration for every cloud agent run and for local Business and Enterprise runs that use customer-supplied inference.
+* [Platform Credits](/support-and-community/plans-and-billing/platform-credits/) — the third credit bucket, which covers Warp's platform infrastructure for every cloud agent run and for local Business and Enterprise runs that use customer-supplied inference.
 * [Bring Your Own API Key](/support-and-community/plans-and-billing/bring-your-own-api-key/) — connect your own model provider API keys for custom usage and billing.
 * [Overages (Legacy)](/support-and-community/plans-and-billing/overages-legacy/) — information for users on legacy plans with overages enabled.
 * [Pricing FAQs](/support-and-community/plans-and-billing/pricing-faqs/) — answers to common questions about plans, billing, and usage. Don’t have Warp yet? [Download Warp](https://warp.dev/download) and get started for free today.

src/content/docs/support-and-community/plans-and-billing/platform-credits.mdx

@@ -1,23 +1,24 @@
 ---
 title: Platform Credits
 description: >-
-  Platform Credits charge for Warp's platform infrastructure when Warp isn't
-  paying for inference or compute. Learn when they apply and where they appear.
+  Platform Credits charge for Warp's platform infrastructure on every cloud
+  agent run, plus local agent runs on Business and Enterprise plans that use
+  customer-supplied inference. Learn when they apply and where they appear.
 ---
 
 Warp meters credits across three types of infrastructure: **inference** (the model call), **compute** (the sandbox an agent runs in), and **platform** (everything that runs around the agent — run lifecycle, integrations, dashboard, APIs, and observability). Each type maps to one credit bucket: [AI credits](/support-and-community/plans-and-billing/credits/), [Cloud Agent Credits](/support-and-community/plans-and-billing/credits/#cloud-agent-credits), and Platform Credits.
 
-Platform Credits charge for Warp's platform infrastructure when Warp isn't paying for the inference or compute. Customers who bring their own model provider (BYOLLM via Amazon Bedrock or Google Vertex), connect their own LLM API keys, or run cloud agents on their own compute still rely on Warp's platform to coordinate, observe, and integrate their agents — and Platform Credits charge for that.
+Platform Credits charge for Warp's platform infrastructure on every cloud agent run, plus local agent runs on Business and Enterprise plans that use customer-supplied inference. Even when you bring your own model provider, connect your own LLM API keys, or run cloud agents on your own compute, Warp's platform still coordinates, observes, and integrates your agents — and Platform Credits charge for that.
 
-Platform Credits apply to every cloud agent run, and to local agent runs on Business and Enterprise plans that use customer-supplied inference — [Bring Your Own API Key (BYOK)](/support-and-community/plans-and-billing/bring-your-own-api-key/) or BYOLLM via Amazon Bedrock or Google Vertex. They don't apply to local runs on Free, Build, or Max plans, or to local Business and Enterprise runs where Warp pays for inference through AI credits.
+Customer-supplied inference covers [Bring Your Own API Key (BYOK)](/support-and-community/plans-and-billing/bring-your-own-api-key/) and BYOLLM via Amazon Bedrock or Google Vertex. Platform Credits don't apply to local runs on Free, Build, or Max plans, or to local Business and Enterprise runs where Warp pays for inference through AI credits.
 
 ## The three credit buckets
 
 Each credit bucket charges for a different layer of the infrastructure Warp provides:
 
-* **AI credits** - Charged for inference infrastructure Warp pays for. Consumed by Agent conversations, [Generate](/agent-platform/local-agents/generate/), Workflow autofill, and other AI features that route through Warp-managed model providers. See [credits](/support-and-community/plans-and-billing/credits/) for how AI credits are calculated.
+* **AI credits** - Charged for inference infrastructure Warp pays for. Consumed by Agent conversations, [Generate](/agent-platform/local-agents/generate/), [AI Autofill](/knowledge-and-collaboration/warp-drive/workflows/#ai-autofill), and other AI features that route through Warp-managed model providers. See [credits](/support-and-community/plans-and-billing/credits/) for how AI credits are calculated.
 * **Cloud Agent Credits** - Charged for compute infrastructure when cloud agents run on Warp-hosted compute. Consumed by Slack and Linear integrations, `oz agent run-cloud`, the Oz API, and Cloud Mode in the Warp app. See [Cloud Agent Credits](/support-and-community/plans-and-billing/credits/#cloud-agent-credits).
-* **Platform Credits** - Charged for platform infrastructure (run lifecycle, integrations, dashboard, APIs, and observability) when an agent is actively working but Warp isn't paying for inference or compute. Applies to every cloud agent run, plus local runs on Business and Enterprise plans that use customer-supplied inference.
+* **Platform Credits** - Charged for Warp's platform infrastructure (run lifecycle, integrations, dashboard, APIs, and observability). Applies to every cloud agent run, plus local agent runs on Business and Enterprise plans that use customer-supplied inference.
 
 The three buckets are independent and a single run can consume from more than one. A Warp-managed cloud agent run, for example, consumes AI credits for the model call, Cloud Agent Credits for the hosted compute, and Platform Credits for the platform infrastructure that runs the agent.
 
@@ -33,8 +34,8 @@ Whether Platform Credits are charged depends on where the agent runs and who's p
 
 ### Charged
 
-* **Cloud agents on any plan** - Every cloud agent run charges Platform Credits, regardless of harness (Warp Agent, Claude Code, Codex, Gemini) or inference source (Warp-managed, BYOK, or BYOLLM). Warp's platform infrastructure is always running the agent.
-* **Local agents on Business or Enterprise with customer-supplied inference** - Local Oz runs on a Business or Enterprise plan that use [Bring Your Own API Key (BYOK)](/support-and-community/plans-and-billing/bring-your-own-api-key/) or BYOLLM (Amazon Bedrock, Google Vertex). Warp isn't paying for the model call, but Warp's platform infrastructure is still running the local agent.
+* **Cloud agents on any plan** - Every cloud agent run charges Platform Credits, regardless of harness (Warp Agent, Claude Code, Codex, Gemini), inference source (Warp-managed, BYOK, or BYOLLM), or compute source (Warp-hosted or self-hosted workers). Warp's platform infrastructure is always running the agent.
+* **Local agents on Business or Enterprise with customer-supplied inference** - Local agent runs on a Business or Enterprise plan that use [BYOK](/support-and-community/plans-and-billing/bring-your-own-api-key/) or BYOLLM via Amazon Bedrock or Google Vertex. Warp isn't paying for the model call, but Warp's platform infrastructure is still running the local agent.
 
 ### Not charged