Skip to content

Commit e0b0e9f

Browse files
missBergclaude
andcommitted
docs: fix prettier formatting in quota-policy guide
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> Signed-off-by: Erica Hughberg <erica.sundberg.90@gmail.com>
1 parent 2c7219d commit e0b0e9f

1 file changed

Lines changed: 11 additions & 11 deletions

File tree

site/docs/capabilities/traffic/quota-policy.md

Lines changed: 11 additions & 11 deletions
Original file line numberDiff line numberDiff line change
@@ -56,8 +56,8 @@ spec:
5656
# Quota applied across all models and all clients.
5757
serviceQuota:
5858
quota:
59-
limit: 100000 # Maximum tokens allowed in the window.
60-
duration: "1h" # Sliding window duration.
59+
limit: 100000 # Maximum tokens allowed in the window.
60+
duration: "1h" # Sliding window duration.
6161
```
6262
6363
### Custom Cost Expression
@@ -92,13 +92,13 @@ perModelQuotas:
9292
quota:
9393
mode: Exclusive
9494
defaultBucket:
95-
limit: 10000 # Strict limit for expensive model.
95+
limit: 10000 # Strict limit for expensive model.
9696
duration: "1h"
9797
- modelName: gpt-3.5-turbo
9898
quota:
9999
mode: Exclusive
100100
defaultBucket:
101-
limit: 100000 # Higher limit for cost-effective model.
101+
limit: 100000 # Higher limit for cost-effective model.
102102
duration: "1h"
103103
```
104104

@@ -117,7 +117,7 @@ when a request matches one or more rules.
117117
perModelQuotas:
118118
- modelName: gpt-4
119119
quota:
120-
mode: Shared # Charge both default and matching rule buckets.
120+
mode: Shared # Charge both default and matching rule buckets.
121121
defaultBucket:
122122
limit: 10000
123123
duration: "1h"
@@ -127,7 +127,7 @@ perModelQuotas:
127127
- name: x-tenant-id
128128
type: Distinct
129129
quota:
130-
limit: 2000 # Per-tenant limit within the shared budget.
130+
limit: 2000 # Per-tenant limit within the shared budget.
131131
duration: "1h"
132132
```
133133

@@ -148,7 +148,7 @@ perModelQuotas:
148148
quota:
149149
mode: Exclusive
150150
defaultBucket:
151-
limit: 10000 # Fallback quota for unmatched tenants.
151+
limit: 10000 # Fallback quota for unmatched tenants.
152152
duration: "1h"
153153
bucketRules:
154154
- clientSelectors:
@@ -157,7 +157,7 @@ perModelQuotas:
157157
type: Exact
158158
value: premium-tenant
159159
quota:
160-
limit: 50000 # Premium tenant gets a larger budget.
160+
limit: 50000 # Premium tenant gets a larger budget.
161161
duration: "1h"
162162
```
163163

@@ -168,7 +168,7 @@ bucketRules:
168168
- clientSelectors:
169169
- headers:
170170
- name: x-tenant-id
171-
type: Distinct # One bucket per unique tenant ID.
171+
type: Distinct # One bucket per unique tenant ID.
172172
quota:
173173
limit: 5000
174174
duration: "1h"
@@ -190,7 +190,7 @@ bucketRules:
190190
quota:
191191
limit: 5000
192192
duration: "1h"
193-
shadowMode: true # Evaluate but do not enforce.
193+
shadowMode: true # Evaluate but do not enforce.
194194
```
195195

196196
:::tip
@@ -203,7 +203,7 @@ set correctly before switching to enforcement by removing `shadowMode` (or setti
203203
The `duration` field on `QuotaValue` accepts a number followed by a unit suffix:
204204

205205
| Suffix | Unit | Example |
206-
|--------|---------|---------|
206+
| ------ | ------- | ------- |
207207
| `s` | Seconds | `"30s"` |
208208
| `m` | Minutes | `"15m"` |
209209
| `h` | Hours | `"1h"` |

0 commit comments

Comments
 (0)