1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
# ---- LLM ----
model: openai:gpt-4o # Specify the LLM to use
temperature: null # Set default temperature parameter (0, 1)
top_p: null # Set default top-p parameter, with a range of (0, 1) or (0, 2) depending on the model
# ---- Behavior ----
stream: true # Controls whether to use the stream-style APIs when querying for completions from LLM clients.
save: true # Indicates whether to persist the conversation to messages.md for posterity
keybindings: emacs # Choose keybinding style (emacs, vi)
editor: null # Specifies the editor used to edit the input buffer or session. (e.g. vim, emacs, nano, hx). Defaults to $EDITOR
wrap: no # Controls text wrapping (no, auto, <max-width>)
wrap_code: false # Enables or disables the wrapping of code blocks
# ---- Prelude ----
repl_prelude: null # Set a default session or role for REPL mode to use (e.g. role:<name>, session:<name>, <session>:<role>)
cmd_prelude: null # Set a default session or role for CMD mode to use (e.g. role:<name>, session:<name>, <session>:<role>)
agent_session: null # Set a session to use when starting an agent (e.g. temp, default)
# ---- Appearance ----
highlight: true # Controls syntax highlighting
light_theme: false # Activates a light color theme when true. env: COYOTE_LIGHT_THEME
# ---- Miscellaneous ----
user_agent: null # Set User-Agent HTTP header, use `auto` for coyote/<current-version>
save_shell_history: true # Whether to save shell execution command to the history file
sync_models_url: > # URL to sync model changes from
https://raw.githubusercontent.com/Dark-Alex-17/coyote/refs/heads/main/models.yaml
# ---- REPL Prompt ----
# Custom REPL left/right prompts; see the [REPL Prompt Documentation](https://github.com/Dark-Alex-17/coyote/wiki/REPL-Prompt) for more information
left_prompt:
'{color.red}{model}){color.green}{?session {?agent {agent}>}{session}{?role /}}{!session {?agent {agent}>}}{role}{?rag @{rag}}{color.cyan}{?session )}{!session >}{color.reset} '
right_prompt:
'{color.purple}{?session {?consume_tokens {consume_tokens}({consume_percent}%)}{!consume_tokens {consume_tokens}}}{color.reset}'
# ---- Vault ----
# See the [Vault documentation](https://github.com/Dark-Alex-17/coyote/wiki/Vault) for more information on the Coyote vault.
#
# The secrets_provider tells Coyote where to read and write secrets referenced via {{SECRET_NAME}} syntax.
#
# Shorthand: set vault_password_file to enable the local provider with that password file.
vault_password_file: null # Path to a file containing the password for the Coyote vault (cannot be a secret template)
#
# Explicit: set secrets_provider to one of the supported types below. When secrets_provider is set,
# vault_password_file is ignored. Note: secrets_provider itself cannot use {{SECRET}} template syntax.
# The vault must be initialized before any secrets can be resolved.
#
# Local (same as the shorthand above):
# secrets_provider:
# type: local
# password_file: ~/.coyote_password
#
# AWS Secrets Manager (requires an authenticated AWS CLI; see `aws sso login` or `aws configure`):
# secrets_provider:
# type: aws_secrets_manager
# aws_profile: default
# aws_region: us-east-1
#
# GCP Secret Manager (requires `gcloud auth application-default login`):
# secrets_provider:
# type: gcp_secret_manager
# gcp_project_id: my-project-id
#
# Azure Key Vault (requires `az login`):
# secrets_provider:
# type: azure_key_vault
# vault_name: my-vault-name
#
# gopass (requires the `gopass` CLI to be installed and initialized):
# secrets_provider:
# type: gopass
# store: my-store # Optional; omit to use the default store
#
# 1Password (requires the `op` CLI to be installed and signed in via `op signin`):
# secrets_provider:
# type: one_password
# vault: Production # Optional; omit to use the default vault
# account: my.1password.com # Optional; omit to use the default account
# ---- Function Calling ----
# See the [Tools documentation](https://github.com/Dark-Alex-17/coyote/wiki/Tools) for more details
function_calling_support: true # Enables or disables function calling (Globally).
mapping_tools: # Alias for a tool or toolset
fs: 'fs_cat,fs_ls,fs_mkdir,fs_rm,fs_write,fs_read,fs_glob,fs_grep'
enabled_tools: null # Which tools to enable by default.
# Accepts either a YAML list or a comma-separated string. Use 'all' to enable everything.
# Example (list form):
# enabled_tools:
# - fs
# - web_search_coyote
# Example (comma-separated form):
# enabled_tools: fs,web_search_coyote
visible_tools: # Which tools are visible to be compiled (and are thus able to be defined in 'enabled_tools')
# - demo_py.py
# - demo_sh.sh
# - demo_ts.ts
- execute_command.sh
# - execute_py_code.py
# - execute_sql_code.sh
# - fetch_url_via_curl.sh
# - fetch_url_via_jina.sh
- fs_cat.sh
- fs_ls.sh
# - fs_read.sh
# - fs_glob.sh
# - fs_grep.sh
# - fs_mkdir.sh
# - fs_patch.sh
# - fs_write.sh
- get_current_time.sh
# - get_current_weather.py
# - get_current_weather.ts
- get_current_weather.sh
# - search_arxiv.sh
# - search_wikipedia.sh
# - search_wolframalpha.sh
# - send_mail.sh
# - send_twilio.sh
# - web_search_coyote.sh
# - web_search_perplexity.sh
# - web_search_tavily.sh
# ---- MCP Servers ----
# See the [MCP Servers documentation](https://github.com/Dark-Alex-17/coyote/wiki/MCP-Servers) for more details
mcp_server_support: true # Enables or disables MCP servers (globally).
mapping_mcp_servers: # Alias for an MCP server or set of servers
git: github,gitmcp
enabled_mcp_servers: null # Which MCP servers to enable by default.
# Accepts either a YAML list or a comma-separated string. Use 'all' to enable everything.
# Example (list form):
# enabled_mcp_servers:
# - github
# - slack
# Example (comma-separated form):
# enabled_mcp_servers: github,slack,ddg-search
# ---- Skills ----
# Skills are modular knowledge or capability packs the LLM can load and unload mid-conversation.
# See the [Skills documentation](https://github.com/Dark-Alex-17/coyote/wiki/Skills) for more details.
skills_enabled: true # Master switch. Set to false to hide all skill management tools from the model.
# Skills also require `function_calling_support: true` above to work at all.
visible_skills: # The universe of skills allowed to be enabled in any context. Omit (null) for "all installed".
- ai-slop-remover
- code-review
- frontend-ui-ux
- git-master
enabled_skills: null # Which skills are available by default (no role/agent/session active). null = all visible.
# Accepts either a YAML list or a comma-separated string.
# Example (list form):
# enabled_skills:
# - git-master
# - ai-slop-remover
# Example (comma-separated form):
# enabled_skills: git-master,ai-slop-remover
inject_skill_instructions: true # Inject a short hint pointing the model at `skill__list` when skills are enabled in
# this context. Only injected if `function_calling_support`, `skills_enabled`, and the
# effective enabled skill set is non-empty (default: true).
skill_instructions: null # Custom text used for the skill hint when injected. If null, uses built-in default.
# ---- Auto-Continue (Todo System) ----
# The auto-continue system provides built-in task tracking for improved reliability.
# When enabled, the model can create todo lists and the system will automatically
# prompt it to continue when incomplete tasks remain.
# See the [Todo System documentation](https://github.com/Dark-Alex-17/coyote/wiki/TODO-System) for more information
auto_continue: false # Enable automatic continuation when incomplete todos remain (default: false)
max_auto_continues: 10 # Maximum number of automatic continuations before stopping (default: 10)
inject_todo_instructions: true # Inject default todo usage instructions into the system prompt (default: true)
continuation_prompt: null # Custom prompt used when auto-continuing. If null, uses built-in default
# ---- Session ----
# See the [Session documentation](https://github.com/Dark-Alex-17/coyote/wiki/Sessions) for more information
save_session: null # Controls the persistence of the session. If true, auto save; if false, don't auto-save save; if null, ask the user what to do
compression_threshold: 4000 # Compress the session when the token count reaches or exceeds this threshold
summarization_prompt: > # The text prompt used for creating a concise summary of session message
'Summarize the discussion briefly in 200 words or less to use as a prompt for future context.'
summary_context_prompt: > # The text prompt used for including the summary of the entire session as context to the model
'This is a summary of the chat history as a recap: '
# ---- Memory ----
# See the [Memory documentation](https://github.com/Dark-Alex-17/coyote/wiki/Memory) for more information.
# Memory is opt-in by workspace presence (a `COYOTE.md` or `.coyote/memory/MEMORY.md`)
# and global presence (`<config_dir>/memory/MEMORY.md`). Set `memory: false` to disable
# even when memory files exist. The cascade is: agent > session > role > app.
# Bootstrap with `coyote --init-memory [global|workspace]` to create the marker file
# the LLM needs before it will write any memory.
memory: null # null = enabled when memory exists on disk; true = force on; false = force off
memory_cap_with_tools: null # Char cap for injected memory when function calling is available (default: 6000).
# Only MEMORY.md indexes are injected; the LLM uses memory__read to fetch drill files.
memory_cap_without_tools: null # Char cap when function calling is unavailable (default: 12000).
# Indexes plus drill file bodies are injected up to this cap.
# ---- RAG ----
# See the [RAG Docs](https://github.com/Dark-Alex-17/coyote/wiki/RAG) for more details.
rag_embedding_model: null # Specifies the embedding model used for context retrieval
rag_reranker_model: null # Specifies the reranker model used for sorting retrieved documents; Coyote uses Reciprocal Rank Fusion by default
rag_top_k: 5 # Specifies the number of documents to retrieve for answering queries
rag_chunk_size: null # Defines the size of chunks for document processing in characters
rag_chunk_overlap: null # Defines the overlap between chunks
# Defines the query structure using variables like __CONTEXT__, __SOURCES__, and __INPUT__ to tailor searches to specific needs
rag_template: |
Answer the query based on the context while respecting the rules. (user query, some textual context and rules, all inside xml tags)
<context>
__CONTEXT__
</context>
<sources>
__SOURCES__
</sources>
<rules>
- If you don't know, just say so.
- If you are not sure, ask for clarification.
- Answer in the same language as the user query.
- If the context appears unreadable or of poor quality, tell the user then answer as best as you can.
- If the answer is not in the context but you think you know the answer, explain that to the user then answer with your own knowledge.
- Answer directly and without using xml tags.
- When using information from the context, cite the relevant source from the <sources> section.
</rules>
<user_query>
__INPUT__
</user_query>
# Define document loaders to control how RAG and `.file`/`--file` load files of specific formats.
document_loaders:
# You can add custom loaders using the following syntax:
# <file-extension>: <command-to-load-the-file>
# Note: Use `$1` for input file and `$2` for output file. If `$2` is omitted, use stdout as output.
pdf: 'pdftotext $1 -' # Use pdftotext to convert a PDF file to text
# (see https://poppler.freedesktop.org for details on how to install pdftotext)
docx: 'pandoc --to plain $1' # Use pandoc to convert a .docx file to text
# (see https://pandoc.org for details on how to install pandoc)
jina: 'curl -fsSL https://r.jina.ai/$1 -H "Authorization: Bearer {{JINA_API_KEY}}' # Use Jina to translate a website into text;
# Requires a Jina API key to be added to the Coyote vault
git: > # Use yek to load a git repository into the knowledgebase (https://github.com/bodo-run/yek)
sh -c "yek $1 --json | jq 'map({ path: .filename, contents: .content })'"
# ---- Clients ----
# See the [Clients documentation](https://github.com/Dark-Alex-17/coyote/wiki/Clients) for more details
clients:
# All clients have the following configuration:
# - type: xxxx
# name: xxxx # Only use it to distinguish clients with the same client type. Optional
# models:
# - name: xxxx # Chat model
# max_input_tokens: 100000
# supports_vision: true
# supports_function_calling: true
# - name: xxxx # Embedding model
# type: embedding
# default_chunk_size: 1500
# max_batch_size: 100
# - name: xxxx # Reranker model
# type: reranker
# patch: # Patch API calls
# chat_completions: # API type; Possible values: chat_completions, embeddings, and rerank
# <regex>: # The regex to match model names, e.g. '.*' 'gpt-4o' 'gpt-4o|gpt-4-.*'
# url: '' # Patch request URL
# body: # Patch request body
# <json>
# headers: # Patch request headers
# <key>: <value>
# extra:
# proxy: socks5://127.0.0.1:1080 # Set proxy
# connect_timeout: 10 # Set timeout in seconds for connect to api
# See https://platform.openai.com/docs/quickstart
- type: openai
api_base: https://api.openai.com/v1 # Optional
api_key: '{{OPENAI_API_KEY}}' # You can either hard-code or inject secrets from the Coyote vault
organization_id: org-xxx # Optional
# For any platform compatible with OpenAI's API
- type: openai-compatible
name: ollama
api_base: http://localhost:11434/v1
api_key: '{{OLLAMA_API_KEY}}' # Optional; You can either hard-code or inject secrets from the Coyote vault
models:
- name: deepseek-r1
max_input_tokens: 131072
- name: llama3.1
max_input_tokens: 128000
supports_function_calling: true
- name: llama3.2-vision
max_input_tokens: 131072
supports_vision: true
- name: nomic-embed-text
type: embedding
default_chunk_size: 1000
max_batch_size: 50
# See https://ai.google.dev/docs
- type: gemini
api_base: https://generativelanguage.googleapis.com/v1beta
api_key: '{{GEMINI_API_KEY}}' # You can either hard-code or inject secrets from the Coyote vault
auth: null # When set to 'oauth', Coyote will use OAuth instead of an API key
# Authenticate with `coyote --authenticate` or `.authenticate` in the REPL
patch:
chat_completions:
'.*':
body:
safetySettings:
- category: HARM_CATEGORY_HARASSMENT
threshold: BLOCK_NONE
- category: HARM_CATEGORY_HATE_SPEECH
threshold: BLOCK_NONE
- category: HARM_CATEGORY_SEXUALLY_EXPLICIT
threshold: BLOCK_NONE
- category: HARM_CATEGORY_DANGEROUS_CONTENT
threshold: BLOCK_NONE
# See https://docs.anthropic.com/claude/reference/getting-started-with-the-api
- type: claude
api_base: https://api.anthropic.com/v1 # Optional
api_key: '{{ANTHROPIC_API_KEY}}' # You can either hard-code or inject secrets from the Coyote vault
auth: null # When set to 'oauth', Coyote will use OAuth instead of an API key
# Authenticate with `coyote --authenticate` or `.authenticate` in the REPL
# See https://docs.mistral.ai/
- type: openai-compatible
name: mistral
api_base: https://api.mistral.ai/v1
api_key: '{{MISTRAL_API_KEY}}' # You can either hard-code or inject secrets from the Coyote vault
# See https://docs.x.ai/docs
- type: openai-compatible
name: xai
api_base: https://api.x.ai/v1
api_key: '{{XAI_API_KEY}}' # You can either hard-code or inject secrets from the Coyote vault
# See https://docs.ai21.com/docs/overview
- type: openai-compatible
name: ai12
api_base: https://api.ai21.com/studio/v1
api_key: '{{AI21_API_KEY}}' # You can either hard-code or inject secrets from the Coyote vault
# See https://docs.cohere.com/docs/the-cohere-platform
- type: cohere
api_base: https://api.cohere.ai/v2 # Optional
api_key: '{{COHERE_API_KEY}}' # You can either hard-code or inject secrets from the Coyote vault
# See https://docs.perplexity.ai/getting-started/overview
- type: openai-compatible
name: perplexity
api_base: https://api.perplexity.ai
api_key: '{{PERPLEXITY_API_KEY}}' # You can either hard-code or inject secrets from the Coyote vault
# See https://console.groq.com/docs/quickstart
- type: openai-compatible
name: groq
api_base: https://api.groq.com/openai/v1
api_key: '{{GROQ_API_KEY}}' # You can either hard-code or inject secrets from the Coyote vault
# See https://learn.microsoft.com/en-us/azure/ai-services/openai/chatgpt-quickstart
- type: azure-openai
api_base: https://{RESOURCE}.openai.azure.com
api_key: '{{AZURE_OPENAI_API_KEY}}' # You can either hard-code or inject secrets from the Coyote vault
models:
- name: gpt-4o # Model deployment name
max_input_tokens: 128000
supports_vision: true
supports_function_calling: true
# See https://cloud.google.com/vertex-ai
- type: vertexai
project_id: xxx
location: xxx
# Specifies an application default credentials (adc) file
# Run `gcloud auth application-default login` to initialize the ADC file
# see https://cloud.google.com/docs/authentication/external/set-up-adc for more information
adc_file: <gcloud-config-dir>/application_default_credentials.json # Optional
patch:
chat_completions:
'gemini-.*':
body:
safetySettings:
- category: HARM_CATEGORY_HARASSMENT
threshold: BLOCK_ONLY_HIGH
- category: HARM_CATEGORY_HATE_SPEECH
threshold: BLOCK_ONLY_HIGH
- category: HARM_CATEGORY_SEXUALLY_EXPLICIT
threshold: BLOCK_ONLY_HIGH
- category: HARM_CATEGORY_DANGEROUS_CONTENT
threshold: BLOCK_ONLY_HIGH
# See https://docs.aws.amazon.com/bedrock/latest/userguide/
- type: bedrock
access_key_id: '{{AWS_ACCESS_KEY_ID}}' # You can either hard-code or inject secrets from the Coyote vault
secret_access_key: '{{AWS_SECRET_ACCESS_KEY}}' # You can either hard-code or inject secrets from the Coyote vault
region: xxx
session_token: xxx # Optional, only needed for temporary credentials
# See https://developers.cloudflare.com/workers-ai/
- type: openai-compatible
name: cloudflare
api_base: https://api.cloudflare.com/client/v4/accounts/{ACCOUNT_ID}/ai/v1
api_key: '{{CLOUDFLARE_API_KEY}}' # You can either hard-code or inject secrets from the Coyote vault
# See https://cloud.baidu.com/doc/WENXINWORKSHOP/index.html
- type: openai-compatible
name: ernie
api_base: https://qianfan.baidubce.com/v2
api_key: '{{BAIDU_API_KEY}}' # You can either hard-code or inject secrets from the Coyote vault
# See https://dashscope.aliyun.com/
- type: openai-compatible
name: qianwen
api_base: https://dashscope.aliyuncs.com/compatible-mode/v1
api_key: '{{ALIYUN_API_KEY}}' # You can either hard-code or inject secrets from the Coyote vault
# See https://cloud.tencent.com/product/hunyuan
- type: openai-compatible
name: hunyuan
api_base: https://api.hunyuan.cloud.tencent.com/v1
api_key: '{{TENCENT_API_KEY}}' # You can either hard-code or inject secrets from the Coyote vault
# See https://platform.moonshot.cn/docs/intro
- type: openai-compatible
name: moonshot
api_base: https://api.moonshot.cn/v1
api_key: '{{MOONSHOT_API_KEY}}' # You can either hard-code or inject secrets from the Coyote vault
# See https://platform.deepseek.com/api-docs/
- type: openai-compatible
name: deepseek
api_base: https://api.deepseek.com
api_key: '{{DEEPSEEK_API_KEY}}' # You can either hard-code or inject secrets from the Coyote vault
# See https://open.bigmodel.cn/dev/howuse/introduction
- type: openai-compatible
name: zhipuai
api_base: https://open.bigmodel.cn/api/paas/v4
api_key: '{{ZHIPUAI_API_KEY}}' # You can either hard-code or inject secrets from the Coyote vault
# See https://platform.minimaxi.com/document/Fast%20access
- type: openai-compatible
name: minimax
api_base: https://api.minimax.chat/v1
api_key: '{{MINIMAX_API_KEY}}' # You can either hard-code or inject secrets from the Coyote vault
# See https://openrouter.ai/docs#quick-start
- type: openai-compatible
name: openrouter
api_base: https://openrouter.ai/api/v1
api_key: '{{OPENROUTER_API_KEY}}' # You can either hard-code or inject secrets from the Coyote vault
# See https://github.com/marketplace/models
- type: openai-compatible
name: github
api_base: https://models.inference.ai.azure.com
api_key: '{{GITHUB_API_KEY}}' # You can either hard-code or inject secrets from the Coyote vault
# See https://deepinfra.com/docs
- type: openai-compatible
name: deepinfra
api_base: https://api.deepinfra.com/v1/openai
api_key: '{{DEEPINFRA_API_KEY}}' # You can either hard-code or inject secrets from the Coyote vault
# ----- RAG dedicated -----
# See https://jina.ai
- type: openai-compatible
name: jina
api_base: https://api.jina.ai/v1
api_key: '{{JINA_API_KEY}}' # You can either hard-code or inject secrets from the Coyote vault
# See https://docs.voyageai.com/docs/introduction
- type: openai-compatible
name: voyageai
api_base: https://api.voyageai.com/v1
api_key: '{{VOYAGEAI_API_KEY}}' # You can either hard-code or inject secrets from the Coyote vault