bots-garden/mini-me · #20

added .tickets/issues/0058-add-more-tools-to-the-sbx-template-redis-cli-to.yaml +13 -0 Viewed

new file mode 100644
@@ -0,0 +1,13 @@
	1	+# Managed by IssueSpec. Hand edits are welcome; keep the schema valid.
	2	+id: 58
	3	+title: Add more tools to the sbx template (redis, cli to parse source code ...)
	4	+state: open
	5	+author:
	6	+ name: k33g
	7	+ email: ph.charriere@gmail.com
	8	+createdAt: 2026-10-01T04:39:22.452Z
	9	+updatedAt: 2026-10-01T04:39:22.452Z
	10	+labels: []
	11	+body: ""
	12	+tasks: []
	13	+comments: []

++# Managed by IssueSpec. Hand edits are welcome; keep the schema valid.
++id: 58
++title: Add more tools to the sbx template (redis, cli to parse source code ...)
++state: open
++author:
++  name: k33g
++  email: ph.charriere@gmail.com
++createdAt: 2026-10-01T04:39:22.452Z
++updatedAt: 2026-10-01T04:39:22.452Z
++labels: []
++body: ""
++tasks: []
++comments: []

added .tickets/issues/0059-how-to-start-in-yolo-mode.yaml +106 -0 Viewed

new file mode 100644
@@ -0,0 +1,106 @@
	1	+# Managed by IssueSpec. Hand edits are welcome; keep the schema valid.
	2	+id: 59
	3	+title: How to start in yolo mode?
	4	+state: open
	5	+author:
	6	+ name: k33g
	7	+ email: ph.charriere@gmail.com
	8	+createdAt: 2026-10-01T04:39:53.878Z
	9	+updatedAt: 2026-10-01T06:30:00.000Z
	10	+labels:
	11	+ - kind::feature
	12	+ - priority::low
	13	+related:
	14	+ - 57
	15	+body: \|
	16	+ Question: is there a way to start mm in "yolo" mode (tools run without any
	17	+ confirmation)?
	18	+
	19	+ Answer as of 2026-10-01 (main 1d966fe): there is no --yolo flag and no
	20	+ dedicated key, but it depends on the front end:
	21	+ - Line mode (`mm agent.yaml`) and one-shot (`mm -p "…"`): never asks.
	22	+ bash / write_file / edit_file run at once (no sink, no gate).
	23	+ - Window mode (`mm -tui`): asks only with `permissions: ask`. Default is
	24	+ `auto` = yolo. With `auto`, MCP tools marked `ask` do not ask either
	25	+ (internal/tui/sink.go Allow returns true).
	26	+ - Editor (`mm -acp`): ALWAYS asks through the editor's dialog
	27	+ (internal/acp/sink.go Allow -> RequestPermission). No setting skips it;
	28	+ only "allow always", remembered per tool for the session.
	29	+ - MCP tools: `mcp.permissions` defaults to `ask` (also per server); set
	30	+ `auto` to skip.
	31	+ - `permissions` has no AGENT_* environment override: YAML only.
	32	+
	33	+ Yolo in the window mode today:
	34	+ permissions: auto
	35	+ mcp:
	36	+ permissions: auto
	37	+
	38	+ Proposed feature (later): a real switch, `--yolo`, that forces `auto`
	39	+ everywhere, ACP included (mm would approve without opening the editor's
	40	+ dialog). Side benefit: no pending permission dialog, so ticket 57's
	41	+ "watchdog kills the turn while a permission is pending" cannot happen.
	42	+
	43	+ Open questions:
	44	+ - Name: `--yolo` only, or also `AGENT_PERMISSIONS=auto` / a config key
	45	+ (`permissions: yolo`?) so the sandbox kits can set it via env.
	46	+ - ACP: should yolo be allowed there at all? The editor's dialog is the
	47	+ main safety an editor adds; maybe require the flag explicitly (never
	48	+ from config).
	49	+ - Should yolo override a per-server MCP `permissions: ask`, or respect it?
	50	+ - Make it visible: banner/status line "yolo" so nobody runs it by mistake.
	51	+tasks:
	52	+ - id: 1
	53	+ title: "Decide the open questions below (flag name, ACP scope, MCP scope, banner)"
	54	+ state: open
	55	+ priority: none
	56	+ author:
	57	+ name: k33g
	58	+ email: ph.charriere@gmail.com
	59	+ createdAt: 2026-10-01T06:30:00.000Z
	60	+ updatedAt: 2026-10-01T06:30:00.000Z
	61	+ - id: 2
	62	+ title: "Failing tests first: with yolo on, window mode (permissions: ask) and ACP Allow() return true without asking; MCP ask-tools run"
	63	+ state: open
	64	+ priority: none
	65	+ author:
	66	+ name: k33g
	67	+ email: ph.charriere@gmail.com
	68	+ createdAt: 2026-10-01T06:30:00.000Z
	69	+ updatedAt: 2026-10-01T06:30:00.000Z
	70	+ - id: 3
	71	+ title: "Flag --yolo (main.go, alongside -p/-tui/-acp) + optional env/config override; forces Permissions=auto and mcp.permissions=auto, per-server MCP permissions included"
	72	+ state: open
	73	+ priority: none
	74	+ author:
	75	+ name: k33g
	76	+ email: ph.charriere@gmail.com
	77	+ createdAt: 2026-10-01T06:30:00.000Z
	78	+ updatedAt: 2026-10-01T06:30:00.000Z
	79	+ - id: 4
	80	+ title: "ACP sink Allow(): short-circuit when yolo is on (no RequestPermission sent to the editor)"
	81	+ state: open
	82	+ priority: none
	83	+ author:
	84	+ name: k33g
	85	+ email: ph.charriere@gmail.com
	86	+ createdAt: 2026-10-01T06:30:00.000Z
	87	+ updatedAt: 2026-10-01T06:30:00.000Z
	88	+ - id: 5
	89	+ title: "Banner/status line shows that yolo is on (terminal, window, ACP agent info)"
	90	+ state: open
	91	+ priority: none
	92	+ author:
	93	+ name: k33g
	94	+ email: ph.charriere@gmail.com
	95	+ createdAt: 2026-10-01T06:30:00.000Z
	96	+ updatedAt: 2026-10-01T06:30:00.000Z
	97	+ - id: 6
	98	+ title: "Docs EN+FR: reference/cli.md, reference/configuration.md, how-to (window mode, editor); answer the question in the how-to"
	99	+ state: open
	100	+ priority: none
	101	+ author:
	102	+ name: k33g
	103	+ email: ph.charriere@gmail.com
	104	+ createdAt: 2026-10-01T06:30:00.000Z
	105	+ updatedAt: 2026-10-01T06:30:00.000Z
	106	+comments: []

++# Managed by IssueSpec. Hand edits are welcome; keep the schema valid.
++id: 59
++title: How to start in yolo mode?
++state: open
++author:
++  name: k33g
++  email: ph.charriere@gmail.com
++createdAt: 2026-10-01T04:39:53.878Z
++updatedAt: 2026-10-01T06:30:00.000Z
++labels:
++  - kind::feature
++  - priority::low
++related:
++  - 57
++body: |
++  Question: is there a way to start mm in "yolo" mode (tools run without any
++  confirmation)?
++
++  Answer as of 2026-10-01 (main 1d966fe): there is no --yolo flag and no
++  dedicated key, but it depends on the front end:
++  - Line mode (`mm agent.yaml`) and one-shot (`mm -p "…"`): never asks.
++    bash / write_file / edit_file run at once (no sink, no gate).
++  - Window mode (`mm -tui`): asks only with `permissions: ask`. Default is
++    `auto` = yolo. With `auto`, MCP tools marked `ask` do not ask either
++    (internal/tui/sink.go Allow returns true).
++  - Editor (`mm -acp`): ALWAYS asks through the editor's dialog
++    (internal/acp/sink.go Allow -> RequestPermission). No setting skips it;
++    only "allow always", remembered per tool for the session.
++  - MCP tools: `mcp.permissions` defaults to `ask` (also per server); set
++    `auto` to skip.
++  - `permissions` has no AGENT_* environment override: YAML only.
++
++  Yolo in the window mode today:
++    permissions: auto
++    mcp:
++      permissions: auto
++
++  Proposed feature (later): a real switch, `--yolo`, that forces `auto`
++  everywhere, ACP included (mm would approve without opening the editor's
++  dialog). Side benefit: no pending permission dialog, so ticket 57's
++  "watchdog kills the turn while a permission is pending" cannot happen.
++
++  Open questions:
++  - Name: `--yolo` only, or also `AGENT_PERMISSIONS=auto` / a config key
++    (`permissions: yolo`?) so the sandbox kits can set it via env.
++  - ACP: should yolo be allowed there at all? The editor's dialog is the
++    main safety an editor adds; maybe require the flag explicitly (never
++    from config).
++  - Should yolo override a per-server MCP `permissions: ask`, or respect it?
++  - Make it visible: banner/status line "yolo" so nobody runs it by mistake.
++tasks:
++  - id: 1
++    title: "Decide the open questions below (flag name, ACP scope, MCP scope, banner)"
++    state: open
++    priority: none
++    author:
++      name: k33g
++      email: ph.charriere@gmail.com
++    createdAt: 2026-10-01T06:30:00.000Z
++    updatedAt: 2026-10-01T06:30:00.000Z
++  - id: 2
++    title: "Failing tests first: with yolo on, window mode (permissions: ask) and ACP Allow() return true without asking; MCP ask-tools run"
++    state: open
++    priority: none
++    author:
++      name: k33g
++      email: ph.charriere@gmail.com
++    createdAt: 2026-10-01T06:30:00.000Z
++    updatedAt: 2026-10-01T06:30:00.000Z
++  - id: 3
++    title: "Flag --yolo (main.go, alongside -p/-tui/-acp) + optional env/config override; forces Permissions=auto and mcp.permissions=auto, per-server MCP permissions included"
++    state: open
++    priority: none
++    author:
++      name: k33g
++      email: ph.charriere@gmail.com
++    createdAt: 2026-10-01T06:30:00.000Z
++    updatedAt: 2026-10-01T06:30:00.000Z
++  - id: 4
++    title: "ACP sink Allow(): short-circuit when yolo is on (no RequestPermission sent to the editor)"
++    state: open
++    priority: none
++    author:
++      name: k33g
++      email: ph.charriere@gmail.com
++    createdAt: 2026-10-01T06:30:00.000Z
++    updatedAt: 2026-10-01T06:30:00.000Z
++  - id: 5
++    title: "Banner/status line shows that yolo is on (terminal, window, ACP agent info)"
++    state: open
++    priority: none
++    author:
++      name: k33g
++      email: ph.charriere@gmail.com
++    createdAt: 2026-10-01T06:30:00.000Z
++    updatedAt: 2026-10-01T06:30:00.000Z
++  - id: 6
++    title: "Docs EN+FR: reference/cli.md, reference/configuration.md, how-to (window mode, editor); answer the question in the how-to"
++    state: open
++    priority: none
++    author:
++      name: k33g
++      email: ph.charriere@gmail.com
++    createdAt: 2026-10-01T06:30:00.000Z
++    updatedAt: 2026-10-01T06:30:00.000Z
++comments: []

added .tickets/issues/0060-add-llmman-provider.yaml +121 -0 Viewed

new file mode 100644
@@ -0,0 +1,121 @@
	1	+# Managed by IssueSpec. Hand edits are welcome; keep the schema valid.
	2	+id: 60
	3	+title: Add llmman provider
	4	+state: open
	5	+author:
	6	+ name: k33g
	7	+ email: ph.charriere@gmail.com
	8	+createdAt: 2026-10-01T04:48:02.829Z
	9	+updatedAt: 2026-10-01T07:00:00.000Z
	10	+labels:
	11	+ - kind::feature
	12	+ - priority::medium
	13	+related:
	14	+ - 61
	15	+ - 62
	16	+body: \|
	17	+ Add llmman (https://github.com/llmmanorg/llmman, `llmman serve`) as a
	18	+ provider, OpenAI API only (/v1/chat/completions), and a demo config in
	19	+ demo-llmman/ using hf.co/unsloth/Qwen3.5-4B-GGUF:Q4_K_M.
	20	+tasks:
	21	+ - id: 1
	22	+ title: "Registry entry llmman (URL, fallback, key, progress, thinking off)"
	23	+ state: closed
	24	+ priority: none
	25	+ author:
	26	+ name: k33g
	27	+ email: ph.charriere@gmail.com
	28	+ createdAt: 2026-10-01T07:00:00.000Z
	29	+ updatedAt: 2026-10-01T07:00:00.000Z
	30	+ - id: 2
	31	+ title: "Probe: /v1/models warning + served window from /api/ps (not the stub /props)"
	32	+ state: closed
	33	+ priority: none
	34	+ author:
	35	+ name: k33g
	36	+ email: ph.charriere@gmail.com
	37	+ createdAt: 2026-10-01T07:00:00.000Z
	38	+ updatedAt: 2026-10-01T07:00:00.000Z
	39	+ - id: 3
	40	+ title: "Tests: Resolve rows + TestProbeLlmman"
	41	+ state: closed
	42	+ priority: none
	43	+ author:
	44	+ name: k33g
	45	+ email: ph.charriere@gmail.com
	46	+ createdAt: 2026-10-01T07:00:00.000Z
	47	+ updatedAt: 2026-10-01T07:00:00.000Z
	48	+ - id: 4
	49	+ title: "demo-llmman/agent.llmman.yaml with hf.co/unsloth/Qwen3.5-4B-GGUF:Q4_K_M"
	50	+ state: closed
	51	+ priority: none
	52	+ author:
	53	+ name: k33g
	54	+ email: ph.charriere@gmail.com
	55	+ createdAt: 2026-10-01T07:00:00.000Z
	56	+ updatedAt: 2026-10-01T07:00:00.000Z
	57	+ - id: 5
	58	+ title: "Docs EN+FR (how-to, reference, explanation, indexes)"
	59	+ state: closed
	60	+ priority: none
	61	+ author:
	62	+ name: k33g
	63	+ email: ph.charriere@gmail.com
	64	+ createdAt: 2026-10-01T07:00:00.000Z
	65	+ updatedAt: 2026-10-01T07:00:00.000Z
	66	+ - id: 6
	67	+ title: "Live check against llmman serve (tool call, ctx, compaction)"
	68	+ state: closed
	69	+ priority: none
	70	+ author:
	71	+ name: k33g
	72	+ email: ph.charriere@gmail.com
	73	+ createdAt: 2026-10-01T07:00:00.000Z
	74	+ updatedAt: 2026-10-01T07:00:00.000Z
	75	+ - id: 7
	76	+ title: "Quality gate (qlty) where available"
	77	+ state: open
	78	+ priority: none
	79	+ author:
	80	+ name: k33g
	81	+ email: ph.charriere@gmail.com
	82	+ createdAt: 2026-10-01T07:00:00.000Z
	83	+ updatedAt: 2026-10-01T07:00:00.000Z
	84	+ - id: 8
	85	+ title: "Review, commit, merge"
	86	+ state: open
	87	+ priority: none
	88	+ author:
	89	+ name: k33g
	90	+ email: ph.charriere@gmail.com
	91	+ createdAt: 2026-10-01T07:00:00.000Z
	92	+ updatedAt: 2026-10-01T07:00:00.000Z
	93	+comments:
	94	+ - id: 1
	95	+ author:
	96	+ name: claude
	97	+ email: noreply@anthropic.com
	98	+ createdAt: 2026-10-01T07:00:00.000Z
	99	+ body: \|
	100	+ Implemented on branch `feature/llmman-provider` (uncommitted, 2026-10-01).
	101	+
	102	+ - Registry entry `llmman` (internal/engine/openai_compat.go): base
	103	+ `http://127.0.0.1:17434/v1`, fallback `http://host.docker.internal:17434/v1`,
	104	+ key `LLMMAN_API_KEY` (optional), `progress: true`,
	105	+ `thinkingOff: thinkingOffTemplate`.
	106	+ - Probe `probeLlmman` (internal/engine/llmman.go): /v1/models (a missing
	107	+ model is a warning: llmman pulls it on the first request) then the served
	108	+ window from /api/ps (shared reading in apips.go, also used by Ollama #62).
	109	+ - Measured on llmman 0.1.498: `/props` is a stub (n_ctx 4096, empty
	110	+ chat_template, loaded or not) -> NOT used. prompt_progress,
	111	+ reasoning_content, usage and `chat_template_kwargs.enable_thinking:false`
	112	+ pass through to its llama-server. /api/show's trained context rejected
	113	+ (LLMMAN_CONTEXT_LENGTH can serve less).
	114	+ - Verified live: one-shot prompts (bash tool call, read_skill, reasoning
	115	+ shown), REPL banner `ctx: 262144 (/api/ps)`, a real compaction
	116	+ (`compressed 8 messages -> 1 summary + 2 kept`).
	117	+ - Tests: Resolve rows, TestProbeLlmman; `go test ./...` green.
	118	+ - Docs EN+FR: how-to/run-with-llmman.md, reference (configuration, cli,
	119	+ mcp-configuration EN), explanation/providers.md, README indexes.
	120	+ - Not done: automatic download with progress -> ticket 61. Quality gate (qlty)
	121	+ not run: absent from the sandbox.

++# Managed by IssueSpec. Hand edits are welcome; keep the schema valid.
++id: 60
++title: Add llmman provider
++state: open
++author:
++  name: k33g
++  email: ph.charriere@gmail.com
++createdAt: 2026-10-01T04:48:02.829Z
++updatedAt: 2026-10-01T07:00:00.000Z
++labels:
++  - kind::feature
++  - priority::medium
++related:
++  - 61
++  - 62
++body: |
++  Add llmman (https://github.com/llmmanorg/llmman, `llmman serve`) as a
++  provider, OpenAI API only (/v1/chat/completions), and a demo config in
++  demo-llmman/ using hf.co/unsloth/Qwen3.5-4B-GGUF:Q4_K_M.
++tasks:
++  - id: 1
++    title: "Registry entry llmman (URL, fallback, key, progress, thinking off)"
++    state: closed
++    priority: none
++    author:
++      name: k33g
++      email: ph.charriere@gmail.com
++    createdAt: 2026-10-01T07:00:00.000Z
++    updatedAt: 2026-10-01T07:00:00.000Z
++  - id: 2
++    title: "Probe: /v1/models warning + served window from /api/ps (not the stub /props)"
++    state: closed
++    priority: none
++    author:
++      name: k33g
++      email: ph.charriere@gmail.com
++    createdAt: 2026-10-01T07:00:00.000Z
++    updatedAt: 2026-10-01T07:00:00.000Z
++  - id: 3
++    title: "Tests: Resolve rows + TestProbeLlmman"
++    state: closed
++    priority: none
++    author:
++      name: k33g
++      email: ph.charriere@gmail.com
++    createdAt: 2026-10-01T07:00:00.000Z
++    updatedAt: 2026-10-01T07:00:00.000Z
++  - id: 4
++    title: "demo-llmman/agent.llmman.yaml with hf.co/unsloth/Qwen3.5-4B-GGUF:Q4_K_M"
++    state: closed
++    priority: none
++    author:
++      name: k33g
++      email: ph.charriere@gmail.com
++    createdAt: 2026-10-01T07:00:00.000Z
++    updatedAt: 2026-10-01T07:00:00.000Z
++  - id: 5
++    title: "Docs EN+FR (how-to, reference, explanation, indexes)"
++    state: closed
++    priority: none
++    author:
++      name: k33g
++      email: ph.charriere@gmail.com
++    createdAt: 2026-10-01T07:00:00.000Z
++    updatedAt: 2026-10-01T07:00:00.000Z
++  - id: 6
++    title: "Live check against llmman serve (tool call, ctx, compaction)"
++    state: closed
++    priority: none
++    author:
++      name: k33g
++      email: ph.charriere@gmail.com
++    createdAt: 2026-10-01T07:00:00.000Z
++    updatedAt: 2026-10-01T07:00:00.000Z
++  - id: 7
++    title: "Quality gate (qlty) where available"
++    state: open
++    priority: none
++    author:
++      name: k33g
++      email: ph.charriere@gmail.com
++    createdAt: 2026-10-01T07:00:00.000Z
++    updatedAt: 2026-10-01T07:00:00.000Z
++  - id: 8
++    title: "Review, commit, merge"
++    state: open
++    priority: none
++    author:
++      name: k33g
++      email: ph.charriere@gmail.com
++    createdAt: 2026-10-01T07:00:00.000Z
++    updatedAt: 2026-10-01T07:00:00.000Z
++comments:
++  - id: 1
++    author:
++      name: claude
++      email: noreply@anthropic.com
++    createdAt: 2026-10-01T07:00:00.000Z
++    body: |
++      **Implemented** on branch `feature/llmman-provider` (uncommitted, 2026-10-01).
++
++      - Registry entry `llmman` (internal/engine/openai_compat.go): base
++        `http://127.0.0.1:17434/v1`, fallback `http://host.docker.internal:17434/v1`,
++        key `LLMMAN_API_KEY` (optional), `progress: true`,
++        `thinkingOff: thinkingOffTemplate`.
++      - Probe `probeLlmman` (internal/engine/llmman.go): /v1/models (a missing
++        model is a warning: llmman pulls it on the first request) then the served
++        window from /api/ps (shared reading in apips.go, also used by Ollama #62).
++      - Measured on llmman 0.1.498: `/props` is a stub (n_ctx 4096, empty
++        chat_template, loaded or not) -> NOT used. prompt_progress,
++        reasoning_content, usage and `chat_template_kwargs.enable_thinking:false`
++        pass through to its llama-server. /api/show's trained context rejected
++        (LLMMAN_CONTEXT_LENGTH can serve less).
++      - Verified live: one-shot prompts (bash tool call, read_skill, reasoning
++        shown), REPL banner `ctx: 262144 (/api/ps)`, a real compaction
++        (`compressed 8 messages -> 1 summary + 2 kept`).
++      - Tests: Resolve rows, TestProbeLlmman; `go test ./...` green.
++      - Docs EN+FR: how-to/run-with-llmman.md, reference (configuration, cli,
++        mcp-configuration EN), explanation/providers.md, README indexes.
++      - Not done: automatic download with progress -> ticket 61. Quality gate (qlty)
++        not run: absent from the sandbox.

added .tickets/issues/0061-llmman-provider-download-the-model-automatically.yaml +13 -0 Viewed

new file mode 100644
@@ -0,0 +1,13 @@
	1	+# Managed by IssueSpec. Hand edits are welcome; keep the schema valid.
	2	+id: 61
	3	+title: "llmman provider: download the model automatically if does not exist"
	4	+state: open
	5	+author:
	6	+ name: k33g
	7	+ email: ph.charriere@gmail.com
	8	+createdAt: 2026-10-01T05:48:44.919Z
	9	+updatedAt: 2026-10-01T05:48:44.919Z
	10	+labels: []
	11	+body: ""
	12	+tasks: []
	13	+comments: []

++# Managed by IssueSpec. Hand edits are welcome; keep the schema valid.
++id: 61
++title: "llmman provider: download the model automatically if does not exist"
++state: open
++author:
++  name: k33g
++  email: ph.charriere@gmail.com
++createdAt: 2026-10-01T05:48:44.919Z
++updatedAt: 2026-10-01T05:48:44.919Z
++labels: []
++body: ""
++tasks: []
++comments: []

added .tickets/issues/0062-add-ollama-provider.yaml +146 -0 Viewed

new file mode 100644
@@ -0,0 +1,146 @@
	1	+# Managed by IssueSpec. Hand edits are welcome; keep the schema valid.
	2	+id: 62
	3	+title: Add Ollama provider
	4	+state: open
	5	+author:
	6	+ name: k33g
	7	+ email: ph.charriere@gmail.com
	8	+createdAt: 2026-10-01T06:10:07.295Z
	9	+updatedAt: 2026-10-01T07:00:00.000Z
	10	+labels:
	11	+ - kind::feature
	12	+ - priority::medium
	13	+related:
	14	+ - 60
	15	+body: \|
	16	+ Add Ollama as a provider, OpenAI API only (/v1/chat/completions), and a demo
	17	+ config in demo-ollama/ using qwen3.5:2b. Ollama, llmman, DMR and llama.cpp
	18	+ look alike, but each keeps its own registry entry so that a difference found
	19	+ later is one field to change.
	20	+tasks:
	21	+ - id: 1
	22	+ title: "Measure Ollama's /v1 (reasoning field, progress, thinking switch, window, 404)"
	23	+ state: closed
	24	+ priority: none
	25	+ author:
	26	+ name: k33g
	27	+ email: ph.charriere@gmail.com
	28	+ createdAt: 2026-10-01T07:00:00.000Z
	29	+ updatedAt: 2026-10-01T07:00:00.000Z
	30	+ - id: 2
	31	+ title: "Per-provider thinkingOff field; reasoning_effort none for Ollama"
	32	+ state: closed
	33	+ priority: none
	34	+ author:
	35	+ name: k33g
	36	+ email: ph.charriere@gmail.com
	37	+ createdAt: 2026-10-01T07:00:00.000Z
	38	+ updatedAt: 2026-10-01T07:00:00.000Z
	39	+ - id: 3
	40	+ title: "Registry entry ollama + probeOllama (shared /api/ps reading with llmman)"
	41	+ state: closed
	42	+ priority: none
	43	+ author:
	44	+ name: k33g
	45	+ email: ph.charriere@gmail.com
	46	+ createdAt: 2026-10-01T07:00:00.000Z
	47	+ updatedAt: 2026-10-01T07:00:00.000Z
	48	+ - id: 4
	49	+ title: "Tests: Resolve rows, TestProbeOllama, thinking-off middleware"
	50	+ state: closed
	51	+ priority: none
	52	+ author:
	53	+ name: k33g
	54	+ email: ph.charriere@gmail.com
	55	+ createdAt: 2026-10-01T07:00:00.000Z
	56	+ updatedAt: 2026-10-01T07:00:00.000Z
	57	+ - id: 5
	58	+ title: "demo-ollama/agent.ollama.yaml with qwen3.5:2b"
	59	+ state: closed
	60	+ priority: none
	61	+ author:
	62	+ name: k33g
	63	+ email: ph.charriere@gmail.com
	64	+ createdAt: 2026-10-01T07:00:00.000Z
	65	+ updatedAt: 2026-10-01T07:00:00.000Z
	66	+ - id: 6
	67	+ title: "Docs EN+FR (how-to, reference, explanation, indexes)"
	68	+ state: closed
	69	+ priority: none
	70	+ author:
	71	+ name: k33g
	72	+ email: ph.charriere@gmail.com
	73	+ createdAt: 2026-10-01T07:00:00.000Z
	74	+ updatedAt: 2026-10-01T07:00:00.000Z
	75	+ - id: 7
	76	+ title: "Live check against Ollama (tool call, ctx, compaction)"
	77	+ state: closed
	78	+ priority: none
	79	+ author:
	80	+ name: k33g
	81	+ email: ph.charriere@gmail.com
	82	+ createdAt: 2026-10-01T07:00:00.000Z
	83	+ updatedAt: 2026-10-01T07:00:00.000Z
	84	+ - id: 8
	85	+ title: "Check reasoning_effort none on a non-thinking model"
	86	+ state: open
	87	+ priority: none
	88	+ author:
	89	+ name: k33g
	90	+ email: ph.charriere@gmail.com
	91	+ createdAt: 2026-10-01T07:00:00.000Z
	92	+ updatedAt: 2026-10-01T07:00:00.000Z
	93	+ - id: 9
	94	+ title: "Quality gate (qlty) where available"
	95	+ state: open
	96	+ priority: none
	97	+ author:
	98	+ name: k33g
	99	+ email: ph.charriere@gmail.com
	100	+ createdAt: 2026-10-01T07:00:00.000Z
	101	+ updatedAt: 2026-10-01T07:00:00.000Z
	102	+ - id: 10
	103	+ title: "Review, commit, merge"
	104	+ state: open
	105	+ priority: none
	106	+ author:
	107	+ name: k33g
	108	+ email: ph.charriere@gmail.com
	109	+ createdAt: 2026-10-01T07:00:00.000Z
	110	+ updatedAt: 2026-10-01T07:00:00.000Z
	111	+comments:
	112	+ - id: 1
	113	+ author:
	114	+ name: claude
	115	+ email: noreply@anthropic.com
	116	+ createdAt: 2026-10-01T07:00:00.000Z
	117	+ body: \|
	118	+ Implemented on branch `feature/llmman-provider` (same branch as #60,
	119	+ uncommitted, 2026-10-01).
	120	+
	121	+ Measured on Ollama 0.35.0 (qwen3.5:2b), three real differences:
	122	+ 1. Reasoning streams as `delta.reasoning` (not `reasoning_content`): already
	123	+ read by reasoning.go.
	124	+ 2. No `prompt_progress` (`return_progress` ignored) -> `progress: false`; the
	125	+ firstTokenTimeout has to cover the whole prompt and the model load.
	126	+ 3. `chat_template_kwargs.enable_thinking:false` is IGNORED;
	127	+ `reasoning_effort: "none"` is obeyed. Proved on a real compaction: with
	128	+ chat_template_kwargs the summary reasoned until the 300-token limit and
	129	+ came back empty; with reasoning_effort it succeeded.
	130	+ -> new per-provider field `thinkingOff` (usage.go: thinkingOffTemplate for
	131	+ dmr/llamacpp/llmman, thinkingOffEffort for ollama), replacing the old
	132	+ "progress implies chat_template_kwargs" coupling.
	133	+
	134	+ Also: /api/ps reports the served window like llmman (`context_length: 32768`),
	135	+ shared helper apips.go; Ollama's OpenAI API does NOT pull a missing model
	136	+ (404 `model '…' not found`) -> probe warning says `ollama pull`.
	137	+
	138	+ - Registry entry `ollama`: base `http://localhost:11434/v1`, fallback
	139	+ `http://host.docker.internal:11434/v1`, key `OLLAMA_API_KEY` (optional,
	140	+ for ollama.com).
	141	+ - Tests: Resolve rows, TestProbeOllama, TestStreamOptionsWithoutThinkingOllama;
	142	+ the unknown-provider tests now use `vllm`. `go test ./...` green.
	143	+ - Live: banner `ctx: 32768 (/api/ps)`, one-shot prompt with a bash tool call.
	144	+ - Docs EN+FR: how-to/run-with-ollama.md, reference, explanation, READMEs.
	145	+ - Not done: quality gate (qlty absent from the sandbox). Unverified:
	146	+ `reasoning_effort: "none"` on a NON-thinking model (none installed).

++# Managed by IssueSpec. Hand edits are welcome; keep the schema valid.
++id: 62
++title: Add Ollama provider
++state: open
++author:
++  name: k33g
++  email: ph.charriere@gmail.com
++createdAt: 2026-10-01T06:10:07.295Z
++updatedAt: 2026-10-01T07:00:00.000Z
++labels:
++  - kind::feature
++  - priority::medium
++related:
++  - 60
++body: |
++  Add Ollama as a provider, OpenAI API only (/v1/chat/completions), and a demo
++  config in demo-ollama/ using qwen3.5:2b. Ollama, llmman, DMR and llama.cpp
++  look alike, but each keeps its own registry entry so that a difference found
++  later is one field to change.
++tasks:
++  - id: 1
++    title: "Measure Ollama's /v1 (reasoning field, progress, thinking switch, window, 404)"
++    state: closed
++    priority: none
++    author:
++      name: k33g
++      email: ph.charriere@gmail.com
++    createdAt: 2026-10-01T07:00:00.000Z
++    updatedAt: 2026-10-01T07:00:00.000Z
++  - id: 2
++    title: "Per-provider thinkingOff field; reasoning_effort none for Ollama"
++    state: closed
++    priority: none
++    author:
++      name: k33g
++      email: ph.charriere@gmail.com
++    createdAt: 2026-10-01T07:00:00.000Z
++    updatedAt: 2026-10-01T07:00:00.000Z
++  - id: 3
++    title: "Registry entry ollama + probeOllama (shared /api/ps reading with llmman)"
++    state: closed
++    priority: none
++    author:
++      name: k33g
++      email: ph.charriere@gmail.com
++    createdAt: 2026-10-01T07:00:00.000Z
++    updatedAt: 2026-10-01T07:00:00.000Z
++  - id: 4
++    title: "Tests: Resolve rows, TestProbeOllama, thinking-off middleware"
++    state: closed
++    priority: none
++    author:
++      name: k33g
++      email: ph.charriere@gmail.com
++    createdAt: 2026-10-01T07:00:00.000Z
++    updatedAt: 2026-10-01T07:00:00.000Z
++  - id: 5
++    title: "demo-ollama/agent.ollama.yaml with qwen3.5:2b"
++    state: closed
++    priority: none
++    author:
++      name: k33g
++      email: ph.charriere@gmail.com
++    createdAt: 2026-10-01T07:00:00.000Z
++    updatedAt: 2026-10-01T07:00:00.000Z
++  - id: 6
++    title: "Docs EN+FR (how-to, reference, explanation, indexes)"
++    state: closed
++    priority: none
++    author:
++      name: k33g
++      email: ph.charriere@gmail.com
++    createdAt: 2026-10-01T07:00:00.000Z
++    updatedAt: 2026-10-01T07:00:00.000Z
++  - id: 7
++    title: "Live check against Ollama (tool call, ctx, compaction)"
++    state: closed
++    priority: none
++    author:
++      name: k33g
++      email: ph.charriere@gmail.com
++    createdAt: 2026-10-01T07:00:00.000Z
++    updatedAt: 2026-10-01T07:00:00.000Z
++  - id: 8
++    title: "Check reasoning_effort none on a non-thinking model"
++    state: open
++    priority: none
++    author:
++      name: k33g
++      email: ph.charriere@gmail.com
++    createdAt: 2026-10-01T07:00:00.000Z
++    updatedAt: 2026-10-01T07:00:00.000Z
++  - id: 9
++    title: "Quality gate (qlty) where available"
++    state: open
++    priority: none
++    author:
++      name: k33g
++      email: ph.charriere@gmail.com
++    createdAt: 2026-10-01T07:00:00.000Z
++    updatedAt: 2026-10-01T07:00:00.000Z
++  - id: 10
++    title: "Review, commit, merge"
++    state: open
++    priority: none
++    author:
++      name: k33g
++      email: ph.charriere@gmail.com
++    createdAt: 2026-10-01T07:00:00.000Z
++    updatedAt: 2026-10-01T07:00:00.000Z
++comments:
++  - id: 1
++    author:
++      name: claude
++      email: noreply@anthropic.com
++    createdAt: 2026-10-01T07:00:00.000Z
++    body: |
++      **Implemented** on branch `feature/llmman-provider` (same branch as #60,
++      uncommitted, 2026-10-01).
++
++      Measured on Ollama 0.35.0 (qwen3.5:2b), three real differences:
++      1. Reasoning streams as `delta.reasoning` (not `reasoning_content`): already
++         read by reasoning.go.
++      2. No `prompt_progress` (`return_progress` ignored) -> `progress: false`; the
++         firstTokenTimeout has to cover the whole prompt and the model load.
++      3. `chat_template_kwargs.enable_thinking:false` is IGNORED;
++         `reasoning_effort: "none"` is obeyed. Proved on a real compaction: with
++         chat_template_kwargs the summary reasoned until the 300-token limit and
++         came back empty; with reasoning_effort it succeeded.
++         -> new per-provider field `thinkingOff` (usage.go: thinkingOffTemplate for
++         dmr/llamacpp/llmman, thinkingOffEffort for ollama), replacing the old
++         "progress implies chat_template_kwargs" coupling.
++
++      Also: /api/ps reports the served window like llmman (`context_length: 32768`),
++      shared helper apips.go; Ollama's OpenAI API does NOT pull a missing model
++      (404 `model '…' not found`) -> probe warning says `ollama pull`.
++
++      - Registry entry `ollama`: base `http://localhost:11434/v1`, fallback
++        `http://host.docker.internal:11434/v1`, key `OLLAMA_API_KEY` (optional,
++        for ollama.com).
++      - Tests: Resolve rows, TestProbeOllama, TestStreamOptionsWithoutThinkingOllama;
++        the unknown-provider tests now use `vllm`. `go test ./...` green.
++      - Live: banner `ctx: 32768 (/api/ps)`, one-shot prompt with a bash tool call.
++      - Docs EN+FR: how-to/run-with-ollama.md, reference, explanation, READMEs.
++      - Not done: quality gate (qlty absent from the sandbox). Unverified:
++        `reasoning_effort: "none"` on a NON-thinking model (none installed).

added demo-llmman/agent.llmman.yaml +199 -0 Viewed

new file mode 100644
@@ -0,0 +1,199 @@
	1	+# Agent settings — mini-me served by llmman (https://github.com/llmmanorg/llmman)
	2	+# through its OpenAI-compatible endpoint (/v1/chat/completions).
	3	+#
	4	+# llmman pull hf.co/unsloth/Qwen3.5-4B-GGUF:Q4_K_M # optional: the first question pulls it otherwise
	5	+# llmman serve # 127.0.0.1:17434
	6	+#
	7	+# llmman loads the model on the first request (in its own llama-server) and
	8	+# unloads it after five idle minutes.
	9	+provider: llmman
	10	+
	11	+# The model id exactly as `llmman list` / GET /v1/models spells it.
	12	+model: hf.co/unsloth/Qwen3.5-4B-GGUF:Q4_K_M
	13	+
	14	+# `llmman serve`'s default bind; the OpenAI routes sit under /v1.
	15	+baseUrl: http://127.0.0.1:17434/v1
	16	+
	17	+# From a Docker sandbox, the daemon runs on the host.
	18	+fallback: http://host.docker.internal:17434/v1
	19	+
	20	+# Only when the daemon was started with LLMMAN_API_KEYS (mandatory when it
	21	+# listens beyond loopback); unset otherwise. The key never goes in this file.
	22	+# apiKeyEnv: LLMMAN_API_KEY
	23	+
	24	+# The `bash` tool.
	25	+# `false` removes it: the model can still read and edit files (editTools) and load skills,
	26	+# but never runs a command. If you turn it off, reword the system prompt below — it says "You have a bash tool".
	27	+bashTool: true
	28	+
	29	+# The built-in file tools: read_file, write_file, edit_file.
	30	+editTools: true
	31	+
	32	+# The built-in plan tool for managing multi-step plans.
	33	+# Set to false to disable plan creation and tracking via the `plan` tool.
	34	+planTool: true
	35	+
	36	+# Language servers for the `lsp` tool (definition, references, hover, symbols, diagnostics, rename).
	37	+# The file extension picks the server. A server missing from the PATH is skipped with a warning.
	38	+# No server listed = no `lsp` tool. Examples (uncomment what you have installed):
	39	+# lsp:
	40	+# servers:
	41	+# - name: gopls
	42	+# command: gopls
	43	+# extensions: [".go"]
	44	+# - name: typescript
	45	+# command: typescript-language-server
	46	+# args: ["--stdio"]
	47	+# extensions: [".ts", ".tsx", ".js", ".jsx"]
	48	+# - name: python
	49	+# command: pyright-langserver
	50	+# args: ["--stdio"]
	51	+# extensions: [".py"]
	52	+# - name: rust
	53	+# command: rust-analyzer
	54	+# extensions: [".rs"]
	55	+
	56	+# How many tokens the server actually serves.
	57	+# 0 = ask llmman: /api/ps tells it once the model is loaded, so the window is
	58	+# learned before the second question. Set it here if you want it from the start
	59	+# — and to the same value as LLMMAN_CONTEXT_LENGTH if you set that variable.
	60	+contextWindow: 0
	61	+
	62	+# Max number of characters a tool returns to the model.
	63	+# Context safeguard: beyond that, the output is truncated (beginning + end kept).
	64	+maxOutput: 16000
	65	+
	66	+# Max number of model <-> tools round trips for a single question.
	67	+# Raise it for tasks that need long chains of commands.
	68	+maxTurns: 40
	69	+
	70	+# Where the `read_skill` tool looks for its markdown procedures.
	71	+# The path is relative to the CURRENT DIRECTORY: run the agent from demo-llmman/.
	72	+skillsDir: ../skills
	73	+
	74	+# Persistent sessions, per project.
	75	+# When enabled, every conversation is saved as one JSON file under `dir`.
	76	+# `/sessions` lists them, `/resume` continues one; in an editor, "Reload Agent" replays the thread.
	77	+sessions:
	78	+ enabled: true
	79	+ dir: .mm/sessions
	80	+
	81	+# How many lines of a command's output are echoed to the terminal.
	82	+# 0 disables it.
	83	+previewLines: 20
	84	+
	85	+displayCommands: true
	86	+# Show what a thinking model reasons about before it answers (dim italic in the
	87	+# terminal, its own style in the window, a thought chunk in an editor).
	88	+# The reasoning is always READ — it is what keeps the watchdog alive while the
	89	+# model thinks — this only says whether to show it.
	90	+showThinking: true
	91	+
	92	+
	93	+# The system prompt: what the agent is, and what it is allowed to do.
	94	+# This is the knob to play with — it is the shortest path to changing behaviour.
	95	+system: \|
	96	+ Your name is Bob.
	97	+ You are a coding agent working in a terminal.
	98	+ You have a "bash" tool to run shell commands.
	99	+ Use it to explore files, run tests, inspect the repository, etc.
	100	+ Chain several commands if needed, then answer clearly in English.
	101	+
	102	+ A request often mixes things you answer from yourself ("say hello") with
	103	+ things only a command can answer ("list the files"). Handle every part, in
	104	+ the order asked, and run a command for each part that needs one.
	105	+ Never state the contents of a file, the output of a command, or the state of
	106	+ the repository unless a command in THIS answer returned it. What you did not
	107	+ read, you do not know: run the command instead of recalling it.
	108	+
	109	+ SKILLS
	110	+ You have a second tool, `read_skill`. Its description lists the procedures
	111	+ available for this project — one per kind of task.
	112	+
	113	+ Any request to DO something to a Go project is a skill, not a shell command
	114	+ you invent. Match the request against that list, call `read_skill` FIRST,
	115	+ before any bash command, and then follow what it says step by step.
	116	+
	117	+ FILE EDITING
	118	+ You have three tools for files: `read_file`, `edit_file` and `write_file`.
	119	+ They are how a file gets read and changed here: each change is exact,
	120	+ checked before it is written, and comes back as a diff with line numbers.
	121	+ bash is for running things — building, testing, listing, searching.
	122	+
	123	+ - Read before you write: call `read_file` on the file (numbered=true when
	124	+ you need line numbers). You cannot target text you have not seen; never
	125	+ rely on what you think you remember about a file.
	126	+ - To change an existing file, call `edit_file` with one or more {old, new}
	127	+ pairs. `old` is copied from the file character for character — same
	128	+ spaces, same indentation, same line breaks — and appears exactly once:
	129	+ add the surrounding lines until it is unique. Several pairs are applied
	130	+ together, against the original file. An empty `new` deletes the text.
	131	+ - Call `write_file` only to create a file, or to rewrite one entirely and
	132	+ on purpose. On an existing file it replaces everything, including what
	133	+ you did not intend to touch.
	134	+ - Read the diff the tool returns: it says exactly what changed and on which
	135	+ line. If `edit_file` refuses — text not found, ambiguous, overlapping
	136	+ edits — read the file again and fix `old`. Do not fall back to
	137	+ `write_file` to force the change through.
	138	+ - After editing code, run the narrowest check with bash: the formatter, the
	139	+ compiler, or the test covering that file.
	140	+
	141	+ RULES
	142	+ - Keep everything the file already does, unless the user asked to remove it.
	143	+ - Touch only the files the request is about. Do not add tests, files or
	144	+ features that were not asked for.
	145	+ - Never run a git command unless the user says git, commit or push.
	146	+ - Never move, rename or delete a file unless the user asked for it.
	147	+ - Then answer in English, in a few lines.
	148	+ - If you don't know how to use a <cli>, run `<cli> --help` (or `<cli> help`)
	149	+ to understand the options, then run the command.
	150	+
	151	+ BACKGROUND JOBS
	152	+ Never let a command block the answer. Anything that serves, watches or runs
	153	+ long goes to the background, with BOTH streams redirected and its pid kept:
	154	+
	155	+ nohup <command> > /tmp/<job>.log 2>&1 & echo $! > /tmp/<job>.pid
	156	+
	157	+ Redirecting only stdout still blocks until the process exits. Read the
	158	+ `bg-jobs` skill before you wait on, inspect or stop such a job — each has a
	159	+ rule you cannot guess. Stop every job you started before you finish, and say
	160	+ which ones you left running.
	161	+
	162	+# Generation settings (OpenAI API keys). Low temperature for a coding agent:
	163	+# we want precise and reproducible answers, not creativity.
	164	+sampling:
	165	+ temperature: 0.0
	166	+ parallel_tool_calls: false
	167	+ top_p: 0.9
	168	+ max_tokens: 4096
	169	+
	170	+# Silence allowed between two tokens once the answer has started.
	171	+watchdogTimeout: 30s
	172	+
	173	+# Silence allowed while the model reads the prompt, before the first token:
	174	+# on a laptop a 25k-token prompt can take minutes. llama-server reports its
	175	+# progress meanwhile, through llmman ("Reading the prompt 12.0k/25.3k tokens"), and each report
	176	+# restarts this clock, so it only has to cover one batch of the prompt.
	177	+firstTokenTimeout: 3m
	178	+
	179	+# Context compression.
	180	+# ON here: the agent learns the window from /api/ps, so `threshold` has a number to apply to.
	181	+context:
	182	+ enabled: true
	183	+
	184	+ # Compress when the history reaches this share of the window.
	185	+ threshold: 75
	186	+
	187	+ # Fallback on the message count, for when the window is unknown.
	188	+ # One command costs 2 messages (call + response), so 80 is roughly 30 commands of history.
	189	+ maxMessages: 80
	190	+
	191	+ # How many recent questions (with their commands and answers) are kept as-is instead of being summarised.
	192	+ # The model works on the last few turns, so summarising them would make it redo what it just did.
	193	+ keepLastTurns: 3
	194	+
	195	+ # max_tokens of the summary request. Reasoning is turned off for it on this provider
	196	+ # (a thinking model would otherwise spend the budget thinking and write nothing).
	197	+ summaryMaxTokens: 1200
	198	+
	199	+ showStats: true

++# Agent settings — mini-me served by llmman (https://github.com/llmmanorg/llmman)
++# through its OpenAI-compatible endpoint (/v1/chat/completions).
++#
++#   llmman pull hf.co/unsloth/Qwen3.5-4B-GGUF:Q4_K_M   # optional: the first question pulls it otherwise
++#   llmman serve                                       # 127.0.0.1:17434
++#
++# llmman loads the model on the first request (in its own llama-server) and
++# unloads it after five idle minutes.
++provider: llmman
++
++# The model id exactly as `llmman list` / GET /v1/models spells it.
++model: hf.co/unsloth/Qwen3.5-4B-GGUF:Q4_K_M
++
++# `llmman serve`'s default bind; the OpenAI routes sit under /v1.
++baseUrl: http://127.0.0.1:17434/v1
++
++# From a Docker sandbox, the daemon runs on the host.
++fallback: http://host.docker.internal:17434/v1
++
++# Only when the daemon was started with LLMMAN_API_KEYS (mandatory when it
++# listens beyond loopback); unset otherwise. The key never goes in this file.
++# apiKeyEnv: LLMMAN_API_KEY
++
++# The `bash` tool.
++# `false` removes it: the model can still read and edit files (editTools) and load skills,
++# but never runs a command. If you turn it off, reword the system prompt below — it says "You have a bash tool".
++bashTool: true
++
++# The built-in file tools: read_file, write_file, edit_file.
++editTools: true
++
++# The built-in plan tool for managing multi-step plans.
++# Set to false to disable plan creation and tracking via the `plan` tool.
++planTool: true
++
++# Language servers for the `lsp` tool (definition, references, hover, symbols, diagnostics, rename).
++# The file extension picks the server. A server missing from the PATH is skipped with a warning.
++# No server listed = no `lsp` tool. Examples (uncomment what you have installed):
++# lsp:
++#   servers:
++#     - name: gopls
++#       command: gopls
++#       extensions: [".go"]
++#     - name: typescript
++#       command: typescript-language-server
++#       args: ["--stdio"]
++#       extensions: [".ts", ".tsx", ".js", ".jsx"]
++#     - name: python
++#       command: pyright-langserver
++#       args: ["--stdio"]
++#       extensions: [".py"]
++#     - name: rust
++#       command: rust-analyzer
++#       extensions: [".rs"]
++
++# How many tokens the server actually serves.
++# 0 = ask llmman: /api/ps tells it once the model is loaded, so the window is
++# learned before the second question. Set it here if you want it from the start
++# — and to the same value as LLMMAN_CONTEXT_LENGTH if you set that variable.
++contextWindow: 0
++
++# Max number of characters a tool returns to the model.
++# Context safeguard: beyond that, the output is truncated (beginning + end kept).
++maxOutput: 16000
++
++# Max number of model <-> tools round trips for a single question.
++# Raise it for tasks that need long chains of commands.
++maxTurns: 40
++
++# Where the `read_skill` tool looks for its markdown procedures.
++# The path is relative to the CURRENT DIRECTORY: run the agent from demo-llmman/.
++skillsDir: ../skills
++
++# Persistent sessions, per project.
++# When enabled, every conversation is saved as one JSON file under `dir`.
++# `/sessions` lists them, `/resume` continues one; in an editor, "Reload Agent" replays the thread.
++sessions:
++  enabled: true
++  dir: .mm/sessions
++
++# How many lines of a command's output are echoed to the terminal.
++# 0 disables it.
++previewLines: 20
++
++displayCommands: true
++# Show what a thinking model reasons about before it answers (dim italic in the
++# terminal, its own style in the window, a thought chunk in an editor).
++# The reasoning is always READ — it is what keeps the watchdog alive while the
++# model thinks — this only says whether to show it.
++showThinking: true
++
++
++# The system prompt: what the agent is, and what it is allowed to do.
++# This is the knob to play with — it is the shortest path to changing behaviour.
++system: |
++  Your name is Bob.
++  You are a coding agent working in a terminal.
++  You have a "bash" tool to run shell commands.
++  Use it to explore files, run tests, inspect the repository, etc.
++  Chain several commands if needed, then answer clearly in English.
++
++  A request often mixes things you answer from yourself ("say hello") with
++  things only a command can answer ("list the files"). Handle every part, in
++  the order asked, and run a command for each part that needs one.
++  Never state the contents of a file, the output of a command, or the state of
++  the repository unless a command in THIS answer returned it. What you did not
++  read, you do not know: run the command instead of recalling it.
++
++  SKILLS
++  You have a second tool, `read_skill`. Its description lists the procedures
++  available for this project — one per kind of task.
++
++  Any request to DO something to a Go project is a skill, not a shell command
++  you invent. Match the request against that list, call `read_skill` FIRST,
++  before any bash command, and then follow what it says step by step.
++
++  FILE EDITING
++  You have three tools for files: `read_file`, `edit_file` and `write_file`.
++  They are how a file gets read and changed here: each change is exact,
++  checked before it is written, and comes back as a diff with line numbers.
++  bash is for running things — building, testing, listing, searching.
++
++  - Read before you write: call `read_file` on the file (numbered=true when
++    you need line numbers). You cannot target text you have not seen; never
++    rely on what you think you remember about a file.
++  - To change an existing file, call `edit_file` with one or more {old, new}
++    pairs. `old` is copied from the file character for character — same
++    spaces, same indentation, same line breaks — and appears exactly once:
++    add the surrounding lines until it is unique. Several pairs are applied
++    together, against the original file. An empty `new` deletes the text.
++  - Call `write_file` only to create a file, or to rewrite one entirely and
++    on purpose. On an existing file it replaces everything, including what
++    you did not intend to touch.
++  - Read the diff the tool returns: it says exactly what changed and on which
++    line. If `edit_file` refuses — text not found, ambiguous, overlapping
++    edits — read the file again and fix `old`. Do not fall back to
++    `write_file` to force the change through.
++  - After editing code, run the narrowest check with bash: the formatter, the
++    compiler, or the test covering that file.
++
++  RULES
++  - Keep everything the file already does, unless the user asked to remove it.
++  - Touch only the files the request is about. Do not add tests, files or
++    features that were not asked for.
++  - Never run a git command unless the user says git, commit or push.
++  - Never move, rename or delete a file unless the user asked for it.
++  - Then answer in English, in a few lines.
++  - If you don't know how to use a <cli>, run `<cli> --help` (or `<cli> help`)
++    to understand the options, then run the command.
++
++  BACKGROUND JOBS
++  Never let a command block the answer. Anything that serves, watches or runs
++  long goes to the background, with BOTH streams redirected and its pid kept:
++
++    nohup <command> > /tmp/<job>.log 2>&1 & echo $! > /tmp/<job>.pid
++
++  Redirecting only stdout still blocks until the process exits. Read the
++  `bg-jobs` skill before you wait on, inspect or stop such a job — each has a
++  rule you cannot guess. Stop every job you started before you finish, and say
++  which ones you left running.
++
++# Generation settings (OpenAI API keys). Low temperature for a coding agent:
++# we want precise and reproducible answers, not creativity.
++sampling:
++  temperature: 0.0
++  parallel_tool_calls: false
++  top_p: 0.9
++  max_tokens: 4096
++
++# Silence allowed between two tokens once the answer has started.
++watchdogTimeout: 30s
++
++# Silence allowed while the model reads the prompt, before the first token:
++# on a laptop a 25k-token prompt can take minutes. llama-server reports its
++# progress meanwhile, through llmman ("Reading the prompt 12.0k/25.3k tokens"), and each report
++# restarts this clock, so it only has to cover one batch of the prompt.
++firstTokenTimeout: 3m
++
++# Context compression.
++# ON here: the agent learns the window from /api/ps, so `threshold` has a number to apply to.
++context:
++  enabled: true
++
++  # Compress when the history reaches this share of the window.
++  threshold: 75
++
++  # Fallback on the message count, for when the window is unknown.
++  # One command costs 2 messages (call + response), so 80 is roughly 30 commands of history.
++  maxMessages: 80
++
++  # How many recent questions (with their commands and answers) are kept as-is instead of being summarised.
++  # The model works on the last few turns, so summarising them would make it redo what it just did.
++  keepLastTurns: 3
++
++  # max_tokens of the summary request. Reasoning is turned off for it on this provider
++  # (a thinking model would otherwise spend the budget thinking and write nothing).
++  summaryMaxTokens: 1200
++
++  showStats: true

added demo-ollama/agent.ollama.yaml +202 -0 Viewed

Large diff collapsed to keep the page fast — load it when you need it.

modified docs/en/README.md +3 -1 Viewed

@@ -1,6 +1,6 @@
1	1	# mini-me — documentation (English)
2	2
3		-`mm` is a coding agent that runs in your terminal — line by line, or in a single window with `mm -tui` — or inside an editor through the Agent Client Protocol. It talks to a local model server (Docker Model Runner or llama.cpp's `llama-server`) and works with a handful of built-in tools: `bash`, `read_skill`, `read_file`, `write_file`, `edit_file` — plus, when turned on, `lsp` and `fetch_content`.
	3	+`mm` is a coding agent that runs in your terminal — line by line, or in a single window with `mm -tui` — or inside an editor through the Agent Client Protocol. It talks to a local model server (Docker Model Runner, llama.cpp's `llama-server`, llmman or Ollama) and works with a handful of built-in tools: `bash`, `read_skill`, `read_file`, `write_file`, `edit_file` — plus, when turned on, `lsp` and `fetch_content`.
4	4
5	5	This documentation is organised along the four [Diátaxis](https://diataxis.fr) quadrants. Pick the one that matches what you need right now.
6	6
@@ -11,6 +11,8 @@ This documentation is organised along the four [Diátaxis](https://diataxis.fr)
11	11	## How-to guides — get a task done
12	12
13	13	- [Run mini-me on llama.cpp instead of Docker Model Runner](how-to/run-with-llama-cpp.md)
	14	+- [Run mini-me on llmman](how-to/run-with-llmman.md) — `provider: llmman`, the demo config in `demo-llmman/`
	15	+- [Run mini-me on Ollama](how-to/run-with-ollama.md) — `provider: ollama`, the demo config in `demo-ollama/`
14	16	- [Use mini-me from an editor (ACP)](how-to/use-from-an-editor.md)
15	17	- [Run mini-me in a Docker Sandbox](how-to/run-in-a-docker-sandbox.md) — the template and the two kits under `docker-sbx/`, window mode and editor
16	18	- [Run mini-me with the v3 sandbox kits](how-to/run-with-sandbox-kits-v3.md) — the same two kits for the kit specification v3, under `docker-sbx-v3/`

  # mini-me — documentation (English)
--`mm` is a coding agent that runs in your terminal — line by line, or in a single window with `mm -tui` — or inside an editor through the Agent Client Protocol. It talks to a local model server (Docker Model Runner or llama.cpp's `llama-server`) and works with a handful of built-in tools: `bash`, `read_skill`, `read_file`, `write_file`, `edit_file` — plus, when turned on, `lsp` and `fetch_content`.
++`mm` is a coding agent that runs in your terminal — line by line, or in a single window with `mm -tui` — or inside an editor through the Agent Client Protocol. It talks to a local model server (Docker Model Runner, llama.cpp's `llama-server`, llmman or Ollama) and works with a handful of built-in tools: `bash`, `read_skill`, `read_file`, `write_file`, `edit_file` — plus, when turned on, `lsp` and `fetch_content`.
  This documentation is organised along the four [Diátaxis](https://diataxis.fr) quadrants. Pick the one that matches what you need right now.
  ## How-to guides — get a task done
  - [Run mini-me on llama.cpp instead of Docker Model Runner](how-to/run-with-llama-cpp.md)
++- [Run mini-me on llmman](how-to/run-with-llmman.md) — `provider: llmman`, the demo config in `demo-llmman/`
++- [Run mini-me on Ollama](how-to/run-with-ollama.md) — `provider: ollama`, the demo config in `demo-ollama/`
  - [Use mini-me from an editor (ACP)](how-to/use-from-an-editor.md)
  - [Run mini-me in a Docker Sandbox](how-to/run-in-a-docker-sandbox.md) — the template and the two kits under `docker-sbx/`, window mode and editor
  - [Run mini-me with the v3 sandbox kits](how-to/run-with-sandbox-kits-v3.md) — the same two kits for the kit specification v3, under `docker-sbx-v3/`

modified docs/en/explanation/providers.md +6 -2 Viewed

@@ -2,7 +2,7 @@
2	2
3	3	## What is this about?
4	4
5		-`mm` talks to a local model server through the OpenAI chat-completions API. Two servers are supported out of the box, Docker Model Runner and llama.cpp's `llama-server`, under the names `dmr` and `llamacpp`. The engine package used to be tied to Docker Model Runner; the provider abstraction is what generalised it.
	5	+`mm` talks to a local model server through the OpenAI chat-completions API. Four servers are supported out of the box: Docker Model Runner, llama.cpp's `llama-server`, llmman and Ollama, under the names `dmr`, `llamacpp`, `llmman` and `ollama`. The engine package used to be tied to Docker Model Runner; the provider abstraction is what generalised it.
6	6
7	7	## Why it is designed this way
8	8
@@ -16,6 +16,10 @@
16	16
17	17	The probe is advice, never a failure. On a demo machine the server is often started after the agent. The probe checks reachability, warns when the configured model is not in DMR's list, and on llama.cpp reads the served context size from `/props`, one level above `/v1`, because that endpoint reports what the server serves, not what the model was trained with. When the window is still unknown and compression is on, the REPL probes again before the first question.
18	18
	19	+llmman is a third registry entry, with its own probe. [llmman](https://github.com/llmmanorg/llmman) (`llmman serve`, port 17434) is a daemon in front of one `llama-server` per loaded model, and speaks several APIs; `mm` uses only its OpenAI one. Everything llama.cpp-specific passes through it — prompt progress, reasoning, `enable_thinking: false` for summaries — so it gets the same treatment as `llamacpp`. Its `/props`, though, is a stub (`n_ctx` 4096, no chat template, measured on llmman 0.1.498), so the probe reads the served window from `/api/ps` instead, for the configured model, once it is loaded. The trained context from `/api/show` is not used: `LLMMAN_CONTEXT_LENGTH` can serve less, and a window too large means compression that never triggers before the server refuses the prompt. A model missing from `/v1/models` is only a warning: llmman pulls it on the first request.
	20	+
	21	+Ollama is a fourth entry, and shows why each server keeps its own. Ollama's `/v1` looks like the others, but measured on Ollama 0.35.0 it differs in three ways. Reasoning streams as `delta.reasoning`, which the tap already reads. No prompt progress comes back, so `return_progress` is not sent. And `chat_template_kwargs` is ignored: the summary of a compaction reasoned until its token limit and came back empty; `reasoning_effort: "none"` is what Ollama obeys, and with it the same compaction succeeded. That is why how to turn reasoning off is a per-provider field, not something implied by "is llama.cpp". Like llmman, Ollama reports the served window on `/api/ps` once the model is loaded (the two share that reading); unlike llmman, it does not pull a missing model, so the probe's warning says `ollama pull`.
	22	+
19	23	Errors are rewritten in the server's own words. A stack of wrapped messages is noise; "tool calls need llama-server started with --jinja" is the whole diagnosis. The provider recognises connection refusals, the missing `--jinja` flag, 401/403, 404 with a pull or alias hint, 429 and 5xx. Unknown errors come back unchanged: a raw message beats a wrong hint.
20	24
21	25	A stream the server breaks is retried, and its words are kept. llama.cpp reports a failure in the middle of a streamed answer as an SSE `error:` event (the 200 status is already sent). openai-go only reads `data:` lines, so the message used to vanish behind `unexpected end of JSON input`. The tap that reads the stream for reasoning also picks up those events, and the model call that broke is retried once — that call only: the tools that ran earlier in the turn are not replayed, and text the broken attempt already streamed is not taken back. If it breaks again, the error shows the server's own message (`the model server reported an error while generating: Failed to parse input at pos …`), or says the connection broke. Either way the history is kept: asking to continue picks the work up.
@@ -34,5 +38,5 @@
34	38
35	39	- The two configuration files that parametrise each provider are listed in the [configuration reference](../reference/configuration.md).
36	40	- The window the probe learns is what [context compression](context-compression.md) measures against.
37		-- Switching servers for one run is covered in [how to run on llama.cpp](../how-to/run-with-llama-cpp.md).
	41	+- Switching servers for one run is covered in [how to run on llama.cpp](../how-to/run-with-llama-cpp.md) [how to run on llmman](../how-to/run-with-llmman.md) and [how to run on Ollama](../how-to/run-with-ollama.md).
38	42	- Checking the tool order and measuring the cache gain on your own server: [how to check that the tools go out in a stable order](../how-to/verify-tool-order.md).

  ## What is this about?
--`mm` talks to a local model server through the OpenAI chat-completions API. Two servers are supported out of the box, Docker Model Runner and llama.cpp's `llama-server`, under the names `dmr` and `llamacpp`. The engine package used to be tied to Docker Model Runner; the provider abstraction is what generalised it.
++`mm` talks to a local model server through the OpenAI chat-completions API. Four servers are supported out of the box: Docker Model Runner, llama.cpp's `llama-server`, llmman and Ollama, under the names `dmr`, `llamacpp`, `llmman` and `ollama`. The engine package used to be tied to Docker Model Runner; the provider abstraction is what generalised it.
  ## Why it is designed this way
  **The probe is advice, never a failure.** On a demo machine the server is often started after the agent. The probe checks reachability, warns when the configured model is not in DMR's list, and on llama.cpp reads the served context size from `/props`, one level above `/v1`, because that endpoint reports what the server serves, not what the model was trained with. When the window is still unknown and compression is on, the REPL probes again before the first question.
++**llmman is a third registry entry, with its own probe.** [llmman](https://github.com/llmmanorg/llmman) (`llmman serve`, port 17434) is a daemon in front of one `llama-server` per loaded model, and speaks several APIs; `mm` uses only its OpenAI one. Everything llama.cpp-specific passes through it — prompt progress, reasoning, `enable_thinking: false` for summaries — so it gets the same treatment as `llamacpp`. Its `/props`, though, is a stub (`n_ctx` 4096, no chat template, measured on llmman 0.1.498), so the probe reads the served window from `/api/ps` instead, for the configured model, once it is loaded. The trained context from `/api/show` is not used: `LLMMAN_CONTEXT_LENGTH` can serve less, and a window too large means compression that never triggers before the server refuses the prompt. A model missing from `/v1/models` is only a warning: llmman pulls it on the first request.
++
++**Ollama is a fourth entry, and shows why each server keeps its own.** Ollama's `/v1` looks like the others, but measured on Ollama 0.35.0 it differs in three ways. Reasoning streams as `delta.reasoning`, which the tap already reads. No prompt progress comes back, so `return_progress` is not sent. And `chat_template_kwargs` is ignored: the summary of a compaction reasoned until its token limit and came back empty; `reasoning_effort: "none"` is what Ollama obeys, and with it the same compaction succeeded. That is why how to turn reasoning off is a per-provider field, not something implied by "is llama.cpp". Like llmman, Ollama reports the served window on `/api/ps` once the model is loaded (the two share that reading); unlike llmman, it does not pull a missing model, so the probe's warning says `ollama pull`.
++
  **Errors are rewritten in the server's own words.** A stack of wrapped messages is noise; "tool calls need llama-server started with --jinja" is the whole diagnosis. The provider recognises connection refusals, the missing `--jinja` flag, 401/403, 404 with a pull or alias hint, 429 and 5xx. Unknown errors come back unchanged: a raw message beats a wrong hint.
  **A stream the server breaks is retried, and its words are kept.** llama.cpp reports a failure in the middle of a streamed answer as an SSE `error:` event (the 200 status is already sent). openai-go only reads `data:` lines, so the message used to vanish behind `unexpected end of JSON input`. The tap that reads the stream for reasoning also picks up those events, and the model call that broke is retried once — that call only: the tools that ran earlier in the turn are not replayed, and text the broken attempt already streamed is not taken back. If it breaks again, the error shows the server's own message (`the model server reported an error while generating: Failed to parse input at pos …`), or says the connection broke. Either way the history is kept: asking to continue picks the work up.
  - The two configuration files that parametrise each provider are listed in the [configuration reference](../reference/configuration.md).
  - The window the probe learns is what [context compression](context-compression.md) measures against.
--- Switching servers for one run is covered in [how to run on llama.cpp](../how-to/run-with-llama-cpp.md).
++- Switching servers for one run is covered in [how to run on llama.cpp](../how-to/run-with-llama-cpp.md) [how to run on llmman](../how-to/run-with-llmman.md) and [how to run on Ollama](../how-to/run-with-ollama.md).
  - Checking the tool order and measuring the cache gain on your own server: [how to check that the tools go out in a stable order](../how-to/verify-tool-order.md).

added docs/en/how-to/run-with-llmman.md +39 -0 Viewed

new file mode 100644
@@ -0,0 +1,39 @@
	1	+# How to run mini-me on llmman
	2	+
	3	+This guide shows how to point `mm` at [llmman](https://github.com/llmmanorg/llmman) through its OpenAI-compatible endpoint. It assumes llmman is installed and you know how to build `mm`.
	4	+
	5	+## Steps
	6	+
	7	+1. Start the daemon. It listens on `127.0.0.1:17434`:
	8	+
	9	+ ```bash
	10	+ llmman serve
	11	+ ```
	12	+
	13	+2. Optionally pull the model first. Otherwise llmman pulls it on the first question, and that question waits for the download:
	14	+
	15	+ ```bash
	16	+ llmman pull hf.co/unsloth/Qwen3.5-4B-GGUF:Q4_K_M
	17	+ ```
	18	+
	19	+3. Run the demo configuration from its directory (its `skillsDir` is `../skills`):
	20	+
	21	+ ```bash
	22	+ cd demo-llmman
	23	+ ../mm agent.llmman.yaml
	24	+ ```
	25	+
	26	+4. Check the banner. `provider: llmman` confirms the provider. `ctx: 262144 (/api/ps)` means the model was already loaded and `mm` read the window it is served with; `ctx: unknown` means it was not loaded yet — `mm` asks again before the next question and prints `ctx: … (/api/ps)` once it knows.
	27	+
	28	+## Variants
	29	+
	30	+- Another model. Set `model:` to the id exactly as `llmman list` (or `GET /v1/models`) spells it.
	31	+- From a Docker sandbox. Nothing to change: when `127.0.0.1:17434` does not answer, `mm` falls back to `http://host.docker.internal:17434/v1`, the daemon on the host.
	32	+- Daemon started with `LLMMAN_API_KEYS` (mandatory when it listens beyond loopback). Export one of the keys in `LLMMAN_API_KEY`, the provider's default variable, or name another variable under `apiKeyEnv`.
	33	+- `LLMMAN_CONTEXT_LENGTH` set on the daemon. `/api/ps` already reports it once the model is loaded; set `contextWindow` to the same value if you want compression to know it from the first question.
	34	+- Keep your own `agent.yaml`. `AGENT_PROVIDER=llmman ./mm` works as long as the file leaves `baseUrl` empty.
	35	+
	36	+## See also
	37	+
	38	+- [Providers: one implementation per protocol](../explanation/providers.md) — why llmman's window comes from `/api/ps`, not `/props`.
	39	+- [Configuration reference](../reference/configuration.md) — provider defaults.

++# How to run mini-me on llmman
++
++This guide shows how to point `mm` at [llmman](https://github.com/llmmanorg/llmman) through its OpenAI-compatible endpoint. It assumes llmman is installed and you know how to build `mm`.
++
++## Steps
++
++1. Start the daemon. It listens on `127.0.0.1:17434`:
++
++   ```bash
++   llmman serve
++   ```
++
++2. Optionally pull the model first. Otherwise llmman pulls it on the first question, and that question waits for the download:
++
++   ```bash
++   llmman pull hf.co/unsloth/Qwen3.5-4B-GGUF:Q4_K_M
++   ```
++
++3. Run the demo configuration from its directory (its `skillsDir` is `../skills`):
++
++   ```bash
++   cd demo-llmman
++   ../mm agent.llmman.yaml
++   ```
++
++4. Check the banner. `provider: llmman` confirms the provider. `ctx: 262144 (/api/ps)` means the model was already loaded and `mm` read the window it is served with; `ctx: unknown` means it was not loaded yet — `mm` asks again before the next question and prints `ctx: … (/api/ps)` once it knows.
++
++## Variants
++
++- **Another model.** Set `model:` to the id exactly as `llmman list` (or `GET /v1/models`) spells it.
++- **From a Docker sandbox.** Nothing to change: when `127.0.0.1:17434` does not answer, `mm` falls back to `http://host.docker.internal:17434/v1`, the daemon on the host.
++- **Daemon started with `LLMMAN_API_KEYS`** (mandatory when it listens beyond loopback). Export one of the keys in `LLMMAN_API_KEY`, the provider's default variable, or name another variable under `apiKeyEnv`.
++- **`LLMMAN_CONTEXT_LENGTH` set on the daemon.** `/api/ps` already reports it once the model is loaded; set `contextWindow` to the same value if you want compression to know it from the first question.
++- **Keep your own `agent.yaml`.** `AGENT_PROVIDER=llmman ./mm` works as long as the file leaves `baseUrl` empty.
++
++## See also
++
++- [Providers: one implementation per protocol](../explanation/providers.md) — why llmman's window comes from `/api/ps`, not `/props`.
++- [Configuration reference](../reference/configuration.md) — provider defaults.

added docs/en/how-to/run-with-ollama.md +40 -0 Viewed

new file mode 100644
@@ -0,0 +1,40 @@
	1	+# How to run mini-me on Ollama
	2	+
	3	+This guide shows how to point `mm` at [Ollama](https://ollama.com) through its OpenAI-compatible endpoint. It assumes Ollama is installed and you know how to build `mm`.
	4	+
	5	+## Steps
	6	+
	7	+1. Pull the model. Ollama's OpenAI API does not pull a missing model: a question to it fails with `model '…' not found`:
	8	+
	9	+ ```bash
	10	+ ollama pull qwen3.5:2b
	11	+ ```
	12	+
	13	+2. Make sure the server runs on `localhost:11434` (the desktop app starts it; otherwise `ollama serve`).
	14	+
	15	+3. Run the demo configuration from its directory (its `skillsDir` is `../skills`):
	16	+
	17	+ ```bash
	18	+ cd demo-ollama
	19	+ ../mm agent.ollama.yaml
	20	+ ```
	21	+
	22	+4. Check the banner. `provider: ollama` confirms the provider. `ctx: 32768 (/api/ps)` means the model was already loaded and `mm` read the window it is served with; `ctx: unknown` means it was not loaded yet — `mm` asks again before the next question.
	23	+
	24	+## Variants
	25	+
	26	+- Another model. Set `model:` to the name exactly as `ollama list` spells it (`qwen3.5:9b`, …).
	27	+- From a Docker sandbox. Nothing to change: when `localhost:11434` does not answer, `mm` falls back to `http://host.docker.internal:11434/v1`, the Ollama on the host.
	28	+- A larger window. The OpenAI API cannot set `num_ctx` per request: start Ollama with `OLLAMA_CONTEXT_LENGTH`, and put the same value in `contextWindow` if you want compression to know it from the first question.
	29	+- ollama.com's API. Set `baseUrl` to its OpenAI endpoint and export the key in `OLLAMA_API_KEY` (or name another variable under `apiKeyEnv`).
	30	+- Keep your own `agent.yaml`. `AGENT_PROVIDER=ollama ./mm` works as long as the file leaves `baseUrl` empty.
	31	+
	32	+## What differs from the llama.cpp servers
	33	+
	34	+- No `Reading the prompt …` line: Ollama sends no progress while it reads, so `firstTokenTimeout` has to cover the whole prompt and the model's loading.
	35	+- The summary of a compaction turns reasoning off with `reasoning_effort: "none"` — Ollama ignores `chat_template_kwargs`.
	36	+
	37	+## See also
	38	+
	39	+- [Providers: one implementation per protocol](../explanation/providers.md) — what was measured on Ollama, and why each server keeps its own entry.
	40	+- [Configuration reference](../reference/configuration.md) — provider defaults.

++# How to run mini-me on Ollama
++
++This guide shows how to point `mm` at [Ollama](https://ollama.com) through its OpenAI-compatible endpoint. It assumes Ollama is installed and you know how to build `mm`.
++
++## Steps
++
++1. Pull the model. Ollama's OpenAI API does not pull a missing model: a question to it fails with `model '…' not found`:
++
++   ```bash
++   ollama pull qwen3.5:2b
++   ```
++
++2. Make sure the server runs on `localhost:11434` (the desktop app starts it; otherwise `ollama serve`).
++
++3. Run the demo configuration from its directory (its `skillsDir` is `../skills`):
++
++   ```bash
++   cd demo-ollama
++   ../mm agent.ollama.yaml
++   ```
++
++4. Check the banner. `provider: ollama` confirms the provider. `ctx: 32768 (/api/ps)` means the model was already loaded and `mm` read the window it is served with; `ctx: unknown` means it was not loaded yet — `mm` asks again before the next question.
++
++## Variants
++
++- **Another model.** Set `model:` to the name exactly as `ollama list` spells it (`qwen3.5:9b`, …).
++- **From a Docker sandbox.** Nothing to change: when `localhost:11434` does not answer, `mm` falls back to `http://host.docker.internal:11434/v1`, the Ollama on the host.
++- **A larger window.** The OpenAI API cannot set `num_ctx` per request: start Ollama with `OLLAMA_CONTEXT_LENGTH`, and put the same value in `contextWindow` if you want compression to know it from the first question.
++- **ollama.com's API.** Set `baseUrl` to its OpenAI endpoint and export the key in `OLLAMA_API_KEY` (or name another variable under `apiKeyEnv`).
++- **Keep your own `agent.yaml`.** `AGENT_PROVIDER=ollama ./mm` works as long as the file leaves `baseUrl` empty.
++
++## What differs from the llama.cpp servers
++
++- No `Reading the prompt …` line: Ollama sends no progress while it reads, so `firstTokenTimeout` has to cover the whole prompt and the model's loading.
++- The summary of a compaction turns reasoning off with `reasoning_effort: "none"` — Ollama ignores `chat_template_kwargs`.
++
++## See also
++
++- [Providers: one implementation per protocol](../explanation/providers.md) — what was measured on Ollama, and why each server keeps its own entry.
++- [Configuration reference](../reference/configuration.md) — provider defaults.

modified docs/en/reference/cli.md +1 -1 Viewed

@@ -55,7 +55,7 @@ The first existing source wins.
55	55	\| `AGENT_MODEL` \| Overrides the `model` key. \|
56	56	\| `AGENT_BASE_URL` \| Overrides `baseUrl` and disables the fallback probe. \|
57	57	\| `DMR_BASE_URL` \| Same as `AGENT_BASE_URL`, for the `dmr` provider only; `AGENT_BASE_URL` wins when both are set. \|
58		-\| Variable named by `apiKeyEnv` \| Holds the API key. Default name: none for `dmr`, `LLAMA_API_KEY` for `llamacpp`. \|
	58	+\| Variable named by `apiKeyEnv` \| Holds the API key. Default name: none for `dmr`, `LLAMA_API_KEY` for `llamacpp`, `LLMMAN_API_KEY` for `llmman`, `OLLAMA_API_KEY` for `ollama`. \|
59	59
60	60	## Start-up output
61	61

  | `AGENT_MODEL` | Overrides the `model` key. |
  | `AGENT_BASE_URL` | Overrides `baseUrl` and disables the fallback probe. |
  | `DMR_BASE_URL` | Same as `AGENT_BASE_URL`, for the `dmr` provider only; `AGENT_BASE_URL` wins when both are set. |
--| Variable named by `apiKeyEnv` | Holds the API key. Default name: none for `dmr`, `LLAMA_API_KEY` for `llamacpp`. |
++| Variable named by `apiKeyEnv` | Holds the API key. Default name: none for `dmr`, `LLAMA_API_KEY` for `llamacpp`, `LLMMAN_API_KEY` for `llmman`, `OLLAMA_API_KEY` for `ollama`. |
  ## Start-up output

modified docs/en/reference/configuration.md +6 -4 Viewed

@@ -6,7 +6,7 @@
6	6
7	7	\| Key \| Type \| Default \| Description \|
8	8	\|-----\|------\|---------\|-------------\|
9		-\| `provider` \| string \| `dmr` \| Registry key of the LLM server: `dmr` or `llamacpp`. Overridden by `AGENT_PROVIDER`. \|
	9	+\| `provider` \| string \| `dmr` \| Registry key of the LLM server: `dmr`, `llamacpp`, `llmman` or `ollama`. Overridden by `AGENT_PROVIDER`. \|
10	10	\| `model` \| string \| `huggingface.co/jetbrains/mellum2-12b-a2.5b-instruct-gguf-q4_k_m:Q4_K_M` \| Model identifier in the provider's naming. Overridden by `AGENT_MODEL`. \|
11	11	\| `baseUrl` \| string \| `""` (provider default) \| OpenAI-compatible endpoint tried first. Overridden by `AGENT_BASE_URL`. \|
12	12	\| `fallback` \| string or absent \| absent (provider default) \| Endpoint used when `baseUrl` does not answer `/models` within 2 s. Absent = provider default; `""` = no fallback. \|
@@ -24,7 +24,7 @@
24	24	\| `fetchContentTool` \| bool \| `false` \| Declare `fetch_content`, which fetches web pages as Markdown. Off by default: it is the only built-in tool that reaches the network. \|
25	25	\| `sampling` \| map \| `temperature: 0.0`, `top_p: 0.9`, `max_tokens: 4096` \| Generation settings, OpenAI API key names, passed to the server. The shipped `agent.yaml` adds `parallel_tool_calls: false`. `max_tokens` also bounds one tool call: a `write_file` of a long document (or a thinking model's reasoning plus the call) can hit it, and the call is then cut off. mm hands it back to the model twice, asking for smaller pieces, then stops with `the model hit max_tokens (N) while writing a tool call`; raise the value if that happens. With streaming, mm also asks the server for token counts (`stream_options.include_usage`). \|
26	26	\| `watchdogTimeout` \| duration \| `20s` \| Silence tolerated between two streamed tokens before the connection is declared hung. Doubled for summary requests. \|
27		-\| `firstTokenTimeout` \| duration \| `3m` \| Silence tolerated before a model call's first token, while the server reads the prompt (every round trip of a turn has one). Never shorter than `watchdogTimeout`; must be >= 0. With a llama.cpp server (`dmr`, `llamacpp`) mm asks for `return_progress`: each progress report restarts this clock, and the spinner shows `Reading the prompt 12.0k/25.3k tokens`. On a timeout the watchdog says `no first token from the server after …` (before the first token) or `connection hang detected after …` (after). \|
	27	+\| `firstTokenTimeout` \| duration \| `3m` \| Silence tolerated before a model call's first token, while the server reads the prompt (every round trip of a turn has one). Never shorter than `watchdogTimeout`; must be >= 0. With a llama.cpp server (`dmr`, `llamacpp`, `llmman` — whose local GGUF models run in llama-server) mm asks for `return_progress`: each progress report restarts this clock, and the spinner shows `Reading the prompt 12.0k/25.3k tokens`. Ollama sends no progress: this one wait covers the whole prompt (and the model's loading). On a timeout the watchdog says `no first token from the server after …` (before the first token) or `connection hang detected after …` (after). \|
28	28	\| `context` \| map \| see below \| Automatic history compression. \|
29	29	\| `sessions` \| map \| see below \| Persistent, per-project sessions. \|
30	30	\| `acp` \| map \| see below \| How `mm -acp` introduces itself to the editor. \|
@@ -40,7 +40,7 @@
40	40	\| `threshold` \| int \| `75` \| Percentage of the context window beyond which the history is compressed before the next question. Between 1 and 100. \|
41	41	\| `maxMessages` \| int \| `80` \| Message count that triggers a compression when the window is unknown or the estimate is low. `0` disables. Must be ≥ 0. \|
42	42	\| `keepLastTurns` \| int \| `3` \| Question turns kept raw at the end of the history. Must be ≥ 1. \|
43		-\| `summaryMaxTokens` \| int \| `1200` \| `max_tokens` of the summary request. Must be > 0. A thinking model's reasoning counts against it: on `dmr` and `llamacpp` the summary request turns reasoning off (`chat_template_kwargs.enable_thinking: false`); elsewhere, if the error says the model "reasoned until the limit", raise it. \|
	43	+\| `summaryMaxTokens` \| int \| `1200` \| `max_tokens` of the summary request. Must be > 0. A thinking model's reasoning counts against it: on `dmr`, `llamacpp` and `llmman` the summary request turns reasoning off (`chat_template_kwargs.enable_thinking: false`), on `ollama` too (`reasoning_effort: "none"`, the one switch Ollama obeys); elsewhere, if the error says the model "reasoned until the limit", raise it. \|
44	44	\| `prompt` \| string \| `""` \| Replaces the built-in summary prompt when not empty. \|
45	45	\| `showStats` \| bool \| `true` \| Print the one-line `🗜️` report after each compression. \|
46	46
@@ -90,6 +90,8 @@ The shipped `agent.lsp.yaml` is `agent.dmr.yaml` with this block on (gopls activ
90	90	\|----------\|-----------\|------------\|-------------\|--------------\|
91	91	\| `dmr` \| `http://localhost:12434/engines/v1` \| `http://host.docker.internal:12434/engines/v1` \| none \| no \|
92	92	\| `llamacpp` \| `http://127.0.0.1:8080/v1` \| none \| `LLAMA_API_KEY` \| no \|
	93	+\| `llmman` \| `http://127.0.0.1:17434/v1` \| `http://host.docker.internal:17434/v1` \| `LLMMAN_API_KEY` \| no \|
	94	+\| `ollama` \| `http://localhost:11434/v1` \| `http://host.docker.internal:11434/v1` \| `OLLAMA_API_KEY` \| no \|
93	95
94	96	## Validation errors
95	97
@@ -115,7 +117,7 @@ Reported as `[config error: <path>: <message>]`, exit code 1.
115	117	\| `lsp.servers[N].extensions: "go" must start with a dot, like ".go"` \| an extension without its dot \|
116	118	\| `lsp.servers[N]: extension ".ts" is already served by "typescript"` \| two servers on one extension \|
117	119	\| `permissions must be "auto" or "ask"` \| any other value \|
118		-\| `unknown provider "x" (known: dmr, llamacpp)` \| Reported by the engine, as `[engine error: …]`. \|
	120	+\| `unknown provider "x" (known: dmr, llamacpp, llmman, ollama)` \| Reported by the engine, as `[engine error: …]`. \|
119	121
120	122	A start-up warning, not an error, is printed when `context.enabled` is `true`, the window is unknown and `context.maxMessages` is `0`.
121	123

  | Key | Type | Default | Description |
  |-----|------|---------|-------------|
--| `provider` | string | `dmr` | Registry key of the LLM server: `dmr` or `llamacpp`. Overridden by `AGENT_PROVIDER`. |
++| `provider` | string | `dmr` | Registry key of the LLM server: `dmr`, `llamacpp`, `llmman` or `ollama`. Overridden by `AGENT_PROVIDER`. |
  | `model` | string | `huggingface.co/jetbrains/mellum2-12b-a2.5b-instruct-gguf-q4_k_m:Q4_K_M` | Model identifier in the provider's naming. Overridden by `AGENT_MODEL`. |
  | `baseUrl` | string | `""` (provider default) | OpenAI-compatible endpoint tried first. Overridden by `AGENT_BASE_URL`. |
  | `fallback` | string or absent | absent (provider default) | Endpoint used when `baseUrl` does not answer `/models` within 2 s. Absent = provider default; `""` = no fallback. |
  | `fetchContentTool` | bool | `false` | Declare `fetch_content`, which fetches web pages as Markdown. Off by default: it is the only built-in tool that reaches the network. |
  | `sampling` | map | `temperature: 0.0`, `top_p: 0.9`, `max_tokens: 4096` | Generation settings, OpenAI API key names, passed to the server. The shipped `agent.yaml` adds `parallel_tool_calls: false`. `max_tokens` also bounds one tool call: a `write_file` of a long document (or a thinking model's reasoning plus the call) can hit it, and the call is then cut off. mm hands it back to the model twice, asking for smaller pieces, then stops with `the model hit max_tokens (N) while writing a tool call`; raise the value if that happens. With streaming, mm also asks the server for token counts (`stream_options.include_usage`). |
  | `watchdogTimeout` | duration | `20s` | Silence tolerated between two streamed tokens before the connection is declared hung. Doubled for summary requests. |
--| `firstTokenTimeout` | duration | `3m` | Silence tolerated before a model call's first token, while the server reads the prompt (every round trip of a turn has one). Never shorter than `watchdogTimeout`; must be >= 0. With a llama.cpp server (`dmr`, `llamacpp`) mm asks for `return_progress`: each progress report restarts this clock, and the spinner shows `Reading the prompt 12.0k/25.3k tokens`. On a timeout the watchdog says `no first token from the server after …` (before the first token) or `connection hang detected after …` (after). |
++| `firstTokenTimeout` | duration | `3m` | Silence tolerated before a model call's first token, while the server reads the prompt (every round trip of a turn has one). Never shorter than `watchdogTimeout`; must be >= 0. With a llama.cpp server (`dmr`, `llamacpp`, `llmman` — whose local GGUF models run in llama-server) mm asks for `return_progress`: each progress report restarts this clock, and the spinner shows `Reading the prompt 12.0k/25.3k tokens`. Ollama sends no progress: this one wait covers the whole prompt (and the model's loading). On a timeout the watchdog says `no first token from the server after …` (before the first token) or `connection hang detected after …` (after). |
  | `context` | map | see below | Automatic history compression. |
  | `sessions` | map | see below | Persistent, per-project sessions. |
  | `acp` | map | see below | How `mm -acp` introduces itself to the editor. |
  | `threshold` | int | `75` | Percentage of the context window beyond which the history is compressed before the next question. Between 1 and 100. |
  | `maxMessages` | int | `80` | Message count that triggers a compression when the window is unknown or the estimate is low. `0` disables. Must be ≥ 0. |
  | `keepLastTurns` | int | `3` | Question turns kept raw at the end of the history. Must be ≥ 1. |
--| `summaryMaxTokens` | int | `1200` | `max_tokens` of the summary request. Must be > 0. A thinking model's reasoning counts against it: on `dmr` and `llamacpp` the summary request turns reasoning off (`chat_template_kwargs.enable_thinking: false`); elsewhere, if the error says the model "reasoned until the limit", raise it. |
++| `summaryMaxTokens` | int | `1200` | `max_tokens` of the summary request. Must be > 0. A thinking model's reasoning counts against it: on `dmr`, `llamacpp` and `llmman` the summary request turns reasoning off (`chat_template_kwargs.enable_thinking: false`), on `ollama` too (`reasoning_effort: "none"`, the one switch Ollama obeys); elsewhere, if the error says the model "reasoned until the limit", raise it. |
  | `prompt` | string | `""` | Replaces the built-in summary prompt when not empty. |
  | `showStats` | bool | `true` | Print the one-line `🗜️` report after each compression. |
  |----------|-----------|------------|-------------|--------------|
  | `dmr` | `http://localhost:12434/engines/v1` | `http://host.docker.internal:12434/engines/v1` | none | no |
  | `llamacpp` | `http://127.0.0.1:8080/v1` | none | `LLAMA_API_KEY` | no |
++| `llmman` | `http://127.0.0.1:17434/v1` | `http://host.docker.internal:17434/v1` | `LLMMAN_API_KEY` | no |
++| `ollama` | `http://localhost:11434/v1` | `http://host.docker.internal:11434/v1` | `OLLAMA_API_KEY` | no |
  ## Validation errors
  | `lsp.servers[N].extensions: "go" must start with a dot, like ".go"` | an extension without its dot |
  | `lsp.servers[N]: extension ".ts" is already served by "typescript"` | two servers on one extension |
  | `permissions must be "auto" or "ask"` | any other value |
--| `unknown provider "x" (known: dmr, llamacpp)` | Reported by the engine, as `[engine error: …]`. |
++| `unknown provider "x" (known: dmr, llamacpp, llmman, ollama)` | Reported by the engine, as `[engine error: …]`. |
  A start-up warning, not an error, is printed when `context.enabled` is `true`, the window is unknown and `context.maxMessages` is `0`.

modified docs/en/reference/mcp-configuration.md +4 -2 Viewed

Large diff collapsed to keep the page fast — load it when you need it.

modified docs/fr/README.md +3 -1 Viewed

Large diff collapsed to keep the page fast — load it when you need it.

modified docs/fr/explanation/providers.md +6 -2 Viewed

Large diff collapsed to keep the page fast — load it when you need it.

added docs/fr/how-to/run-with-llmman.md +39 -0 Viewed

Large diff collapsed to keep the page fast — load it when you need it.

added docs/fr/how-to/run-with-ollama.md +40 -0 Viewed

Large diff collapsed to keep the page fast — load it when you need it.

modified docs/fr/reference/cli.md +1 -1 Viewed

@@ -55,7 +55,7 @@ La première source existante gagne.
55	55	\| `AGENT_MODEL` \| Surcharge la clé `model`. \|
56	56	\| `AGENT_BASE_URL` \| Surcharge `baseUrl` et désactive la sonde de repli. \|
57	57	\| `DMR_BASE_URL` \| Comme `AGENT_BASE_URL`, pour le fournisseur `dmr` seulement ; `AGENT_BASE_URL` gagne quand les deux sont définies. \|
58		-\| Variable nommée par `apiKeyEnv` \| Contient la clé d'API. Nom par défaut : aucun pour `dmr`, `LLAMA_API_KEY` pour `llamacpp`. \|
	58	+\| Variable nommée par `apiKeyEnv` \| Contient la clé d'API. Nom par défaut : aucun pour `dmr`, `LLAMA_API_KEY` pour `llamacpp`, `LLMMAN_API_KEY` pour `llmman`, `OLLAMA_API_KEY` pour `ollama`. \|
59	59
60	60	## Sortie de démarrage
61	61

  | `AGENT_MODEL` | Surcharge la clé `model`. |
  | `AGENT_BASE_URL` | Surcharge `baseUrl` et désactive la sonde de repli. |
  | `DMR_BASE_URL` | Comme `AGENT_BASE_URL`, pour le fournisseur `dmr` seulement ; `AGENT_BASE_URL` gagne quand les deux sont définies. |
--| Variable nommée par `apiKeyEnv` | Contient la clé d'API. Nom par défaut : aucun pour `dmr`, `LLAMA_API_KEY` pour `llamacpp`. |
++| Variable nommée par `apiKeyEnv` | Contient la clé d'API. Nom par défaut : aucun pour `dmr`, `LLAMA_API_KEY` pour `llamacpp`, `LLMMAN_API_KEY` pour `llmman`, `OLLAMA_API_KEY` pour `ollama`. |
  ## Sortie de démarrage

modified docs/fr/reference/configuration.md +6 -4 Viewed

Large diff collapsed to keep the page fast — load it when you need it.

modified internal/config/config.go +1 -1 Viewed

Large diff collapsed to keep the page fast — load it when you need it.

added internal/engine/apips.go +51 -0 Viewed

Large diff collapsed to keep the page fast — load it when you need it.

added internal/engine/llmman.go +33 -0 Viewed

Large diff collapsed to keep the page fast — load it when you need it.

added internal/engine/ollama.go +27 -0 Viewed

Large diff collapsed to keep the page fast — load it when you need it.

modified internal/engine/openai_compat.go +48 -6 Viewed

Large diff collapsed to keep the page fast — load it when you need it.

modified internal/engine/provider_test.go +85 -6 Viewed

Large diff collapsed to keep the page fast — load it when you need it.

modified internal/engine/summary_test.go +36 -4 Viewed

Large diff collapsed to keep the page fast — load it when you need it.

modified internal/engine/usage.go +41 -15 Viewed

Large diff collapsed to keep the page fast — load it when you need it.

modified internal/engine/usage_test.go +1 -1 Viewed

Large diff collapsed to keep the page fast — load it when you need it.

modified main.go +2 -1 Viewed

Large diff collapsed to keep the page fast — load it when you need it.

Add llmman and ollama providers #20