From 0f9f877a5aa7271a47d00efe99b75e05ee497522 Mon Sep 17 00:00:00 2001 From: Codeman maintainer Date: Wed, 11 Nov 2026 10:16:40 +0100 Subject: [PATCH] docs(local-model): what today's DeepSeek Harness showed A second scripted run, on dsh 0.2.2-rc.1 with a freshly installed dsh-TUI 0.19.0 under a scratch home: the model name reaches the endpoint unchanged, the first request is 6,983 tokens with 27 tools, and a tool round trip completes. Two things that version does differently are written down where a reader of the harness table looks: a setup guide opens in every session until a person has finished it once (and its cursor is the readiness mark), and its transcript file was renamed, so `last-response` is empty for it. Co-Authored-By: Claude Fable 5.2 --- docs/local-models.md | 8 ++++++-- src/config/local-model-catalog.ts | 15 ++++++++++----- 2 files changed, 16 insertions(+), 7 deletions(-) diff --git a/docs/local-models.md b/docs/local-models.md index e6f1f58d..accd8311 100644 --- a/docs/local-models.md +++ b/docs/local-models.md @@ -223,7 +223,7 @@ the agent, so a session with one agent and a session with another run on the sam | OpenCode | about 8,100 tokens, 11 tools (v1.19.5; more with user-level skills) | yes | A tool round trip on a Mac with a real model (the catalogue's tested entry), and on a scripted endpoint for v1.19.5 | | Claude Code | about 36,000 tokens, so the first answer takes minutes | yes | Shipped in 1.50.0; not measured again for this table | | Pi | 2,096 tokens, 4 tools (v1.5.2) | yes | A complete tool round trip against a real model: tool call, tool result, final answer, the file on disk | -| DeepSeek Harness | about 7,650 tokens, 25 tools (0.1.1-rc.2) | **no** | A tool round trip on a scripted endpoint only. Against a real model the launch and the model name reached the runtime, and no turn finished | +| DeepSeek Harness | about 7,650 tokens, 25 tools (0.1.1-rc.2); 6,983, 27 tools (0.2.2-rc.1) | **no** | A tool round trip on a scripted endpoint only, on both versions. Against a real model the launch and the model name reached the runtime, and no turn finished | How to read the last column: the runs of 2026-11-10 were made on **Linux**, through Codeman's own custom model launch, against Ollama 0.13.0 with a 1.7B model on a CPU ("a real model") or @@ -248,7 +248,11 @@ Three things follow from how the agents differ: the one agent of the four besides Claude Code that reports the end of a turn. Its custom endpoint recipe itself was verified with a real model on a llama.cpp server ([custom-model-endpoints.md](custom-model-endpoints.md)); what is missing is a finished turn - on this feature's runtime. + on this feature's runtime. On today's version (0.2.2-rc.1 with dsh-TUI 0.19.0) two more + things were seen: a setup guide opens in every session until a person has finished it once + (a person in a tab presses through it; a script must not, see the codeman skill), and its + transcript file was renamed, so Codeman's response viewer and `last-response` are empty for + a dsh session on that version until the reader learns the new name. - **OpenCode and DeepSeek Harness send a second, small request** beside the first prompt (a title, a side question). The runtime answers one request at a time, so it queues. diff --git a/src/config/local-model-catalog.ts b/src/config/local-model-catalog.ts index 49fcf1db..91302862 100644 --- a/src/config/local-model-catalog.ts +++ b/src/config/local-model-catalog.ts @@ -83,10 +83,11 @@ * | | | | prompts sent at the rule stayed | * | | | | unsent), and it draws nothing that | * | | | | is a contract once it does | - * | `deepseek` | about 7,650 tokens, 25 tools | SCRIPTED only (0.1.1-rc.2 with dsh-TUI | none here: the CLI registry's `❯` | - * | | (0.1.1-rc.2) | 0.10.0-beta.1, not today's versions). | stands; a prompt sent at it was | - * | | | REAL: the launch and the model name | submitted, 2 of 2 launches | - * | | | reached the runtime, no turn finished | | + * | `deepseek` | about 7,650 tokens, 25 tools | SCRIPTED only, on both versions | none here: the CLI registry's `❯` | + * | | (0.1.1-rc.2); 6,983 tokens, 27 | (0.1.1-rc.2 with dsh-TUI 0.10.0-beta.1 | stands; a prompt sent at it was | + * | | tools (0.2.2-rc.1) | and 0.2.2-rc.1 with dsh-TUI 0.19.0). | submitted, 2 of 2 launches. On | + * | | | REAL: the launch and the model name | dsh-TUI 0.19.0 a setup guide draws | + * | | | reached the runtime, no turn finished | `❯` too until it was finished once | * * Every one of them sent the `name:tag` model id unchanged. `pi` was gated until 2026-11-10 for * two open questions, both answered by its run: the id (above), and the window, which Codeman @@ -94,7 +95,11 @@ * 128,000-token one). `deepseek` is a LAUNCHER: its install command leaves it with nothing to * launch, so src/local-model/harness-facts.ts never reports it installable and a Mac is offered * it only where it was already set up. It is offered on a scripted run and one unfinished real - * one: gate the row again (`gated: true`) should a run on a Mac not finish a turn. + * one: gate the row again (`gated: true`) should a run on a Mac not finish a turn. Two things + * about dsh-TUI 0.19.0 that a client of its `readyMark` must know: until a person has finished + * its setup guide once, every session opens on that guide and the guide's cursor is the mark + * (the codeman skill reads the pane after the mark for that reason), and its transcript file + * was renamed, so Codeman's `last-response` is empty for it for now. * * MEMORY. The need is `bytes + heldBytesPerToken x context + overheadBytes + peakExtraBytes` * (src/local-model/recommend.ts). The two runners spend memory differently, so a row's three