jpmschweitzer/odysseus
1
0
Fork 0
mirror of https://github.com/pewdiepie-archdaemon/odysseus.git synced 2026-10-23 23:32:22 +02:00
Code Issues Packages Projects Releases Wiki Activity

docs(specs): routine specifications update

Browse Source
This commit is contained in:
RaresKeY
2026-10-15 16:52:16 +00:00
parent c74f475679
commit bead6a6797
29 changed files with 767 additions and 511 deletions
Download Patch File Download Diff File Expand all files Collapse all files
specs/model-quirks.md
+8 -21
View File
@@ -1,19 +1,12 @@
# Model Behavior Observations
Last updated: dev@2e2bb52 | 2026-08-16
Last updated: dev@86b886c | 2026-10-14
## Scope
This file records model- or provider+model-specific behavior observed in
Odysseus code, tests, Issues, PRs, commits, and provider documentation. It is a
compact evidence map, not a runtime matcher. General canonical rules belong in
[model-capability-canonical.md](model-capability-canonical.md); provider-wide
transport belongs in [the provider map](model-providers/_readme.md).
This file records model- or provider+model-specific behavior observed in Odysseus code, tests, Issues, PRs, commits, and provider documentation. It is a compact evidence map, not a runtime matcher. General canonical rules belong in [model-capability-canonical.md](model-capability-canonical.md); provider-wide transport belongs in [the provider map](model-providers/_readme.md).
The canonical capability layer intentionally has no
`src/model_behavior_quirks.py`.
Adding a registry before runtime call sites carry structured provider, model,
version, and dialect identity would create another model-name matching layer.
The canonical capability layer intentionally has no `src/model_behavior_quirks.py`. Adding a registry before runtime call sites carry structured provider, model, version, and dialect identity would create another model-name matching layer.
## General Observation Template
@@ -27,9 +20,7 @@ Record only the fields supported by the evidence:
- source, confidence, status, and reproduction date;
- whether the behavior is already implemented in runtime code.
If exact structured identity is unavailable, keep the observation here and in
its current tested runtime location. Do not promote it through substring,
regex, prose, or serialized-prompt parsing in the canonical layer.
If exact structured identity is unavailable, keep the observation here and in its current tested runtime location. Do not promote it through substring, regex, prose, or serialized-prompt parsing in the canonical layer.
## Model-Specific Observation Map
@@ -43,9 +34,7 @@ regex, prose, or serialized-prompt parsing in the canonical layer.
| Ollama native `gpt-oss` reasoning level | `gpt-oss` served through Ollama native | `think` accepts low/medium/high and does not represent off | provider docs; deployment scoped |
| Ollama compatibility disable observation | Ollama 0.20.6+, observed Qwen3.5 compatibility path | `reasoning_effort: none` was reported to disable reasoning | #5503; unmerged/low confidence until reproduced |
Issue and commit references are evidence identifiers, not runtime dependencies.
Open or unmerged observations remain provisional until reproduced or supported
by current provider documentation.
Issue and commit references are evidence identifiers, not runtime dependencies. Open or unmerged observations remain provisional until reproduced or supported by current provider documentation.
## Other Model-Level Observations
@@ -73,13 +62,11 @@ by current provider documentation.
#1704, #1478). Native engine metadata or a verified endpoint probe outranks
a model-family name list.
Current `src.model_profiles` is a separate runtime schema/thinking profile helper: bounded `odysseus`/`ajax` tokens in the model ID leaf select compact schema and progressive thinking. It is not the absent canonical behavior registry. `src.utility_effort` validates utility effort against ChatGPT metadata that includes maintained/model-name defaults; callers must not describe those defaults as verified provider capability.
## Promotion Gate
Before an observation becomes canonical runtime behavior, a consumer must
already have the necessary structured identity and tests must cover both its
positive scope and a neighboring negative scope. Request control and response
visibility remain separate: hiding reasoning text is not the same as disabling
reasoning at the provider (#2905).
Before an observation becomes canonical runtime behavior, a consumer must already have the necessary structured identity and tests must cover both its positive scope and a neighboring negative scope. Request control and response visibility remain separate: hiding reasoning text is not the same as disabling reasoning at the provider (#2905).
## Current Gaps